Compare commits
2 Commits
bold_front
...
hongyi-zha
| Author | SHA1 | Date | |
|---|---|---|---|
|
e8c17a099e | ||
|
|
3f36cfea38 |
3
.gitignore
vendored
3
.gitignore
vendored
@@ -153,6 +153,3 @@ media
|
||||
flagged
|
||||
request_llms/ChatGLM-6b-onnx-u8s8
|
||||
.pre-commit-config.yaml
|
||||
test.html
|
||||
objdump*
|
||||
*.min.*.js
|
||||
@@ -12,16 +12,11 @@ RUN echo '[global]' > /etc/pip.conf && \
|
||||
echo 'trusted-host = mirrors.aliyun.com' >> /etc/pip.conf
|
||||
|
||||
|
||||
# 语音输出功能（以下两行，第一行更换阿里源，第二行安装ffmpeg，都可以删除）
|
||||
RUN UBUNTU_VERSION=$(awk -F= '/^VERSION_CODENAME=/{print $2}' /etc/os-release); echo "deb https://mirrors.aliyun.com/debian/ $UBUNTU_VERSION main non-free contrib" > /etc/apt/sources.list; apt-get update
|
||||
RUN apt-get install ffmpeg -y
|
||||
|
||||
|
||||
# 进入工作路径（必要）
|
||||
WORKDIR /gpt
|
||||
|
||||
|
||||
# 安装大部分依赖，利用Docker缓存加速以后的构建 （以下两行，可以删除）
|
||||
# 安装大部分依赖，利用Docker缓存加速以后的构建 （以下三行，可以删除）
|
||||
COPY requirements.txt ./
|
||||
RUN pip3 install -r requirements.txt
|
||||
|
||||
|
||||
15
README.md
15
README.md
@@ -1,7 +1,7 @@
|
||||
> [!IMPORTANT]
|
||||
> 2024.6.1: 版本3.80加入插件二级菜单功能（详见wiki）
|
||||
> 2024.5.1: 加入Doc2x翻译PDF论文的功能，[查看详情](https://github.com/binary-husky/gpt_academic/wiki/Doc2x)
|
||||
> 2024.3.11: 全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！ SoVits语音克隆模块，[查看详情](https://www.bilibili.com/video/BV1Rp421S7tF/)
|
||||
> 2024.1.18: 更新3.70版本，支持Mermaid绘图库（让大模型绘制脑图）
|
||||
> 2024.1.17: 恭迎GLM4，全力支持Qwen、GLM、DeepseekCoder等国内中文大语言基座模型！
|
||||
> 2024.1.17: 某些依赖包尚不兼容python 3.12，推荐python 3.11。
|
||||
> 2024.1.17: 安装依赖时，请选择`requirements.txt`中**指定的版本**。 安装命令：`pip install -r requirements.txt`。本项目完全开源免费，您可通过订阅[在线服务](https://github.com/binary-husky/gpt_academic/wiki/online)的方式鼓励本项目的发展。
|
||||
|
||||
<br>
|
||||
@@ -67,7 +67,7 @@ Read this in [English](docs/README.English.md) | [日本語](docs/README.Japanes
|
||||
读论文、[翻译](https://www.bilibili.com/video/BV1KT411x7Wn)论文 | [插件] 一键解读latex/pdf论文全文并生成摘要
|
||||
Latex全文[翻译](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[润色](https://www.bilibili.com/video/BV1FT411H7c5/) | [插件] 一键翻译或润色latex论文
|
||||
批量注释生成 | [插件] 一键批量生成函数注释
|
||||
Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [插件] 看到上面5种语言的[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README.English.md)了吗？就是出自他的手笔
|
||||
Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [插件] 看到上面5种语言的[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)了吗？就是出自他的手笔
|
||||
[PDF论文全文翻译功能](https://www.bilibili.com/video/BV1KT411x7Wn) | [插件] PDF论文提取题目&摘要+翻译全文（多线程）
|
||||
[Arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [插件] 输入arxiv文章url即可一键翻译摘要+下载PDF
|
||||
Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼写纠错+输出对照PDF
|
||||
@@ -87,10 +87,6 @@ Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼
|
||||
<img src="https://user-images.githubusercontent.com/96192199/279702205-d81137c3-affd-4cd1-bb5e-b15610389762.gif" width="700" >
|
||||
</div>
|
||||
|
||||
<div align="center">
|
||||
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/70ff1ec5-e589-4561-a29e-b831079b37fb.gif" width="700" >
|
||||
</div>
|
||||
|
||||
|
||||
- 所有按钮都通过读取functional.py动态生成，可随意加自定义功能，解放剪贴板
|
||||
<div align="center">
|
||||
@@ -257,7 +253,8 @@ P.S. 如果需要依赖Latex的插件功能，请见Wiki。另外，您也可以
|
||||
# Advanced Usage
|
||||
### I：自定义新的便捷按钮（学术快捷键）
|
||||
|
||||
现在已可以通过UI中的`界面外观`菜单中的`自定义菜单`添加新的便捷按钮。如果需要在代码中定义，请使用任意文本编辑器打开`core_functional.py`，添加如下条目即可：
|
||||
任意文本编辑器打开`core_functional.py`，添加如下条目，然后重启程序。（如果按钮已存在，那么可以直接修改（前缀、后缀都已支持热修改），无需重启程序即可生效。）
|
||||
例如
|
||||
|
||||
```python
|
||||
"超级英译中": {
|
||||
|
||||
@@ -1,44 +1,33 @@
|
||||
|
||||
def check_proxy(proxies, return_ip=False):
|
||||
def check_proxy(proxies):
|
||||
import requests
|
||||
proxies_https = proxies['https'] if proxies is not None else '无'
|
||||
ip = None
|
||||
try:
|
||||
response = requests.get("https://ipapi.co/json/", proxies=proxies, timeout=4)
|
||||
data = response.json()
|
||||
if 'country_name' in data:
|
||||
country = data['country_name']
|
||||
result = f"代理配置 {proxies_https}, 代理所在地：{country}"
|
||||
if 'ip' in data: ip = data['ip']
|
||||
elif 'error' in data:
|
||||
alternative, ip = _check_with_backup_source(proxies)
|
||||
alternative = _check_with_backup_source(proxies)
|
||||
if alternative is None:
|
||||
result = f"代理配置 {proxies_https}, 代理所在地：未知，IP查询频率受限"
|
||||
else:
|
||||
result = f"代理配置 {proxies_https}, 代理所在地：{alternative}"
|
||||
else:
|
||||
result = f"代理配置 {proxies_https}, 代理数据解析失败：{data}"
|
||||
if not return_ip:
|
||||
print(result)
|
||||
return result
|
||||
else:
|
||||
return ip
|
||||
except:
|
||||
result = f"代理配置 {proxies_https}, 代理所在地查询超时，代理可能无效"
|
||||
if not return_ip:
|
||||
print(result)
|
||||
return result
|
||||
else:
|
||||
return ip
|
||||
|
||||
def _check_with_backup_source(proxies):
|
||||
import random, string, requests
|
||||
random_string = ''.join(random.choices(string.ascii_letters + string.digits, k=32))
|
||||
try:
|
||||
res_json = requests.get(f"http://{random_string}.edns.ip-api.com/json", proxies=proxies, timeout=4).json()
|
||||
return res_json['dns']['geo'], res_json['dns']['ip']
|
||||
except:
|
||||
return None, None
|
||||
try: return requests.get(f"http://{random_string}.edns.ip-api.com/json", proxies=proxies, timeout=4).json()['dns']['geo']
|
||||
except: return None
|
||||
|
||||
def backup_and_download(current_version, remote_version):
|
||||
"""
|
||||
@@ -58,7 +47,7 @@ def backup_and_download(current_version, remote_version):
|
||||
shutil.copytree('./', backup_dir, ignore=lambda x, y: ['history'])
|
||||
proxies = get_conf('proxies')
|
||||
try: r = requests.get('https://github.com/binary-husky/chatgpt_academic/archive/refs/heads/master.zip', proxies=proxies, stream=True)
|
||||
except: r = requests.get('https://public.agent-matrix.com/publish/master.zip', proxies=proxies, stream=True)
|
||||
except: r = requests.get('https://public.gpt-academic.top/publish/master.zip', proxies=proxies, stream=True)
|
||||
zip_file_path = backup_dir+'/master.zip'
|
||||
with open(zip_file_path, 'wb+') as f:
|
||||
f.write(r.content)
|
||||
@@ -82,7 +71,7 @@ def patch_and_restart(path):
|
||||
import sys
|
||||
import time
|
||||
import glob
|
||||
from shared_utils.colorful import print亮黄, print亮绿, print亮红
|
||||
from colorful import print亮黄, print亮绿, print亮红
|
||||
# if not using config_private, move origin config.py as config_private.py
|
||||
if not os.path.exists('config_private.py'):
|
||||
print亮黄('由于您没有设置config_private.py私密配置，现将您的现有配置移动至config_private.py以防止配置丢失，',
|
||||
@@ -124,7 +113,7 @@ def auto_update(raise_error=False):
|
||||
import json
|
||||
proxies = get_conf('proxies')
|
||||
try: response = requests.get("https://raw.githubusercontent.com/binary-husky/chatgpt_academic/master/version", proxies=proxies, timeout=5)
|
||||
except: response = requests.get("https://public.agent-matrix.com/publish/version", proxies=proxies, timeout=5)
|
||||
except: response = requests.get("https://public.gpt-academic.top/publish/version", proxies=proxies, timeout=5)
|
||||
remote_json_data = json.loads(response.text)
|
||||
remote_version = remote_json_data['version']
|
||||
if remote_json_data["show_feature"]:
|
||||
@@ -135,7 +124,7 @@ def auto_update(raise_error=False):
|
||||
current_version = f.read()
|
||||
current_version = json.loads(current_version)['version']
|
||||
if (remote_version - current_version) >= 0.01-1e-5:
|
||||
from shared_utils.colorful import print亮黄
|
||||
from colorful import print亮黄
|
||||
print亮黄(f'\n新版本可用。新版本:{remote_version}，当前版本:{current_version}。{new_feature}')
|
||||
print('（1）Github更新地址:\nhttps://github.com/binary-husky/chatgpt_academic\n')
|
||||
user_instruction = input('（2）是否一键更新代码（Y+回车=确认，输入其他/无输入+回车=不更新）？')
|
||||
|
||||
153
config.py
153
config.py
@@ -30,40 +30,11 @@ if USE_PROXY:
|
||||
else:
|
||||
proxies = None
|
||||
|
||||
# [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
|
||||
LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
|
||||
AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
|
||||
"gpt-4o", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
|
||||
"gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
|
||||
"gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
|
||||
"gemini-pro", "chatglm3"
|
||||
]
|
||||
# --- --- --- ---
|
||||
# P.S. 其他可用的模型还包括
|
||||
# AVAIL_LLM_MODELS = [
|
||||
# "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-flash",
|
||||
# "qianfan", "deepseekcoder",
|
||||
# "spark", "sparkv2", "sparkv3", "sparkv3.5", "sparkv4",
|
||||
# "qwen-turbo", "qwen-plus", "qwen-max", "qwen-local",
|
||||
# "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
|
||||
# "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125", "gpt-4o-2024-05-13"
|
||||
# "claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
|
||||
# "moss", "llama2", "chatglm_onnx", "internlm", "jittorllms_pangualpha", "jittorllms_llama",
|
||||
# "deepseek-chat" ,"deepseek-coder",
|
||||
# "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
|
||||
# ]
|
||||
# --- --- --- ---
|
||||
# 此外，您还可以在接入one-api/vllm/ollama时，
|
||||
# 使用"one-api-*","vllm-*","ollama-*"前缀直接使用非标准方式接入的模型，例如
|
||||
# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)", "ollama-phi3(max_token=4096)"]
|
||||
# --- --- --- ---
|
||||
|
||||
|
||||
# --------------- 以下配置可以优化体验 ---------------
|
||||
# ------------------------------------ 以下配置可以优化体验, 但大部分场合下并不需要修改 ------------------------------------
|
||||
|
||||
# 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
|
||||
# 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
|
||||
# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions", "http://localhost:11434/api/chat": "在这里填写您ollama的URL"}
|
||||
# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions"}
|
||||
API_URL_REDIRECT = {}
|
||||
|
||||
|
||||
@@ -106,10 +77,6 @@ TIMEOUT_SECONDS = 30
|
||||
WEB_PORT = -1
|
||||
|
||||
|
||||
# 是否自动打开浏览器页面
|
||||
AUTO_OPEN_BROWSER = True
|
||||
|
||||
|
||||
# 如果OpenAI不响应（网络卡顿、代理失败、KEY失效），重试的次数限制
|
||||
MAX_RETRY = 2
|
||||
|
||||
@@ -118,6 +85,20 @@ MAX_RETRY = 2
|
||||
DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
|
||||
|
||||
|
||||
# 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
|
||||
LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
|
||||
AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
|
||||
"gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
|
||||
"gpt-4", "gpt-4-32k", "azure-gpt-4", "api2d-gpt-4",
|
||||
"gemini-pro", "chatglm3", "claude-2", "zhipuai"]
|
||||
# P.S. 其他可用的模型还包括 [
|
||||
# "moss", "qwen-turbo", "qwen-plus", "qwen-max"
|
||||
# "zhipuai", "qianfan", "deepseekcoder", "llama2", "qwen-local", "gpt-3.5-turbo-0613",
|
||||
# "gpt-3.5-turbo-16k-0613", "gpt-3.5-random", "api2d-gpt-3.5-turbo", 'api2d-gpt-3.5-turbo-16k',
|
||||
# "spark", "sparkv2", "sparkv3", "chatglm_onnx", "claude-1-100k", "claude-2", "internlm", "jittorllms_pangualpha", "jittorllms_llama"
|
||||
# ]
|
||||
|
||||
|
||||
# 定义界面上“询问多个GPT模型”插件应该使用哪些模型，请从AVAIL_LLM_MODELS中选择，并在不同模型之间用`&`间隔，例如"gpt-3.5-turbo&chatglm3&azure-gpt-4"
|
||||
MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
|
||||
|
||||
@@ -135,7 +116,7 @@ DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
|
||||
# 百度千帆（LLM_MODEL="qianfan"）
|
||||
BAIDU_CLOUD_API_KEY = ''
|
||||
BAIDU_CLOUD_SECRET_KEY = ''
|
||||
BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot' # 可选 "ERNIE-Bot-4"(文心大模型4.0), "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat", "ERNIE-Speed-128K", "ERNIE-Speed-8K", "ERNIE-Lite-8K"
|
||||
BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot' # 可选 "ERNIE-Bot-4"(文心大模型4.0), "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat"
|
||||
|
||||
|
||||
# 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
|
||||
@@ -146,7 +127,6 @@ CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b
|
||||
LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
|
||||
LOCAL_MODEL_QUANT = "FP16" # 默认 "FP16" "INT4" 启用量化INT4版本 "INT8" 启用量化INT8版本
|
||||
|
||||
|
||||
# 设置gradio的并行线程数（不需要修改）
|
||||
CONCURRENT_COUNT = 100
|
||||
|
||||
@@ -164,8 +144,7 @@ ADD_WAIFU = False
|
||||
AUTHENTICATION = []
|
||||
|
||||
|
||||
# 如果需要在二级路径下运行（常规情况下，不要修改!!）
|
||||
# （举例 CUSTOM_PATH = "/gpt_academic"，可以让软件运行在 http://ip:port/gpt_academic/ 下。）
|
||||
# 如果需要在二级路径下运行（常规情况下，不要修改!!）（需要配合修改main.py才能生效!）
|
||||
CUSTOM_PATH = "/"
|
||||
|
||||
|
||||
@@ -193,8 +172,14 @@ AZURE_ENGINE = "填入你亲手写的部署名" # 读 docs\use_azure.
|
||||
AZURE_CFG_ARRAY = {}
|
||||
|
||||
|
||||
# 阿里云实时语音识别 配置难度较高
|
||||
# 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
|
||||
# 使用Newbing (不推荐使用，未来将删除)
|
||||
NEWBING_STYLE = "creative" # ["creative", "balanced", "precise"]
|
||||
NEWBING_COOKIES = """
|
||||
put your new bing cookies here
|
||||
"""
|
||||
|
||||
|
||||
# 阿里云实时语音识别 配置难度较高 仅建议高手用户使用 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
|
||||
ENABLE_AUDIO = False
|
||||
ALIYUN_TOKEN="" # 例如 f37f30e0f9934c34a992f6f64f7eba4f
|
||||
ALIYUN_APPKEY="" # 例如 RoPlZrM88DnAFkZK
|
||||
@@ -202,12 +187,6 @@ ALIYUN_ACCESSKEY="" # （无需填写）
|
||||
ALIYUN_SECRET="" # （无需填写）
|
||||
|
||||
|
||||
# GPT-SOVITS 文本转语音服务的运行地址（将语言模型的生成文本朗读出来）
|
||||
TTS_TYPE = "EDGE_TTS" # EDGE_TTS / LOCAL_SOVITS_API / DISABLE
|
||||
GPT_SOVITS_URL = ""
|
||||
EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
|
||||
|
||||
|
||||
# 接入讯飞星火大模型 https://console.xfyun.cn/services/iat
|
||||
XFYUN_APPID = "00000000"
|
||||
XFYUN_API_SECRET = "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"
|
||||
@@ -216,38 +195,19 @@ XFYUN_API_KEY = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
|
||||
|
||||
# 接入智谱大模型
|
||||
ZHIPUAI_API_KEY = ""
|
||||
ZHIPUAI_MODEL = "" # 此选项已废弃，不再需要填写
|
||||
ZHIPUAI_MODEL = "glm-4" # 可选 "glm-3-turbo" "glm-4"
|
||||
|
||||
|
||||
# # 火山引擎YUNQUE大模型
|
||||
# YUNQUE_SECRET_KEY = ""
|
||||
# YUNQUE_ACCESS_KEY = ""
|
||||
# YUNQUE_MODEL = ""
|
||||
|
||||
|
||||
# Claude API KEY
|
||||
ANTHROPIC_API_KEY = ""
|
||||
|
||||
|
||||
# 月之暗面 API KEY
|
||||
MOONSHOT_API_KEY = ""
|
||||
|
||||
|
||||
# 零一万物(Yi Model) API KEY
|
||||
YIMODEL_API_KEY = ""
|
||||
|
||||
|
||||
# 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
|
||||
DEEPSEEK_API_KEY = ""
|
||||
|
||||
|
||||
# 紫东太初大模型 https://ai-maas.wair.ac.cn
|
||||
TAICHU_API_KEY = ""
|
||||
|
||||
|
||||
# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
|
||||
MATHPIX_APPID = ""
|
||||
MATHPIX_APPKEY = ""
|
||||
|
||||
|
||||
# DOC2X的PDF解析服务，注册账号并获取API KEY: https://doc2x.noedgeai.com/login
|
||||
DOC2X_API_KEY = ""
|
||||
|
||||
|
||||
# 自定义API KEY格式
|
||||
CUSTOM_API_KEY_PATTERN = ""
|
||||
|
||||
@@ -269,10 +229,6 @@ GROBID_URLS = [
|
||||
]
|
||||
|
||||
|
||||
# Searxng互联网检索服务
|
||||
SEARXNG_URL = "https://cloud-1.agent-matrix.com/"
|
||||
|
||||
|
||||
# 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
|
||||
ALLOW_RESET_CONFIG = False
|
||||
|
||||
@@ -281,23 +237,23 @@ ALLOW_RESET_CONFIG = False
|
||||
AUTOGEN_USE_DOCKER = False
|
||||
|
||||
|
||||
# 临时的上传文件夹位置，请尽量不要修改
|
||||
# 临时的上传文件夹位置，请勿修改
|
||||
PATH_PRIVATE_UPLOAD = "private_upload"
|
||||
|
||||
|
||||
# 日志文件夹的位置，请尽量不要修改
|
||||
# 日志文件夹的位置，请勿修改
|
||||
PATH_LOGGING = "gpt_log"
|
||||
|
||||
|
||||
# 存储翻译好的arxiv论文的路径，请尽量不要修改
|
||||
ARXIV_CACHE_DIR = "gpt_log/arxiv_cache"
|
||||
|
||||
|
||||
# 除了连接OpenAI之外，还有哪些场合允许使用代理，请尽量不要修改
|
||||
# 除了连接OpenAI之外，还有哪些场合允许使用代理，请勿修改
|
||||
WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
|
||||
"Warmup_Modules", "Nougat_Download", "AutoGen"]
|
||||
|
||||
|
||||
# *实验性功能*: 自动检测并屏蔽失效的KEY，请勿使用
|
||||
BLOCK_INVALID_APIKEY = False
|
||||
|
||||
|
||||
# 启用插件热加载
|
||||
PLUGIN_HOT_RELOAD = False
|
||||
|
||||
@@ -305,11 +261,7 @@ PLUGIN_HOT_RELOAD = False
|
||||
# 自定义按钮的最大数量限制
|
||||
NUM_CUSTOM_BASIC_BTN = 4
|
||||
|
||||
|
||||
|
||||
"""
|
||||
--------------- 配置关联关系说明 ---------------
|
||||
|
||||
在线大模型配置关联关系示意图
|
||||
│
|
||||
├── "gpt-3.5-turbo" 等openai模型
|
||||
@@ -333,7 +285,7 @@ NUM_CUSTOM_BASIC_BTN = 4
|
||||
│ ├── XFYUN_API_SECRET
|
||||
│ └── XFYUN_API_KEY
|
||||
│
|
||||
├── "claude-3-opus-20240229" 等claude模型
|
||||
├── "claude-1-100k" 等claude模型
|
||||
│ └── ANTHROPIC_API_KEY
|
||||
│
|
||||
├── "stack-claude"
|
||||
@@ -345,11 +297,9 @@ NUM_CUSTOM_BASIC_BTN = 4
|
||||
│ ├── BAIDU_CLOUD_API_KEY
|
||||
│ └── BAIDU_CLOUD_SECRET_KEY
|
||||
│
|
||||
├── "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
|
||||
│ └── ZHIPUAI_API_KEY
|
||||
│
|
||||
├── "yi-34b-chat-0205", "yi-34b-chat-200k" 等零一万物(Yi Model)大模型
|
||||
│ └── YIMODEL_API_KEY
|
||||
├── "zhipuai" 智谱AI大模型chatglm_turbo
|
||||
│ ├── ZHIPUAI_API_KEY
|
||||
│ └── ZHIPUAI_MODEL
|
||||
│
|
||||
├── "qwen-turbo" 等通义千问大模型
|
||||
│ └── DASHSCOPE_API_KEY
|
||||
@@ -357,10 +307,9 @@ NUM_CUSTOM_BASIC_BTN = 4
|
||||
├── "Gemini"
|
||||
│ └── GEMINI_API_KEY
|
||||
│
|
||||
└── "one-api-...(max_token=...)" 用一种更方便的方式接入one-api多模型管理界面
|
||||
├── AVAIL_LLM_MODELS
|
||||
├── API_KEY
|
||||
└── API_URL_REDIRECT
|
||||
└── "newbing" Newbing接口不再稳定，不推荐使用
|
||||
├── NEWBING_STYLE
|
||||
└── NEWBING_COOKIES
|
||||
|
||||
|
||||
本地大模型示意图
|
||||
@@ -394,9 +343,6 @@ NUM_CUSTOM_BASIC_BTN = 4
|
||||
|
||||
插件在线服务配置依赖关系示意图
|
||||
│
|
||||
├── 互联网检索
|
||||
│ └── SEARXNG_URL
|
||||
│
|
||||
├── 语音功能
|
||||
│ ├── ENABLE_AUDIO
|
||||
│ ├── ALIYUN_TOKEN
|
||||
@@ -405,9 +351,6 @@ NUM_CUSTOM_BASIC_BTN = 4
|
||||
│ └── ALIYUN_SECRET
|
||||
│
|
||||
└── PDF文档精准解析
|
||||
├── GROBID_URLS
|
||||
├── MATHPIX_APPID
|
||||
└── MATHPIX_APPKEY
|
||||
|
||||
└── GROBID_URLS
|
||||
|
||||
"""
|
||||
|
||||
@@ -33,19 +33,17 @@ def get_core_functions():
|
||||
"AutoClearHistory": False,
|
||||
# [6] 文本预处理 （可选参数，默认 None，举例：写个函数移除所有的换行符）
|
||||
"PreProcess": None,
|
||||
# [7] 模型选择 （可选参数。如不设置，则使用当前全局模型；如设置，则用指定模型覆盖全局模型。）
|
||||
# "ModelOverride": "gpt-3.5-turbo", # 主要用途：强制点击此基础功能按钮时，使用指定的模型。
|
||||
},
|
||||
|
||||
|
||||
"总结绘制脑图": {
|
||||
# 前缀，会被加在你的输入之前。例如，用来描述你的要求，例如翻译、解释代码、润色等等
|
||||
"Prefix": '''"""\n\n''',
|
||||
"Prefix": r"",
|
||||
# 后缀，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来
|
||||
"Suffix":
|
||||
# dedent() 函数用于去除多行字符串的缩进
|
||||
dedent("\n\n"+r'''
|
||||
"""
|
||||
dedent("\n"+r'''
|
||||
==============================
|
||||
|
||||
使用mermaid flowchart对以上文本进行总结，概括上述段落的内容以及内在逻辑关系，例如：
|
||||
|
||||
@@ -59,7 +57,7 @@ def get_core_functions():
|
||||
C --> |"箭头名2"| F["节点名6"]
|
||||
```
|
||||
|
||||
注意：
|
||||
警告：
|
||||
（1）使用中文
|
||||
（2）节点名字使用引号包裹，如["Laptop"]
|
||||
（3）`|` 和 `"`之间不要存在空格
|
||||
|
||||
@@ -15,43 +15,32 @@ def get_crazy_functions():
|
||||
from crazy_functions.解析项目源代码 import 解析一个Java项目
|
||||
from crazy_functions.解析项目源代码 import 解析一个前端项目
|
||||
from crazy_functions.高级功能函数模板 import 高阶功能模板函数
|
||||
from crazy_functions.高级功能函数模板 import Demo_Wrap
|
||||
from crazy_functions.Latex全文润色 import Latex英文润色
|
||||
from crazy_functions.询问多个大语言模型 import 同时问询
|
||||
from crazy_functions.解析项目源代码 import 解析一个Lua项目
|
||||
from crazy_functions.解析项目源代码 import 解析一个CSharp项目
|
||||
from crazy_functions.总结word文档 import 总结word文档
|
||||
from crazy_functions.解析JupyterNotebook import 解析ipynb文件
|
||||
from crazy_functions.Conversation_To_File import 载入对话历史存档
|
||||
from crazy_functions.Conversation_To_File import 对话历史存档
|
||||
from crazy_functions.Conversation_To_File import Conversation_To_File_Wrap
|
||||
from crazy_functions.Conversation_To_File import 删除所有本地对话历史记录
|
||||
from crazy_functions.对话历史存档 import 对话历史存档
|
||||
from crazy_functions.对话历史存档 import 载入对话历史存档
|
||||
from crazy_functions.对话历史存档 import 删除所有本地对话历史记录
|
||||
from crazy_functions.辅助功能 import 清除缓存
|
||||
from crazy_functions.Markdown_Translate import Markdown英译中
|
||||
from crazy_functions.批量Markdown翻译 import Markdown英译中
|
||||
from crazy_functions.批量总结PDF文档 import 批量总结PDF文档
|
||||
from crazy_functions.PDF_Translate import 批量翻译PDF文档
|
||||
from crazy_functions.批量翻译PDF文档_多线程 import 批量翻译PDF文档
|
||||
from crazy_functions.谷歌检索小助手 import 谷歌检索小助手
|
||||
from crazy_functions.理解PDF文档内容 import 理解PDF文档内容标准文件输入
|
||||
from crazy_functions.Latex全文润色 import Latex中文润色
|
||||
from crazy_functions.Latex全文润色 import Latex英文纠错
|
||||
from crazy_functions.Markdown_Translate import Markdown中译英
|
||||
from crazy_functions.批量Markdown翻译 import Markdown中译英
|
||||
from crazy_functions.虚空终端 import 虚空终端
|
||||
from crazy_functions.生成多种Mermaid图表 import Mermaid_Gen
|
||||
from crazy_functions.PDF_Translate_Wrap import PDF_Tran
|
||||
from crazy_functions.Latex_Function import Latex英文纠错加PDF对比
|
||||
from crazy_functions.Latex_Function import Latex翻译中文并重新编译PDF
|
||||
from crazy_functions.Latex_Function import PDF翻译中文并重新编译PDF
|
||||
from crazy_functions.Latex_Function_Wrap import Arxiv_Localize
|
||||
from crazy_functions.Latex_Function_Wrap import PDF_Localize
|
||||
from crazy_functions.Internet_GPT import 连接网络回答问题
|
||||
from crazy_functions.Internet_GPT_Wrap import NetworkGPT_Wrap
|
||||
from crazy_functions.生成多种Mermaid图表 import 生成多种Mermaid图表
|
||||
|
||||
function_plugins = {
|
||||
"虚空终端": {
|
||||
"Group": "对话|编程|学术|智能体",
|
||||
"Color": "stop",
|
||||
"AsButton": True,
|
||||
"Info": "使用自然语言实现您的想法",
|
||||
"Function": HotReload(虚空终端),
|
||||
},
|
||||
"解析整个Python项目": {
|
||||
@@ -81,26 +70,19 @@ def get_crazy_functions():
|
||||
"Info": "清除所有缓存文件，谨慎操作 | 不需要输入参数",
|
||||
"Function": HotReload(清除缓存),
|
||||
},
|
||||
"生成多种Mermaid图表(从当前对话或路径(.pdf/.md/.docx)中生产图表）": {
|
||||
"生成多种Mermaid图表(从当前对话或文件(.pdf/.md)中生产图表）": {
|
||||
"Group": "对话",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"Info" : "基于当前对话或文件生成多种Mermaid图表,图表类型由模型判断",
|
||||
"Function": None,
|
||||
"Class": Mermaid_Gen
|
||||
},
|
||||
"Arxiv论文翻译": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": True,
|
||||
"Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF), # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
|
||||
"Class": Arxiv_Localize, # 新一代插件需要注册Class
|
||||
"Info" : "基于当前对话或PDF生成多种Mermaid图表,图表类型由模型判断",
|
||||
"Function": HotReload(生成多种Mermaid图表),
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": "请输入图类型对应的数字,不输入则为模型自行判断:1-流程图,2-序列图,3-类图,4-饼图,5-甘特图,6-状态图,7-实体关系图,8-象限提示图,9-思维导图",
|
||||
},
|
||||
"批量总结Word文档": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AsButton": True,
|
||||
"Info": "批量总结word文档 | 输入参数为路径",
|
||||
"Function": HotReload(总结word文档),
|
||||
},
|
||||
@@ -206,42 +188,28 @@ def get_crazy_functions():
|
||||
},
|
||||
"保存当前的对话": {
|
||||
"Group": "对话",
|
||||
"Color": "stop",
|
||||
"AsButton": True,
|
||||
"Info": "保存当前的对话 | 不需要输入参数",
|
||||
"Function": HotReload(对话历史存档), # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
|
||||
"Class": Conversation_To_File_Wrap # 新一代插件需要注册Class
|
||||
"Function": HotReload(对话历史存档),
|
||||
},
|
||||
"[多线程Demo]解析此项目本身（源码自译解）": {
|
||||
"Group": "对话|编程",
|
||||
"Color": "stop",
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Info": "多线程解析并翻译此项目的源码 | 不需要输入参数",
|
||||
"Function": HotReload(解析项目本身),
|
||||
},
|
||||
"查互联网后回答": {
|
||||
"Group": "对话",
|
||||
"Color": "stop",
|
||||
"AsButton": True, # 加入下拉菜单中
|
||||
# "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
|
||||
"Function": HotReload(连接网络回答问题),
|
||||
"Class": NetworkGPT_Wrap # 新一代插件需要注册Class
|
||||
},
|
||||
"历史上的今天": {
|
||||
"Group": "对话",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AsButton": True,
|
||||
"Info": "查看历史上的今天事件 (这是一个面向开发者的插件Demo) | 不需要输入参数",
|
||||
"Function": None,
|
||||
"Class": Demo_Wrap, # 新一代插件需要注册Class
|
||||
"Function": HotReload(高阶功能模板函数),
|
||||
},
|
||||
"精准翻译PDF论文": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": True,
|
||||
"Info": "精准翻译PDF论文为中文 | 输入参数为路径",
|
||||
"Function": HotReload(批量翻译PDF文档), # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
|
||||
"Class": PDF_Tran, # 新一代插件需要注册Class
|
||||
"Function": HotReload(批量翻译PDF文档),
|
||||
},
|
||||
"询问多个GPT模型": {
|
||||
"Group": "对话",
|
||||
@@ -316,51 +284,7 @@ def get_crazy_functions():
|
||||
"Info": "批量将Markdown文件中文翻译为英文 | 输入参数为路径或上传压缩包",
|
||||
"Function": HotReload(Markdown中译英),
|
||||
},
|
||||
"Latex英文纠错+高亮修正位置 [需Latex]": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": "如果有必要, 请在此处追加更细致的矫错指令（使用英文）。",
|
||||
"Function": HotReload(Latex英文纠错加PDF对比),
|
||||
},
|
||||
"Arxiv论文精细翻译（输入arxivID）[需Latex]": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
|
||||
r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
|
||||
r'If the term "agent" is used in this section, it should be translated to "智能体". ',
|
||||
"Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF), # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
|
||||
"Class": Arxiv_Localize, # 新一代插件需要注册Class
|
||||
},
|
||||
"本地Latex论文精细翻译（上传Latex项目）[需Latex]": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
|
||||
r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
|
||||
r'If the term "agent" is used in this section, it should be translated to "智能体". ',
|
||||
"Info": "本地Latex论文精细翻译 | 输入参数是路径",
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF),
|
||||
},
|
||||
"PDF翻译中文并重新编译PDF（上传PDF）[需Latex]": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
|
||||
r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
|
||||
r'If the term "agent" is used in this section, it should be translated to "智能体". ',
|
||||
"Info": "PDF翻译中文，并重新编译PDF | 输入参数为路径",
|
||||
"Function": HotReload(PDF翻译中文并重新编译PDF), # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
|
||||
"Class": PDF_Localize # 新一代插件需要注册Class
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
# -=--=- 尚未充分测试的实验性插件 & 需要额外依赖的插件 -=--=-
|
||||
try:
|
||||
@@ -381,36 +305,36 @@ def get_crazy_functions():
|
||||
print(trimmed_format_exc())
|
||||
print("Load function plugin failed")
|
||||
|
||||
# try:
|
||||
# from crazy_functions.联网的ChatGPT import 连接网络回答问题
|
||||
try:
|
||||
from crazy_functions.联网的ChatGPT import 连接网络回答问题
|
||||
|
||||
# function_plugins.update(
|
||||
# {
|
||||
# "连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
|
||||
# "Group": "对话",
|
||||
# "Color": "stop",
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# # "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
|
||||
# "Function": HotReload(连接网络回答问题),
|
||||
# }
|
||||
# }
|
||||
# )
|
||||
# from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题
|
||||
function_plugins.update(
|
||||
{
|
||||
"连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
|
||||
"Group": "对话",
|
||||
"Color": "stop",
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
# "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
|
||||
"Function": HotReload(连接网络回答问题),
|
||||
}
|
||||
}
|
||||
)
|
||||
from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题
|
||||
|
||||
# function_plugins.update(
|
||||
# {
|
||||
# "连接网络回答问题（中文Bing版，输入问题后点击该插件）": {
|
||||
# "Group": "对话",
|
||||
# "Color": "stop",
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Info": "连接网络回答问题（需要访问中文Bing）| 输入参数是一个问题",
|
||||
# "Function": HotReload(连接bing搜索回答问题),
|
||||
# }
|
||||
# }
|
||||
# )
|
||||
# except:
|
||||
# print(trimmed_format_exc())
|
||||
# print("Load function plugin failed")
|
||||
function_plugins.update(
|
||||
{
|
||||
"连接网络回答问题（中文Bing版，输入问题后点击该插件）": {
|
||||
"Group": "对话",
|
||||
"Color": "stop",
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Info": "连接网络回答问题（需要访问中文Bing）| 输入参数是一个问题",
|
||||
"Function": HotReload(连接bing搜索回答问题),
|
||||
}
|
||||
}
|
||||
)
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
print("Load function plugin failed")
|
||||
|
||||
try:
|
||||
from crazy_functions.解析项目源代码 import 解析任意code项目
|
||||
@@ -439,7 +363,7 @@ def get_crazy_functions():
|
||||
"询问多个GPT模型（手动指定询问哪些模型）": {
|
||||
"Group": "对话",
|
||||
"Color": "stop",
|
||||
"AsButton": True,
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
|
||||
"ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&gpt-4", # 高级参数输入区的显示提示
|
||||
"Function": HotReload(同时问询_指定模型),
|
||||
@@ -534,7 +458,7 @@ def get_crazy_functions():
|
||||
print("Load function plugin failed")
|
||||
|
||||
try:
|
||||
from crazy_functions.Markdown_Translate import Markdown翻译指定语言
|
||||
from crazy_functions.批量Markdown翻译 import Markdown翻译指定语言
|
||||
|
||||
function_plugins.update(
|
||||
{
|
||||
@@ -607,6 +531,47 @@ def get_crazy_functions():
|
||||
print(trimmed_format_exc())
|
||||
print("Load function plugin failed")
|
||||
|
||||
try:
|
||||
from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比
|
||||
from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
|
||||
|
||||
function_plugins.update(
|
||||
{
|
||||
"Latex英文纠错+高亮修正位置 [需Latex]": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": "如果有必要, 请在此处追加更细致的矫错指令（使用英文）。",
|
||||
"Function": HotReload(Latex英文纠错加PDF对比),
|
||||
},
|
||||
"Arxiv论文精细翻译（输入arxivID）[需Latex]": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
|
||||
+ "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
|
||||
+ 'If the term "agent" is used in this section, it should be translated to "智能体". ',
|
||||
"Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF),
|
||||
},
|
||||
"本地Latex论文精细翻译（上传Latex项目）[需Latex]": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
|
||||
+ "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
|
||||
+ 'If the term "agent" is used in this section, it should be translated to "智能体". ',
|
||||
"Info": "本地Latex论文精细翻译 | 输入参数是路径",
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF),
|
||||
}
|
||||
}
|
||||
)
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
print("Load function plugin failed")
|
||||
|
||||
try:
|
||||
from toolbox import get_conf
|
||||
|
||||
232
crazy_functions/CodeInterpreter.py
Normal file
232
crazy_functions/CodeInterpreter.py
Normal file
@@ -0,0 +1,232 @@
|
||||
from collections.abc import Callable, Iterable, Mapping
|
||||
from typing import Any
|
||||
from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc
|
||||
from toolbox import promote_file_to_downloadzone, get_log_folder
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from .crazy_utils import input_clipping, try_install_deps
|
||||
from multiprocessing import Process, Pipe
|
||||
import os
|
||||
import time
|
||||
|
||||
templete = """
|
||||
```python
|
||||
import ... # Put dependencies here, e.g. import numpy as np
|
||||
|
||||
class TerminalFunction(object): # Do not change the name of the class, The name of the class must be `TerminalFunction`
|
||||
|
||||
def run(self, path): # The name of the function must be `run`, it takes only a positional argument.
|
||||
# rewrite the function you have just written here
|
||||
...
|
||||
return generated_file_path
|
||||
```
|
||||
"""
|
||||
|
||||
def inspect_dependency(chatbot, history):
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return True
|
||||
|
||||
def get_code_block(reply):
|
||||
import re
|
||||
pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
|
||||
matches = re.findall(pattern, reply) # find all code blocks in text
|
||||
if len(matches) == 1:
|
||||
return matches[0].strip('python') # code block
|
||||
for match in matches:
|
||||
if 'class TerminalFunction' in match:
|
||||
return match.strip('python') # code block
|
||||
raise RuntimeError("GPT is not generating proper code.")
|
||||
|
||||
def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
|
||||
# 输入
|
||||
prompt_compose = [
|
||||
f'Your job:\n'
|
||||
f'1. write a single Python function, which takes a path of a `{file_type}` file as the only argument and returns a `string` containing the result of analysis or the path of generated files. \n',
|
||||
f"2. You should write this function to perform following task: " + txt + "\n",
|
||||
f"3. Wrap the output python function with markdown codeblock."
|
||||
]
|
||||
i_say = "".join(prompt_compose)
|
||||
demo = []
|
||||
|
||||
# 第一步
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
|
||||
sys_prompt= r"You are a programmer."
|
||||
)
|
||||
history.extend([i_say, gpt_say])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
# 第二步
|
||||
prompt_compose = [
|
||||
"If previous stage is successful, rewrite the function you have just written to satisfy following templete: \n",
|
||||
templete
|
||||
]
|
||||
i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=inputs_show_user,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
sys_prompt= r"You are a programmer."
|
||||
)
|
||||
code_to_return = gpt_say
|
||||
history.extend([i_say, gpt_say])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
# # 第三步
|
||||
# i_say = "Please list to packages to install to run the code above. Then show me how to use `try_install_deps` function to install them."
|
||||
# i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
|
||||
# installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
# inputs=i_say, inputs_show_user=inputs_show_user,
|
||||
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
# sys_prompt= r"You are a programmer."
|
||||
# )
|
||||
# # # 第三步
|
||||
# i_say = "Show me how to use `pip` to install packages to run the code above. "
|
||||
# i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
|
||||
# installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
# inputs=i_say, inputs_show_user=i_say,
|
||||
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
# sys_prompt= r"You are a programmer."
|
||||
# )
|
||||
installation_advance = ""
|
||||
|
||||
return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history
|
||||
|
||||
def make_module(code):
|
||||
module_file = 'gpt_fn_' + gen_time_str().replace('-','_')
|
||||
with open(f'{get_log_folder()}/{module_file}.py', 'w', encoding='utf8') as f:
|
||||
f.write(code)
|
||||
|
||||
def get_class_name(class_string):
|
||||
import re
|
||||
# Use regex to extract the class name
|
||||
class_name = re.search(r'class (\w+)\(', class_string).group(1)
|
||||
return class_name
|
||||
|
||||
class_name = get_class_name(code)
|
||||
return f"{get_log_folder().replace('/', '.')}.{module_file}->{class_name}"
|
||||
|
||||
def init_module_instance(module):
|
||||
import importlib
|
||||
module_, class_ = module.split('->')
|
||||
init_f = getattr(importlib.import_module(module_), class_)
|
||||
return init_f()
|
||||
|
||||
def for_immediate_show_off_when_possible(file_type, fp, chatbot):
|
||||
if file_type in ['png', 'jpg']:
|
||||
image_path = os.path.abspath(fp)
|
||||
chatbot.append(['这是一张图片, 展示如下:',
|
||||
f'本地文件地址: <br/>`{image_path}`<br/>'+
|
||||
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
|
||||
])
|
||||
return chatbot
|
||||
|
||||
def subprocess_worker(instance, file_path, return_dict):
|
||||
return_dict['result'] = instance.run(file_path)
|
||||
|
||||
def have_any_recent_upload_files(chatbot):
|
||||
_5min = 5 * 60
|
||||
if not chatbot: return False # chatbot is None
|
||||
most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
|
||||
if not most_recent_uploaded: return False # most_recent_uploaded is None
|
||||
if time.time() - most_recent_uploaded["time"] < _5min: return True # most_recent_uploaded is new
|
||||
else: return False # most_recent_uploaded is too old
|
||||
|
||||
def get_recent_file_prompt_support(chatbot):
|
||||
most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
|
||||
path = most_recent_uploaded['path']
|
||||
return path
|
||||
|
||||
@CatchException
|
||||
def 虚空终端CodeInterpreter(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
txt 输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
|
||||
llm_kwargs gpt模型参数，如温度和top_p等，一般原样传递下去就行
|
||||
plugin_kwargs 插件模型的参数，暂时没有用武之地
|
||||
chatbot 聊天显示框的句柄，用于显示给用户
|
||||
history 聊天历史，前情提要
|
||||
system_prompt 给gpt的静默提醒
|
||||
user_request 当前用户的请求信息（IP地址等）
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
# 清空历史，以免输入溢出
|
||||
history = []; clear_file_downloadzone(chatbot)
|
||||
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"CodeInterpreter开源版, 此插件处于开发阶段, 建议暂时不要使用, 插件初始化中 ..."
|
||||
])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
if have_any_recent_upload_files(chatbot):
|
||||
file_path = get_recent_file_prompt_support(chatbot)
|
||||
else:
|
||||
chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 读取文件
|
||||
if ("recently_uploaded_files" in plugin_kwargs) and (plugin_kwargs["recently_uploaded_files"] == ""): plugin_kwargs.pop("recently_uploaded_files")
|
||||
recently_uploaded_files = plugin_kwargs.get("recently_uploaded_files", None)
|
||||
file_path = recently_uploaded_files[-1]
|
||||
file_type = file_path.split('.')[-1]
|
||||
|
||||
# 粗心检查
|
||||
if is_the_upload_folder(txt):
|
||||
chatbot.append([
|
||||
"...",
|
||||
f"请在输入框内填写需求，然后再次点击该插件（文件路径 {file_path} 已经被记忆）"
|
||||
])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 开始干正事
|
||||
for j in range(5): # 最多重试5次
|
||||
try:
|
||||
code, installation_advance, txt, file_type, llm_kwargs, chatbot, history = \
|
||||
yield from gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history)
|
||||
code = get_code_block(code)
|
||||
res = make_module(code)
|
||||
instance = init_module_instance(res)
|
||||
break
|
||||
except Exception as e:
|
||||
chatbot.append([f"第{j}次代码生成尝试，失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 代码生成结束, 开始执行
|
||||
try:
|
||||
import multiprocessing
|
||||
manager = multiprocessing.Manager()
|
||||
return_dict = manager.dict()
|
||||
|
||||
p = multiprocessing.Process(target=subprocess_worker, args=(instance, file_path, return_dict))
|
||||
# only has 10 seconds to run
|
||||
p.start(); p.join(timeout=10)
|
||||
if p.is_alive(): p.terminate(); p.join()
|
||||
p.close()
|
||||
res = return_dict['result']
|
||||
# res = instance.run(file_path)
|
||||
except Exception as e:
|
||||
chatbot.append(["执行失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
|
||||
# chatbot.append(["如果是缺乏依赖，请参考以下建议", installation_advance])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 顺利完成，收尾
|
||||
res = str(res)
|
||||
if os.path.exists(res):
|
||||
chatbot.append(["执行成功了，结果是一个有效文件", "结果：" + res])
|
||||
new_file_path = promote_file_to_downloadzone(res, chatbot=chatbot)
|
||||
chatbot = for_immediate_show_off_when_possible(file_type, new_file_path, chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
else:
|
||||
chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
"""
|
||||
测试：
|
||||
裁剪图像，保留下半部分
|
||||
交换图像的蓝色通道和红色通道
|
||||
将图像转为灰度图像
|
||||
将csv文件转excel表格
|
||||
"""
|
||||
@@ -1,142 +0,0 @@
|
||||
from toolbox import CatchException, update_ui, get_conf
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from request_llms.bridge_all import model_info
|
||||
import urllib.request
|
||||
import random
|
||||
from functools import lru_cache
|
||||
from check_proxy import check_proxy
|
||||
|
||||
@lru_cache
|
||||
def get_auth_ip():
|
||||
ip = check_proxy(None, return_ip=True)
|
||||
if ip is None:
|
||||
return '114.114.114.' + str(random.randint(1, 10))
|
||||
return ip
|
||||
|
||||
def searxng_request(query, proxies, categories='general', searxng_url=None, engines=None):
|
||||
if searxng_url is None:
|
||||
url = get_conf("SEARXNG_URL")
|
||||
else:
|
||||
url = searxng_url
|
||||
|
||||
if engines is None:
|
||||
engines = 'bing'
|
||||
|
||||
if categories == 'general':
|
||||
params = {
|
||||
'q': query, # 搜索查询
|
||||
'format': 'json', # 输出格式为JSON
|
||||
'language': 'zh', # 搜索语言
|
||||
'engines': engines,
|
||||
}
|
||||
elif categories == 'science':
|
||||
params = {
|
||||
'q': query, # 搜索查询
|
||||
'format': 'json', # 输出格式为JSON
|
||||
'language': 'zh', # 搜索语言
|
||||
'categories': 'science'
|
||||
}
|
||||
else:
|
||||
raise ValueError('不支持的检索类型')
|
||||
|
||||
headers = {
|
||||
'Accept-Language': 'zh-CN,zh;q=0.9',
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
|
||||
'X-Forwarded-For': get_auth_ip(),
|
||||
'X-Real-IP': get_auth_ip()
|
||||
}
|
||||
results = []
|
||||
response = requests.post(url, params=params, headers=headers, proxies=proxies, timeout=30)
|
||||
if response.status_code == 200:
|
||||
json_result = response.json()
|
||||
for result in json_result['results']:
|
||||
item = {
|
||||
"title": result.get("title", ""),
|
||||
"source": result.get("engines", "unknown"),
|
||||
"content": result.get("content", ""),
|
||||
"link": result["url"],
|
||||
}
|
||||
results.append(item)
|
||||
return results
|
||||
else:
|
||||
if response.status_code == 429:
|
||||
raise ValueError("Searxng（在线搜索服务）当前使用人数太多，请稍后。")
|
||||
else:
|
||||
raise ValueError("在线搜索失败，状态码: " + str(response.status_code) + '\t' + response.content.decode('utf-8'))
|
||||
|
||||
def scrape_text(url, proxies) -> str:
|
||||
"""Scrape text from a webpage
|
||||
|
||||
Args:
|
||||
url (str): The URL to scrape text from
|
||||
|
||||
Returns:
|
||||
str: The scraped text
|
||||
"""
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36',
|
||||
'Content-Type': 'text/plain',
|
||||
}
|
||||
try:
|
||||
response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
|
||||
if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
|
||||
except:
|
||||
return "无法连接到该网页"
|
||||
soup = BeautifulSoup(response.text, "html.parser")
|
||||
for script in soup(["script", "style"]):
|
||||
script.extract()
|
||||
text = soup.get_text()
|
||||
lines = (line.strip() for line in text.splitlines())
|
||||
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
|
||||
text = "\n".join(chunk for chunk in chunks if chunk)
|
||||
return text
|
||||
|
||||
@CatchException
|
||||
def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
chatbot.append((f"请结合互联网信息回答以下问题：{txt}", "检索中..."))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# ------------- < 第1步：爬取搜索引擎的结果 > -------------
|
||||
from toolbox import get_conf
|
||||
proxies = get_conf('proxies')
|
||||
categories = plugin_kwargs.get('categories', 'general')
|
||||
searxng_url = plugin_kwargs.get('searxng_url', None)
|
||||
engines = plugin_kwargs.get('engine', None)
|
||||
urls = searxng_request(txt, proxies, categories, searxng_url, engines=engines)
|
||||
history = []
|
||||
if len(urls) == 0:
|
||||
chatbot.append((f"结论：{txt}",
|
||||
"[Local Message] 受到限制，无法从searxng获取信息！请尝试更换搜索引擎。"))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
# ------------- < 第2步：依次访问网页 > -------------
|
||||
max_search_result = 5 # 最多收纳多少个网页的结果
|
||||
chatbot.append([f"联网检索中 ...", None])
|
||||
for index, url in enumerate(urls[:max_search_result]):
|
||||
res = scrape_text(url['link'], proxies)
|
||||
prefix = f"第{index}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
|
||||
history.extend([prefix, res])
|
||||
res_squeeze = res.replace('\n', '...')
|
||||
chatbot[-1] = [prefix + "\n\n" + res_squeeze[:500] + "......", None]
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# ------------- < 第3步：ChatGPT综合 > -------------
|
||||
i_say = f"从以上搜索结果中抽取信息，然后回答问题：{txt}"
|
||||
i_say, history = input_clipping( # 裁剪输入，从最长的条目开始裁剪，防止爆token
|
||||
inputs=i_say,
|
||||
history=history,
|
||||
max_token_limit=min(model_info[llm_kwargs['llm_model']]['max_token']*3//4, 8192)
|
||||
)
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
sys_prompt="请从给定的若干条搜索结果中抽取信息，对最相关的两个搜索结果进行总结，然后回答问题。"
|
||||
)
|
||||
chatbot[-1] = (i_say, gpt_say)
|
||||
history.append(i_say);history.append(gpt_say)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
@@ -1,44 +0,0 @@
|
||||
|
||||
from toolbox import get_conf
|
||||
from crazy_functions.Internet_GPT import 连接网络回答问题
|
||||
from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
|
||||
|
||||
|
||||
class NetworkGPT_Wrap(GptAcademicPluginTemplate):
|
||||
def __init__(self):
|
||||
"""
|
||||
请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
|
||||
"""
|
||||
pass
|
||||
|
||||
def define_arg_selection_menu(self):
|
||||
"""
|
||||
定义插件的二级选项菜单
|
||||
|
||||
第一个参数，名称`main_input`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
|
||||
第二个参数，名称`advanced_arg`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
|
||||
第三个参数，名称`allow_cache`，参数`type`声明这是一个下拉菜单，下拉菜单上方显示`title`+`description`，下拉菜单的选项为`options`，`default_value`为下拉菜单默认值；
|
||||
|
||||
"""
|
||||
gui_definition = {
|
||||
"main_input":
|
||||
ArgProperty(title="输入问题", description="待通过互联网检索的问题", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||
"categories":
|
||||
ArgProperty(title="搜索分类", options=["网页", "学术论文"], default_value="网页", description="无", type="dropdown").model_dump_json(),
|
||||
"engine":
|
||||
ArgProperty(title="选择搜索引擎", options=["bing", "google", "duckduckgo"], default_value="bing", description="无", type="dropdown").model_dump_json(),
|
||||
"searxng_url":
|
||||
ArgProperty(title="Searxng服务地址", description="输入Searxng的地址", default_value=get_conf("SEARXNG_URL"), type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||
|
||||
}
|
||||
return gui_definition
|
||||
|
||||
def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
执行插件
|
||||
"""
|
||||
if plugin_kwargs["categories"] == "网页": plugin_kwargs["categories"] = "general"
|
||||
if plugin_kwargs["categories"] == "学术论文": plugin_kwargs["categories"] = "science"
|
||||
|
||||
yield from 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
|
||||
@@ -1,548 +0,0 @@
|
||||
from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone, check_repeat_upload, map_file_to_sha256
|
||||
from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
|
||||
from functools import partial
|
||||
import glob, os, requests, time, json, tarfile
|
||||
|
||||
pj = os.path.join
|
||||
ARXIV_CACHE_DIR = get_conf("ARXIV_CACHE_DIR")
|
||||
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
|
||||
# 专业词汇声明 = 'If the term "agent" is used in this section, it should be translated to "智能体". '
|
||||
def switch_prompt(pfg, mode, more_requirement):
|
||||
"""
|
||||
Generate prompts and system prompts based on the mode for proofreading or translating.
|
||||
Args:
|
||||
- pfg: Proofreader or Translator instance.
|
||||
- mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
|
||||
|
||||
Returns:
|
||||
- inputs_array: A list of strings containing prompts for users to respond to.
|
||||
- sys_prompt_array: A list of strings containing prompts for system prompts.
|
||||
"""
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
if mode == 'proofread_en':
|
||||
inputs_array = [r"Below is a section from an academic paper, proofread this section." +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
|
||||
r"Answer me only with the revised text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
|
||||
elif mode == 'translate_zh':
|
||||
inputs_array = [
|
||||
r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
|
||||
r"Answer me only with the translated text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
|
||||
else:
|
||||
assert False, "未知指令"
|
||||
return inputs_array, sys_prompt_array
|
||||
|
||||
|
||||
def desend_to_extracted_folder_if_exist(project_folder):
|
||||
"""
|
||||
Descend into the extracted folder if it exists, otherwise return the original folder.
|
||||
|
||||
Args:
|
||||
- project_folder: A string specifying the folder path.
|
||||
|
||||
Returns:
|
||||
- A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
|
||||
"""
|
||||
maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
|
||||
if len(maybe_dir) == 0: return project_folder
|
||||
if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
|
||||
return project_folder
|
||||
|
||||
|
||||
def move_project(project_folder, arxiv_id=None):
|
||||
"""
|
||||
Create a new work folder and copy the project folder to it.
|
||||
|
||||
Args:
|
||||
- project_folder: A string specifying the folder path of the project.
|
||||
|
||||
Returns:
|
||||
- A string specifying the path to the new work folder.
|
||||
"""
|
||||
import shutil, time
|
||||
time.sleep(2) # avoid time string conflict
|
||||
if arxiv_id is not None:
|
||||
new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
|
||||
else:
|
||||
new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
|
||||
try:
|
||||
shutil.rmtree(new_workfolder)
|
||||
except:
|
||||
pass
|
||||
|
||||
# align subfolder if there is a folder wrapper
|
||||
items = glob.glob(pj(project_folder, '*'))
|
||||
items = [item for item in items if os.path.basename(item) != '__MACOSX']
|
||||
if len(glob.glob(pj(project_folder, '*.tex'))) == 0 and len(items) == 1:
|
||||
if os.path.isdir(items[0]): project_folder = items[0]
|
||||
|
||||
shutil.copytree(src=project_folder, dst=new_workfolder)
|
||||
return new_workfolder
|
||||
|
||||
|
||||
def arxiv_download(chatbot, history, txt, allow_cache=True):
|
||||
def check_cached_translation_pdf(arxiv_id):
|
||||
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
|
||||
if not os.path.exists(translation_dir):
|
||||
os.makedirs(translation_dir)
|
||||
target_file = pj(translation_dir, 'translate_zh.pdf')
|
||||
if os.path.exists(target_file):
|
||||
promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
|
||||
target_file_compare = pj(translation_dir, 'comparison.pdf')
|
||||
if os.path.exists(target_file_compare):
|
||||
promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
|
||||
return target_file
|
||||
return False
|
||||
|
||||
def is_float(s):
|
||||
try:
|
||||
float(s)
|
||||
return True
|
||||
except ValueError:
|
||||
return False
|
||||
|
||||
if txt.startswith('https://arxiv.org/pdf/'):
|
||||
arxiv_id = txt.split('/')[-1] # 2402.14207v2.pdf
|
||||
txt = arxiv_id.split('v')[0] # 2402.14207
|
||||
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt.strip()
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt[:10]
|
||||
|
||||
if not txt.startswith('https://arxiv.org'):
|
||||
return txt, None # 是本地文件，跳过下载
|
||||
|
||||
# <-------------- inspect format ------------->
|
||||
chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
time.sleep(1) # 刷新界面
|
||||
|
||||
url_ = txt # https://arxiv.org/abs/1707.06690
|
||||
|
||||
if not txt.startswith('https://arxiv.org/abs/'):
|
||||
msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
|
||||
yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
|
||||
return msg, None
|
||||
# <-------------- set format ------------->
|
||||
arxiv_id = url_.split('/abs/')[-1]
|
||||
if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
|
||||
cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
|
||||
if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
|
||||
|
||||
url_tar = url_.replace('/abs/', '/e-print/')
|
||||
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
|
||||
extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
|
||||
os.makedirs(translation_dir, exist_ok=True)
|
||||
|
||||
# <-------------- download arxiv source file ------------->
|
||||
dst = pj(translation_dir, arxiv_id + '.tar')
|
||||
if os.path.exists(dst):
|
||||
yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history) # 刷新界面
|
||||
else:
|
||||
yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history) # 刷新界面
|
||||
proxies = get_conf('proxies')
|
||||
r = requests.get(url_tar, proxies=proxies)
|
||||
with open(dst, 'wb+') as f:
|
||||
f.write(r.content)
|
||||
# <-------------- extract file ------------->
|
||||
yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history) # 刷新界面
|
||||
from toolbox import extract_archive
|
||||
extract_archive(file_path=dst, dest_dir=extract_dst)
|
||||
return extract_dst, arxiv_id
|
||||
|
||||
|
||||
def pdf2tex_project(pdf_file_path, plugin_kwargs):
|
||||
if plugin_kwargs["method"] == "MATHPIX":
|
||||
# Mathpix API credentials
|
||||
app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
|
||||
headers = {"app_id": app_id, "app_key": app_key}
|
||||
|
||||
# Step 1: Send PDF file for processing
|
||||
options = {
|
||||
"conversion_formats": {"tex.zip": True},
|
||||
"math_inline_delimiters": ["$", "$"],
|
||||
"rm_spaces": True
|
||||
}
|
||||
|
||||
response = requests.post(url="https://api.mathpix.com/v3/pdf",
|
||||
headers=headers,
|
||||
data={"options_json": json.dumps(options)},
|
||||
files={"file": open(pdf_file_path, "rb")})
|
||||
|
||||
if response.ok:
|
||||
pdf_id = response.json()["pdf_id"]
|
||||
print(f"PDF processing initiated. PDF ID: {pdf_id}")
|
||||
|
||||
# Step 2: Check processing status
|
||||
while True:
|
||||
conversion_response = requests.get(f"https://api.mathpix.com/v3/pdf/{pdf_id}", headers=headers)
|
||||
conversion_data = conversion_response.json()
|
||||
|
||||
if conversion_data["status"] == "completed":
|
||||
print("PDF processing completed.")
|
||||
break
|
||||
elif conversion_data["status"] == "error":
|
||||
print("Error occurred during processing.")
|
||||
else:
|
||||
print(f"Processing status: {conversion_data['status']}")
|
||||
time.sleep(5) # wait for a few seconds before checking again
|
||||
|
||||
# Step 3: Save results to local files
|
||||
output_dir = os.path.join(os.path.dirname(pdf_file_path), 'mathpix_output')
|
||||
if not os.path.exists(output_dir):
|
||||
os.makedirs(output_dir)
|
||||
|
||||
url = f"https://api.mathpix.com/v3/pdf/{pdf_id}.tex"
|
||||
response = requests.get(url, headers=headers)
|
||||
file_name_wo_dot = '_'.join(os.path.basename(pdf_file_path).split('.')[:-1])
|
||||
output_name = f"{file_name_wo_dot}.tex.zip"
|
||||
output_path = os.path.join(output_dir, output_name)
|
||||
with open(output_path, "wb") as output_file:
|
||||
output_file.write(response.content)
|
||||
print(f"tex.zip file saved at: {output_path}")
|
||||
|
||||
import zipfile
|
||||
unzip_dir = os.path.join(output_dir, file_name_wo_dot)
|
||||
with zipfile.ZipFile(output_path, 'r') as zip_ref:
|
||||
zip_ref.extractall(unzip_dir)
|
||||
|
||||
return unzip_dir
|
||||
|
||||
else:
|
||||
print(f"Error sending PDF for processing. Status code: {response.status_code}")
|
||||
return None
|
||||
else:
|
||||
from crazy_functions.pdf_fns.parse_pdf_via_doc2x import 解析PDF_DOC2X_转Latex
|
||||
unzip_dir = 解析PDF_DOC2X_转Latex(pdf_file_path)
|
||||
return unzip_dir
|
||||
|
||||
|
||||
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
|
||||
|
||||
@CatchException
|
||||
def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append(["函数插件功能？",
|
||||
"对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
history = []
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
from shared_utils.fastapi_server import validate_path_safety
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
project_folder = move_project(project_folder, arxiv_id=None)
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='proofread_en',
|
||||
switch_prompt=_switch_prompt_)
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge',
|
||||
main_file_modified='merge_proofread_en',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder,
|
||||
work_folder=project_folder)
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了",
|
||||
'虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+Conversation_To_File进行反馈 ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
|
||||
@CatchException
|
||||
def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
no_cache = more_req.startswith("--no-cache")
|
||||
if no_cache: more_req.lstrip("--no-cache")
|
||||
allow_cache = not no_cache
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
history = []
|
||||
try:
|
||||
txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
|
||||
except tarfile.ReadError as e:
|
||||
yield from update_ui_lastest_msg(
|
||||
"无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。",
|
||||
chatbot=chatbot, history=history)
|
||||
return
|
||||
|
||||
if txt.endswith('.pdf'):
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现已经存在翻译好的PDF文档")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无法处理: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
from shared_utils.fastapi_server import validate_path_safety
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
project_folder = move_project(project_folder, arxiv_id)
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='translate_zh',
|
||||
switch_prompt=_switch_prompt_)
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge',
|
||||
main_file_modified='merge_translate_zh', mode='translate_zh',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder,
|
||||
work_folder=project_folder)
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了",
|
||||
'虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 插件主程序3 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
|
||||
@CatchException
|
||||
def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"将PDF转换为Latex项目，翻译为中文后重新编译为PDF。函数插件贡献者: Marroh。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
no_cache = more_req.startswith("--no-cache")
|
||||
if no_cache: more_req.lstrip("--no-cache")
|
||||
allow_cache = not no_cache
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无法处理: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.pdf文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
if len(file_manifest) != 1:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"不支持同时处理多个pdf文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
if plugin_kwargs.get("method", "") == 'MATHPIX':
|
||||
app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
|
||||
if len(app_id) == 0 or len(app_key) == 0:
|
||||
report_exception(chatbot, history, a="缺失 MATHPIX_APPID 和 MATHPIX_APPKEY。", b=f"请配置 MATHPIX_APPID 和 MATHPIX_APPKEY")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
if plugin_kwargs.get("method", "") == 'DOC2X':
|
||||
app_id, app_key = "", ""
|
||||
DOC2X_API_KEY = get_conf('DOC2X_API_KEY')
|
||||
if len(DOC2X_API_KEY) == 0:
|
||||
report_exception(chatbot, history, a="缺失 DOC2X_API_KEY。", b=f"请配置 DOC2X_API_KEY")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
hash_tag = map_file_to_sha256(file_manifest[0])
|
||||
|
||||
# # <-------------- check repeated pdf ------------->
|
||||
# chatbot.append([f"检查PDF是否被重复上传", "正在检查..."])
|
||||
# yield from update_ui(chatbot=chatbot, history=history)
|
||||
# repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)
|
||||
|
||||
# if repeat:
|
||||
# yield from update_ui_lastest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)
|
||||
# try:
|
||||
# translate_pdf = [f for f in glob.glob(f'{project_folder}/**/merge_translate_zh.pdf', recursive=True)][0]
|
||||
# promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)
|
||||
# comparison_pdf = [f for f in glob.glob(f'{project_folder}/**/comparison.pdf', recursive=True)][0]
|
||||
# promote_file_to_downloadzone(comparison_pdf, rename_file=None, chatbot=chatbot)
|
||||
# zip_res = zip_result(project_folder)
|
||||
# promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
# return
|
||||
# except:
|
||||
# report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现重复上传，但是无法找到相关文件")
|
||||
# yield from update_ui(chatbot=chatbot, history=history)
|
||||
# else:
|
||||
# yield from update_ui_lastest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
|
||||
|
||||
# <-------------- convert pdf into tex ------------->
|
||||
chatbot.append([f"解析项目: {txt}", "正在将PDF转换为tex项目，请耐心等待..."])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
project_folder = pdf2tex_project(file_manifest[0], plugin_kwargs)
|
||||
if project_folder is None:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"PDF转换为tex项目失败")
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
return False
|
||||
|
||||
# <-------------- translate latex file into Chinese ------------->
|
||||
yield from update_ui_lastest_msg("正在tex项目将翻译为中文...", chatbot=chatbot, history=history)
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
from shared_utils.fastapi_server import validate_path_safety
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
project_folder = move_project(project_folder)
|
||||
|
||||
# <-------------- set a hash tag for repeat-checking ------------->
|
||||
with open(pj(project_folder, hash_tag + '.tag'), 'w') as f:
|
||||
f.write(hash_tag)
|
||||
f.close()
|
||||
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='translate_zh',
|
||||
switch_prompt=_switch_prompt_)
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
yield from update_ui_lastest_msg("正在将翻译好的项目tex项目编译为PDF...", chatbot=chatbot, history=history)
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge',
|
||||
main_file_modified='merge_translate_zh', mode='translate_zh',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder,
|
||||
work_folder=project_folder)
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了",
|
||||
'虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history);
|
||||
time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
@@ -1,78 +0,0 @@
|
||||
|
||||
from crazy_functions.Latex_Function import Latex翻译中文并重新编译PDF, PDF翻译中文并重新编译PDF
|
||||
from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
|
||||
|
||||
|
||||
class Arxiv_Localize(GptAcademicPluginTemplate):
|
||||
def __init__(self):
|
||||
"""
|
||||
请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
|
||||
"""
|
||||
pass
|
||||
|
||||
def define_arg_selection_menu(self):
|
||||
"""
|
||||
定义插件的二级选项菜单
|
||||
|
||||
第一个参数，名称`main_input`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
|
||||
第二个参数，名称`advanced_arg`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
|
||||
第三个参数，名称`allow_cache`，参数`type`声明这是一个下拉菜单，下拉菜单上方显示`title`+`description`，下拉菜单的选项为`options`，`default_value`为下拉菜单默认值；
|
||||
|
||||
"""
|
||||
gui_definition = {
|
||||
"main_input":
|
||||
ArgProperty(title="ArxivID", description="输入Arxiv的ID或者网址", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||
"advanced_arg":
|
||||
ArgProperty(title="额外的翻译提示词",
|
||||
description=r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
|
||||
r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
|
||||
r'If the term "agent" is used in this section, it should be translated to "智能体". ',
|
||||
default_value="", type="string").model_dump_json(), # 高级参数输入区，自动同步
|
||||
"allow_cache":
|
||||
ArgProperty(title="是否允许从缓存中调取结果", options=["允许缓存", "从头执行"], default_value="允许缓存", description="无", type="dropdown").model_dump_json(),
|
||||
}
|
||||
return gui_definition
|
||||
|
||||
def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
执行插件
|
||||
"""
|
||||
allow_cache = plugin_kwargs["allow_cache"]
|
||||
advanced_arg = plugin_kwargs["advanced_arg"]
|
||||
|
||||
if allow_cache == "从头执行": plugin_kwargs["advanced_arg"] = "--no-cache " + plugin_kwargs["advanced_arg"]
|
||||
yield from Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
|
||||
|
||||
|
||||
class PDF_Localize(GptAcademicPluginTemplate):
|
||||
def __init__(self):
|
||||
"""
|
||||
请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
|
||||
"""
|
||||
pass
|
||||
|
||||
def define_arg_selection_menu(self):
|
||||
"""
|
||||
定义插件的二级选项菜单
|
||||
"""
|
||||
gui_definition = {
|
||||
"main_input":
|
||||
ArgProperty(title="PDF文件路径", description="未指定路径，请上传文件后，再点击该插件", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||
"advanced_arg":
|
||||
ArgProperty(title="额外的翻译提示词",
|
||||
description=r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
|
||||
r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
|
||||
r'If the term "agent" is used in this section, it should be translated to "智能体". ',
|
||||
default_value="", type="string").model_dump_json(), # 高级参数输入区，自动同步
|
||||
"method":
|
||||
ArgProperty(title="采用哪种方法执行转换", options=["MATHPIX", "DOC2X"], default_value="DOC2X", description="无", type="dropdown").model_dump_json(),
|
||||
|
||||
}
|
||||
return gui_definition
|
||||
|
||||
def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
执行插件
|
||||
"""
|
||||
yield from PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
@@ -81,8 +81,8 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
# <-------- 多线程润色开始 ---------->
|
||||
if language == 'en':
|
||||
if mode == 'polish':
|
||||
inputs_array = [r"Below is a section from an academic paper, polish this section to meet the academic standard, " +
|
||||
r"improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" +
|
||||
inputs_array = ["Below is a section from an academic paper, polish this section to meet the academic standard, " +
|
||||
"improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
else:
|
||||
inputs_array = [r"Below is a section from an academic paper, proofread this section." +
|
||||
@@ -93,10 +93,10 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
|
||||
elif language == 'zh':
|
||||
if mode == 'polish':
|
||||
inputs_array = [r"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
|
||||
inputs_array = [f"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
else:
|
||||
inputs_array = [r"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
|
||||
inputs_array = [f"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
inputs_show_user_array = [f"润色 {f}" for f in pfg.sp_file_tag]
|
||||
sys_prompt_array=["你是一位专业的中文学术论文作家。" for _ in range(n_split)]
|
||||
|
||||
313
crazy_functions/Latex输出PDF结果.py
Normal file
313
crazy_functions/Latex输出PDF结果.py
Normal file
@@ -0,0 +1,313 @@
|
||||
from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
|
||||
from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
|
||||
from functools import partial
|
||||
import glob, os, requests, time, tarfile
|
||||
pj = os.path.join
|
||||
ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
|
||||
# 专业词汇声明 = 'If the term "agent" is used in this section, it should be translated to "智能体". '
|
||||
def switch_prompt(pfg, mode, more_requirement):
|
||||
"""
|
||||
Generate prompts and system prompts based on the mode for proofreading or translating.
|
||||
Args:
|
||||
- pfg: Proofreader or Translator instance.
|
||||
- mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
|
||||
|
||||
Returns:
|
||||
- inputs_array: A list of strings containing prompts for users to respond to.
|
||||
- sys_prompt_array: A list of strings containing prompts for system prompts.
|
||||
"""
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
if mode == 'proofread_en':
|
||||
inputs_array = [r"Below is a section from an academic paper, proofread this section." +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
|
||||
r"Answer me only with the revised text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
|
||||
elif mode == 'translate_zh':
|
||||
inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
|
||||
r"Answer me only with the translated text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
|
||||
else:
|
||||
assert False, "未知指令"
|
||||
return inputs_array, sys_prompt_array
|
||||
|
||||
def desend_to_extracted_folder_if_exist(project_folder):
|
||||
"""
|
||||
Descend into the extracted folder if it exists, otherwise return the original folder.
|
||||
|
||||
Args:
|
||||
- project_folder: A string specifying the folder path.
|
||||
|
||||
Returns:
|
||||
- A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
|
||||
"""
|
||||
maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
|
||||
if len(maybe_dir) == 0: return project_folder
|
||||
if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
|
||||
return project_folder
|
||||
|
||||
def move_project(project_folder, arxiv_id=None):
|
||||
"""
|
||||
Create a new work folder and copy the project folder to it.
|
||||
|
||||
Args:
|
||||
- project_folder: A string specifying the folder path of the project.
|
||||
|
||||
Returns:
|
||||
- A string specifying the path to the new work folder.
|
||||
"""
|
||||
import shutil, time
|
||||
time.sleep(2) # avoid time string conflict
|
||||
if arxiv_id is not None:
|
||||
new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
|
||||
else:
|
||||
new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
|
||||
try:
|
||||
shutil.rmtree(new_workfolder)
|
||||
except:
|
||||
pass
|
||||
|
||||
# align subfolder if there is a folder wrapper
|
||||
items = glob.glob(pj(project_folder,'*'))
|
||||
items = [item for item in items if os.path.basename(item)!='__MACOSX']
|
||||
if len(glob.glob(pj(project_folder,'*.tex'))) == 0 and len(items) == 1:
|
||||
if os.path.isdir(items[0]): project_folder = items[0]
|
||||
|
||||
shutil.copytree(src=project_folder, dst=new_workfolder)
|
||||
return new_workfolder
|
||||
|
||||
def arxiv_download(chatbot, history, txt, allow_cache=True):
|
||||
def check_cached_translation_pdf(arxiv_id):
|
||||
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
|
||||
if not os.path.exists(translation_dir):
|
||||
os.makedirs(translation_dir)
|
||||
target_file = pj(translation_dir, 'translate_zh.pdf')
|
||||
if os.path.exists(target_file):
|
||||
promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
|
||||
target_file_compare = pj(translation_dir, 'comparison.pdf')
|
||||
if os.path.exists(target_file_compare):
|
||||
promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
|
||||
return target_file
|
||||
return False
|
||||
def is_float(s):
|
||||
try:
|
||||
float(s)
|
||||
return True
|
||||
except ValueError:
|
||||
return False
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt.strip()
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt[:10]
|
||||
if not txt.startswith('https://arxiv.org'):
|
||||
return txt, None # 是本地文件，跳过下载
|
||||
|
||||
# <-------------- inspect format ------------->
|
||||
chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
time.sleep(1) # 刷新界面
|
||||
|
||||
url_ = txt # https://arxiv.org/abs/1707.06690
|
||||
if not txt.startswith('https://arxiv.org/abs/'):
|
||||
msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
|
||||
yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
|
||||
return msg, None
|
||||
# <-------------- set format ------------->
|
||||
arxiv_id = url_.split('/abs/')[-1]
|
||||
if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
|
||||
cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
|
||||
if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
|
||||
|
||||
url_tar = url_.replace('/abs/', '/e-print/')
|
||||
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
|
||||
extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
|
||||
os.makedirs(translation_dir, exist_ok=True)
|
||||
|
||||
# <-------------- download arxiv source file ------------->
|
||||
dst = pj(translation_dir, arxiv_id+'.tar')
|
||||
if os.path.exists(dst):
|
||||
yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history) # 刷新界面
|
||||
else:
|
||||
yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history) # 刷新界面
|
||||
proxies = get_conf('proxies')
|
||||
r = requests.get(url_tar, proxies=proxies)
|
||||
with open(dst, 'wb+') as f:
|
||||
f.write(r.content)
|
||||
# <-------------- extract file ------------->
|
||||
yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history) # 刷新界面
|
||||
from toolbox import extract_archive
|
||||
extract_archive(file_path=dst, dest_dir=extract_dst)
|
||||
return extract_dst, arxiv_id
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
|
||||
|
||||
@CatchException
|
||||
def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append([ "函数插件功能？",
|
||||
"对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([ f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
history = []
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
project_folder = move_project(project_folder, arxiv_id=None)
|
||||
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='proofread_en', switch_prompt=_switch_prompt_)
|
||||
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread_en',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
|
||||
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
|
||||
@CatchException
|
||||
def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
no_cache = more_req.startswith("--no-cache")
|
||||
if no_cache: more_req.lstrip("--no-cache")
|
||||
allow_cache = not no_cache
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([ f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
history = []
|
||||
try:
|
||||
txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
|
||||
except tarfile.ReadError as e:
|
||||
yield from update_ui_lastest_msg(
|
||||
"无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。",
|
||||
chatbot=chatbot, history=history)
|
||||
return
|
||||
|
||||
if txt.endswith('.pdf'):
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"发现已经存在翻译好的PDF文档")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无法处理: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
project_folder = move_project(project_folder, arxiv_id)
|
||||
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='translate_zh', switch_prompt=_switch_prompt_)
|
||||
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_translate_zh', mode='translate_zh',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
@@ -1,83 +0,0 @@
|
||||
from toolbox import CatchException, check_packages, get_conf
|
||||
from toolbox import update_ui, update_ui_lastest_msg, disable_auto_promotion
|
||||
from toolbox import trimmed_format_exc_markdown
|
||||
from crazy_functions.crazy_utils import get_files_from_everything
|
||||
from crazy_functions.pdf_fns.parse_pdf import get_avail_grobid_url
|
||||
from crazy_functions.pdf_fns.parse_pdf_via_doc2x import 解析PDF_基于DOC2X
|
||||
from crazy_functions.pdf_fns.parse_pdf_legacy import 解析PDF_简单拆解
|
||||
from crazy_functions.pdf_fns.parse_pdf_grobid import 解析PDF_基于GROBID
|
||||
from shared_utils.colorful import *
|
||||
|
||||
@CatchException
|
||||
def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
|
||||
disable_auto_promotion(chatbot)
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([None, "插件功能：批量翻译PDF文档。函数插件贡献者: Binary-Husky"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
try:
|
||||
check_packages(["fitz", "tiktoken", "scipdf"])
|
||||
except:
|
||||
chatbot.append([None, f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf tiktoken scipdf_parser```。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 清空历史，以免输入溢出
|
||||
history = []
|
||||
success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
|
||||
|
||||
# 检测输入参数，如没有给定输入参数，直接退出
|
||||
if (not success) and txt == "": txt = '空空如也的输入栏。提示：请先上传文件（把PDF文件拖入对话）。'
|
||||
|
||||
# 如果没找到任何文件
|
||||
if len(file_manifest) == 0:
|
||||
chatbot.append([None, f"找不到任何.pdf拓展名的文件: {txt}"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 开始正式执行任务
|
||||
method = plugin_kwargs.get("pdf_parse_method", None)
|
||||
if method == "DOC2X":
|
||||
# ------- 第一种方法，效果最好，但是需要DOC2X服务 -------
|
||||
DOC2X_API_KEY = get_conf("DOC2X_API_KEY")
|
||||
if len(DOC2X_API_KEY) != 0:
|
||||
try:
|
||||
yield from 解析PDF_基于DOC2X(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request)
|
||||
return
|
||||
except:
|
||||
chatbot.append([None, f"DOC2X服务不可用，现在将执行效果稍差的旧版代码。{trimmed_format_exc_markdown()}"])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
if method == "GROBID":
|
||||
# ------- 第二种方法，效果次优 -------
|
||||
grobid_url = get_avail_grobid_url()
|
||||
if grobid_url is not None:
|
||||
yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
|
||||
return
|
||||
|
||||
if method == "ClASSIC":
|
||||
# ------- 第三种方法，早期代码，效果不理想 -------
|
||||
yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
|
||||
yield from 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
return
|
||||
|
||||
if method is None:
|
||||
# ------- 以上三种方法都试一遍 -------
|
||||
DOC2X_API_KEY = get_conf("DOC2X_API_KEY")
|
||||
if len(DOC2X_API_KEY) != 0:
|
||||
try:
|
||||
yield from 解析PDF_基于DOC2X(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request)
|
||||
return
|
||||
except:
|
||||
chatbot.append([None, f"DOC2X服务不可用，正在尝试GROBID。{trimmed_format_exc_markdown()}"])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
grobid_url = get_avail_grobid_url()
|
||||
if grobid_url is not None:
|
||||
yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
|
||||
return
|
||||
yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
|
||||
yield from 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
return
|
||||
|
||||
@@ -1,33 +0,0 @@
|
||||
from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
|
||||
from .PDF_Translate import 批量翻译PDF文档
|
||||
|
||||
|
||||
class PDF_Tran(GptAcademicPluginTemplate):
|
||||
def __init__(self):
|
||||
"""
|
||||
请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
|
||||
"""
|
||||
pass
|
||||
|
||||
def define_arg_selection_menu(self):
|
||||
"""
|
||||
定义插件的二级选项菜单
|
||||
"""
|
||||
gui_definition = {
|
||||
"main_input":
|
||||
ArgProperty(title="PDF文件路径", description="未指定路径，请上传文件后，再点击该插件", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||
"additional_prompt":
|
||||
ArgProperty(title="额外提示词", description="例如：对专有名词、翻译语气等方面的要求", default_value="", type="string").model_dump_json(), # 高级参数输入区，自动同步
|
||||
"pdf_parse_method":
|
||||
ArgProperty(title="PDF解析方法", options=["DOC2X", "GROBID", "ClASSIC"], description="无", default_value="GROBID", type="dropdown").model_dump_json(),
|
||||
}
|
||||
return gui_definition
|
||||
|
||||
def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
执行插件
|
||||
"""
|
||||
main_input = plugin_kwargs["main_input"]
|
||||
additional_prompt = plugin_kwargs["additional_prompt"]
|
||||
pdf_parse_method = plugin_kwargs["pdf_parse_method"]
|
||||
yield from 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
@@ -1,20 +1,9 @@
|
||||
from toolbox import update_ui, get_conf, trimmed_format_exc, get_max_token, Singleton
|
||||
from shared_utils.char_visual_effect import scolling_visual_effect
|
||||
import threading
|
||||
import os
|
||||
import logging
|
||||
|
||||
def input_clipping(inputs, history, max_token_limit):
|
||||
"""
|
||||
当输入文本 + 历史文本超出最大限制时，采取措施丢弃一部分文本。
|
||||
输入：
|
||||
- inputs 本次请求
|
||||
- history 历史上下文
|
||||
- max_token_limit 最大token限制
|
||||
输出:
|
||||
- inputs 本次请求（经过clip）
|
||||
- history 历史上下文（经过clip）
|
||||
"""
|
||||
import numpy as np
|
||||
from request_llms.bridge_all import model_info
|
||||
enc = model_info["gpt-3.5-turbo"]['tokenizer']
|
||||
@@ -146,30 +135,18 @@ def request_gpt_model_in_new_thread_with_ui_alive(
|
||||
yield from update_ui(chatbot=chatbot, history=[]) # 如果最后成功了，则删除报错信息
|
||||
return final_result
|
||||
|
||||
def can_multi_process(llm) -> bool:
|
||||
from request_llms.bridge_all import model_info
|
||||
|
||||
def default_condition(llm) -> bool:
|
||||
# legacy condition
|
||||
def can_multi_process(llm):
|
||||
if llm.startswith('gpt-'): return True
|
||||
if llm.startswith('api2d-'): return True
|
||||
if llm.startswith('azure-'): return True
|
||||
if llm.startswith('spark'): return True
|
||||
if llm.startswith('zhipuai') or llm.startswith('glm-'): return True
|
||||
if llm.startswith('zhipuai'): return True
|
||||
return False
|
||||
|
||||
if llm in model_info:
|
||||
if 'can_multi_thread' in model_info[llm]:
|
||||
return model_info[llm]['can_multi_thread']
|
||||
else:
|
||||
return default_condition(llm)
|
||||
else:
|
||||
return default_condition(llm)
|
||||
|
||||
def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
inputs_array, inputs_show_user_array, llm_kwargs,
|
||||
chatbot, history_array, sys_prompt_array,
|
||||
refresh_interval=0.2, max_workers=-1, scroller_max_len=75,
|
||||
refresh_interval=0.2, max_workers=-1, scroller_max_len=30,
|
||||
handle_token_exceed=True, show_user_at_complete=False,
|
||||
retry_times_at_unknown_error=2,
|
||||
):
|
||||
@@ -294,8 +271,6 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
futures = [executor.submit(_req_gpt, index, inputs, history, sys_prompt) for index, inputs, history, sys_prompt in zip(
|
||||
range(len(inputs_array)), inputs_array, history_array, sys_prompt_array)]
|
||||
cnt = 0
|
||||
|
||||
|
||||
while True:
|
||||
# yield一次以刷新前端页面
|
||||
time.sleep(refresh_interval)
|
||||
@@ -308,7 +283,8 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
mutable[thread_index][1] = time.time()
|
||||
# 在前端打印些好玩的东西
|
||||
for thread_index, _ in enumerate(worker_done):
|
||||
print_something_really_funny = f"[ ...`{scolling_visual_effect(mutable[thread_index][0], scroller_max_len)}`... ]"
|
||||
print_something_really_funny = "[ ...`"+mutable[thread_index][0][-scroller_max_len:].\
|
||||
replace('\n', '').replace('`', '.').replace(' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
|
||||
observe_win.append(print_something_really_funny)
|
||||
# 在前端打印些好玩的东西
|
||||
stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
|
||||
@@ -361,7 +337,7 @@ def read_and_clean_pdf_text(fp):
|
||||
import fitz, copy
|
||||
import re
|
||||
import numpy as np
|
||||
from shared_utils.colorful import print亮黄, print亮绿
|
||||
from colorful import print亮黄, print亮绿
|
||||
fc = 0 # Index 0 文本
|
||||
fs = 1 # Index 1 字体
|
||||
fb = 2 # Index 2 框框
|
||||
@@ -580,7 +556,7 @@ class nougat_interface():
|
||||
from toolbox import ProxyNetworkActivate
|
||||
logging.info(f'正在执行命令 {command}')
|
||||
with ProxyNetworkActivate("Nougat_Download"):
|
||||
process = subprocess.Popen(command, shell=False, cwd=cwd, env=os.environ)
|
||||
process = subprocess.Popen(command, shell=True, cwd=cwd, env=os.environ)
|
||||
try:
|
||||
stdout, stderr = process.communicate(timeout=timeout)
|
||||
except subprocess.TimeoutExpired:
|
||||
@@ -604,8 +580,7 @@ class nougat_interface():
|
||||
|
||||
yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
command = ['nougat', '--out', os.path.abspath(dst), os.path.abspath(fp)]
|
||||
self.nougat_with_timeout(command, cwd=os.getcwd(), timeout=3600)
|
||||
self.nougat_with_timeout(f'nougat --out "{os.path.abspath(dst)}" "{os.path.abspath(fp)}"', os.getcwd(), timeout=3600)
|
||||
res = glob.glob(os.path.join(dst,'*.mmd'))
|
||||
if len(res) == 0:
|
||||
self.threadLock.release()
|
||||
|
||||
@@ -62,8 +62,8 @@ class GptJsonIO():
|
||||
if "type" in reduced_schema:
|
||||
del reduced_schema["type"]
|
||||
# Ensure json in context is well-formed with double quotes.
|
||||
schema_str = json.dumps(reduced_schema)
|
||||
if self.example_instruction:
|
||||
schema_str = json.dumps(reduced_schema)
|
||||
return PYDANTIC_FORMAT_INSTRUCTIONS.format(schema=schema_str)
|
||||
else:
|
||||
return PYDANTIC_FORMAT_INSTRUCTIONS_SIMPLE.format(schema=schema_str)
|
||||
|
||||
@@ -1,11 +1,10 @@
|
||||
from toolbox import update_ui, update_ui_lastest_msg, get_log_folder
|
||||
from toolbox import get_conf, promote_file_to_downloadzone
|
||||
from toolbox import get_conf, objdump, objload, promote_file_to_downloadzone
|
||||
from .latex_toolbox import PRESERVE, TRANSFORM
|
||||
from .latex_toolbox import set_forbidden_text, set_forbidden_text_begin_end, set_forbidden_text_careful_brace
|
||||
from .latex_toolbox import reverse_forbidden_text_careful_brace, reverse_forbidden_text, convert_to_linklist, post_process
|
||||
from .latex_toolbox import fix_content, find_main_tex_file, merge_tex_files, compile_latex_with_timeout
|
||||
from .latex_toolbox import find_title_and_abs
|
||||
from .latex_pickle_io import objdump, objload
|
||||
|
||||
import os, shutil
|
||||
import re
|
||||
|
||||
@@ -1,46 +0,0 @@
|
||||
import pickle
|
||||
|
||||
|
||||
class SafeUnpickler(pickle.Unpickler):
|
||||
|
||||
def get_safe_classes(self):
|
||||
from crazy_functions.latex_fns.latex_actions import LatexPaperFileGroup, LatexPaperSplit
|
||||
from crazy_functions.latex_fns.latex_toolbox import LinkedListNode
|
||||
# 定义允许的安全类
|
||||
safe_classes = {
|
||||
# 在这里添加其他安全的类
|
||||
'LatexPaperFileGroup': LatexPaperFileGroup,
|
||||
'LatexPaperSplit': LatexPaperSplit,
|
||||
'LinkedListNode': LinkedListNode,
|
||||
}
|
||||
return safe_classes
|
||||
|
||||
def find_class(self, module, name):
|
||||
# 只允许特定的类进行反序列化
|
||||
self.safe_classes = self.get_safe_classes()
|
||||
match_class_name = None
|
||||
for class_name in self.safe_classes.keys():
|
||||
if (class_name in f'{module}.{name}'):
|
||||
match_class_name = class_name
|
||||
if module == 'numpy' or module.startswith('numpy.'):
|
||||
return super().find_class(module, name)
|
||||
if match_class_name is not None:
|
||||
return self.safe_classes[match_class_name]
|
||||
# 如果尝试加载未授权的类，则抛出异常
|
||||
raise pickle.UnpicklingError(f"Attempted to deserialize unauthorized class '{name}' from module '{module}'")
|
||||
|
||||
def objdump(obj, file="objdump.tmp"):
|
||||
|
||||
with open(file, "wb+") as f:
|
||||
pickle.dump(obj, f)
|
||||
return
|
||||
|
||||
|
||||
def objload(file="objdump.tmp"):
|
||||
import os
|
||||
|
||||
if not os.path.exists(file):
|
||||
return
|
||||
with open(file, "rb") as f:
|
||||
unpickler = SafeUnpickler(f)
|
||||
return unpickler.load()
|
||||
@@ -4,7 +4,7 @@ from toolbox import promote_file_to_downloadzone
|
||||
from toolbox import write_history_to_file, promote_file_to_downloadzone
|
||||
from toolbox import get_conf
|
||||
from toolbox import ProxyNetworkActivate
|
||||
from shared_utils.colorful import *
|
||||
from colorful import *
|
||||
import requests
|
||||
import random
|
||||
import copy
|
||||
@@ -72,7 +72,7 @@ def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chat
|
||||
generated_conclusion_files.append(res_path)
|
||||
return res_path
|
||||
|
||||
def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG, plugin_kwargs={}):
|
||||
def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG):
|
||||
from crazy_functions.pdf_fns.report_gen_html import construct_html
|
||||
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
@@ -138,7 +138,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
|
||||
chatbot=chatbot,
|
||||
history_array=[meta for _ in inputs_array],
|
||||
sys_prompt_array=[
|
||||
"请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" + plugin_kwargs.get("additional_prompt", "") for _ in inputs_array],
|
||||
"请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in inputs_array],
|
||||
)
|
||||
# -=-=-=-=-=-=-=-= 写出Markdown文件 -=-=-=-=-=-=-=-=
|
||||
produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files)
|
||||
|
||||
@@ -1,26 +0,0 @@
|
||||
import os
|
||||
from toolbox import CatchException, report_exception, get_log_folder, gen_time_str, check_packages
|
||||
from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
|
||||
from toolbox import write_history_to_file, promote_file_to_downloadzone, get_conf, extract_archive
|
||||
from crazy_functions.pdf_fns.parse_pdf import parse_pdf, translate_pdf
|
||||
|
||||
def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url):
|
||||
import copy, json
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 1024
|
||||
generated_conclusion_files = []
|
||||
generated_html_files = []
|
||||
DST_LANG = "中文"
|
||||
from crazy_functions.pdf_fns.report_gen_html import construct_html
|
||||
for index, fp in enumerate(file_manifest):
|
||||
chatbot.append(["当前进度：", f"正在连接GROBID服务，请稍候: {grobid_url}\n如果等待时间过长，请修改config中的GROBID_URL，可修改成本地GROBID服务。"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
article_dict = parse_pdf(fp, grobid_url)
|
||||
grobid_json_res = os.path.join(get_log_folder(), gen_time_str() + "grobid.json")
|
||||
with open(grobid_json_res, 'w+', encoding='utf8') as f:
|
||||
f.write(json.dumps(article_dict, indent=4, ensure_ascii=False))
|
||||
promote_file_to_downloadzone(grobid_json_res, chatbot=chatbot)
|
||||
if article_dict is None: raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
|
||||
yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG, plugin_kwargs=plugin_kwargs)
|
||||
chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
|
||||
@@ -1,213 +0,0 @@
|
||||
from toolbox import get_log_folder, gen_time_str, get_conf
|
||||
from toolbox import update_ui, promote_file_to_downloadzone
|
||||
from toolbox import promote_file_to_downloadzone, extract_archive
|
||||
from toolbox import generate_file_link, zip_folder
|
||||
from crazy_functions.crazy_utils import get_files_from_everything
|
||||
from shared_utils.colorful import *
|
||||
import os
|
||||
|
||||
def refresh_key(doc2x_api_key):
|
||||
import requests, json
|
||||
url = "https://api.doc2x.noedgeai.com/api/token/refresh"
|
||||
res = requests.post(
|
||||
url,
|
||||
headers={"Authorization": "Bearer " + doc2x_api_key}
|
||||
)
|
||||
res_json = []
|
||||
if res.status_code == 200:
|
||||
decoded = res.content.decode("utf-8")
|
||||
res_json = json.loads(decoded)
|
||||
doc2x_api_key = res_json['data']['token']
|
||||
else:
|
||||
raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
|
||||
return doc2x_api_key
|
||||
|
||||
def 解析PDF_DOC2X_转Latex(pdf_file_path):
|
||||
import requests, json, os
|
||||
DOC2X_API_KEY = get_conf('DOC2X_API_KEY')
|
||||
latex_dir = get_log_folder(plugin_name="pdf_ocr_latex")
|
||||
doc2x_api_key = DOC2X_API_KEY
|
||||
if doc2x_api_key.startswith('sk-'):
|
||||
url = "https://api.doc2x.noedgeai.com/api/v1/pdf"
|
||||
else:
|
||||
doc2x_api_key = refresh_key(doc2x_api_key)
|
||||
url = "https://api.doc2x.noedgeai.com/api/platform/pdf"
|
||||
|
||||
res = requests.post(
|
||||
url,
|
||||
files={"file": open(pdf_file_path, "rb")},
|
||||
data={"ocr": "1"},
|
||||
headers={"Authorization": "Bearer " + doc2x_api_key}
|
||||
)
|
||||
res_json = []
|
||||
if res.status_code == 200:
|
||||
decoded = res.content.decode("utf-8")
|
||||
for z_decoded in decoded.split('\n'):
|
||||
if len(z_decoded) == 0: continue
|
||||
assert z_decoded.startswith("data: ")
|
||||
z_decoded = z_decoded[len("data: "):]
|
||||
decoded_json = json.loads(z_decoded)
|
||||
res_json.append(decoded_json)
|
||||
else:
|
||||
raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
|
||||
|
||||
uuid = res_json[0]['uuid']
|
||||
to = "latex" # latex, md, docx
|
||||
url = "https://api.doc2x.noedgeai.com/api/export"+"?request_id="+uuid+"&to="+to
|
||||
|
||||
res = requests.get(url, headers={"Authorization": "Bearer " + doc2x_api_key})
|
||||
latex_zip_path = os.path.join(latex_dir, gen_time_str() + '.zip')
|
||||
latex_unzip_path = os.path.join(latex_dir, gen_time_str())
|
||||
if res.status_code == 200:
|
||||
with open(latex_zip_path, "wb") as f: f.write(res.content)
|
||||
else:
|
||||
raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
|
||||
|
||||
import zipfile
|
||||
with zipfile.ZipFile(latex_zip_path, 'r') as zip_ref:
|
||||
zip_ref.extractall(latex_unzip_path)
|
||||
|
||||
|
||||
return latex_unzip_path
|
||||
|
||||
|
||||
|
||||
|
||||
def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request):
|
||||
|
||||
|
||||
def pdf2markdown(filepath):
|
||||
import requests, json, os
|
||||
markdown_dir = get_log_folder(plugin_name="pdf_ocr")
|
||||
doc2x_api_key = DOC2X_API_KEY
|
||||
if doc2x_api_key.startswith('sk-'):
|
||||
url = "https://api.doc2x.noedgeai.com/api/v1/pdf"
|
||||
else:
|
||||
doc2x_api_key = refresh_key(doc2x_api_key)
|
||||
url = "https://api.doc2x.noedgeai.com/api/platform/pdf"
|
||||
|
||||
chatbot.append((None, "加载PDF文件，发送至DOC2X解析..."))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
res = requests.post(
|
||||
url,
|
||||
files={"file": open(filepath, "rb")},
|
||||
data={"ocr": "1"},
|
||||
headers={"Authorization": "Bearer " + doc2x_api_key}
|
||||
)
|
||||
res_json = []
|
||||
if res.status_code == 200:
|
||||
decoded = res.content.decode("utf-8")
|
||||
for z_decoded in decoded.split('\n'):
|
||||
if len(z_decoded) == 0: continue
|
||||
assert z_decoded.startswith("data: ")
|
||||
z_decoded = z_decoded[len("data: "):]
|
||||
decoded_json = json.loads(z_decoded)
|
||||
res_json.append(decoded_json)
|
||||
if 'limit exceeded' in decoded_json.get('status', ''):
|
||||
raise RuntimeError("Doc2x API 页数受限，请联系 Doc2x 方面，并更换新的 API 秘钥。")
|
||||
else:
|
||||
raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
|
||||
uuid = res_json[0]['uuid']
|
||||
to = "md" # latex, md, docx
|
||||
url = "https://api.doc2x.noedgeai.com/api/export"+"?request_id="+uuid+"&to="+to
|
||||
|
||||
chatbot.append((None, f"读取解析: {url} ..."))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
res = requests.get(url, headers={"Authorization": "Bearer " + doc2x_api_key})
|
||||
md_zip_path = os.path.join(markdown_dir, gen_time_str() + '.zip')
|
||||
if res.status_code == 200:
|
||||
with open(md_zip_path, "wb") as f: f.write(res.content)
|
||||
else:
|
||||
raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
|
||||
promote_file_to_downloadzone(md_zip_path, chatbot=chatbot)
|
||||
chatbot.append((None, f"完成解析 {md_zip_path} ..."))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return md_zip_path
|
||||
|
||||
def deliver_to_markdown_plugin(md_zip_path, user_request):
|
||||
from crazy_functions.Markdown_Translate import Markdown英译中
|
||||
import shutil, re
|
||||
|
||||
time_tag = gen_time_str()
|
||||
target_path_base = get_log_folder(chatbot.get_user())
|
||||
file_origin_name = os.path.basename(md_zip_path)
|
||||
this_file_path = os.path.join(target_path_base, file_origin_name)
|
||||
os.makedirs(target_path_base, exist_ok=True)
|
||||
shutil.copyfile(md_zip_path, this_file_path)
|
||||
ex_folder = this_file_path + ".extract"
|
||||
extract_archive(
|
||||
file_path=this_file_path, dest_dir=ex_folder
|
||||
)
|
||||
|
||||
# edit markdown files
|
||||
success, file_manifest, project_folder = get_files_from_everything(ex_folder, type='.md')
|
||||
for generated_fp in file_manifest:
|
||||
# 修正一些公式问题
|
||||
with open(generated_fp, 'r', encoding='utf8') as f:
|
||||
content = f.read()
|
||||
# 将公式中的\[ \]替换成$$
|
||||
content = content.replace(r'\[', r'$$').replace(r'\]', r'$$')
|
||||
# 将公式中的\( \)替换成$
|
||||
content = content.replace(r'\(', r'$').replace(r'\)', r'$')
|
||||
content = content.replace('```markdown', '\n').replace('```', '\n')
|
||||
with open(generated_fp, 'w', encoding='utf8') as f:
|
||||
f.write(content)
|
||||
promote_file_to_downloadzone(generated_fp, chatbot=chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 生成在线预览html
|
||||
file_name = '在线预览翻译（原文）' + gen_time_str() + '.html'
|
||||
preview_fp = os.path.join(ex_folder, file_name)
|
||||
from shared_utils.advanced_markdown_format import markdown_convertion_for_file
|
||||
with open(generated_fp, "r", encoding="utf-8") as f:
|
||||
md = f.read()
|
||||
# # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
|
||||
# md = re.sub(r'^<table>', r'.<table>', md, flags=re.MULTILINE)
|
||||
html = markdown_convertion_for_file(md)
|
||||
with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
|
||||
chatbot.append([None, f"生成在线预览：{generate_file_link([preview_fp])}"])
|
||||
promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
|
||||
|
||||
|
||||
|
||||
chatbot.append((None, f"调用Markdown插件 {ex_folder} ..."))
|
||||
plugin_kwargs['markdown_expected_output_dir'] = ex_folder
|
||||
|
||||
translated_f_name = 'translated_markdown.md'
|
||||
generated_fp = plugin_kwargs['markdown_expected_output_path'] = os.path.join(ex_folder, translated_f_name)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
yield from Markdown英译中(ex_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
if os.path.exists(generated_fp):
|
||||
# 修正一些公式问题
|
||||
with open(generated_fp, 'r', encoding='utf8') as f: content = f.read()
|
||||
content = content.replace('```markdown', '\n').replace('```', '\n')
|
||||
# Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
|
||||
# content = re.sub(r'^<table>', r'.<table>', content, flags=re.MULTILINE)
|
||||
with open(generated_fp, 'w', encoding='utf8') as f: f.write(content)
|
||||
# 生成在线预览html
|
||||
file_name = '在线预览翻译' + gen_time_str() + '.html'
|
||||
preview_fp = os.path.join(ex_folder, file_name)
|
||||
from shared_utils.advanced_markdown_format import markdown_convertion_for_file
|
||||
with open(generated_fp, "r", encoding="utf-8") as f:
|
||||
md = f.read()
|
||||
html = markdown_convertion_for_file(md)
|
||||
with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
|
||||
promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
|
||||
# 生成包含图片的压缩包
|
||||
dest_folder = get_log_folder(chatbot.get_user())
|
||||
zip_name = '翻译后的带图文档.zip'
|
||||
zip_folder(source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name)
|
||||
zip_fp = os.path.join(dest_folder, zip_name)
|
||||
promote_file_to_downloadzone(zip_fp, chatbot=chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
md_zip_path = yield from pdf2markdown(fp)
|
||||
yield from deliver_to_markdown_plugin(md_zip_path, user_request)
|
||||
|
||||
def 解析PDF_基于DOC2X(file_manifest, *args):
|
||||
for index, fp in enumerate(file_manifest):
|
||||
yield from 解析PDF_DOC2X_单文件(fp, *args)
|
||||
return
|
||||
|
||||
|
||||
@@ -1,85 +0,0 @@
|
||||
from crazy_functions.crazy_utils import read_and_clean_pdf_text, get_files_from_everything
|
||||
import os
|
||||
import re
|
||||
def extract_text_from_files(txt, chatbot, history):
|
||||
"""
|
||||
查找pdf/md/word并获取文本内容并返回状态以及文本
|
||||
|
||||
输入参数 Args:
|
||||
chatbot: chatbot inputs and outputs （用户界面对话窗口句柄，用于数据流可视化）
|
||||
history (list): List of chat history （历史，对话历史列表）
|
||||
|
||||
输出 Returns:
|
||||
文件是否存在(bool)
|
||||
final_result(list):文本内容
|
||||
page_one(list):第一页内容/摘要
|
||||
file_manifest(list):文件路径
|
||||
excption(string):需要用户手动处理的信息,如没出错则保持为空
|
||||
"""
|
||||
|
||||
final_result = []
|
||||
page_one = []
|
||||
file_manifest = []
|
||||
excption = ""
|
||||
|
||||
if txt == "":
|
||||
final_result.append(txt)
|
||||
return False, final_result, page_one, file_manifest, excption #如输入区内容不是文件则直接返回输入区内容
|
||||
|
||||
#查找输入区内容中的文件
|
||||
file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
|
||||
file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
|
||||
file_word,word_manifest,folder_word = get_files_from_everything(txt, '.docx')
|
||||
file_doc,doc_manifest,folder_doc = get_files_from_everything(txt, '.doc')
|
||||
|
||||
if file_doc:
|
||||
excption = "word"
|
||||
return False, final_result, page_one, file_manifest, excption
|
||||
|
||||
file_num = len(pdf_manifest) + len(md_manifest) + len(word_manifest)
|
||||
if file_num == 0:
|
||||
final_result.append(txt)
|
||||
return False, final_result, page_one, file_manifest, excption #如输入区内容不是文件则直接返回输入区内容
|
||||
|
||||
if file_pdf:
|
||||
try: # 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
import fitz
|
||||
except:
|
||||
excption = "pdf"
|
||||
return False, final_result, page_one, file_manifest, excption
|
||||
for index, fp in enumerate(pdf_manifest):
|
||||
file_content, pdf_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
pdf_one = str(pdf_one).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
final_result.append(file_content)
|
||||
page_one.append(pdf_one)
|
||||
file_manifest.append(os.path.relpath(fp, folder_pdf))
|
||||
|
||||
if file_md:
|
||||
for index, fp in enumerate(md_manifest):
|
||||
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
|
||||
file_content = f.read()
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode()
|
||||
headers = re.findall(r'^#\s(.*)$', file_content, re.MULTILINE) #接下来提取md中的一级/二级标题作为摘要
|
||||
if len(headers) > 0:
|
||||
page_one.append("\n".join(headers)) #合并所有的标题,以换行符分割
|
||||
else:
|
||||
page_one.append("")
|
||||
final_result.append(file_content)
|
||||
file_manifest.append(os.path.relpath(fp, folder_md))
|
||||
|
||||
if file_word:
|
||||
try: # 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
from docx import Document
|
||||
except:
|
||||
excption = "word_pip"
|
||||
return False, final_result, page_one, file_manifest, excption
|
||||
for index, fp in enumerate(word_manifest):
|
||||
doc = Document(fp)
|
||||
file_content = '\n'.join([p.text for p in doc.paragraphs])
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode()
|
||||
page_one.append(file_content[:200])
|
||||
final_result.append(file_content)
|
||||
file_manifest.append(os.path.relpath(fp, folder_word))
|
||||
|
||||
return True, final_result, page_one, file_manifest, excption
|
||||
@@ -1,73 +0,0 @@
|
||||
<!DOCTYPE html>
|
||||
<html xmlns="http://www.w3.org/1999/xhtml">
|
||||
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
|
||||
<title>GPT-Academic 翻译报告书</title>
|
||||
<style>
|
||||
.centered-a {
|
||||
color: red;
|
||||
text-align: center;
|
||||
margin-bottom: 2%;
|
||||
font-size: 1.5em;
|
||||
}
|
||||
.centered-b {
|
||||
color: red;
|
||||
text-align: center;
|
||||
margin-top: 10%;
|
||||
margin-bottom: 20%;
|
||||
font-size: 1.5em;
|
||||
}
|
||||
.centered-c {
|
||||
color: rgba(255, 0, 0, 0);
|
||||
text-align: center;
|
||||
margin-top: 2%;
|
||||
margin-bottom: 20%;
|
||||
font-size: 7em;
|
||||
}
|
||||
</style>
|
||||
<script>
|
||||
// Configure MathJax settings
|
||||
MathJax = {
|
||||
tex: {
|
||||
inlineMath: [
|
||||
['$', '$'],
|
||||
['\(', '\)']
|
||||
]
|
||||
}
|
||||
}
|
||||
addEventListener('zero-md-rendered', () => {MathJax.typeset(); console.log('MathJax typeset!');})
|
||||
</script>
|
||||
<!-- Load MathJax library -->
|
||||
<script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-chtml.js"></script>
|
||||
<script
|
||||
type="module"
|
||||
src="https://cdn.jsdelivr.net/gh/zerodevx/zero-md@2/dist/zero-md.min.js"
|
||||
></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body>
|
||||
<div class="test_temp1" style="width:10%; height: 500px; float:left;">
|
||||
|
||||
</div>
|
||||
<div class="test_temp2" style="width:80%; height: 500px; float:left;">
|
||||
<!-- Simply set the `src` attribute to your MD file and win -->
|
||||
<div class="centered-a">
|
||||
请按Ctrl+S保存此页面，否则该页面可能在几分钟后失效。
|
||||
</div>
|
||||
<zero-md src="translated_markdown.md" no-shadow>
|
||||
</zero-md>
|
||||
<div class="centered-b">
|
||||
本报告由GPT-Academic开源项目生成，地址：https://github.com/binary-husky/gpt_academic。
|
||||
</div>
|
||||
<div class="centered-c">
|
||||
本报告由GPT-Academic开源项目生成，地址：https://github.com/binary-husky/gpt_academic。
|
||||
</div>
|
||||
</div>
|
||||
<div class="test_temp3" style="width:10%; height: 500px; float:left;">
|
||||
</div>
|
||||
|
||||
</body>
|
||||
|
||||
</html>
|
||||
@@ -1,52 +0,0 @@
|
||||
import os, json, base64
|
||||
from pydantic import BaseModel, Field
|
||||
from textwrap import dedent
|
||||
from typing import List
|
||||
|
||||
class ArgProperty(BaseModel): # PLUGIN_ARG_MENU
|
||||
title: str = Field(description="The title", default="")
|
||||
description: str = Field(description="The description", default="")
|
||||
default_value: str = Field(description="The default value", default="")
|
||||
type: str = Field(description="The type", default="") # currently we support ['string', 'dropdown']
|
||||
options: List[str] = Field(default=[], description="List of options available for the argument") # only used when type is 'dropdown'
|
||||
|
||||
class GptAcademicPluginTemplate():
|
||||
def __init__(self):
|
||||
# please note that `execute` method may run in different threads,
|
||||
# thus you should not store any state in the plugin instance,
|
||||
# which may be accessed by multiple threads
|
||||
pass
|
||||
|
||||
|
||||
def define_arg_selection_menu(self):
|
||||
"""
|
||||
An example as below:
|
||||
```
|
||||
def define_arg_selection_menu(self):
|
||||
gui_definition = {
|
||||
"main_input":
|
||||
ArgProperty(title="main input", description="description", default_value="default_value", type="string").model_dump_json(),
|
||||
"advanced_arg":
|
||||
ArgProperty(title="advanced arguments", description="description", default_value="default_value", type="string").model_dump_json(),
|
||||
"additional_arg_01":
|
||||
ArgProperty(title="additional", description="description", default_value="default_value", type="string").model_dump_json(),
|
||||
}
|
||||
return gui_definition
|
||||
```
|
||||
"""
|
||||
raise NotImplementedError("You need to implement this method in your plugin class")
|
||||
|
||||
|
||||
def get_js_code_for_generating_menu(self, btnName):
|
||||
define_arg_selection = self.define_arg_selection_menu()
|
||||
|
||||
if len(define_arg_selection.keys()) > 8:
|
||||
raise ValueError("You can only have up to 8 arguments in the define_arg_selection")
|
||||
# if "main_input" not in define_arg_selection:
|
||||
# raise ValueError("You must have a 'main_input' in the define_arg_selection")
|
||||
|
||||
DEFINE_ARG_INPUT_INTERFACE = json.dumps(define_arg_selection)
|
||||
return base64.b64encode(DEFINE_ARG_INPUT_INTERFACE.encode('utf-8')).decode('utf-8')
|
||||
|
||||
def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
raise NotImplementedError("You need to implement this method in your plugin class")
|
||||
@@ -10,7 +10,7 @@ def read_avail_plugin_enum():
|
||||
from crazy_functional import get_crazy_functions
|
||||
plugin_arr = get_crazy_functions()
|
||||
# remove plugins with out explaination
|
||||
plugin_arr = {k:v for k, v in plugin_arr.items() if ('Info' in v) and ('Function' in v)}
|
||||
plugin_arr = {k:v for k, v in plugin_arr.items() if 'Info' in v}
|
||||
plugin_arr_info = {"F_{:04d}".format(i):v["Info"] for i, v in enumerate(plugin_arr.values(), start=1)}
|
||||
plugin_arr_dict = {"F_{:04d}".format(i):v for i, v in enumerate(plugin_arr.values(), start=1)}
|
||||
plugin_arr_dict_parse = {"F_{:04d}".format(i):v for i, v in enumerate(plugin_arr.values(), start=1)}
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
from toolbox import CatchException, update_ui, promote_file_to_downloadzone, get_log_folder, get_user
|
||||
from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
|
||||
import re
|
||||
|
||||
f_prefix = 'GPT-Academic对话存档'
|
||||
@@ -10,61 +9,27 @@ def write_chat_to_file(chatbot, history=None, file_name=None):
|
||||
"""
|
||||
import os
|
||||
import time
|
||||
from themes.theme import advanced_css
|
||||
|
||||
if file_name is None:
|
||||
file_name = f_prefix + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.html'
|
||||
fp = os.path.join(get_log_folder(get_user(chatbot), plugin_name='chat_history'), file_name)
|
||||
|
||||
with open(fp, 'w', encoding='utf8') as f:
|
||||
from textwrap import dedent
|
||||
form = dedent("""
|
||||
<!DOCTYPE html><head><meta charset="utf-8"><title>对话存档</title><style>{CSS}</style></head>
|
||||
<body>
|
||||
<div class="test_temp1" style="width:10%; height: 500px; float:left;"></div>
|
||||
<div class="test_temp2" style="width:80%;padding: 40px;float:left;padding-left: 20px;padding-right: 20px;box-shadow: rgba(0, 0, 0, 0.2) 0px 0px 8px 8px;border-radius: 10px;">
|
||||
<div class="chat-body" style="display: flex;justify-content: center;flex-direction: column;align-items: center;flex-wrap: nowrap;">
|
||||
{CHAT_PREVIEW}
|
||||
<div></div>
|
||||
<div></div>
|
||||
<div style="text-align: center;width:80%;padding: 0px;float:left;padding-left:20px;padding-right:20px;box-shadow: rgba(0, 0, 0, 0.05) 0px 0px 1px 2px;border-radius: 1px;">对话（原始数据）</div>
|
||||
{HISTORY_PREVIEW}
|
||||
</div>
|
||||
</div>
|
||||
<div class="test_temp3" style="width:10%; height: 500px; float:left;"></div>
|
||||
</body>
|
||||
""")
|
||||
|
||||
qa_from = dedent("""
|
||||
<div class="QaBox" style="width:80%;padding: 20px;margin-bottom: 20px;box-shadow: rgb(0 255 159 / 50%) 0px 0px 1px 2px;border-radius: 4px;">
|
||||
<div class="Question" style="border-radius: 2px;">{QUESTION}</div>
|
||||
<hr color="blue" style="border-top: dotted 2px #ccc;">
|
||||
<div class="Answer" style="border-radius: 2px;">{ANSWER}</div>
|
||||
</div>
|
||||
""")
|
||||
|
||||
history_from = dedent("""
|
||||
<div class="historyBox" style="width:80%;padding: 0px;float:left;padding-left:20px;padding-right:20px;box-shadow: rgba(0, 0, 0, 0.05) 0px 0px 1px 2px;border-radius: 1px;">
|
||||
<div class="entry" style="border-radius: 2px;">{ENTRY}</div>
|
||||
</div>
|
||||
""")
|
||||
CHAT_PREVIEW_BUF = ""
|
||||
from themes.theme import advanced_css
|
||||
f.write(f'<!DOCTYPE html><head><meta charset="utf-8"><title>对话历史</title><style>{advanced_css}</style></head>')
|
||||
for i, contents in enumerate(chatbot):
|
||||
question, answer = contents[0], contents[1]
|
||||
if question is None: question = ""
|
||||
try: question = str(question)
|
||||
except: question = ""
|
||||
if answer is None: answer = ""
|
||||
try: answer = str(answer)
|
||||
except: answer = ""
|
||||
CHAT_PREVIEW_BUF += qa_from.format(QUESTION=question, ANSWER=answer)
|
||||
|
||||
HISTORY_PREVIEW_BUF = ""
|
||||
for j, content in enumerate(contents):
|
||||
try: # 这个bug没找到触发条件，暂时先这样顶一下
|
||||
if type(content) != str: content = str(content)
|
||||
except:
|
||||
continue
|
||||
f.write(content)
|
||||
if j == 0:
|
||||
f.write('<hr style="border-top: dotted 3px #ccc;">')
|
||||
f.write('<hr color="red"> \n\n')
|
||||
f.write('<hr color="blue"> \n\n raw chat context:\n')
|
||||
f.write('<code>')
|
||||
for h in history:
|
||||
HISTORY_PREVIEW_BUF += history_from.format(ENTRY=h)
|
||||
html_content = form.format(CHAT_PREVIEW=CHAT_PREVIEW_BUF, HISTORY_PREVIEW=HISTORY_PREVIEW_BUF, CSS=advanced_css)
|
||||
f.write(html_content)
|
||||
|
||||
f.write("\n>>>" + h)
|
||||
f.write('</code>')
|
||||
promote_file_to_downloadzone(fp, rename_file=file_name, chatbot=chatbot)
|
||||
return '对话历史写入：' + fp
|
||||
|
||||
@@ -75,7 +40,7 @@ def gen_file_preview(file_name):
|
||||
# pattern to match the text between <head> and </head>
|
||||
pattern = re.compile(r'<head>.*?</head>', flags=re.DOTALL)
|
||||
file_content = re.sub(pattern, '', file_content)
|
||||
html, history = file_content.split('<hr color="blue"> \n\n 对话数据 (无渲染):\n')
|
||||
html, history = file_content.split('<hr color="blue"> \n\n raw chat context:\n')
|
||||
history = history.strip('<code>')
|
||||
history = history.strip('</code>')
|
||||
history = history.split("\n>>>")
|
||||
@@ -86,25 +51,21 @@ def gen_file_preview(file_name):
|
||||
def read_file_to_chat(chatbot, history, file_name):
|
||||
with open(file_name, 'r', encoding='utf8') as f:
|
||||
file_content = f.read()
|
||||
from bs4 import BeautifulSoup
|
||||
soup = BeautifulSoup(file_content, 'lxml')
|
||||
# 提取QaBox信息
|
||||
# pattern to match the text between <head> and </head>
|
||||
pattern = re.compile(r'<head>.*?</head>', flags=re.DOTALL)
|
||||
file_content = re.sub(pattern, '', file_content)
|
||||
html, history = file_content.split('<hr color="blue"> \n\n raw chat context:\n')
|
||||
history = history.strip('<code>')
|
||||
history = history.strip('</code>')
|
||||
history = history.split("\n>>>")
|
||||
history = list(filter(lambda x:x!="", history))
|
||||
html = html.split('<hr color="red"> \n\n')
|
||||
html = list(filter(lambda x:x!="", html))
|
||||
chatbot.clear()
|
||||
qa_box_list = []
|
||||
qa_boxes = soup.find_all("div", class_="QaBox")
|
||||
for box in qa_boxes:
|
||||
question = box.find("div", class_="Question").get_text(strip=False)
|
||||
answer = box.find("div", class_="Answer").get_text(strip=False)
|
||||
qa_box_list.append({"Question": question, "Answer": answer})
|
||||
chatbot.append([question, answer])
|
||||
# 提取historyBox信息
|
||||
history_box_list = []
|
||||
history_boxes = soup.find_all("div", class_="historyBox")
|
||||
for box in history_boxes:
|
||||
entry = box.find("div", class_="entry").get_text(strip=False)
|
||||
history_box_list.append(entry)
|
||||
history = history_box_list
|
||||
chatbot.append([None, f"[Local Message] 载入对话{len(qa_box_list)}条，上下文{len(history)}条。"])
|
||||
for i, h in enumerate(html):
|
||||
i_say, gpt_say = h.split('<hr style="border-top: dotted 3px #ccc;">')
|
||||
chatbot.append([i_say, gpt_say])
|
||||
chatbot.append([f"存档文件详情？", f"[Local Message] 载入对话{len(html)}条，上下文{len(history)}条。"])
|
||||
return chatbot, history
|
||||
|
||||
@CatchException
|
||||
@@ -118,42 +79,11 @@ def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
system_prompt 给gpt的静默提醒
|
||||
user_request 当前用户的请求信息（IP地址等）
|
||||
"""
|
||||
file_name = plugin_kwargs.get("file_name", None)
|
||||
if (file_name is not None) and (file_name != "") and (not file_name.endswith('.html')): file_name += '.html'
|
||||
else: file_name = None
|
||||
|
||||
chatbot.append((None, f"[Local Message] {write_chat_to_file(chatbot, history, file_name)}，您可以调用下拉菜单中的“载入对话历史存档”还原当下的对话。"))
|
||||
chatbot.append(("保存当前对话",
|
||||
f"[Local Message] {write_chat_to_file(chatbot, history)}，您可以调用下拉菜单中的“载入对话历史存档”还原当下的对话。"))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
|
||||
|
||||
|
||||
class Conversation_To_File_Wrap(GptAcademicPluginTemplate):
|
||||
def __init__(self):
|
||||
"""
|
||||
请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
|
||||
"""
|
||||
pass
|
||||
|
||||
def define_arg_selection_menu(self):
|
||||
"""
|
||||
定义插件的二级选项菜单
|
||||
|
||||
第一个参数，名称`file_name`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
|
||||
"""
|
||||
gui_definition = {
|
||||
"file_name": ArgProperty(title="保存文件名", description="输入对话存档文件名，留空则使用时间作为文件名", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||
}
|
||||
return gui_definition
|
||||
|
||||
def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
执行插件
|
||||
"""
|
||||
yield from 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def hide_cwd(str):
|
||||
import os
|
||||
current_path = os.getcwd()
|
||||
@@ -218,3 +148,5 @@ def 删除所有本地对话历史记录(txt, llm_kwargs, plugin_kwargs, chatbot
|
||||
chatbot.append([f"删除所有历史对话文件", f"已删除<br/>{local_history}"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import glob, shutil, os, re, logging
|
||||
from toolbox import update_ui, trimmed_format_exc, gen_time_str
|
||||
import glob, time, os, re, logging
|
||||
from toolbox import update_ui, trimmed_format_exc, gen_time_str, disable_auto_promotion
|
||||
from toolbox import CatchException, report_exception, get_log_folder
|
||||
from toolbox import write_history_to_file, promote_file_to_downloadzone
|
||||
fast_debug = False
|
||||
@@ -18,7 +18,7 @@ class PaperFileGroup():
|
||||
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
||||
self.get_token_num = get_token_num
|
||||
|
||||
def run_file_split(self, max_token_limit=2048):
|
||||
def run_file_split(self, max_token_limit=1900):
|
||||
"""
|
||||
将长文本分离开来
|
||||
"""
|
||||
@@ -64,25 +64,25 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
pfg.file_contents.append(file_content)
|
||||
|
||||
# <-------- 拆分过长的Markdown文件 ---------->
|
||||
pfg.run_file_split(max_token_limit=2048)
|
||||
pfg.run_file_split(max_token_limit=1500)
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
|
||||
# <-------- 多线程翻译开始 ---------->
|
||||
if language == 'en->zh':
|
||||
inputs_array = ["This is a Markdown file, translate it into Chinese, do NOT modify any existing Markdown commands, do NOT use code wrapper (```), ONLY answer me with translated results:" +
|
||||
inputs_array = ["This is a Markdown file, translate it into Chinese, do not modify any existing Markdown commands:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
|
||||
sys_prompt_array = ["You are a professional academic paper translator." + plugin_kwargs.get("additional_prompt", "") for _ in range(n_split)]
|
||||
sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
|
||||
elif language == 'zh->en':
|
||||
inputs_array = [f"This is a Markdown file, translate it into English, do NOT modify any existing Markdown commands, do NOT use code wrapper (```), ONLY answer me with translated results:" +
|
||||
inputs_array = [f"This is a Markdown file, translate it into English, do not modify any existing Markdown commands:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
|
||||
sys_prompt_array = ["You are a professional academic paper translator." + plugin_kwargs.get("additional_prompt", "") for _ in range(n_split)]
|
||||
sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
|
||||
else:
|
||||
inputs_array = [f"This is a Markdown file, translate it into {language}, do NOT modify any existing Markdown commands, do NOT use code wrapper (```), ONLY answer me with translated results:" +
|
||||
inputs_array = [f"This is a Markdown file, translate it into {language}, do not modify any existing Markdown commands, only answer me with translated results:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
|
||||
sys_prompt_array = ["You are a professional academic paper translator." + plugin_kwargs.get("additional_prompt", "") for _ in range(n_split)]
|
||||
sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
|
||||
|
||||
gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
inputs_array=inputs_array,
|
||||
@@ -99,12 +99,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
for i_say, gpt_say in zip(gpt_response_collection[0::2], gpt_response_collection[1::2]):
|
||||
pfg.sp_file_result.append(gpt_say)
|
||||
pfg.merge_result()
|
||||
output_file_arr = pfg.write_result(language)
|
||||
for output_file in output_file_arr:
|
||||
promote_file_to_downloadzone(output_file, chatbot=chatbot)
|
||||
if 'markdown_expected_output_path' in plugin_kwargs:
|
||||
expected_f_name = plugin_kwargs['markdown_expected_output_path']
|
||||
shutil.copyfile(output_file, expected_f_name)
|
||||
pfg.write_result(language)
|
||||
except:
|
||||
logging.error(trimmed_format_exc())
|
||||
|
||||
@@ -164,6 +159,7 @@ def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
|
||||
"函数插件功能？",
|
||||
"对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
disable_auto_promotion(chatbot)
|
||||
|
||||
# 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
try:
|
||||
@@ -203,6 +199,7 @@ def Markdown中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
|
||||
"函数插件功能？",
|
||||
"对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
disable_auto_promotion(chatbot)
|
||||
|
||||
# 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
try:
|
||||
@@ -235,6 +232,7 @@ def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history,
|
||||
"函数插件功能？",
|
||||
"对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
disable_auto_promotion(chatbot)
|
||||
|
||||
# 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
try:
|
||||
@@ -5,7 +5,7 @@ from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
from .crazy_utils import read_and_clean_pdf_text
|
||||
from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
|
||||
from shared_utils.colorful import *
|
||||
from colorful import *
|
||||
import copy
|
||||
import os
|
||||
import math
|
||||
|
||||
@@ -1,15 +1,83 @@
|
||||
from toolbox import get_log_folder
|
||||
from toolbox import update_ui, promote_file_to_downloadzone
|
||||
from toolbox import CatchException, report_exception, get_log_folder, gen_time_str, check_packages
|
||||
from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
|
||||
from toolbox import write_history_to_file, promote_file_to_downloadzone
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
from crazy_functions.crazy_utils import read_and_clean_pdf_text
|
||||
from shared_utils.colorful import *
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
from .crazy_utils import read_and_clean_pdf_text
|
||||
from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
|
||||
from colorful import *
|
||||
import os
|
||||
|
||||
def 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
|
||||
|
||||
@CatchException
|
||||
def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
|
||||
disable_auto_promotion(chatbot)
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"批量翻译PDF文档。函数插件贡献者: Binary-Husky"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
try:
|
||||
check_packages(["fitz", "tiktoken", "scipdf"])
|
||||
except:
|
||||
report_exception(chatbot, history,
|
||||
a=f"解析项目: {txt}",
|
||||
b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf tiktoken scipdf_parser```。")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 清空历史，以免输入溢出
|
||||
history = []
|
||||
|
||||
from .crazy_utils import get_files_from_everything
|
||||
success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
|
||||
# 检测输入参数，如没有给定输入参数，直接退出
|
||||
if not success:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
|
||||
# 如果没找到任何文件
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history,
|
||||
a=f"解析项目: {txt}", b=f"找不到任何.pdf拓展名的文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 开始正式执行任务
|
||||
grobid_url = get_avail_grobid_url()
|
||||
if grobid_url is not None:
|
||||
yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
|
||||
else:
|
||||
yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
|
||||
yield from 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
|
||||
|
||||
def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url):
|
||||
import copy, json
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 1024
|
||||
generated_conclusion_files = []
|
||||
generated_html_files = []
|
||||
DST_LANG = "中文"
|
||||
from crazy_functions.pdf_fns.report_gen_html import construct_html
|
||||
for index, fp in enumerate(file_manifest):
|
||||
chatbot.append(["当前进度：", f"正在连接GROBID服务，请稍候: {grobid_url}\n如果等待时间过长，请修改config中的GROBID_URL，可修改成本地GROBID服务。"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
article_dict = parse_pdf(fp, grobid_url)
|
||||
grobid_json_res = os.path.join(get_log_folder(), gen_time_str() + "grobid.json")
|
||||
with open(grobid_json_res, 'w+', encoding='utf8') as f:
|
||||
f.write(json.dumps(article_dict, indent=4, ensure_ascii=False))
|
||||
promote_file_to_downloadzone(grobid_json_res, chatbot=chatbot)
|
||||
|
||||
if article_dict is None: raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
|
||||
yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG)
|
||||
chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
|
||||
def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
|
||||
"""
|
||||
注意：此函数已经弃用！！新函数位于：crazy_functions/pdf_fns/parse_pdf.py
|
||||
此函数已经弃用
|
||||
"""
|
||||
import copy
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 1024
|
||||
@@ -48,8 +116,7 @@ def 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwa
|
||||
chatbot=chatbot,
|
||||
history_array=[[paper_meta] for _ in paper_fragments],
|
||||
sys_prompt_array=[
|
||||
"请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" + plugin_kwargs.get("additional_prompt", "")
|
||||
for _ in paper_fragments],
|
||||
"请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in paper_fragments],
|
||||
# max_workers=5 # OpenAI所允许的最大并行过载
|
||||
)
|
||||
gpt_response_collection_md = copy.deepcopy(gpt_response_collection)
|
||||
@@ -1,9 +1,7 @@
|
||||
from toolbox import CatchException, update_ui, report_exception
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from crazy_functions.plugin_template.plugin_class_template import (
|
||||
GptAcademicPluginTemplate,
|
||||
)
|
||||
from crazy_functions.plugin_template.plugin_class_template import ArgProperty
|
||||
from .crazy_utils import read_and_clean_pdf_text
|
||||
import datetime
|
||||
|
||||
#以下是每类图表的PROMPT
|
||||
SELECT_PROMPT = """
|
||||
@@ -23,21 +21,19 @@ SELECT_PROMPT = """
|
||||
#没有思维导图!!!测试发现模型始终会优先选择思维导图
|
||||
#流程图
|
||||
PROMPT_1 = """
|
||||
请你给出围绕“{subject}”的逻辑关系图，使用mermaid语法，注意需要使用双引号将内容括起来。
|
||||
mermaid语法举例：
|
||||
请你给出围绕“{subject}”的逻辑关系图，使用mermaid语法，mermaid语法举例：
|
||||
```mermaid
|
||||
graph TD
|
||||
P("编程") --> L1("Python")
|
||||
P("编程") --> L2("C")
|
||||
P("编程") --> L3("C++")
|
||||
P("编程") --> L4("Javascipt")
|
||||
P("编程") --> L5("PHP")
|
||||
P(编程) --> L1(Python)
|
||||
P(编程) --> L2(C)
|
||||
P(编程) --> L3(C++)
|
||||
P(编程) --> L4(Javascipt)
|
||||
P(编程) --> L5(PHP)
|
||||
```
|
||||
"""
|
||||
#序列图
|
||||
PROMPT_2 = """
|
||||
请你给出围绕“{subject}”的序列图，使用mermaid语法。
|
||||
mermaid语法举例：
|
||||
请你给出围绕“{subject}”的序列图，使用mermaid语法，mermaid语法举例：
|
||||
```mermaid
|
||||
sequenceDiagram
|
||||
participant A as 用户
|
||||
@@ -50,8 +46,7 @@ sequenceDiagram
|
||||
"""
|
||||
#类图
|
||||
PROMPT_3 = """
|
||||
请你给出围绕“{subject}”的类图，使用mermaid语法。
|
||||
mermaid语法举例：
|
||||
请你给出围绕“{subject}”的类图，使用mermaid语法，mermaid语法举例：
|
||||
```mermaid
|
||||
classDiagram
|
||||
Class01 <|-- AveryLongClass : Cool
|
||||
@@ -71,8 +66,7 @@ classDiagram
|
||||
"""
|
||||
#饼图
|
||||
PROMPT_4 = """
|
||||
请你给出围绕“{subject}”的饼图，使用mermaid语法，注意需要使用双引号将内容括起来。
|
||||
mermaid语法举例：
|
||||
请你给出围绕“{subject}”的饼图，使用mermaid语法，mermaid语法举例：
|
||||
```mermaid
|
||||
pie title Pets adopted by volunteers
|
||||
"狗" : 386
|
||||
@@ -82,39 +76,36 @@ pie title Pets adopted by volunteers
|
||||
"""
|
||||
#甘特图
|
||||
PROMPT_5 = """
|
||||
请你给出围绕“{subject}”的甘特图，使用mermaid语法，注意需要使用双引号将内容括起来。
|
||||
mermaid语法举例：
|
||||
请你给出围绕“{subject}”的甘特图，使用mermaid语法，mermaid语法举例：
|
||||
```mermaid
|
||||
gantt
|
||||
title "项目开发流程"
|
||||
title 项目开发流程
|
||||
dateFormat YYYY-MM-DD
|
||||
section "设计"
|
||||
"需求分析" :done, des1, 2024-01-06,2024-01-08
|
||||
"原型设计" :active, des2, 2024-01-09, 3d
|
||||
"UI设计" : des3, after des2, 5d
|
||||
section "开发"
|
||||
"前端开发" :2024-01-20, 10d
|
||||
"后端开发" :2024-01-20, 10d
|
||||
section 设计
|
||||
需求分析 :done, des1, 2024-01-06,2024-01-08
|
||||
原型设计 :active, des2, 2024-01-09, 3d
|
||||
UI设计 : des3, after des2, 5d
|
||||
section 开发
|
||||
前端开发 :2024-01-20, 10d
|
||||
后端开发 :2024-01-20, 10d
|
||||
```
|
||||
"""
|
||||
#状态图
|
||||
PROMPT_6 = """
|
||||
请你给出围绕“{subject}”的状态图，使用mermaid语法，注意需要使用双引号将内容括起来。
|
||||
mermaid语法举例：
|
||||
请你给出围绕“{subject}”的状态图，使用mermaid语法，mermaid语法举例：
|
||||
```mermaid
|
||||
stateDiagram-v2
|
||||
[*] --> "Still"
|
||||
"Still" --> [*]
|
||||
"Still" --> "Moving"
|
||||
"Moving" --> "Still"
|
||||
"Moving" --> "Crash"
|
||||
"Crash" --> [*]
|
||||
[*] --> Still
|
||||
Still --> [*]
|
||||
Still --> Moving
|
||||
Moving --> Still
|
||||
Moving --> Crash
|
||||
Crash --> [*]
|
||||
```
|
||||
"""
|
||||
#实体关系图
|
||||
PROMPT_7 = """
|
||||
请你给出围绕“{subject}”的实体关系图，使用mermaid语法。
|
||||
mermaid语法举例：
|
||||
请你给出围绕“{subject}”的实体关系图，使用mermaid语法，mermaid语法举例：
|
||||
```mermaid
|
||||
erDiagram
|
||||
CUSTOMER ||--o{ ORDER : places
|
||||
@@ -136,171 +127,142 @@ erDiagram
|
||||
"""
|
||||
#象限提示图
|
||||
PROMPT_8 = """
|
||||
请你给出围绕“{subject}”的象限图，使用mermaid语法，注意需要使用双引号将内容括起来。
|
||||
mermaid语法举例：
|
||||
请你给出围绕“{subject}”的象限图，使用mermaid语法，mermaid语法举例：
|
||||
```mermaid
|
||||
graph LR
|
||||
A["Hard skill"] --> B("Programming")
|
||||
A["Hard skill"] --> C("Design")
|
||||
D["Soft skill"] --> E("Coordination")
|
||||
D["Soft skill"] --> F("Communication")
|
||||
A[Hard skill] --> B(Programming)
|
||||
A[Hard skill] --> C(Design)
|
||||
D[Soft skill] --> E(Coordination)
|
||||
D[Soft skill] --> F(Communication)
|
||||
```
|
||||
"""
|
||||
#思维导图
|
||||
PROMPT_9 = """
|
||||
{subject}
|
||||
==========
|
||||
请给出上方内容的思维导图，充分考虑其之间的逻辑，使用mermaid语法，注意需要使用双引号将内容括起来。
|
||||
mermaid语法举例：
|
||||
请给出上方内容的思维导图，充分考虑其之间的逻辑，使用mermaid语法，mermaid语法举例：
|
||||
```mermaid
|
||||
mindmap
|
||||
root((mindmap))
|
||||
("Origins")
|
||||
("Long history")
|
||||
Origins
|
||||
Long history
|
||||
::icon(fa fa-book)
|
||||
("Popularisation")
|
||||
("British popular psychology author Tony Buzan")
|
||||
::icon(fa fa-user)
|
||||
("Research")
|
||||
("On effectiveness<br/>and features")
|
||||
::icon(fa fa-search)
|
||||
("On Automatic creation")
|
||||
::icon(fa fa-robot)
|
||||
("Uses")
|
||||
("Creative techniques")
|
||||
::icon(fa fa-lightbulb-o)
|
||||
("Strategic planning")
|
||||
::icon(fa fa-flag)
|
||||
("Argument mapping")
|
||||
::icon(fa fa-comments)
|
||||
("Tools")
|
||||
("Pen and paper")
|
||||
::icon(fa fa-pencil)
|
||||
("Mermaid")
|
||||
::icon(fa fa-code)
|
||||
Popularisation
|
||||
British popular psychology author Tony Buzan
|
||||
Research
|
||||
On effectiveness<br/>and features
|
||||
On Automatic creation
|
||||
Uses
|
||||
Creative techniques
|
||||
Strategic planning
|
||||
Argument mapping
|
||||
Tools
|
||||
Pen and paper
|
||||
Mermaid
|
||||
```
|
||||
"""
|
||||
|
||||
|
||||
def 解析历史输入(history, llm_kwargs, file_manifest, chatbot, plugin_kwargs):
|
||||
def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
|
||||
############################## <第 0 步，切割输入> ##################################
|
||||
# 借用PDF切割中的函数对文本进行切割
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 2500
|
||||
txt = (
|
||||
str(history).encode("utf-8", "ignore").decode()
|
||||
) # avoid reading non-utf8 chars
|
||||
from crazy_functions.pdf_fns.breakdown_txt import (
|
||||
breakdown_text_to_satisfy_token_limit,
|
||||
)
|
||||
|
||||
txt = breakdown_text_to_satisfy_token_limit(
|
||||
txt=txt, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs["llm_model"]
|
||||
)
|
||||
txt = str(history).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
|
||||
txt = breakdown_text_to_satisfy_token_limit(txt=txt, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
|
||||
############################## <第 1 步，迭代地历遍整个文章，提取精炼信息> ##################################
|
||||
i_say_show_user = f'首先你从历史记录或文件中提取摘要。'; gpt_say = "[Local Message] 收到。" # 用户提示
|
||||
chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history) # 更新UI
|
||||
results = []
|
||||
MAX_WORD_TOTAL = 4096
|
||||
n_txt = len(txt)
|
||||
last_iteration_result = "从以下文本中提取摘要。"
|
||||
if n_txt >= 20:
|
||||
print("文章极长，不能达到预期效果")
|
||||
if n_txt >= 20: print('文章极长，不能达到预期效果')
|
||||
for i in range(n_txt):
|
||||
NUM_OF_WORD = MAX_WORD_TOTAL // n_txt
|
||||
i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words in Chinese: {txt[i]}"
|
||||
i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i]}"
|
||||
i_say_show_user = f"[{i+1}/{n_txt}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i][:200]} ...."
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
i_say,
|
||||
i_say_show_user, # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
|
||||
llm_kwargs,
|
||||
chatbot,
|
||||
history=[
|
||||
"The main content of the previous section is?",
|
||||
last_iteration_result,
|
||||
], # 迭代上一次的结果
|
||||
sys_prompt="Extracts the main content from the text section where it is located for graphing purposes, answer me with Chinese.", # 提示
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
|
||||
llm_kwargs, chatbot,
|
||||
history=["The main content of the previous section is?", last_iteration_result], # 迭代上一次的结果
|
||||
sys_prompt="Extracts the main content from the text section where it is located for graphing purposes, answer me with Chinese." # 提示
|
||||
)
|
||||
results.append(gpt_say)
|
||||
last_iteration_result = gpt_say
|
||||
############################## <第 2 步，根据整理的摘要选择图表类型> ##################################
|
||||
gpt_say = str(plugin_kwargs) # 将图表类型参数赋值为插件参数
|
||||
results_txt = "\n".join(results) # 合并摘要
|
||||
if gpt_say not in [
|
||||
"1",
|
||||
"2",
|
||||
"3",
|
||||
"4",
|
||||
"5",
|
||||
"6",
|
||||
"7",
|
||||
"8",
|
||||
"9",
|
||||
]: # 如插件参数不正确则使用对话模型判断
|
||||
i_say_show_user = (
|
||||
f"接下来将判断适合的图表类型,如连续3次判断失败将会使用流程图进行绘制"
|
||||
)
|
||||
gpt_say = "[Local Message] 收到。" # 用户提示
|
||||
chatbot.append([i_say_show_user, gpt_say])
|
||||
yield from update_ui(chatbot=chatbot, history=[]) # 更新UI
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
gpt_say = plugin_kwargs.get("advanced_arg", "") #将图表类型参数赋值为插件参数
|
||||
results_txt = '\n'.join(results) #合并摘要
|
||||
if gpt_say not in ['1','2','3','4','5','6','7','8','9']: #如插件参数不正确则使用对话模型判断
|
||||
i_say_show_user = f'接下来将判断适合的图表类型,如连续3次判断失败将会使用流程图进行绘制'; gpt_say = "[Local Message] 收到。" # 用户提示
|
||||
chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=[]) # 更新UI
|
||||
i_say = SELECT_PROMPT.format(subject=results_txt)
|
||||
i_say_show_user = f'请判断适合使用的流程图类型,其中数字对应关系为:1-流程图,2-序列图,3-类图,4-饼图,5-甘特图,6-状态图,7-实体关系图,8-象限提示图。由于不管提供文本是什么,模型大概率认为"思维导图"最合适,因此思维导图仅能通过参数调用。'
|
||||
for i in range(3):
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say_show_user,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
history=[],
|
||||
sys_prompt="",
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt=""
|
||||
)
|
||||
if gpt_say in [
|
||||
"1",
|
||||
"2",
|
||||
"3",
|
||||
"4",
|
||||
"5",
|
||||
"6",
|
||||
"7",
|
||||
"8",
|
||||
"9",
|
||||
]: # 判断返回是否正确
|
||||
if gpt_say in ['1','2','3','4','5','6','7','8','9']: #判断返回是否正确
|
||||
break
|
||||
if gpt_say not in ["1", "2", "3", "4", "5", "6", "7", "8", "9"]:
|
||||
gpt_say = "1"
|
||||
if gpt_say not in ['1','2','3','4','5','6','7','8','9']:
|
||||
gpt_say = '1'
|
||||
############################## <第 3 步，根据选择的图表类型绘制图表> ##################################
|
||||
if gpt_say == "1":
|
||||
if gpt_say == '1':
|
||||
i_say = PROMPT_1.format(subject=results_txt)
|
||||
elif gpt_say == "2":
|
||||
elif gpt_say == '2':
|
||||
i_say = PROMPT_2.format(subject=results_txt)
|
||||
elif gpt_say == "3":
|
||||
elif gpt_say == '3':
|
||||
i_say = PROMPT_3.format(subject=results_txt)
|
||||
elif gpt_say == "4":
|
||||
elif gpt_say == '4':
|
||||
i_say = PROMPT_4.format(subject=results_txt)
|
||||
elif gpt_say == "5":
|
||||
elif gpt_say == '5':
|
||||
i_say = PROMPT_5.format(subject=results_txt)
|
||||
elif gpt_say == "6":
|
||||
elif gpt_say == '6':
|
||||
i_say = PROMPT_6.format(subject=results_txt)
|
||||
elif gpt_say == "7":
|
||||
elif gpt_say == '7':
|
||||
i_say = PROMPT_7.replace("{subject}", results_txt) #由于实体关系图用到了{}符号
|
||||
elif gpt_say == "8":
|
||||
elif gpt_say == '8':
|
||||
i_say = PROMPT_8.format(subject=results_txt)
|
||||
elif gpt_say == "9":
|
||||
elif gpt_say == '9':
|
||||
i_say = PROMPT_9.format(subject=results_txt)
|
||||
i_say_show_user = f"请根据判断结果绘制相应的图表。如需绘制思维导图请使用参数调用,同时过大的图表可能需要复制到在线编辑器中进行渲染。"
|
||||
i_say_show_user = f'请根据判断结果绘制相应的图表。如需绘制思维导图请使用参数调用,同时过大的图表可能需要复制到在线编辑器中进行渲染。'
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say_show_user,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
history=[],
|
||||
sys_prompt="",
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt="你精通使用mermaid语法来绘制图表,首先确保语法正确,其次避免在mermaid语法中使用不允许的字符,此外也应当分考虑图表的可读性。"
|
||||
)
|
||||
history.append(gpt_say)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
def 输入区文件处理(txt):
|
||||
if txt == "": return False, txt
|
||||
success = True
|
||||
import glob
|
||||
from .crazy_utils import get_files_from_everything
|
||||
file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
|
||||
file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
|
||||
if len(pdf_manifest) == 0 and len(md_manifest) == 0:
|
||||
return False, txt #如输入区内容不是文件则直接返回输入区内容
|
||||
|
||||
final_result = ""
|
||||
if file_pdf:
|
||||
for index, fp in enumerate(pdf_manifest):
|
||||
file_content, page_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
final_result += "\n" + file_content
|
||||
if file_md:
|
||||
for index, fp in enumerate(md_manifest):
|
||||
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
|
||||
file_content = f.read()
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode()
|
||||
final_result += "\n" + file_content
|
||||
return True, final_result
|
||||
|
||||
@CatchException
|
||||
def 生成多种Mermaid图表(
|
||||
txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port
|
||||
):
|
||||
def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
"""
|
||||
txt 输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
|
||||
llm_kwargs gpt模型参数，如温度和top_p等，一般原样传递下去就行
|
||||
@@ -313,126 +275,28 @@ def 生成多种Mermaid图表(
|
||||
import os
|
||||
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append(
|
||||
[
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"根据当前聊天历史或指定的路径文件(文件内容优先)绘制多种mermaid图表，将会由对话模型首先判断适合的图表类型，随后绘制图表。\
|
||||
\n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918",
|
||||
]
|
||||
)
|
||||
"根据当前聊天历史或文件中(文件内容优先)绘制多种mermaid图表，将会由对话模型首先判断适合的图表类型，随后绘制图表。\
|
||||
\n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
try:
|
||||
import fitz
|
||||
except:
|
||||
report_exception(chatbot, history,
|
||||
a = f"解析项目: {txt}",
|
||||
b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
if os.path.exists(txt): #如输入区无内容则直接解析历史记录
|
||||
from crazy_functions.pdf_fns.parse_word import extract_text_from_files
|
||||
|
||||
file_exist, final_result, page_one, file_manifest, excption = (
|
||||
extract_text_from_files(txt, chatbot, history)
|
||||
)
|
||||
file_exist, txt = 输入区文件处理(txt)
|
||||
else:
|
||||
file_exist = False
|
||||
excption = ""
|
||||
file_manifest = []
|
||||
|
||||
if excption != "":
|
||||
if excption == "word":
|
||||
report_exception(
|
||||
chatbot,
|
||||
history,
|
||||
a=f"解析项目: {txt}",
|
||||
b=f"找到了.doc文件，但是该文件格式不被支持，请先转化为.docx格式。",
|
||||
)
|
||||
if file_exist : history = [] #如输入区内容为文件则清空历史记录
|
||||
history.append(txt) #将解析后的txt传递加入到历史中
|
||||
|
||||
elif excption == "pdf":
|
||||
report_exception(
|
||||
chatbot,
|
||||
history,
|
||||
a=f"解析项目: {txt}",
|
||||
b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。",
|
||||
)
|
||||
|
||||
elif excption == "word_pip":
|
||||
report_exception(
|
||||
chatbot,
|
||||
history,
|
||||
a=f"解析项目: {txt}",
|
||||
b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade python-docx pywin32```。",
|
||||
)
|
||||
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
else:
|
||||
if not file_exist:
|
||||
history.append(txt) # 如输入区不是文件则将输入区内容加入历史记录
|
||||
i_say_show_user = f"首先你从历史记录中提取摘要。"
|
||||
gpt_say = "[Local Message] 收到。" # 用户提示
|
||||
chatbot.append([i_say_show_user, gpt_say])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 更新UI
|
||||
yield from 解析历史输入(
|
||||
history, llm_kwargs, file_manifest, chatbot, plugin_kwargs
|
||||
)
|
||||
else:
|
||||
file_num = len(file_manifest)
|
||||
for i in range(file_num): # 依次处理文件
|
||||
i_say_show_user = f"[{i+1}/{file_num}]处理文件{file_manifest[i]}"
|
||||
gpt_say = "[Local Message] 收到。" # 用户提示
|
||||
chatbot.append([i_say_show_user, gpt_say])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 更新UI
|
||||
history = [] # 如输入区内容为文件则清空历史记录
|
||||
history.append(final_result[i])
|
||||
yield from 解析历史输入(
|
||||
history, llm_kwargs, file_manifest, chatbot, plugin_kwargs
|
||||
)
|
||||
|
||||
|
||||
class Mermaid_Gen(GptAcademicPluginTemplate):
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
def define_arg_selection_menu(self):
|
||||
gui_definition = {
|
||||
"Type_of_Mermaid": ArgProperty(
|
||||
title="绘制的Mermaid图表类型",
|
||||
options=[
|
||||
"由LLM决定",
|
||||
"流程图",
|
||||
"序列图",
|
||||
"类图",
|
||||
"饼图",
|
||||
"甘特图",
|
||||
"状态图",
|
||||
"实体关系图",
|
||||
"象限提示图",
|
||||
"思维导图",
|
||||
],
|
||||
default_value="由LLM决定",
|
||||
description="选择'由LLM决定'时将由对话模型判断适合的图表类型(不包括思维导图)，选择其他类型时将直接绘制指定的图表类型。",
|
||||
type="dropdown",
|
||||
).model_dump_json(),
|
||||
}
|
||||
return gui_definition
|
||||
|
||||
def execute(
|
||||
txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request
|
||||
):
|
||||
options = [
|
||||
"由LLM决定",
|
||||
"流程图",
|
||||
"序列图",
|
||||
"类图",
|
||||
"饼图",
|
||||
"甘特图",
|
||||
"状态图",
|
||||
"实体关系图",
|
||||
"象限提示图",
|
||||
"思维导图",
|
||||
]
|
||||
plugin_kwargs = options.index(plugin_kwargs['Type_of_Mermaid'])
|
||||
yield from 生成多种Mermaid图表(
|
||||
txt,
|
||||
llm_kwargs,
|
||||
plugin_kwargs,
|
||||
chatbot,
|
||||
history,
|
||||
system_prompt,
|
||||
user_request,
|
||||
)
|
||||
yield from 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs)
|
||||
@@ -12,12 +12,6 @@ class PaperFileGroup():
|
||||
self.sp_file_index = []
|
||||
self.sp_file_tag = []
|
||||
|
||||
# count_token
|
||||
from request_llms.bridge_all import model_info
|
||||
enc = model_info["gpt-3.5-turbo"]['tokenizer']
|
||||
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
||||
self.get_token_num = get_token_num
|
||||
|
||||
def run_file_split(self, max_token_limit=1900):
|
||||
"""
|
||||
将长文本分离开来
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
from toolbox import update_ui, promote_file_to_downloadzone, disable_auto_promotion
|
||||
from toolbox import CatchException, report_exception, write_history_to_file
|
||||
from shared_utils.fastapi_server import validate_path_safety
|
||||
from crazy_functions.crazy_utils import input_clipping
|
||||
from .crazy_utils import input_clipping
|
||||
|
||||
def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
|
||||
import os, copy
|
||||
@@ -129,7 +128,6 @@ def 解析一个Python项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
|
||||
@@ -148,7 +146,6 @@ def 解析一个Matlab项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a = f"解析Matlab项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
|
||||
@@ -167,7 +164,6 @@ def 解析一个C项目的头文件(txt, llm_kwargs, plugin_kwargs, chatbot, his
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
|
||||
@@ -188,7 +184,6 @@ def 解析一个C项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
|
||||
@@ -211,7 +206,6 @@ def 解析一个Java项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
|
||||
@@ -234,7 +228,6 @@ def 解析一个前端项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
|
||||
@@ -264,7 +257,6 @@ def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
|
||||
@@ -286,7 +278,6 @@ def 解析一个Rust项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
|
||||
@@ -307,7 +298,6 @@ def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
|
||||
@@ -330,7 +320,6 @@ def 解析一个CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
|
||||
@@ -356,19 +345,15 @@ def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
|
||||
pattern_except_suffix = [_.lstrip(" ^*.,").rstrip(" ,") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^*.")]
|
||||
pattern_except_suffix += ['zip', 'rar', '7z', 'tar', 'gz'] # 避免解析压缩文件
|
||||
# 将要忽略匹配的文件名(例如: ^README.md)
|
||||
pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", r"\.") # 移除左边通配符，移除右侧逗号，转义点号
|
||||
for _ in txt_pattern.split(" ") # 以空格分割
|
||||
if (_ != "" and _.strip().startswith("^") and not _.strip().startswith("^*.")) # ^开始，但不是^*.开始
|
||||
]
|
||||
pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", "\.") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^") and not _.strip().startswith("^*.")]
|
||||
# 生成正则表达式
|
||||
pattern_except = r'/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
|
||||
pattern_except = '/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
|
||||
pattern_except += '|/(' + "|".join(pattern_except_name) + ')$' if pattern_except_name != [] else ''
|
||||
|
||||
history.clear()
|
||||
import glob, os, re
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
|
||||
|
||||
@@ -2,10 +2,6 @@ from toolbox import CatchException, update_ui
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
import datetime
|
||||
|
||||
####################################################################################################################
|
||||
# Demo 1: 一个非常简单的插件 #########################################################################################
|
||||
####################################################################################################################
|
||||
|
||||
高阶功能模板函数示意图 = f"""
|
||||
```mermaid
|
||||
flowchart TD
|
||||
@@ -30,7 +26,7 @@ flowchart TD
|
||||
"""
|
||||
|
||||
@CatchException
|
||||
def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request, num_day=5):
|
||||
def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
# 高阶功能模板函数示意图：https://mermaid.live/edit#pako:eNptk1tvEkEYhv8KmattQpvlvOyFCcdeeaVXuoYssBwie8gyhCIlqVoLhrbbtAWNUpEGUkyMEDW2Fmn_DDOL_8LZHdOwxrnamX3f7_3mmZk6yKhZCfAgV1KrmYKoQ9fDuKC4yChX0nld1Aou1JzjznQ5fWmejh8LYHW6vG2a47YAnlCLNSIRolnenKBXI_zRIBrcuqRT890u7jZx7zMDt-AaMbnW1--5olGiz2sQjwfoQxsZL0hxplSSU0-rop4vrzmKR6O2JxYjHmwcL2Y_HDatVMkXlf86YzHbGY9bO5j8XE7O8Nsbc3iNB3ukL2SMcH-XIQBgWoVOZzxuOxOJOyc63EPGV6ZQLENVrznViYStTiaJ2vw2M2d9bByRnOXkgCnXylCSU5quyto_IcmkbdvctELmJ-j1ASW3uB3g5xOmKqVTmqr_Na3AtuS_dtBFm8H90XJyHkDDT7S9xXWb4HGmRChx64AOL5HRpUm411rM5uh4H78Z4V7fCZzytjZz2seto9XaNPFue07clLaVZF8UNLygJ-VES8lah_n-O-5Ozc7-77NzJ0-K0yr0ZYrmHdqAk50t2RbA4qq9uNohBASw7YpSgaRkLWCCAtxAlnRZLGbJba9bPwUAC5IsCYAnn1kpJ1ZKUACC0iBSsQLVBzUlA3ioVyQ3qGhZEUrxokiehAz4nFgqk1VNVABfB1uAD_g2_AGPl-W8nMcbCvsDblADfNCz4feyobDPy3rYEMtxwYYbPFNVUoHdCPmDHBv2cP4AMfrCbiBli-Q-3afv0X6WdsIjW2-10fgDy1SAig
|
||||
|
||||
@@ -47,7 +43,7 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
"您正在调用插件：历史上的今天",
|
||||
"[Local Message] 请注意，您正在调用一个[函数插件]的模板，该函数面向希望实现更多有趣功能的开发者，它可以作为创建新功能函数的模板（该函数只有20多行代码）。此外我们也提供可同步处理大量文件的多线程Demo供您参考。您若希望分享新的功能模组，请不吝PR！" + 高阶功能模板函数示意图))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
|
||||
for i in range(int(num_day)):
|
||||
for i in range(5):
|
||||
currentMonth = (datetime.date.today() + datetime.timedelta(days=i)).month
|
||||
currentDay = (datetime.date.today() + datetime.timedelta(days=i)).day
|
||||
i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？列举两条并发送相关图片。发送图片时，请使用Markdown，将Unsplash API中的PUT_YOUR_QUERY_HERE替换成描述该事件的一个最重要的单词。'
|
||||
@@ -63,56 +59,6 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
####################################################################################################################
|
||||
# Demo 2: 一个带二级菜单的插件 #######################################################################################
|
||||
####################################################################################################################
|
||||
|
||||
from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
|
||||
class Demo_Wrap(GptAcademicPluginTemplate):
|
||||
def __init__(self):
|
||||
"""
|
||||
请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
|
||||
"""
|
||||
pass
|
||||
|
||||
def define_arg_selection_menu(self):
|
||||
"""
|
||||
定义插件的二级选项菜单
|
||||
"""
|
||||
gui_definition = {
|
||||
"num_day":
|
||||
ArgProperty(title="日期选择", options=["仅今天", "未来3天", "未来5天"], default_value="未来3天", description="无", type="dropdown").model_dump_json(),
|
||||
}
|
||||
return gui_definition
|
||||
|
||||
def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
执行插件
|
||||
"""
|
||||
num_day = plugin_kwargs["num_day"]
|
||||
if num_day == "仅今天": num_day = 1
|
||||
if num_day == "未来3天": num_day = 3
|
||||
if num_day == "未来5天": num_day = 5
|
||||
yield from 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request, num_day=num_day)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
####################################################################################################################
|
||||
# Demo 3: 绘制脑图的Demo ############################################################################################
|
||||
####################################################################################################################
|
||||
|
||||
PROMPT = """
|
||||
请你给出围绕“{subject}”的逻辑关系图，使用mermaid语法，mermaid语法举例：
|
||||
```mermaid
|
||||
|
||||
@@ -4,9 +4,9 @@
|
||||
# 1. 请在以下方案中选择任意一种，然后删除其他的方案
|
||||
# 2. 修改你选择的方案中的environment环境变量，详情请见github wiki或者config.py
|
||||
# 3. 选择一种暴露服务端口的方法，并对相应的配置做出修改：
|
||||
# 「方法1: 适用于Linux，很方便，可惜windows不支持」与宿主的网络融合为一体，这个是默认配置
|
||||
# 【方法1: 适用于Linux，很方便，可惜windows不支持】与宿主的网络融合为一体，这个是默认配置
|
||||
# network_mode: "host"
|
||||
# 「方法2: 适用于所有系统包括Windows和MacOS」端口映射，把容器的端口映射到宿主的端口（注意您需要先删除network_mode: "host"，再追加以下内容）
|
||||
# 【方法2: 适用于所有系统包括Windows和MacOS】端口映射，把容器的端口映射到宿主的端口（注意您需要先删除network_mode: "host"，再追加以下内容）
|
||||
# ports:
|
||||
# - "12345:12345" # 注意！12345必须与WEB_PORT环境变量相互对应
|
||||
# 4. 最后`docker-compose up`运行
|
||||
@@ -25,7 +25,7 @@
|
||||
## ===================================================
|
||||
|
||||
## ===================================================
|
||||
## 「方案零」 部署项目的全部能力（这个是包含cuda和latex的大型镜像。如果您网速慢、硬盘小或没有显卡，则不推荐使用这个）
|
||||
## 【方案零】 部署项目的全部能力（这个是包含cuda和latex的大型镜像。如果您网速慢、硬盘小或没有显卡，则不推荐使用这个）
|
||||
## ===================================================
|
||||
version: '3'
|
||||
services:
|
||||
@@ -63,10 +63,10 @@ services:
|
||||
# count: 1
|
||||
# capabilities: [gpu]
|
||||
|
||||
# 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
|
||||
# 【WEB_PORT暴露方法1: 适用于Linux】与宿主的网络融合
|
||||
network_mode: "host"
|
||||
|
||||
# 「WEB_PORT暴露方法2: 适用于所有系统」端口映射
|
||||
# 【WEB_PORT暴露方法2: 适用于所有系统】端口映射
|
||||
# ports:
|
||||
# - "12345:12345" # 12345必须与WEB_PORT相互对应
|
||||
|
||||
@@ -75,8 +75,10 @@ services:
|
||||
bash -c "python3 -u main.py"
|
||||
|
||||
|
||||
|
||||
|
||||
## ===================================================
|
||||
## 「方案一」 如果不需要运行本地模型（仅 chatgpt, azure, 星火, 千帆, claude 等在线大模型服务）
|
||||
## 【方案一】 如果不需要运行本地模型（仅 chatgpt, azure, 星火, 千帆, claude 等在线大模型服务）
|
||||
## ===================================================
|
||||
version: '3'
|
||||
services:
|
||||
@@ -95,16 +97,16 @@ services:
|
||||
# DEFAULT_WORKER_NUM: ' 10 '
|
||||
# AUTHENTICATION: ' [("username", "passwd"), ("username2", "passwd2")] '
|
||||
|
||||
# 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
|
||||
# 与宿主的网络融合
|
||||
network_mode: "host"
|
||||
|
||||
# 启动命令
|
||||
# 不使用代理网络拉取最新代码
|
||||
command: >
|
||||
bash -c "python3 -u main.py"
|
||||
|
||||
|
||||
### ===================================================
|
||||
### 「方案二」 如果需要运行ChatGLM + Qwen + MOSS等本地模型
|
||||
### 【方案二】 如果需要运行ChatGLM + Qwen + MOSS等本地模型
|
||||
### ===================================================
|
||||
version: '3'
|
||||
services:
|
||||
@@ -128,10 +130,8 @@ services:
|
||||
devices:
|
||||
- /dev/nvidia0:/dev/nvidia0
|
||||
|
||||
# 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
|
||||
# 与宿主的网络融合
|
||||
network_mode: "host"
|
||||
|
||||
# 启动命令
|
||||
command: >
|
||||
bash -c "python3 -u main.py"
|
||||
|
||||
@@ -139,9 +139,8 @@ services:
|
||||
# command: >
|
||||
# bash -c "pip install -r request_llms/requirements_qwen.txt && python3 -u main.py"
|
||||
|
||||
|
||||
### ===================================================
|
||||
### 「方案三」 如果需要运行ChatGPT + LLAMA + 盘古 + RWKV本地模型
|
||||
### 【方案三】 如果需要运行ChatGPT + LLAMA + 盘古 + RWKV本地模型
|
||||
### ===================================================
|
||||
version: '3'
|
||||
services:
|
||||
@@ -165,16 +164,16 @@ services:
|
||||
devices:
|
||||
- /dev/nvidia0:/dev/nvidia0
|
||||
|
||||
# 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
|
||||
# 与宿主的网络融合
|
||||
network_mode: "host"
|
||||
|
||||
# 启动命令
|
||||
# 不使用代理网络拉取最新代码
|
||||
command: >
|
||||
python3 -u main.py
|
||||
|
||||
|
||||
## ===================================================
|
||||
## 「方案四」 ChatGPT + Latex
|
||||
## 【方案四】 ChatGPT + Latex
|
||||
## ===================================================
|
||||
version: '3'
|
||||
services:
|
||||
@@ -191,16 +190,16 @@ services:
|
||||
DEFAULT_WORKER_NUM: ' 10 '
|
||||
WEB_PORT: ' 12303 '
|
||||
|
||||
# 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
|
||||
# 与宿主的网络融合
|
||||
network_mode: "host"
|
||||
|
||||
# 启动命令
|
||||
# 不使用代理网络拉取最新代码
|
||||
command: >
|
||||
bash -c "python3 -u main.py"
|
||||
|
||||
|
||||
## ===================================================
|
||||
## 「方案五」 ChatGPT + 语音助手 （请先阅读 docs/use_audio.md）
|
||||
## 【方案五】 ChatGPT + 语音助手 （请先阅读 docs/use_audio.md）
|
||||
## ===================================================
|
||||
version: '3'
|
||||
services:
|
||||
@@ -224,9 +223,9 @@ services:
|
||||
# (无需填写) ALIYUN_ACCESSKEY: ' LTAI5q6BrFUzoRXVGUWnekh1 '
|
||||
# (无需填写) ALIYUN_SECRET: ' eHmI20AVWIaQZ0CiTD2bGQVsaP9i68 '
|
||||
|
||||
# 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
|
||||
# 与宿主的网络融合
|
||||
network_mode: "host"
|
||||
|
||||
# 启动命令
|
||||
# 不使用代理网络拉取最新代码
|
||||
command: >
|
||||
bash -c "python3 -u main.py"
|
||||
|
||||
@@ -3,9 +3,6 @@
|
||||
# 从NVIDIA源，从而支持显卡（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
|
||||
FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest
|
||||
|
||||
# edge-tts需要的依赖，某些pip包所需的依赖
|
||||
RUN apt update && apt install ffmpeg build-essential -y
|
||||
|
||||
# use python3 as the system default python
|
||||
WORKDIR /gpt
|
||||
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
|
||||
|
||||
@@ -5,9 +5,6 @@
|
||||
# 从NVIDIA源，从而支持显卡（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
|
||||
FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest
|
||||
|
||||
# edge-tts需要的依赖，某些pip包所需的依赖
|
||||
RUN apt update && apt install ffmpeg build-essential -y
|
||||
|
||||
# use python3 as the system default python
|
||||
WORKDIR /gpt
|
||||
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
|
||||
@@ -39,7 +36,6 @@ RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
|
||||
RUN python3 -m pip install -r request_llms/requirements_newbing.txt
|
||||
RUN python3 -m pip install nougat-ocr
|
||||
|
||||
|
||||
# 预热Tiktoken模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
|
||||
@@ -5,8 +5,6 @@ RUN apt-get update
|
||||
RUN apt-get install -y curl proxychains curl gcc
|
||||
RUN apt-get install -y git python python3 python-dev python3-dev --fix-missing
|
||||
|
||||
# edge-tts需要的依赖，某些pip包所需的依赖
|
||||
RUN apt update && apt install ffmpeg build-essential -y
|
||||
|
||||
# use python3 as the system default python
|
||||
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
|
||||
@@ -24,6 +22,7 @@ RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
|
||||
RUN python3 -m pip install -r request_llms/requirements_newbing.txt
|
||||
|
||||
|
||||
|
||||
# 预热Tiktoken模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
|
||||
@@ -23,9 +23,6 @@ RUN python3 -m pip install -r request_llms/requirements_jittorllms.txt -i https:
|
||||
# 下载JittorLLMs
|
||||
RUN git clone https://github.com/binary-husky/JittorLLMs.git --depth 1 request_llms/jittorllms
|
||||
|
||||
# edge-tts需要的依赖
|
||||
RUN apt update && apt install ffmpeg -y
|
||||
|
||||
# 禁用缓存，确保更新代码
|
||||
ADD "https://www.random.org/cgi-bin/randbyte?nbytes=10&format=h" skipcache
|
||||
RUN git pull
|
||||
|
||||
@@ -12,8 +12,6 @@ COPY . .
|
||||
# 安装依赖
|
||||
RUN pip3 install -r requirements.txt
|
||||
|
||||
# edge-tts需要的依赖
|
||||
RUN apt update && apt install ffmpeg -y
|
||||
|
||||
# 可选步骤，用于预热模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
@@ -13,10 +13,7 @@ COPY . .
|
||||
RUN pip3 install -r requirements.txt
|
||||
|
||||
# 安装语音插件的额外依赖
|
||||
RUN pip3 install aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
|
||||
|
||||
# edge-tts需要的依赖
|
||||
RUN apt update && apt install ffmpeg -y
|
||||
RUN pip3 install pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
|
||||
|
||||
# 可选步骤，用于预热模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
@@ -25,9 +25,6 @@ COPY . .
|
||||
# 安装依赖
|
||||
RUN pip3 install -r requirements.txt
|
||||
|
||||
# edge-tts需要的依赖
|
||||
RUN apt update && apt install ffmpeg -y
|
||||
|
||||
# 可选步骤，用于预热模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
|
||||
@@ -19,9 +19,6 @@ RUN pip3 install transformers protobuf langchain sentence-transformers faiss-cp
|
||||
RUN pip3 install unstructured[all-docs] --upgrade
|
||||
RUN python3 -c 'from check_proxy import warm_up_vectordb; warm_up_vectordb()'
|
||||
|
||||
# edge-tts需要的依赖
|
||||
RUN apt update && apt install ffmpeg -y
|
||||
|
||||
# 可选步骤，用于预热模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
|
||||
@@ -1,189 +0,0 @@
|
||||
# 实现带二级菜单的插件
|
||||
|
||||
## 一、如何写带有二级菜单的插件
|
||||
|
||||
1. 声明一个 `Class`，继承父类 `GptAcademicPluginTemplate`
|
||||
|
||||
```python
|
||||
from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate
|
||||
from crazy_functions.plugin_template.plugin_class_template import ArgProperty
|
||||
|
||||
class Demo_Wrap(GptAcademicPluginTemplate):
|
||||
def __init__(self): ...
|
||||
```
|
||||
|
||||
2. 声明二级菜单中需要的变量，覆盖父类的`define_arg_selection_menu`函数。
|
||||
|
||||
```python
|
||||
class Demo_Wrap(GptAcademicPluginTemplate):
|
||||
...
|
||||
|
||||
def define_arg_selection_menu(self):
|
||||
"""
|
||||
定义插件的二级选项菜单
|
||||
|
||||
第一个参数，名称`main_input`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
|
||||
第二个参数，名称`advanced_arg`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
|
||||
第三个参数，名称`allow_cache`，参数`type`声明这是一个下拉菜单，下拉菜单上方显示`title`+`description`，下拉菜单的选项为`options`，`default_value`为下拉菜单默认值；
|
||||
"""
|
||||
gui_definition = {
|
||||
"main_input":
|
||||
ArgProperty(title="ArxivID", description="输入Arxiv的ID或者网址", default_value="", type="string").model_dump_json(),
|
||||
"advanced_arg":
|
||||
ArgProperty(title="额外的翻译提示词",
|
||||
description=r"如果有必要, 请在此处给出自定义翻译命令",
|
||||
default_value="", type="string").model_dump_json(),
|
||||
"allow_cache":
|
||||
ArgProperty(title="是否允许从缓存中调取结果", options=["允许缓存", "从头执行"], default_value="允许缓存", description="无", type="dropdown").model_dump_json(),
|
||||
}
|
||||
return gui_definition
|
||||
...
|
||||
```
|
||||
|
||||
|
||||
> [!IMPORTANT]
|
||||
>
|
||||
> ArgProperty 中每个条目对应一个参数，`type == "string"`时，使用文本块，`type == dropdown`时，使用下拉菜单。
|
||||
>
|
||||
> 注意：`main_input` 和 `advanced_arg`是两个特殊的参数。`main_input`会自动与界面右上角的`输入区`进行同步，而`advanced_arg`会自动与界面右下角的`高级参数输入区`同步。除此之外，参数名称可以任意选取。其他细节详见`crazy_functions/plugin_template/plugin_class_template.py`。
|
||||
|
||||
|
||||
|
||||
|
||||
3. 编写插件程序，覆盖父类的`execute`函数。
|
||||
|
||||
例如：
|
||||
|
||||
```python
|
||||
class Demo_Wrap(GptAcademicPluginTemplate):
|
||||
...
|
||||
...
|
||||
|
||||
def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
执行插件
|
||||
|
||||
plugin_kwargs字典中会包含用户的选择，与上述 `define_arg_selection_menu` 一一对应
|
||||
"""
|
||||
allow_cache = plugin_kwargs["allow_cache"]
|
||||
advanced_arg = plugin_kwargs["advanced_arg"]
|
||||
|
||||
if allow_cache == "从头执行": plugin_kwargs["advanced_arg"] = "--no-cache " + plugin_kwargs["advanced_arg"]
|
||||
yield from Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
|
||||
```
|
||||
|
||||
|
||||
|
||||
4. 注册插件
|
||||
|
||||
将以下条目插入`crazy_functional.py`即可。注意，与旧插件不同的是，`Function`键值应该为None，而`Class`键值为上述插件的类名称（`Demo_Wrap`）。
|
||||
```
|
||||
"新插件": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": True,
|
||||
"Info": "插件说明",
|
||||
"Function": None,
|
||||
"Class": Demo_Wrap,
|
||||
},
|
||||
```
|
||||
|
||||
5. 已经结束了，启动程序测试吧~！
|
||||
|
||||
|
||||
|
||||
## 二、背后的原理（需要JavaScript的前置知识）
|
||||
|
||||
|
||||
### (I) 首先介绍三个Gradio官方没有的重要前端函数
|
||||
|
||||
主javascript程序`common.js`中有三个Gradio官方没有的重要API
|
||||
|
||||
1. `get_data_from_gradio_component`
|
||||
这个函数可以获取任意gradio组件的当前值，例如textbox中的字符，dropdown中的当前选项，chatbot当前的对话等等。调用方法举例：
|
||||
```javascript
|
||||
// 获取当前的对话
|
||||
let chatbot = await get_data_from_gradio_component('gpt-chatbot');
|
||||
```
|
||||
|
||||
2. `get_gradio_component`
|
||||
有时候我们不仅需要gradio组件的当前值，还需要它的label值、是否隐藏、下拉菜单其他可选选项等等，而通过这个函数可以直接获取这个组件的句柄。举例：
|
||||
```javascript
|
||||
// 获取下拉菜单组件的句柄
|
||||
var model_sel = await get_gradio_component("elem_model_sel");
|
||||
// 获取它的所有属性，包括其所有可选选项
|
||||
console.log(model_sel.props)
|
||||
```
|
||||
|
||||
|
||||
3. `push_data_to_gradio_component`
|
||||
这个函数可以将数据推回gradio组件，例如textbox中的字符，dropdown中的当前选项等等。调用方法举例：
|
||||
|
||||
```javascript
|
||||
// 修改一个按钮上面的文本
|
||||
push_data_to_gradio_component("btnName", "gradio_element_id", "string");
|
||||
|
||||
// 隐藏一个组件
|
||||
push_data_to_gradio_component({ visible: false, __type__: 'update' }, "plugin_arg_menu", "obj");
|
||||
|
||||
// 修改组件label
|
||||
push_data_to_gradio_component({ label: '新label的值', __type__: 'update' }, "gpt-chatbot", "obj")
|
||||
|
||||
// 第一个参数是value，
|
||||
// - 可以是字符串（调整textbox的文本，按钮的文本）；
|
||||
// - 还可以是 { visible: false, __type__: 'update' } 这样的字典（调整visible, label, choices）
|
||||
// 第二个参数是elem_id
|
||||
// 第三个参数是"string" 或者 "obj"
|
||||
```
|
||||
|
||||
|
||||
### (II) 从点击插件到执行插件的逻辑过程
|
||||
|
||||
简述：程序启动时把每个插件的二级菜单编码为BASE64，存储在用户的浏览器前端，用户调用对应功能时，会按照插件的BASE64编码，将平时隐藏的菜单（有选择性地）显示出来。
|
||||
|
||||
1. 启动阶段（主函数 `main.py` 中），遍历每个插件，生成二级菜单的BASE64编码，存入变量`register_advanced_plugin_init_code_arr`。
|
||||
```python
|
||||
def get_js_code_for_generating_menu(self, btnName):
|
||||
define_arg_selection = self.define_arg_selection_menu()
|
||||
DEFINE_ARG_INPUT_INTERFACE = json.dumps(define_arg_selection)
|
||||
return base64.b64encode(DEFINE_ARG_INPUT_INTERFACE.encode('utf-8')).decode('utf-8')
|
||||
```
|
||||
|
||||
|
||||
2. 用户加载阶段（主javascript程序`common.js`中），浏览器加载`register_advanced_plugin_init_code_arr`，存入本地的字典`advanced_plugin_init_code_lib`：
|
||||
|
||||
```javascript
|
||||
advanced_plugin_init_code_lib = {}
|
||||
function register_advanced_plugin_init_code(key, code){
|
||||
advanced_plugin_init_code_lib[key] = code;
|
||||
}
|
||||
```
|
||||
|
||||
3. 用户点击插件按钮（主函数 `main.py` 中）时，仅执行以下javascript代码，唤醒隐藏的二级菜单（生成菜单的代码在`common.js`中的`generate_menu`函数上）：
|
||||
|
||||
|
||||
```javascript
|
||||
// 生成高级插件的选择菜单
|
||||
function run_advanced_plugin_launch_code(key){
|
||||
generate_menu(advanced_plugin_init_code_lib[key], key);
|
||||
}
|
||||
function on_flex_button_click(key){
|
||||
run_advanced_plugin_launch_code(key);
|
||||
}
|
||||
```
|
||||
|
||||
```python
|
||||
click_handle = plugins[k]["Button"].click(None, inputs=[], outputs=None, _js=f"""()=>run_advanced_plugin_launch_code("{k}")""")
|
||||
```
|
||||
|
||||
4. 当用户点击二级菜单的执行键时，通过javascript脚本模拟点击一个隐藏按钮，触发后续程序（`common.js`中的`execute_current_pop_up_plugin`，会把二级菜单中的参数缓存到`invisible_current_pop_up_plugin_arg_final`，然后模拟点击`invisible_callback_btn_for_plugin_exe`按钮）。隐藏按钮的定义在（主函数 `main.py` ），该隐藏按钮会最终触发`route_switchy_bt_with_arg`函数（定义于`themes/gui_advanced_plugin_class.py`）：
|
||||
|
||||
```python
|
||||
click_handle_ng = new_plugin_callback.click(route_switchy_bt_with_arg, [
|
||||
gr.State(["new_plugin_callback", "usr_confirmed_arg"] + input_combo_order),
|
||||
new_plugin_callback, usr_confirmed_arg, *input_combo
|
||||
], output_combo)
|
||||
```
|
||||
|
||||
5. 最后，`route_switchy_bt_with_arg`中，会搜集所有用户参数，统一集中到`plugin_kwargs`参数中，并执行对应插件的`execute`函数。
|
||||
@@ -22,13 +22,13 @@
|
||||
| crazy_functions\下载arxiv论文翻译摘要.py | 下载 `arxiv` 论文的 PDF 文件，并提取摘要和翻译 |
|
||||
| crazy_functions\代码重写为全英文_多线程.py | 将Python源代码文件中的中文内容转化为英文 |
|
||||
| crazy_functions\图片生成.py | 根据激励文本使用GPT模型生成相应的图像 |
|
||||
| crazy_functions\Conversation_To_File.py | 将每次对话记录写入Markdown格式的文件中 |
|
||||
| crazy_functions\对话历史存档.py | 将每次对话记录写入Markdown格式的文件中 |
|
||||
| crazy_functions\总结word文档.py | 对输入的word文档进行摘要生成 |
|
||||
| crazy_functions\总结音视频.py | 对输入的音视频文件进行摘要生成 |
|
||||
| crazy_functions\Markdown_Translate.py | 将指定目录下的Markdown文件进行中英文翻译 |
|
||||
| crazy_functions\批量Markdown翻译.py | 将指定目录下的Markdown文件进行中英文翻译 |
|
||||
| crazy_functions\批量总结PDF文档.py | 对PDF文件进行切割和摘要生成 |
|
||||
| crazy_functions\批量总结PDF文档pdfminer.py | 对PDF文件进行文本内容的提取和摘要生成 |
|
||||
| crazy_functions\PDF_Translate.py | 将指定目录下的PDF文件进行中英文翻译 |
|
||||
| crazy_functions\批量翻译PDF文档_多线程.py | 将指定目录下的PDF文件进行中英文翻译 |
|
||||
| crazy_functions\理解PDF文档内容.py | 对PDF文件进行摘要生成和问题解答 |
|
||||
| crazy_functions\生成函数注释.py | 自动生成Python函数的注释 |
|
||||
| crazy_functions\联网的ChatGPT.py | 使用网络爬虫和ChatGPT模型进行聊天回答 |
|
||||
@@ -155,9 +155,9 @@ toolbox.py是一个工具类库，其中主要包含了一些函数装饰器和
|
||||
|
||||
该程序文件提供了一个用于生成图像的函数`图片生成`。函数实现的过程中，会调用`gen_image`函数来生成图像，并返回图像生成的网址和本地文件地址。函数有多个参数，包括`prompt`(激励文本)、`llm_kwargs`(GPT模型的参数)、`plugin_kwargs`(插件模型的参数)等。函数核心代码使用了`requests`库向OpenAI API请求图像，并做了简单的处理和保存。函数还更新了交互界面，清空聊天历史并显示正在生成图像的消息和最终的图像网址和预览。
|
||||
|
||||
## [18/48] 请对下面的程序文件做一个概述: crazy_functions\Conversation_To_File.py
|
||||
## [18/48] 请对下面的程序文件做一个概述: crazy_functions\对话历史存档.py
|
||||
|
||||
这个文件是名为crazy_functions\Conversation_To_File.py的Python程序文件，包含了4个函数：
|
||||
这个文件是名为crazy_functions\对话历史存档.py的Python程序文件，包含了4个函数：
|
||||
|
||||
1. write_chat_to_file(chatbot, history=None, file_name=None)：用来将对话记录以Markdown格式写入文件中，并且生成文件名，如果没指定文件名则用当前时间。写入完成后将文件路径打印出来。
|
||||
|
||||
@@ -165,7 +165,7 @@ toolbox.py是一个工具类库，其中主要包含了一些函数装饰器和
|
||||
|
||||
3. read_file_to_chat(chatbot, history, file_name)：从传入的文件中读取内容，解析出对话历史记录并更新聊天显示框。
|
||||
|
||||
4. Conversation_To_File(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)：一个主要函数，用于保存当前对话记录并提醒用户。如果用户希望加载历史记录，则调用read_file_to_chat()来更新聊天显示框。如果用户希望删除历史记录，调用删除所有本地对话历史记录()函数完成删除操作。
|
||||
4. 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)：一个主要函数，用于保存当前对话记录并提醒用户。如果用户希望加载历史记录，则调用read_file_to_chat()来更新聊天显示框。如果用户希望删除历史记录，调用删除所有本地对话历史记录()函数完成删除操作。
|
||||
|
||||
## [19/48] 请对下面的程序文件做一个概述: crazy_functions\总结word文档.py
|
||||
|
||||
@@ -175,9 +175,9 @@ toolbox.py是一个工具类库，其中主要包含了一些函数装饰器和
|
||||
|
||||
该程序文件包括两个函数：split_audio_file()和AnalyAudio()，并且导入了一些必要的库并定义了一些工具函数。split_audio_file用于将音频文件分割成多个时长相等的片段，返回一个包含所有切割音频片段文件路径的列表，而AnalyAudio用来分析音频文件，通过调用whisper模型进行音频转文字并使用GPT模型对音频内容进行概述，最终将所有总结结果写入结果文件中。
|
||||
|
||||
## [21/48] 请对下面的程序文件做一个概述: crazy_functions\Markdown_Translate.py
|
||||
## [21/48] 请对下面的程序文件做一个概述: crazy_functions\批量Markdown翻译.py
|
||||
|
||||
该程序文件名为`Markdown_Translate.py`，包含了以下功能：读取Markdown文件，将长文本分离开来，将Markdown文件进行翻译（英译中和中译英），整理结果并退出。程序使用了多线程以提高效率。程序使用了`tiktoken`依赖库，可能需要额外安装。文件中还有一些其他的函数和类，但与文件名所描述的功能无关。
|
||||
该程序文件名为`批量Markdown翻译.py`，包含了以下功能：读取Markdown文件，将长文本分离开来，将Markdown文件进行翻译（英译中和中译英），整理结果并退出。程序使用了多线程以提高效率。程序使用了`tiktoken`依赖库，可能需要额外安装。文件中还有一些其他的函数和类，但与文件名所描述的功能无关。
|
||||
|
||||
## [22/48] 请对下面的程序文件做一个概述: crazy_functions\批量总结PDF文档.py
|
||||
|
||||
@@ -187,9 +187,9 @@ toolbox.py是一个工具类库，其中主要包含了一些函数装饰器和
|
||||
|
||||
该程序文件是一个用于批量总结PDF文档的函数插件，使用了pdfminer插件和BeautifulSoup库来提取PDF文档的文本内容，对每个PDF文件分别进行处理并生成中英文摘要。同时，该程序文件还包括一些辅助工具函数和处理异常的装饰器。
|
||||
|
||||
## [24/48] 请对下面的程序文件做一个概述: crazy_functions\PDF_Translate.py
|
||||
## [24/48] 请对下面的程序文件做一个概述: crazy_functions\批量翻译PDF文档_多线程.py
|
||||
|
||||
这个程序文件是一个Python脚本，文件名为“PDF_Translate.py”。它主要使用了“toolbox”、“request_gpt_model_in_new_thread_with_ui_alive”、“request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency”、“colorful”等Python库和自定义的模块“crazy_utils”的一些函数。程序实现了一个批量翻译PDF文档的功能，可以自动解析PDF文件中的基础信息，递归地切割PDF文件，翻译和处理PDF论文中的所有内容，并生成相应的翻译结果文件（包括md文件和html文件）。功能比较复杂，其中需要调用多个函数和依赖库，涉及到多线程操作和UI更新。文件中有详细的注释和变量命名，代码比较清晰易读。
|
||||
这个程序文件是一个Python脚本，文件名为“批量翻译PDF文档_多线程.py”。它主要使用了“toolbox”、“request_gpt_model_in_new_thread_with_ui_alive”、“request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency”、“colorful”等Python库和自定义的模块“crazy_utils”的一些函数。程序实现了一个批量翻译PDF文档的功能，可以自动解析PDF文件中的基础信息，递归地切割PDF文件，翻译和处理PDF论文中的所有内容，并生成相应的翻译结果文件（包括md文件和html文件）。功能比较复杂，其中需要调用多个函数和依赖库，涉及到多线程操作和UI更新。文件中有详细的注释和变量命名，代码比较清晰易读。
|
||||
|
||||
## [25/48] 请对下面的程序文件做一个概述: crazy_functions\理解PDF文档内容.py
|
||||
|
||||
@@ -331,19 +331,19 @@ check_proxy.py, colorful.py, config.py, config_private.py, core_functional.py, c
|
||||
这些程序源文件提供了基础的文本和语言处理功能、工具函数和高级插件，使 Chatbot 能够处理各种复杂的学术文本问题，包括润色、翻译、搜索、下载、解析等。
|
||||
|
||||
## 用一张Markdown表格简要描述以下文件的功能：
|
||||
crazy_functions\代码重写为全英文_多线程.py, crazy_functions\图片生成.py, crazy_functions\Conversation_To_File.py, crazy_functions\总结word文档.py, crazy_functions\总结音视频.py, crazy_functions\Markdown_Translate.py, crazy_functions\批量总结PDF文档.py, crazy_functions\批量总结PDF文档pdfminer.py, crazy_functions\PDF_Translate.py, crazy_functions\理解PDF文档内容.py, crazy_functions\生成函数注释.py, crazy_functions\联网的ChatGPT.py, crazy_functions\解析JupyterNotebook.py, crazy_functions\解析项目源代码.py, crazy_functions\询问多个大语言模型.py, crazy_functions\读文章写摘要.py。根据以上分析，用一句话概括程序的整体功能。
|
||||
crazy_functions\代码重写为全英文_多线程.py, crazy_functions\图片生成.py, crazy_functions\对话历史存档.py, crazy_functions\总结word文档.py, crazy_functions\总结音视频.py, crazy_functions\批量Markdown翻译.py, crazy_functions\批量总结PDF文档.py, crazy_functions\批量总结PDF文档pdfminer.py, crazy_functions\批量翻译PDF文档_多线程.py, crazy_functions\理解PDF文档内容.py, crazy_functions\生成函数注释.py, crazy_functions\联网的ChatGPT.py, crazy_functions\解析JupyterNotebook.py, crazy_functions\解析项目源代码.py, crazy_functions\询问多个大语言模型.py, crazy_functions\读文章写摘要.py。根据以上分析，用一句话概括程序的整体功能。
|
||||
|
||||
| 文件名 | 功能简述 |
|
||||
| --- | --- |
|
||||
| 代码重写为全英文_多线程.py | 将Python源代码文件中的中文内容转化为英文 |
|
||||
| 图片生成.py | 根据激励文本使用GPT模型生成相应的图像 |
|
||||
| Conversation_To_File.py | 将每次对话记录写入Markdown格式的文件中 |
|
||||
| 对话历史存档.py | 将每次对话记录写入Markdown格式的文件中 |
|
||||
| 总结word文档.py | 对输入的word文档进行摘要生成 |
|
||||
| 总结音视频.py | 对输入的音视频文件进行摘要生成 |
|
||||
| Markdown_Translate.py | 将指定目录下的Markdown文件进行中英文翻译 |
|
||||
| 批量Markdown翻译.py | 将指定目录下的Markdown文件进行中英文翻译 |
|
||||
| 批量总结PDF文档.py | 对PDF文件进行切割和摘要生成 |
|
||||
| 批量总结PDF文档pdfminer.py | 对PDF文件进行文本内容的提取和摘要生成 |
|
||||
| PDF_Translate.py | 将指定目录下的PDF文件进行中英文翻译 |
|
||||
| 批量翻译PDF文档_多线程.py | 将指定目录下的PDF文件进行中英文翻译 |
|
||||
| 理解PDF文档内容.py | 对PDF文件进行摘要生成和问题解答 |
|
||||
| 生成函数注释.py | 自动生成Python函数的注释 |
|
||||
| 联网的ChatGPT.py | 使用网络爬虫和ChatGPT模型进行聊天回答 |
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -36,15 +36,15 @@
|
||||
"总结word文档": "SummarizeWordDocument",
|
||||
"解析ipynb文件": "ParseIpynbFile",
|
||||
"解析JupyterNotebook": "ParseJupyterNotebook",
|
||||
"Conversation_To_File": "ConversationHistoryArchive",
|
||||
"载入Conversation_To_File": "LoadConversationHistoryArchive",
|
||||
"对话历史存档": "ConversationHistoryArchive",
|
||||
"载入对话历史存档": "LoadConversationHistoryArchive",
|
||||
"删除所有本地对话历史记录": "DeleteAllLocalChatHistory",
|
||||
"Markdown英译中": "MarkdownTranslateFromEngToChi",
|
||||
"Markdown_Translate": "BatchTranslateMarkdown",
|
||||
"批量Markdown翻译": "BatchTranslateMarkdown",
|
||||
"批量总结PDF文档": "BatchSummarizePDFDocuments",
|
||||
"批量总结PDF文档pdfminer": "BatchSummarizePDFDocumentsUsingPDFMiner",
|
||||
"批量翻译PDF文档": "BatchTranslatePDFDocuments",
|
||||
"PDF_Translate": "BatchTranslatePDFDocumentsUsingMultiThreading",
|
||||
"批量翻译PDF文档_多线程": "BatchTranslatePDFDocumentsUsingMultiThreading",
|
||||
"谷歌检索小助手": "GoogleSearchAssistant",
|
||||
"理解PDF文档内容标准文件输入": "StandardFileInputForUnderstandingPDFDocumentContent",
|
||||
"理解PDF文档内容": "UnderstandingPDFDocumentContent",
|
||||
@@ -1492,7 +1492,7 @@
|
||||
"交互功能模板函数": "InteractiveFunctionTemplateFunction",
|
||||
"交互功能函数模板": "InteractiveFunctionFunctionTemplate",
|
||||
"Latex英文纠错加PDF对比": "LatexEnglishErrorCorrectionWithPDFComparison",
|
||||
"Latex_Function": "LatexOutputPDFResult",
|
||||
"Latex输出PDF结果": "LatexOutputPDFResult",
|
||||
"Latex翻译中文并重新编译PDF": "TranslateChineseAndRecompilePDF",
|
||||
"语音助手": "VoiceAssistant",
|
||||
"微调数据集生成": "FineTuneDatasetGeneration",
|
||||
|
||||
@@ -6,14 +6,17 @@
|
||||
"Latex英文纠错加PDF对比": "CorrectEnglishInLatexWithPDFComparison",
|
||||
"下载arxiv论文并翻译摘要": "DownloadArxivPaperAndTranslateAbstract",
|
||||
"Markdown翻译指定语言": "TranslateMarkdownToSpecifiedLanguage",
|
||||
"批量翻译PDF文档_多线程": "BatchTranslatePDFDocuments_MultiThreaded",
|
||||
"下载arxiv论文翻译摘要": "DownloadArxivPaperTranslateAbstract",
|
||||
"解析一个Python项目": "ParsePythonProject",
|
||||
"解析一个Golang项目": "ParseGolangProject",
|
||||
"代码重写为全英文_多线程": "RewriteCodeToEnglish_MultiThreaded",
|
||||
"解析一个CSharp项目": "ParsingCSharpProject",
|
||||
"删除所有本地对话历史记录": "DeleteAllLocalConversationHistoryRecords",
|
||||
"批量Markdown翻译": "BatchTranslateMarkdown",
|
||||
"连接bing搜索回答问题": "ConnectBingSearchAnswerQuestion",
|
||||
"Langchain知识库": "LangchainKnowledgeBase",
|
||||
"Latex输出PDF结果": "OutputPDFFromLatex",
|
||||
"把字符太少的块清除为回车": "ClearBlocksWithTooFewCharactersToNewline",
|
||||
"Latex精细分解与转化": "DecomposeAndConvertLatex",
|
||||
"解析一个C项目的头文件": "ParseCProjectHeaderFiles",
|
||||
@@ -43,7 +46,7 @@
|
||||
"高阶功能模板函数": "HighOrderFunctionTemplateFunctions",
|
||||
"高级功能函数模板": "AdvancedFunctionTemplate",
|
||||
"总结word文档": "SummarizingWordDocuments",
|
||||
"载入Conversation_To_File": "LoadConversationHistoryArchive",
|
||||
"载入对话历史存档": "LoadConversationHistoryArchive",
|
||||
"Latex中译英": "LatexChineseToEnglish",
|
||||
"Latex英译中": "LatexEnglishToChinese",
|
||||
"连接网络回答问题": "ConnectToNetworkToAnswerQuestions",
|
||||
@@ -67,6 +70,7 @@
|
||||
"读文章写摘要": "ReadArticleWriteSummary",
|
||||
"生成函数注释": "GenerateFunctionComments",
|
||||
"解析项目本身": "ParseProjectItself",
|
||||
"对话历史存档": "ConversationHistoryArchive",
|
||||
"专业词汇声明": "ProfessionalTerminologyDeclaration",
|
||||
"解析docx": "ParseDocx",
|
||||
"解析源代码新": "ParsingSourceCodeNew",
|
||||
@@ -93,18 +97,5 @@
|
||||
"多智能体": "MultiAgent",
|
||||
"图片生成_DALLE2": "ImageGeneration_DALLE2",
|
||||
"图片生成_DALLE3": "ImageGeneration_DALLE3",
|
||||
"图片修改_DALLE2": "ImageModification_DALLE2",
|
||||
"生成多种Mermaid图表": "GenerateMultipleMermaidCharts",
|
||||
"知识库文件注入": "InjectKnowledgeBaseFiles",
|
||||
"PDF翻译中文并重新编译PDF": "TranslatePDFToChineseAndRecompilePDF",
|
||||
"随机小游戏": "RandomMiniGame",
|
||||
"互动小游戏": "InteractiveMiniGame",
|
||||
"解析历史输入": "ParseHistoricalInput",
|
||||
"高阶功能模板函数示意图": "HighOrderFunctionTemplateDiagram",
|
||||
"载入对话历史存档": "LoadChatHistoryArchive",
|
||||
"对话历史存档": "ChatHistoryArchive",
|
||||
"解析PDF_DOC2X_转Latex": "ParsePDF_DOC2X_toLatex",
|
||||
"解析PDF_基于DOC2X": "ParsePDF_basedDOC2X",
|
||||
"解析PDF_简单拆解": "ParsePDF_simpleDecomposition",
|
||||
"解析PDF_DOC2X_单文件": "ParsePDF_DOC2X_singleFile"
|
||||
"图片修改_DALLE2": "ImageModification_DALLE2"
|
||||
}
|
||||
@@ -35,15 +35,15 @@
|
||||
"总结word文档": "SummarizeWordDocument",
|
||||
"解析ipynb文件": "ParseIpynbFile",
|
||||
"解析JupyterNotebook": "ParseJupyterNotebook",
|
||||
"Conversation_To_File": "ConversationHistoryArchive",
|
||||
"载入Conversation_To_File": "LoadConversationHistoryArchive",
|
||||
"对话历史存档": "ConversationHistoryArchive",
|
||||
"载入对话历史存档": "LoadConversationHistoryArchive",
|
||||
"删除所有本地对话历史记录": "DeleteAllLocalConversationHistoryRecords",
|
||||
"Markdown英译中": "MarkdownEnglishToChinese",
|
||||
"Markdown_Translate": "BatchMarkdownTranslation",
|
||||
"批量Markdown翻译": "BatchMarkdownTranslation",
|
||||
"批量总结PDF文档": "BatchSummarizePDFDocuments",
|
||||
"批量总结PDF文档pdfminer": "BatchSummarizePDFDocumentsPdfminer",
|
||||
"批量翻译PDF文档": "BatchTranslatePDFDocuments",
|
||||
"PDF_Translate": "BatchTranslatePdfDocumentsMultithreaded",
|
||||
"批量翻译PDF文档_多线程": "BatchTranslatePdfDocumentsMultithreaded",
|
||||
"谷歌检索小助手": "GoogleSearchAssistant",
|
||||
"理解PDF文档内容标准文件输入": "StandardFileInputForUnderstandingPdfDocumentContent",
|
||||
"理解PDF文档内容": "UnderstandingPdfDocumentContent",
|
||||
@@ -1468,7 +1468,7 @@
|
||||
"交互功能模板函数": "InteractiveFunctionTemplateFunctions",
|
||||
"交互功能函数模板": "InteractiveFunctionFunctionTemplates",
|
||||
"Latex英文纠错加PDF对比": "LatexEnglishCorrectionWithPDFComparison",
|
||||
"Latex_Function": "OutputPDFFromLatex",
|
||||
"Latex输出PDF结果": "OutputPDFFromLatex",
|
||||
"Latex翻译中文并重新编译PDF": "TranslateLatexToChineseAndRecompilePDF",
|
||||
"语音助手": "VoiceAssistant",
|
||||
"微调数据集生成": "FineTuneDatasetGeneration",
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
|
||||
## 1. 安装额外依赖
|
||||
```
|
||||
pip install --upgrade pyOpenSSL webrtcvad scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
|
||||
pip install --upgrade pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
|
||||
```
|
||||
|
||||
如果因为特色网络问题导致上述命令无法执行：
|
||||
|
||||
@@ -1,58 +0,0 @@
|
||||
# 使用TTS文字转语音
|
||||
|
||||
|
||||
## 1. 使用EDGE-TTS（简单）
|
||||
|
||||
将本项目配置项修改如下即可
|
||||
|
||||
```
|
||||
TTS_TYPE = "EDGE_TTS"
|
||||
EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
|
||||
```
|
||||
|
||||
## 2. 使用SoVITS（需要有显卡）
|
||||
|
||||
使用以下docker-compose.yml文件，先启动SoVITS服务API
|
||||
|
||||
1. 创建以下文件夹结构
|
||||
```shell
|
||||
.
|
||||
├── docker-compose.yml
|
||||
└── reference
|
||||
├── clone_target_txt.txt
|
||||
└── clone_target_wave.mp3
|
||||
```
|
||||
2. 其中`docker-compose.yml`为
|
||||
```yaml
|
||||
version: '3.8'
|
||||
services:
|
||||
gpt-sovits:
|
||||
image: fuqingxu/sovits_gptac_trim:latest
|
||||
container_name: sovits_gptac_container
|
||||
working_dir: /workspace/gpt_sovits_demo
|
||||
environment:
|
||||
- is_half=False
|
||||
- is_share=False
|
||||
volumes:
|
||||
- ./reference:/reference
|
||||
ports:
|
||||
- "19880:9880" # 19880 为 sovits api 的暴露端口，记住它
|
||||
shm_size: 16G
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
count: "all"
|
||||
capabilities: [gpu]
|
||||
command: bash -c "python3 api.py"
|
||||
```
|
||||
3. 其中`clone_target_wave.mp3`为需要克隆的角色音频，`clone_target_txt.txt`为该音频对应的文字文本（ https://wiki.biligame.com/ys/%E8%A7%92%E8%89%B2%E8%AF%AD%E9%9F%B3 ）
|
||||
4. 运行`docker-compose up`
|
||||
5. 将本项目配置项修改如下即可
|
||||
(19880 为 sovits api 的暴露端口，与docker-compose.yml中的端口对应)
|
||||
```
|
||||
TTS_TYPE = "LOCAL_SOVITS_API"
|
||||
GPT_SOVITS_URL = "http://127.0.0.1:19880"
|
||||
```
|
||||
6. 启动本项目
|
||||
@@ -1,46 +0,0 @@
|
||||
# 使用VLLM
|
||||
|
||||
|
||||
## 1. 首先启动 VLLM，自行选择模型
|
||||
|
||||
```
|
||||
python -m vllm.entrypoints.openai.api_server --model /home/hmp/llm/cache/Qwen1___5-32B-Chat --tensor-parallel-size 2 --dtype=half
|
||||
```
|
||||
|
||||
这里使用了存储在 `/home/hmp/llm/cache/Qwen1___5-32B-Chat` 的本地模型，可以根据自己的需求更改。
|
||||
|
||||
## 2. 测试 VLLM
|
||||
|
||||
```
|
||||
curl http://localhost:8000/v1/chat/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "/home/hmp/llm/cache/Qwen1___5-32B-Chat",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": "怎么实现一个去中心化的控制器?"}
|
||||
]
|
||||
}'
|
||||
```
|
||||
|
||||
## 3. 配置本项目
|
||||
|
||||
```
|
||||
API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"
|
||||
LLM_MODEL = "vllm-/home/hmp/llm/cache/Qwen1___5-32B-Chat(max_token=4096)"
|
||||
API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "http://localhost:8000/v1/chat/completions"}
|
||||
```
|
||||
|
||||
```
|
||||
"vllm-/home/hmp/llm/cache/Qwen1___5-32B-Chat(max_token=4096)"
|
||||
其中
|
||||
"vllm-" 是前缀（必要）
|
||||
"/home/hmp/llm/cache/Qwen1___5-32B-Chat" 是模型名（必要）
|
||||
"(max_token=6666)" 是配置（非必要）
|
||||
```
|
||||
|
||||
## 4. 启动！
|
||||
|
||||
```
|
||||
python main.py
|
||||
```
|
||||
30
docs/waifu_plugin/autoload.js
Normal file
30
docs/waifu_plugin/autoload.js
Normal file
@@ -0,0 +1,30 @@
|
||||
try {
|
||||
$("<link>").attr({href: "file=docs/waifu_plugin/waifu.css", rel: "stylesheet", type: "text/css"}).appendTo('head');
|
||||
$('body').append('<div class="waifu"><div class="waifu-tips"></div><canvas id="live2d" class="live2d"></canvas><div class="waifu-tool"><span class="fui-home"></span> <span class="fui-chat"></span> <span class="fui-eye"></span> <span class="fui-user"></span> <span class="fui-photo"></span> <span class="fui-info-circle"></span> <span class="fui-cross"></span></div></div>');
|
||||
$.ajax({url: "file=docs/waifu_plugin/waifu-tips.js", dataType:"script", cache: true, success: function() {
|
||||
$.ajax({url: "file=docs/waifu_plugin/live2d.js", dataType:"script", cache: true, success: function() {
|
||||
/* 可直接修改部分参数 */
|
||||
live2d_settings['hitokotoAPI'] = "hitokoto.cn"; // 一言 API
|
||||
live2d_settings['modelId'] = 5; // 默认模型 ID
|
||||
live2d_settings['modelTexturesId'] = 1; // 默认材质 ID
|
||||
live2d_settings['modelStorage'] = false; // 不储存模型 ID
|
||||
live2d_settings['waifuSize'] = '210x187';
|
||||
live2d_settings['waifuTipsSize'] = '187x52';
|
||||
live2d_settings['canSwitchModel'] = true;
|
||||
live2d_settings['canSwitchTextures'] = true;
|
||||
live2d_settings['canSwitchHitokoto'] = false;
|
||||
live2d_settings['canTakeScreenshot'] = false;
|
||||
live2d_settings['canTurnToHomePage'] = false;
|
||||
live2d_settings['canTurnToAboutPage'] = false;
|
||||
live2d_settings['showHitokoto'] = false; // 显示一言
|
||||
live2d_settings['showF12Status'] = false; // 显示加载状态
|
||||
live2d_settings['showF12Message'] = false; // 显示看板娘消息
|
||||
live2d_settings['showF12OpenMsg'] = false; // 显示控制台打开提示
|
||||
live2d_settings['showCopyMessage'] = false; // 显示 复制内容 提示
|
||||
live2d_settings['showWelcomeMessage'] = true; // 显示进入面页欢迎词
|
||||
|
||||
/* 在 initModel 前添加 */
|
||||
initModel("file=docs/waifu_plugin/waifu-tips.json");
|
||||
}});
|
||||
}});
|
||||
} catch(err) { console.log("[Error] JQuery is not defined.") }
|
||||
|
Before Width: | Height: | Size: 56 KiB After Width: | Height: | Size: 56 KiB |
@@ -92,7 +92,7 @@ String.prototype.render = function(context) {
|
||||
};
|
||||
|
||||
var re = /x/;
|
||||
// console.log(re);
|
||||
console.log(re);
|
||||
|
||||
function empty(obj) {return typeof obj=="undefined"||obj==null||obj==""?true:false}
|
||||
function getRandText(text) {return Array.isArray(text) ? text[Math.floor(Math.random() * text.length + 1)-1] : text}
|
||||
@@ -120,7 +120,7 @@ function hideMessage(timeout) {
|
||||
|
||||
function initModel(waifuPath, type) {
|
||||
/* console welcome message */
|
||||
// eval(function(p,a,c,k,e,r){e=function(c){return(c<a?'':e(parseInt(c/a)))+((c=c%a)>35?String.fromCharCode(c+29):c.toString(36))};if(!''.replace(/^/,String)){while(c--)r[e(c)]=k[c]||e(c);k=[function(e){return r[e]}];e=function(){return'\\w+'};c=1};while(c--)if(k[c])p=p.replace(new RegExp('\\b'+e(c)+'\\b','g'),k[c]);return p}('8.d(" ");8.d("\\U,.\\y\\5.\\1\\1\\1\\1/\\1,\\u\\2 \\H\\n\\1\\1\\1\\1\\1\\b \', !-\\r\\j-i\\1/\\1/\\g\\n\\1\\1\\1 \\1 \\a\\4\\f\'\\1\\1\\1 L/\\a\\4\\5\\2\\n\\1\\1 \\1 /\\1 \\a,\\1 /|\\1 ,\\1 ,\\1\\1\\1 \',\\n\\1\\1\\1\\q \\1/ /-\\j/\\1\\h\\E \\9 \\5!\\1 i\\n\\1\\1\\1 \\3 \\6 7\\q\\4\\c\\1 \\3\'\\s-\\c\\2!\\t|\\1 |\\n\\1\\1\\1\\1 !,/7 \'0\'\\1\\1 \\X\\w| \\1 |\\1\\1\\1\\n\\1\\1\\1\\1 |.\\x\\"\\1\\l\\1\\1 ,,,, / |./ \\1 |\\n\\1\\1\\1\\1 \\3\'| i\\z.\\2,,A\\l,.\\B / \\1.i \\1|\\n\\1\\1\\1\\1\\1 \\3\'| | / C\\D/\\3\'\\5,\\1\\9.\\1|\\n\\1\\1\\1\\1\\1\\1 | |/i \\m|/\\1 i\\1,.\\6 |\\F\\1|\\n\\1\\1\\1\\1\\1\\1.|/ /\\1\\h\\G \\1 \\6!\\1\\1\\b\\1|\\n\\1\\1\\1 \\1 \\1 k\\5>\\2\\9 \\1 o,.\\6\\2 \\1 /\\2!\\n\\1\\1\\1\\1\\1\\1 !\'\\m//\\4\\I\\g\', \\b \\4\'7\'\\J\'\\n\\1\\1\\1\\1\\1\\1 \\3\'\\K|M,p,\\O\\3|\\P\\n\\1\\1\\1\\1\\1 \\1\\1\\1\\c-,/\\1|p./\\n\\1\\1\\1\\1\\1 \\1\\1\\1\'\\f\'\\1\\1!o,.:\\Q \\R\\S\\T v"+e.V+" / W "+e.N);8.d(" ");',60,60,'|u3000|uff64|uff9a|uff40|u30fd|uff8d||console|uff8a|uff0f|uff3c|uff84|log|live2d_settings|uff70|u00b4|uff49||u2010||u3000_|u3008||_|___|uff72|u2500|uff67|u30cf|u30fc||u30bd|u4ece|u30d8|uff1e|__|u30a4|k_|uff17_|u3000L_|u3000i|uff1a|u3009|uff34|uff70r|u30fdL__||___i|l2dVerDate|u30f3|u30ce|nLive2D|u770b|u677f|u5a18|u304f__|l2dVersion|FGHRSH|u00b40i'.split('|'),0,{}));
|
||||
eval(function(p,a,c,k,e,r){e=function(c){return(c<a?'':e(parseInt(c/a)))+((c=c%a)>35?String.fromCharCode(c+29):c.toString(36))};if(!''.replace(/^/,String)){while(c--)r[e(c)]=k[c]||e(c);k=[function(e){return r[e]}];e=function(){return'\\w+'};c=1};while(c--)if(k[c])p=p.replace(new RegExp('\\b'+e(c)+'\\b','g'),k[c]);return p}('8.d(" ");8.d("\\U,.\\y\\5.\\1\\1\\1\\1/\\1,\\u\\2 \\H\\n\\1\\1\\1\\1\\1\\b \', !-\\r\\j-i\\1/\\1/\\g\\n\\1\\1\\1 \\1 \\a\\4\\f\'\\1\\1\\1 L/\\a\\4\\5\\2\\n\\1\\1 \\1 /\\1 \\a,\\1 /|\\1 ,\\1 ,\\1\\1\\1 \',\\n\\1\\1\\1\\q \\1/ /-\\j/\\1\\h\\E \\9 \\5!\\1 i\\n\\1\\1\\1 \\3 \\6 7\\q\\4\\c\\1 \\3\'\\s-\\c\\2!\\t|\\1 |\\n\\1\\1\\1\\1 !,/7 \'0\'\\1\\1 \\X\\w| \\1 |\\1\\1\\1\\n\\1\\1\\1\\1 |.\\x\\"\\1\\l\\1\\1 ,,,, / |./ \\1 |\\n\\1\\1\\1\\1 \\3\'| i\\z.\\2,,A\\l,.\\B / \\1.i \\1|\\n\\1\\1\\1\\1\\1 \\3\'| | / C\\D/\\3\'\\5,\\1\\9.\\1|\\n\\1\\1\\1\\1\\1\\1 | |/i \\m|/\\1 i\\1,.\\6 |\\F\\1|\\n\\1\\1\\1\\1\\1\\1.|/ /\\1\\h\\G \\1 \\6!\\1\\1\\b\\1|\\n\\1\\1\\1 \\1 \\1 k\\5>\\2\\9 \\1 o,.\\6\\2 \\1 /\\2!\\n\\1\\1\\1\\1\\1\\1 !\'\\m//\\4\\I\\g\', \\b \\4\'7\'\\J\'\\n\\1\\1\\1\\1\\1\\1 \\3\'\\K|M,p,\\O\\3|\\P\\n\\1\\1\\1\\1\\1 \\1\\1\\1\\c-,/\\1|p./\\n\\1\\1\\1\\1\\1 \\1\\1\\1\'\\f\'\\1\\1!o,.:\\Q \\R\\S\\T v"+e.V+" / W "+e.N);8.d(" ");',60,60,'|u3000|uff64|uff9a|uff40|u30fd|uff8d||console|uff8a|uff0f|uff3c|uff84|log|live2d_settings|uff70|u00b4|uff49||u2010||u3000_|u3008||_|___|uff72|u2500|uff67|u30cf|u30fc||u30bd|u4ece|u30d8|uff1e|__|u30a4|k_|uff17_|u3000L_|u3000i|uff1a|u3009|uff34|uff70r|u30fdL__||___i|l2dVerDate|u30f3|u30ce|nLive2D|u770b|u677f|u5a18|u304f__|l2dVersion|FGHRSH|u00b40i'.split('|'),0,{}));
|
||||
|
||||
/* 判断 JQuery */
|
||||
if (typeof($.ajax) != 'function') typeof(jQuery.ajax) == 'function' ? window.$ = jQuery : console.log('[Error] JQuery is not defined.');
|
||||
@@ -142,13 +142,7 @@ function initModel(waifuPath, type) {
|
||||
if (live2d_settings.waifuEdgeSide[0] == 'left') $(".waifu").css("left",live2d_settings.waifuEdgeSide[1]+'px');
|
||||
else if (live2d_settings.waifuEdgeSide[0] == 'right') $(".waifu").css("right",live2d_settings.waifuEdgeSide[1]+'px');
|
||||
|
||||
window.waifuResize = function() {
|
||||
console.log('resize');
|
||||
if ($('.waifu')[0].style.display === "none" ){
|
||||
} else{
|
||||
$(window).width() <= Number(live2d_settings.waifuMinWidth.replace('px','')) ? $(".waifu").hide() : $(".waifu").show();
|
||||
}
|
||||
};
|
||||
window.waifuResize = function() { $(window).width() <= Number(live2d_settings.waifuMinWidth.replace('px','')) ? $(".waifu").hide() : $(".waifu").show(); };
|
||||
if (live2d_settings.waifuMinWidth != 'disable') { waifuResize(); $(window).resize(function() {waifuResize()}); }
|
||||
|
||||
try {
|
||||
@@ -44,8 +44,8 @@
|
||||
{ "selector": ".container a[href^='http']", "text": ["要看看 <span style=\"color:#0099cc;\">{text}</span> 么？"] },
|
||||
{ "selector": ".fui-home", "text": ["点击前往首页，想回到上一页可以使用浏览器的后退功能哦"] },
|
||||
{ "selector": ".fui-chat", "text": ["一言一语，一颦一笑。一字一句，一颗赛艇。"] },
|
||||
{ "selector": ".fui-eye", "text": ["嗯··· 要切换 Live2D形象 吗？"] },
|
||||
{ "selector": ".fui-user", "text": ["喜欢换装吗？"] },
|
||||
{ "selector": ".fui-eye", "text": ["嗯··· 要切换 看板娘 吗？"] },
|
||||
{ "selector": ".fui-user", "text": ["喜欢换装 Play 吗？"] },
|
||||
{ "selector": ".fui-photo", "text": ["要拍张纪念照片吗？"] },
|
||||
{ "selector": ".fui-info-circle", "text": ["这里有关于我的信息呢"] },
|
||||
{ "selector": ".fui-cross", "text": ["你不喜欢我了吗..."] },
|
||||
@@ -77,28 +77,14 @@
|
||||
"看什么看(*^▽^*)",
|
||||
"焦虑时，吃顿大餐心情就好啦^_^",
|
||||
"你这个年纪，怎么睡得着觉的你^_^",
|
||||
"打开“界面外观”菜单，可选择关闭Live2D形象",
|
||||
"经常去Github看看我们的更新吧，也许有好玩的新功能呢。",
|
||||
"修改ADD_WAIFU=False，我就不再打扰你了~",
|
||||
"经常去github看看我们的更新吧，也许有好玩的新功能呢。",
|
||||
"试试本地大模型吧，有的也很强大的哦。",
|
||||
"很多强大的函数插件隐藏在下拉菜单中呢。",
|
||||
"插件使用之前，需要把文件上传进去哦。",
|
||||
"上传文件时，可以把文件直接拖进对话中的哦。",
|
||||
"上传文件时，可以文件或图片粘贴到输入区哦。",
|
||||
"想添加基础功能按钮吗？打开“界面外观”菜单进行自定义吧！",
|
||||
"红色的插件，使用之前需要把文件上传进去哦。",
|
||||
"想添加功能按钮吗？读读readme很容易就学会啦。",
|
||||
"敏感或机密的信息，不可以问AI的哦！",
|
||||
"LLM究竟是划时代的创新，还是扼杀创造力的毒药呢？",
|
||||
"休息一下，起来走动走动吧！",
|
||||
"今天的阳光也很不错哦，不妨外出晒晒。",
|
||||
"笑一笑，生活更美好！",
|
||||
"遇到难题，深呼吸就能解决一半。",
|
||||
"偶尔换换环境，灵感也许就来了。",
|
||||
"小憩片刻，醒来便是满血复活。",
|
||||
"技术改变生活，让我们共同进步。",
|
||||
"保持好奇心，探索未知的世界。",
|
||||
"遇到困难，记得还有朋友和AI陪在你身边。",
|
||||
"劳逸结合，方能长久。",
|
||||
"偶尔给自己放个假，放松心情。",
|
||||
"不要害怕失败，勇敢尝试才能成功。"
|
||||
"LLM究竟是划时代的创新，还是扼杀创造力的毒药呢？"
|
||||
] }
|
||||
],
|
||||
"click": [
|
||||
326
main.py
326
main.py
@@ -1,4 +1,4 @@
|
||||
import os, json; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
|
||||
import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
|
||||
|
||||
help_menu_description = \
|
||||
"""Github源代码开源和更新[地址🚀](https://github.com/binary-husky/gpt_academic),
|
||||
@@ -13,42 +13,35 @@ help_menu_description = \
|
||||
</br></br>如何语音对话: 请阅读Wiki
|
||||
</br></br>如何临时更换API_KEY: 在输入区输入临时API_KEY后提交（网页刷新后失效）"""
|
||||
|
||||
def enable_log(PATH_LOGGING):
|
||||
import logging
|
||||
admin_log_path = os.path.join(PATH_LOGGING, "admin")
|
||||
os.makedirs(admin_log_path, exist_ok=True)
|
||||
log_dir = os.path.join(admin_log_path, "chat_secrets.log")
|
||||
try:logging.basicConfig(filename=log_dir, level=logging.INFO, encoding="utf-8", format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
|
||||
except:logging.basicConfig(filename=log_dir, level=logging.INFO, format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
|
||||
# Disable logging output from the 'httpx' logger
|
||||
logging.getLogger("httpx").setLevel(logging.WARNING)
|
||||
print(f"所有对话记录将自动保存在本地目录{log_dir}, 请注意自我隐私保护哦！")
|
||||
|
||||
def main():
|
||||
import gradio as gr
|
||||
if gr.__version__ not in ['3.32.9', '3.32.10', '3.32.11']:
|
||||
if gr.__version__ not in ['3.32.6', '3.32.7']:
|
||||
raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
|
||||
from request_llms.bridge_all import predict
|
||||
from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
|
||||
|
||||
# 读取配置
|
||||
from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, load_chat_cookies, DummyWith
|
||||
# 建议您复制一个config_private.py放自己的秘密, 如API和代理网址
|
||||
proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION')
|
||||
CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
|
||||
ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME, ADD_WAIFU = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME', 'ADD_WAIFU')
|
||||
NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
|
||||
DARK_MODE, INIT_SYS_PROMPT, ADD_WAIFU, TTS_TYPE = get_conf('DARK_MODE', 'INIT_SYS_PROMPT', 'ADD_WAIFU', 'TTS_TYPE')
|
||||
if LLM_MODEL not in AVAIL_LLM_MODELS: AVAIL_LLM_MODELS += [LLM_MODEL]
|
||||
ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME')
|
||||
DARK_MODE, NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('DARK_MODE', 'NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
|
||||
INIT_SYS_PROMPT = get_conf('INIT_SYS_PROMPT')
|
||||
|
||||
# 如果WEB_PORT是-1, 则随机选取WEB端口
|
||||
PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
|
||||
from check_proxy import get_current_version
|
||||
from themes.theme import adjust_theme, advanced_css, theme_declaration, js_code_clear, js_code_reset, js_code_show_or_hide, js_code_show_or_hide_group2
|
||||
from themes.theme import js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
|
||||
from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, assign_user_uuid
|
||||
from themes.theme import adjust_theme, advanced_css, theme_declaration
|
||||
from themes.theme import js_code_for_css_changing, js_code_for_darkmode_init, js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
|
||||
from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, init_cookie
|
||||
title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
|
||||
|
||||
# 对话、日志记录
|
||||
enable_log(PATH_LOGGING)
|
||||
# 问询记录, python 版本建议3.9+（越新越好）
|
||||
import logging, uuid
|
||||
os.makedirs(PATH_LOGGING, exist_ok=True)
|
||||
try:logging.basicConfig(filename=f"{PATH_LOGGING}/chat_secrets.log", level=logging.INFO, encoding="utf-8", format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
|
||||
except:logging.basicConfig(filename=f"{PATH_LOGGING}/chat_secrets.log", level=logging.INFO, format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
|
||||
# Disable logging output from the 'httpx' logger
|
||||
logging.getLogger("httpx").setLevel(logging.WARNING)
|
||||
print(f"所有问询记录将自动保存在本地目录./{PATH_LOGGING}/chat_secrets.log, 请注意自我隐私保护哦！")
|
||||
|
||||
# 一些普通功能模块
|
||||
from core_functional import get_core_functions
|
||||
@@ -71,9 +64,8 @@ def main():
|
||||
from check_proxy import check_proxy, auto_update, warm_up_modules
|
||||
proxy_info = check_proxy(proxies)
|
||||
|
||||
# 切换布局
|
||||
gr_L1 = lambda: gr.Row().style()
|
||||
gr_L2 = lambda scale, elem_id: gr.Column(scale=scale, elem_id=elem_id, min_width=400)
|
||||
gr_L2 = lambda scale, elem_id: gr.Column(scale=scale, elem_id=elem_id)
|
||||
if LAYOUT == "TOP-DOWN":
|
||||
gr_L1 = lambda: DummyWith()
|
||||
gr_L2 = lambda scale, elem_id: gr.Row()
|
||||
@@ -82,18 +74,15 @@ def main():
|
||||
cancel_handles = []
|
||||
customize_btns = {}
|
||||
predefined_btns = {}
|
||||
from shared_utils.cookie_manager import make_cookie_cache, make_history_cache
|
||||
with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as app_block:
|
||||
with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
|
||||
gr.HTML(title_html)
|
||||
secret_css = gr.Textbox(visible=False, elem_id="secret_css")
|
||||
register_advanced_plugin_init_arr = ""
|
||||
|
||||
cookies, web_cookie_cache = make_cookie_cache() # 定义 后端state（cookies）、前端（web_cookie_cache）两兄弟
|
||||
secret_css, dark_mode, persistent_cookie = gr.Textbox(visible=False), gr.Textbox(DARK_MODE, visible=False), gr.Textbox(visible=False)
|
||||
cookies = gr.State(load_chat_cookies())
|
||||
with gr_L1():
|
||||
with gr_L2(scale=2, elem_id="gpt-chat"):
|
||||
chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}", elem_id="gpt-chatbot")
|
||||
if LAYOUT == "TOP-DOWN": chatbot.style(height=CHATBOT_HEIGHT)
|
||||
history, history_cache, history_cache_update = make_history_cache() # 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
|
||||
history = gr.State([])
|
||||
with gr_L2(scale=1, elem_id="gpt-panel"):
|
||||
with gr.Accordion("输入区", open=True, elem_id="input-panel") as area_input_primary:
|
||||
with gr.Row():
|
||||
@@ -108,8 +97,7 @@ def main():
|
||||
with gr.Row():
|
||||
audio_mic = gr.Audio(source="microphone", type="numpy", elem_id="elem_audio", streaming=True, show_label=False).style(container=False)
|
||||
with gr.Row():
|
||||
status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。支持将文件直接粘贴到输入区。", elem_id="state-panel")
|
||||
|
||||
status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。当前模型: {LLM_MODEL} \n {proxy_info}", elem_id="state-panel")
|
||||
with gr.Accordion("基础功能区", open=True, elem_id="basic-panel") as area_basic_fn:
|
||||
with gr.Row():
|
||||
for k in range(NUM_CUSTOM_BASIC_BTN):
|
||||
@@ -124,20 +112,18 @@ def main():
|
||||
predefined_btns.update({k: functional[k]["Button"]})
|
||||
with gr.Accordion("函数插件区", open=True, elem_id="plugin-panel") as area_crazy_fn:
|
||||
with gr.Row():
|
||||
gr.Markdown("<small>插件可读取“输入区”文本/路径作为参数（上传文件自动修正路径）</small>")
|
||||
gr.Markdown("插件可读取“输入区”文本/路径作为参数（上传文件自动修正路径）")
|
||||
with gr.Row(elem_id="input-plugin-group"):
|
||||
plugin_group_sel = gr.Dropdown(choices=all_plugin_groups, label='', show_label=False, value=DEFAULT_FN_GROUPS,
|
||||
multiselect=True, interactive=True, elem_classes='normal_mut_select').style(container=False)
|
||||
with gr.Row():
|
||||
for index, (k, plugin) in enumerate(plugins.items()):
|
||||
for k, plugin in plugins.items():
|
||||
if not plugin.get("AsButton", True): continue
|
||||
visible = True if match_group(plugin['Group'], DEFAULT_FN_GROUPS) else False
|
||||
variant = plugins[k]["Color"] if "Color" in plugin else "secondary"
|
||||
info = plugins[k].get("Info", k)
|
||||
btn_elem_id = f"plugin_btn_{index}"
|
||||
plugin['Button'] = plugins[k]['Button'] = gr.Button(k, variant=variant,
|
||||
visible=visible, info_str=f'函数插件区: {info}', elem_id=btn_elem_id).style(size="sm")
|
||||
plugin['ButtonElemId'] = btn_elem_id
|
||||
visible=visible, info_str=f'函数插件区: {info}').style(size="sm")
|
||||
with gr.Row():
|
||||
with gr.Accordion("更多函数插件", open=True):
|
||||
dropdown_fn_list = []
|
||||
@@ -146,41 +132,129 @@ def main():
|
||||
if not plugin.get("AsButton", True): dropdown_fn_list.append(k) # 排除已经是按钮的插件
|
||||
elif plugin.get('AdvancedArgs', False): dropdown_fn_list.append(k) # 对于需要高级参数的插件，亦在下拉菜单中显示
|
||||
with gr.Row():
|
||||
dropdown = gr.Dropdown(dropdown_fn_list, value=r"点击这里搜索插件列表", label="", show_label=False).style(container=False)
|
||||
dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="", show_label=False).style(container=False)
|
||||
with gr.Row():
|
||||
plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False, elem_id="advance_arg_input_legacy",
|
||||
plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False,
|
||||
placeholder="这里是特殊函数插件的高级参数输入区").style(container=False)
|
||||
with gr.Row():
|
||||
switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary", elem_id="elem_switchy_bt").style(size="sm")
|
||||
switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary").style(size="sm")
|
||||
with gr.Row():
|
||||
with gr.Accordion("点击展开“文件下载区”。", open=False) as area_file_up:
|
||||
file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload")
|
||||
|
||||
# 左上角工具栏定义
|
||||
from themes.gui_toolbar import define_gui_toolbar
|
||||
checkboxes, checkboxes_2, max_length_sl, theme_dropdown, system_prompt, file_upload_2, md_dropdown, top_p, temperature = \
|
||||
define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAIL_THEMES, ADD_WAIFU, help_menu_description, js_code_for_toggle_darkmode)
|
||||
|
||||
# 浮动菜单定义
|
||||
from themes.gui_floating_menu import define_gui_floating_menu
|
||||
area_input_secondary, txt2, area_customize, submitBtn2, resetBtn2, clearBtn2, stopBtn2 = \
|
||||
define_gui_floating_menu(customize_btns, functional, predefined_btns, cookies, web_cookie_cache)
|
||||
with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden", elem_id="tooltip"):
|
||||
with gr.Row():
|
||||
with gr.Tab("上传文件", elem_id="interact-panel"):
|
||||
gr.Markdown("请上传本地文件/压缩包供“函数插件区”功能调用。请注意: 上传文件后会自动把输入区修改为相应路径。")
|
||||
file_upload_2 = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload_float")
|
||||
|
||||
# 插件二级菜单的实现
|
||||
from themes.gui_advanced_plugin_class import define_gui_advanced_plugin_class
|
||||
new_plugin_callback, route_switchy_bt_with_arg, usr_confirmed_arg = \
|
||||
define_gui_advanced_plugin_class(plugins)
|
||||
with gr.Tab("更换模型", elem_id="interact-panel"):
|
||||
md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
|
||||
top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
|
||||
temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature",)
|
||||
max_length_sl = gr.Slider(minimum=256, maximum=1024*32, value=4096, step=128, interactive=True, label="Local LLM MaxLength",)
|
||||
system_prompt = gr.Textbox(show_label=True, lines=2, placeholder=f"System Prompt", label="System prompt", value=INIT_SYS_PROMPT)
|
||||
|
||||
with gr.Tab("界面外观", elem_id="interact-panel"):
|
||||
theme_dropdown = gr.Dropdown(AVAIL_THEMES, value=THEME, label="更换UI主题").style(container=False)
|
||||
checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "浮动输入区", "输入清除键", "插件参数区"],
|
||||
value=["基础功能区", "函数插件区"], label="显示/隐藏功能区", elem_id='cbs').style(container=False)
|
||||
checkboxes_2 = gr.CheckboxGroup(["自定义菜单"],
|
||||
value=[], label="显示/隐藏自定义菜单", elem_id='cbsc').style(container=False)
|
||||
dark_mode_btn = gr.Button("切换界面明暗 ☀", variant="secondary").style(size="sm")
|
||||
dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode)
|
||||
with gr.Tab("帮助", elem_id="interact-panel"):
|
||||
gr.Markdown(help_menu_description)
|
||||
|
||||
with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_input_secondary:
|
||||
with gr.Accordion("浮动输入区", open=True, elem_id="input-panel2"):
|
||||
with gr.Row() as row:
|
||||
row.style(equal_height=True)
|
||||
with gr.Column(scale=10):
|
||||
txt2 = gr.Textbox(show_label=False, placeholder="Input question here.",
|
||||
elem_id='user_input_float', lines=8, label="输入区2").style(container=False)
|
||||
with gr.Column(scale=1, min_width=40):
|
||||
submitBtn2 = gr.Button("提交", variant="primary"); submitBtn2.style(size="sm")
|
||||
resetBtn2 = gr.Button("重置", variant="secondary"); resetBtn2.style(size="sm")
|
||||
stopBtn2 = gr.Button("停止", variant="secondary"); stopBtn2.style(size="sm")
|
||||
clearBtn2 = gr.Button("清除", variant="secondary", visible=False); clearBtn2.style(size="sm")
|
||||
|
||||
|
||||
with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_customize:
|
||||
with gr.Accordion("自定义菜单", open=True, elem_id="edit-panel"):
|
||||
with gr.Row() as row:
|
||||
with gr.Column(scale=10):
|
||||
AVAIL_BTN = [btn for btn in customize_btns.keys()] + [k for k in functional]
|
||||
basic_btn_dropdown = gr.Dropdown(AVAIL_BTN, value="自定义按钮1", label="选择一个需要自定义基础功能区按钮").style(container=False)
|
||||
basic_fn_title = gr.Textbox(show_label=False, placeholder="输入新按钮名称", lines=1).style(container=False)
|
||||
basic_fn_prefix = gr.Textbox(show_label=False, placeholder="输入新提示前缀", lines=4).style(container=False)
|
||||
basic_fn_suffix = gr.Textbox(show_label=False, placeholder="输入新提示后缀", lines=4).style(container=False)
|
||||
with gr.Column(scale=1, min_width=70):
|
||||
basic_fn_confirm = gr.Button("确认并保存", variant="primary"); basic_fn_confirm.style(size="sm")
|
||||
basic_fn_load = gr.Button("加载已保存", variant="primary"); basic_fn_load.style(size="sm")
|
||||
def assign_btn(persistent_cookie_, cookies_, basic_btn_dropdown_, basic_fn_title, basic_fn_prefix, basic_fn_suffix):
|
||||
ret = {}
|
||||
customize_fn_overwrite_ = cookies_['customize_fn_overwrite']
|
||||
customize_fn_overwrite_.update({
|
||||
basic_btn_dropdown_:
|
||||
{
|
||||
"Title":basic_fn_title,
|
||||
"Prefix":basic_fn_prefix,
|
||||
"Suffix":basic_fn_suffix,
|
||||
}
|
||||
}
|
||||
)
|
||||
cookies_.update(customize_fn_overwrite_)
|
||||
if basic_btn_dropdown_ in customize_btns:
|
||||
ret.update({customize_btns[basic_btn_dropdown_]: gr.update(visible=True, value=basic_fn_title)})
|
||||
else:
|
||||
ret.update({predefined_btns[basic_btn_dropdown_]: gr.update(visible=True, value=basic_fn_title)})
|
||||
ret.update({cookies: cookies_})
|
||||
try: persistent_cookie_ = from_cookie_str(persistent_cookie_) # persistent cookie to dict
|
||||
except: persistent_cookie_ = {}
|
||||
persistent_cookie_["custom_bnt"] = customize_fn_overwrite_ # dict update new value
|
||||
persistent_cookie_ = to_cookie_str(persistent_cookie_) # persistent cookie to dict
|
||||
ret.update({persistent_cookie: persistent_cookie_}) # write persistent cookie
|
||||
return ret
|
||||
|
||||
def reflesh_btn(persistent_cookie_, cookies_):
|
||||
ret = {}
|
||||
for k in customize_btns:
|
||||
ret.update({customize_btns[k]: gr.update(visible=False, value="")})
|
||||
|
||||
try: persistent_cookie_ = from_cookie_str(persistent_cookie_) # persistent cookie to dict
|
||||
except: return ret
|
||||
|
||||
customize_fn_overwrite_ = persistent_cookie_.get("custom_bnt", {})
|
||||
cookies_['customize_fn_overwrite'] = customize_fn_overwrite_
|
||||
ret.update({cookies: cookies_})
|
||||
|
||||
for k,v in persistent_cookie_["custom_bnt"].items():
|
||||
if v['Title'] == "": continue
|
||||
if k in customize_btns: ret.update({customize_btns[k]: gr.update(visible=True, value=v['Title'])})
|
||||
else: ret.update({predefined_btns[k]: gr.update(visible=True, value=v['Title'])})
|
||||
return ret
|
||||
|
||||
basic_fn_load.click(reflesh_btn, [persistent_cookie, cookies], [cookies, *customize_btns.values(), *predefined_btns.values()])
|
||||
h = basic_fn_confirm.click(assign_btn, [persistent_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
|
||||
[persistent_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
|
||||
# save persistent cookie
|
||||
h.then(None, [persistent_cookie], None, _js="""(persistent_cookie)=>{setCookie("persistent_cookie", persistent_cookie, 5);}""")
|
||||
|
||||
# 功能区显示开关与功能区的互动
|
||||
def fn_area_visibility(a):
|
||||
ret = {}
|
||||
ret.update({area_basic_fn: gr.update(visible=("基础功能区" in a))})
|
||||
ret.update({area_crazy_fn: gr.update(visible=("函数插件区" in a))})
|
||||
ret.update({area_input_primary: gr.update(visible=("浮动输入区" not in a))})
|
||||
ret.update({area_input_secondary: gr.update(visible=("浮动输入区" in a))})
|
||||
ret.update({clearBtn: gr.update(visible=("输入清除键" in a))})
|
||||
ret.update({clearBtn2: gr.update(visible=("输入清除键" in a))})
|
||||
ret.update({plugin_advanced_arg: gr.update(visible=("插件参数区" in a))})
|
||||
if "浮动输入区" in a: ret.update({txt: gr.update(value="")})
|
||||
return ret
|
||||
checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, plugin_advanced_arg] )
|
||||
checkboxes.select(None, [checkboxes], None, _js=js_code_show_or_hide)
|
||||
checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2, plugin_advanced_arg] )
|
||||
|
||||
# 功能区显示开关与功能区的互动
|
||||
def fn_area_visibility_2(a):
|
||||
@@ -188,11 +262,9 @@ def main():
|
||||
ret.update({area_customize: gr.update(visible=("自定义菜单" in a))})
|
||||
return ret
|
||||
checkboxes_2.select(fn_area_visibility_2, [checkboxes_2], [area_customize] )
|
||||
checkboxes_2.select(None, [checkboxes_2], None, _js=js_code_show_or_hide_group2)
|
||||
|
||||
# 整理反复出现的控件句柄组合
|
||||
input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
|
||||
input_combo_order = ["cookies", "max_length_sl", "md_dropdown", "txt", "txt2", "top_p", "temperature", "chatbot", "history", "system_prompt", "plugin_advanced_arg"]
|
||||
output_combo = [cookies, chatbot, history, status]
|
||||
predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True)], outputs=output_combo)
|
||||
# 提交按钮、重置按钮
|
||||
@@ -200,18 +272,15 @@ def main():
|
||||
cancel_handles.append(txt2.submit(**predict_args))
|
||||
cancel_handles.append(submitBtn.click(**predict_args))
|
||||
cancel_handles.append(submitBtn2.click(**predict_args))
|
||||
resetBtn.click(None, None, [chatbot, history, status], _js=js_code_reset) # 先在前端快速清除chatbot&status
|
||||
resetBtn2.click(None, None, [chatbot, history, status], _js=js_code_reset) # 先在前端快速清除chatbot&status
|
||||
reset_server_side_args = (lambda history: ([], [], "已重置", json.dumps(history)), [history], [chatbot, history, status, history_cache])
|
||||
resetBtn.click(*reset_server_side_args) # 再在后端清除history，把history转存history_cache备用
|
||||
resetBtn2.click(*reset_server_side_args) # 再在后端清除history，把history转存history_cache备用
|
||||
clearBtn.click(None, None, [txt, txt2], _js=js_code_clear)
|
||||
clearBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
|
||||
resetBtn.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
|
||||
resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
|
||||
clearBtn.click(lambda: ("",""), None, [txt, txt2])
|
||||
clearBtn2.click(lambda: ("",""), None, [txt, txt2])
|
||||
if AUTO_CLEAR_TXT:
|
||||
submitBtn.click(None, None, [txt, txt2], _js=js_code_clear)
|
||||
submitBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
|
||||
txt.submit(None, None, [txt, txt2], _js=js_code_clear)
|
||||
txt2.submit(None, None, [txt, txt2], _js=js_code_clear)
|
||||
submitBtn.click(lambda: ("",""), None, [txt, txt2])
|
||||
submitBtn2.click(lambda: ("",""), None, [txt, txt2])
|
||||
txt.submit(lambda: ("",""), None, [txt, txt2])
|
||||
txt2.submit(lambda: ("",""), None, [txt, txt2])
|
||||
# 基础功能区的回调函数注册
|
||||
for k in functional:
|
||||
if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
|
||||
@@ -224,42 +293,27 @@ def main():
|
||||
file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2, cookies]).then(None, None, None, _js=r"()=>{toast_push('上传完毕 ...'); cancel_loading_status();}")
|
||||
file_upload_2.upload(on_file_uploaded, [file_upload_2, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2, cookies]).then(None, None, None, _js=r"()=>{toast_push('上传完毕 ...'); cancel_loading_status();}")
|
||||
# 函数插件-固定按钮区
|
||||
def encode_plugin_info(k, plugin)->str:
|
||||
import copy
|
||||
from themes.theme import to_cookie_str
|
||||
plugin_ = copy.copy(plugin)
|
||||
plugin_.pop("Function", None)
|
||||
plugin_.pop("Class", None)
|
||||
plugin_.pop("Button", None)
|
||||
plugin_["Info"] = plugin.get("Info", k)
|
||||
if plugin.get("AdvancedArgs", False):
|
||||
plugin_["Label"] = f"插件[{k}]的高级参数说明：" + plugin.get("ArgsReminder", f"没有提供高级参数功能说明")
|
||||
else:
|
||||
plugin_["Label"] = f"插件[{k}]不需要高级参数。"
|
||||
return to_cookie_str(plugin_)
|
||||
|
||||
# 插件的注册（前端代码注册）
|
||||
for k in plugins:
|
||||
register_advanced_plugin_init_arr += f"""register_plugin_init("{k}","{encode_plugin_info(k, plugins[k])}");"""
|
||||
if plugins[k].get("Class", None):
|
||||
plugins[k]["JsMenu"] = plugins[k]["Class"]().get_js_code_for_generating_menu(k)
|
||||
register_advanced_plugin_init_arr += """register_advanced_plugin_init_code("{k}","{gui_js}");""".format(k=k, gui_js=plugins[k]["JsMenu"])
|
||||
if not plugins[k].get("AsButton", True): continue
|
||||
if plugins[k].get("Class", None) is None:
|
||||
assert plugins[k].get("Function", None) is not None
|
||||
click_handle = plugins[k]["Button"].click(None, inputs=[], outputs=None, _js=f"""()=>run_classic_plugin_via_id("{plugins[k]["ButtonElemId"]}")""")
|
||||
click_handle = plugins[k]["Button"].click(ArgsGeneralWrapper(plugins[k]["Function"]), [*input_combo], output_combo)
|
||||
click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
|
||||
cancel_handles.append(click_handle)
|
||||
# 函数插件-下拉菜单与随变按钮的互动
|
||||
def on_dropdown_changed(k):
|
||||
variant = plugins[k]["Color"] if "Color" in plugins[k] else "secondary"
|
||||
info = plugins[k].get("Info", k)
|
||||
ret = {switchy_bt: gr.update(value=k, variant=variant, info_str=f'函数插件区: {info}')}
|
||||
if plugins[k].get("AdvancedArgs", False): # 是否唤起高级插件参数区
|
||||
ret.update({plugin_advanced_arg: gr.update(visible=True, label=f"插件[{k}]的高级参数说明：" + plugins[k].get("ArgsReminder", [f"没有提供高级参数功能说明"]))})
|
||||
else:
|
||||
click_handle = plugins[k]["Button"].click(None, inputs=[], outputs=None, _js=f"""()=>run_advanced_plugin_launch_code("{k}")""")
|
||||
ret.update({plugin_advanced_arg: gr.update(visible=False, label=f"插件[{k}]不需要高级参数。")})
|
||||
return ret
|
||||
dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt, plugin_advanced_arg] )
|
||||
|
||||
# 函数插件-下拉菜单与随变按钮的互动（新版-更流畅）
|
||||
dropdown.select(None, [dropdown], None, _js=f"""(dropdown)=>run_dropdown_shift(dropdown)""")
|
||||
|
||||
# 模型切换时的回调
|
||||
def on_md_dropdown_changed(k):
|
||||
return {chatbot: gr.update(label="当前模型："+k)}
|
||||
md_dropdown.select(on_md_dropdown_changed, [md_dropdown], [chatbot] )
|
||||
|
||||
# 主题修改
|
||||
def on_theme_dropdown_changed(theme, secret_css):
|
||||
adjust_theme, css_part1, _, adjust_dynamic_theme = load_dynamic_theme(theme)
|
||||
if adjust_dynamic_theme:
|
||||
@@ -267,29 +321,21 @@ def main():
|
||||
else:
|
||||
css_part2 = adjust_theme()._get_theme_css()
|
||||
return css_part2 + css_part1
|
||||
theme_handle = theme_dropdown.select(on_theme_dropdown_changed, [theme_dropdown, secret_css], [secret_css]) # , _js="""change_theme_prepare""")
|
||||
theme_handle.then(None, [theme_dropdown, secret_css], None, _js="""change_theme""")
|
||||
|
||||
switchy_bt.click(None, [switchy_bt], None, _js="(switchy_bt)=>on_flex_button_click(switchy_bt)")
|
||||
theme_handle = theme_dropdown.select(on_theme_dropdown_changed, [theme_dropdown, secret_css], [secret_css])
|
||||
theme_handle.then(
|
||||
None,
|
||||
[secret_css],
|
||||
None,
|
||||
_js=js_code_for_css_changing
|
||||
)
|
||||
# 随变按钮的回调函数注册
|
||||
def route(request: gr.Request, k, *args, **kwargs):
|
||||
if k not in [r"点击这里搜索插件列表", r"请先从插件列表中选择"]:
|
||||
if plugins[k].get("Class", None) is None:
|
||||
assert plugins[k].get("Function", None) is not None
|
||||
if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
|
||||
yield from ArgsGeneralWrapper(plugins[k]["Function"])(request, *args, **kwargs)
|
||||
# 旧插件的高级参数区确认按钮（隐藏）
|
||||
old_plugin_callback = gr.Button(r"未选定任何插件", variant="secondary", visible=False, elem_id="old_callback_btn_for_plugin_exe")
|
||||
click_handle_ng = old_plugin_callback.click(route, [switchy_bt, *input_combo], output_combo)
|
||||
click_handle_ng.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot]).then(None, [switchy_bt], None, _js=r"(fn)=>on_plugin_exe_complete(fn)")
|
||||
cancel_handles.append(click_handle_ng)
|
||||
# 新一代插件的高级参数区确认按钮（隐藏）
|
||||
click_handle_ng = new_plugin_callback.click(route_switchy_bt_with_arg,
|
||||
[
|
||||
gr.State(["new_plugin_callback", "usr_confirmed_arg"] + input_combo_order), # 第一个参数: 指定了后续参数的名称
|
||||
new_plugin_callback, usr_confirmed_arg, *input_combo # 后续参数: 真正的参数
|
||||
], output_combo)
|
||||
click_handle_ng.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot]).then(None, [switchy_bt], None, _js=r"(fn)=>on_plugin_exe_complete(fn)")
|
||||
cancel_handles.append(click_handle_ng)
|
||||
click_handle = switchy_bt.click(route,[switchy_bt, *input_combo], output_combo)
|
||||
click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
|
||||
cancel_handles.append(click_handle)
|
||||
# 终止按钮的回调函数注册
|
||||
stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
|
||||
stopBtn2.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
|
||||
@@ -306,8 +352,6 @@ def main():
|
||||
elif match_group(plugin['Group'], group_list): fns_list.append(k) # 刷新下拉列表
|
||||
return [*btn_list, gr.Dropdown.update(choices=fns_list)]
|
||||
plugin_group_sel.select(fn=on_group_change, inputs=[plugin_group_sel], outputs=[*[plugin['Button'] for name, plugin in plugins_as_btn.items()], dropdown])
|
||||
|
||||
# 是否启动语音输入功能
|
||||
if ENABLE_AUDIO:
|
||||
from crazy_functions.live_audio.audio_io import RealtimeAudioDistribution
|
||||
rad = RealtimeAudioDistribution()
|
||||
@@ -315,18 +359,14 @@ def main():
|
||||
rad.feed(cookies['uuid'].hex, audio)
|
||||
audio_mic.stream(deal_audio, inputs=[audio_mic, cookies])
|
||||
|
||||
# 生成当前浏览器窗口的uuid（刷新失效）
|
||||
app_block.load(assign_user_uuid, inputs=[cookies], outputs=[cookies])
|
||||
|
||||
# 初始化（前端）
|
||||
from shared_utils.cookie_manager import load_web_cookie_cache__fn_builder
|
||||
load_web_cookie_cache = load_web_cookie_cache__fn_builder(customize_btns, cookies, predefined_btns)
|
||||
app_block.load(load_web_cookie_cache, inputs = [web_cookie_cache, cookies],
|
||||
outputs = [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()], _js=js_code_for_persistent_cookie_init)
|
||||
app_block.load(None, inputs=[], outputs=None, _js=f"""()=>GptAcademicJavaScriptInit("{DARK_MODE}","{INIT_SYS_PROMPT}","{ADD_WAIFU}","{LAYOUT}","{TTS_TYPE}")""") # 配置暗色主题或亮色主题
|
||||
app_block.load(None, inputs=[], outputs=None, _js="""()=>{REP}""".replace("REP", register_advanced_plugin_init_arr))
|
||||
demo.load(init_cookie, inputs=[cookies, chatbot], outputs=[cookies])
|
||||
darkmode_js = js_code_for_darkmode_init
|
||||
demo.load(None, inputs=None, outputs=[persistent_cookie], _js=js_code_for_persistent_cookie_init)
|
||||
demo.load(None, inputs=[dark_mode], outputs=None, _js=darkmode_js) # 配置暗色主题或亮色主题
|
||||
demo.load(None, inputs=[gr.Textbox(LAYOUT, visible=False)], outputs=None, _js='(LAYOUT)=>{GptAcademicJavaScriptInit(LAYOUT);}')
|
||||
|
||||
# Gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
|
||||
# gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
|
||||
def run_delayed_tasks():
|
||||
import threading, webbrowser, time
|
||||
print(f"如果浏览器没有自动打开，请复制并转到以下URL：")
|
||||
@@ -338,17 +378,29 @@ def main():
|
||||
def warm_up_mods(): time.sleep(6); warm_up_modules()
|
||||
|
||||
threading.Thread(target=auto_updates, name="self-upgrade", daemon=True).start() # 查看自动更新
|
||||
threading.Thread(target=warm_up_mods, name="warm-up", daemon=True).start() # 预热tiktoken模块
|
||||
if get_conf('AUTO_OPEN_BROWSER'):
|
||||
threading.Thread(target=open_browser, name="open-browser", daemon=True).start() # 打开浏览器页面
|
||||
threading.Thread(target=warm_up_mods, name="warm-up", daemon=True).start() # 预热tiktoken模块
|
||||
|
||||
# 运行一些异步任务：自动更新、打开浏览器页面、预热tiktoken模块
|
||||
run_delayed_tasks()
|
||||
demo.queue(concurrency_count=CONCURRENT_COUNT).launch(
|
||||
quiet=True,
|
||||
server_name="0.0.0.0",
|
||||
ssl_keyfile=None if SSL_KEYFILE == "" else SSL_KEYFILE,
|
||||
ssl_certfile=None if SSL_CERTFILE == "" else SSL_CERTFILE,
|
||||
ssl_verify=False,
|
||||
server_port=PORT,
|
||||
favicon_path=os.path.join(os.path.dirname(__file__), "docs/logo.png"),
|
||||
auth=AUTHENTICATION if len(AUTHENTICATION) != 0 else None,
|
||||
blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile",f"{PATH_LOGGING}/admin"])
|
||||
|
||||
# 最后，正式开始服务
|
||||
from shared_utils.fastapi_server import start_app
|
||||
start_app(app_block, CONCURRENT_COUNT, AUTHENTICATION, PORT, SSL_KEYFILE, SSL_CERTFILE)
|
||||
|
||||
# 如果需要在二级路径下运行
|
||||
# CUSTOM_PATH = get_conf('CUSTOM_PATH')
|
||||
# if CUSTOM_PATH != "/":
|
||||
# from toolbox import run_gradio_in_subpath
|
||||
# run_gradio_in_subpath(demo, auth=AUTHENTICATION, port=PORT, custom_path=CUSTOM_PATH)
|
||||
# else:
|
||||
# demo.launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION, favicon_path="docs/logo.png",
|
||||
# blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile",f"{PATH_LOGGING}/admin"])
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
@@ -8,10 +8,10 @@
|
||||
具备多线程调用能力的函数：在函数插件中被调用，灵活而简洁
|
||||
2. predict_no_ui_long_connection(...)
|
||||
"""
|
||||
import tiktoken, copy, re
|
||||
import tiktoken, copy
|
||||
from functools import lru_cache
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask, read_one_api_model_name
|
||||
from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask
|
||||
|
||||
from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
|
||||
from .bridge_chatgpt import predict as chatgpt_ui
|
||||
@@ -31,17 +31,6 @@ from .bridge_qianfan import predict as qianfan_ui
|
||||
from .bridge_google_gemini import predict as genai_ui
|
||||
from .bridge_google_gemini import predict_no_ui_long_connection as genai_noui
|
||||
|
||||
from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
|
||||
from .bridge_zhipu import predict as zhipu_ui
|
||||
|
||||
from .bridge_taichu import predict_no_ui_long_connection as taichu_noui
|
||||
from .bridge_taichu import predict as taichu_ui
|
||||
|
||||
from .bridge_cohere import predict as cohere_ui
|
||||
from .bridge_cohere import predict_no_ui_long_connection as cohere_noui
|
||||
|
||||
from .oai_std_model_template import get_predict_function
|
||||
|
||||
colors = ['#FF00FF', '#00FFFF', '#FF0000', '#990099', '#009999', '#990044']
|
||||
|
||||
class LazyloadTiktoken(object):
|
||||
@@ -69,13 +58,6 @@ API_URL_REDIRECT, AZURE_ENDPOINT, AZURE_ENGINE = get_conf("API_URL_REDIRECT", "A
|
||||
openai_endpoint = "https://api.openai.com/v1/chat/completions"
|
||||
api2d_endpoint = "https://openai.api2d.net/v1/chat/completions"
|
||||
newbing_endpoint = "wss://sydney.bing.com/sydney/ChatHub"
|
||||
gemini_endpoint = "https://generativelanguage.googleapis.com/v1beta/models"
|
||||
claude_endpoint = "https://api.anthropic.com/v1/messages"
|
||||
cohere_endpoint = "https://api.cohere.ai/v1/chat"
|
||||
ollama_endpoint = "http://localhost:11434/api/chat"
|
||||
yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"
|
||||
deepseekapi_endpoint = "https://api.deepseek.com/v1/chat/completions"
|
||||
|
||||
if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
|
||||
azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
|
||||
# 兼容旧版的配置
|
||||
@@ -90,12 +72,7 @@ except:
|
||||
if openai_endpoint in API_URL_REDIRECT: openai_endpoint = API_URL_REDIRECT[openai_endpoint]
|
||||
if api2d_endpoint in API_URL_REDIRECT: api2d_endpoint = API_URL_REDIRECT[api2d_endpoint]
|
||||
if newbing_endpoint in API_URL_REDIRECT: newbing_endpoint = API_URL_REDIRECT[newbing_endpoint]
|
||||
if gemini_endpoint in API_URL_REDIRECT: gemini_endpoint = API_URL_REDIRECT[gemini_endpoint]
|
||||
if claude_endpoint in API_URL_REDIRECT: claude_endpoint = API_URL_REDIRECT[claude_endpoint]
|
||||
if cohere_endpoint in API_URL_REDIRECT: cohere_endpoint = API_URL_REDIRECT[cohere_endpoint]
|
||||
if ollama_endpoint in API_URL_REDIRECT: ollama_endpoint = API_URL_REDIRECT[ollama_endpoint]
|
||||
if yimodel_endpoint in API_URL_REDIRECT: yimodel_endpoint = API_URL_REDIRECT[yimodel_endpoint]
|
||||
if deepseekapi_endpoint in API_URL_REDIRECT: deepseekapi_endpoint = API_URL_REDIRECT[deepseekapi_endpoint]
|
||||
|
||||
|
||||
# 获取tokenizer
|
||||
tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
|
||||
@@ -114,15 +91,6 @@ model_info = {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 16385,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
"taichu": {
|
||||
"fn_with_ui": taichu_ui,
|
||||
"fn_without_ui": taichu_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
@@ -164,15 +132,6 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
"gpt-3.5-turbo-0125": { #16k
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 16385,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
"gpt-4": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
@@ -191,35 +150,6 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
"gpt-4o": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"has_multimodal_capacity": True,
|
||||
"max_token": 128000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
"gpt-4o-2024-05-13": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"has_multimodal_capacity": True,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 128000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
"gpt-4-turbo-preview": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 128000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
"gpt-4-1106-preview": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
@@ -229,36 +159,6 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
"gpt-4-0125-preview": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 128000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
"gpt-4-turbo": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"has_multimodal_capacity": True,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 128000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
"gpt-4-turbo-2024-04-09": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"has_multimodal_capacity": True,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 128000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
|
||||
"gpt-3.5-random": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
@@ -297,65 +197,16 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
# 智谱AI
|
||||
"glm-4": {
|
||||
"fn_with_ui": zhipu_ui,
|
||||
"fn_without_ui": zhipu_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 10124 * 8,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"glm-4-0520": {
|
||||
"fn_with_ui": zhipu_ui,
|
||||
"fn_without_ui": zhipu_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 10124 * 8,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"glm-4-air": {
|
||||
"fn_with_ui": zhipu_ui,
|
||||
"fn_without_ui": zhipu_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 10124 * 8,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"glm-4-airx": {
|
||||
"fn_with_ui": zhipu_ui,
|
||||
"fn_without_ui": zhipu_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 10124 * 8,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"glm-4-flash": {
|
||||
"fn_with_ui": zhipu_ui,
|
||||
"fn_without_ui": zhipu_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 10124 * 8,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"glm-4v": {
|
||||
"fn_with_ui": zhipu_ui,
|
||||
"fn_without_ui": zhipu_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 1000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"glm-3-turbo": {
|
||||
"fn_with_ui": zhipu_ui,
|
||||
"fn_without_ui": zhipu_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 10124 * 4,
|
||||
# api_2d (此后不需要在此处添加api2d的接口了，因为下面的代码会自动添加)
|
||||
"api2d-gpt-3.5-turbo": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": api2d_endpoint,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
# api_2d (此后不需要在此处添加api2d的接口了，因为下面的代码会自动添加)
|
||||
"api2d-gpt-4": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
@@ -401,7 +252,7 @@ model_info = {
|
||||
"gemini-pro": {
|
||||
"fn_with_ui": genai_ui,
|
||||
"fn_without_ui": genai_noui,
|
||||
"endpoint": gemini_endpoint,
|
||||
"endpoint": None,
|
||||
"max_token": 1024 * 32,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
@@ -409,56 +260,13 @@ model_info = {
|
||||
"gemini-pro-vision": {
|
||||
"fn_with_ui": genai_ui,
|
||||
"fn_without_ui": genai_noui,
|
||||
"endpoint": gemini_endpoint,
|
||||
"max_token": 1024 * 32,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
# cohere
|
||||
"cohere-command-r-plus": {
|
||||
"fn_with_ui": cohere_ui,
|
||||
"fn_without_ui": cohere_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": cohere_endpoint,
|
||||
"max_token": 1024 * 4,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
}
|
||||
# -=-=-=-=-=-=- 月之暗面 -=-=-=-=-=-=-
|
||||
from request_llms.bridge_moonshot import predict as moonshot_ui
|
||||
from request_llms.bridge_moonshot import predict_no_ui_long_connection as moonshot_no_ui
|
||||
model_info.update({
|
||||
"moonshot-v1-8k": {
|
||||
"fn_with_ui": moonshot_ui,
|
||||
"fn_without_ui": moonshot_no_ui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 1024 * 8,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"moonshot-v1-32k": {
|
||||
"fn_with_ui": moonshot_ui,
|
||||
"fn_without_ui": moonshot_no_ui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 1024 * 32,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"moonshot-v1-128k": {
|
||||
"fn_with_ui": moonshot_ui,
|
||||
"fn_without_ui": moonshot_no_ui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 1024 * 128,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
}
|
||||
})
|
||||
|
||||
# -=-=-=-=-=-=- api2d 对齐支持 -=-=-=-=-=-=-
|
||||
for model in AVAIL_LLM_MODELS:
|
||||
if model.startswith('api2d-') and (model.replace('api2d-','') in model_info.keys()):
|
||||
@@ -474,67 +282,25 @@ for model in AVAIL_LLM_MODELS:
|
||||
model_info.update({model: mi})
|
||||
|
||||
# -=-=-=-=-=-=- 以下部分是新加入的模型，可能附带额外依赖 -=-=-=-=-=-=-
|
||||
# claude家族
|
||||
claude_models = ["claude-instant-1.2","claude-2.0","claude-2.1","claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229"]
|
||||
if any(item in claude_models for item in AVAIL_LLM_MODELS):
|
||||
if "claude-1-100k" in AVAIL_LLM_MODELS or "claude-2" in AVAIL_LLM_MODELS:
|
||||
from .bridge_claude import predict_no_ui_long_connection as claude_noui
|
||||
from .bridge_claude import predict as claude_ui
|
||||
model_info.update({
|
||||
"claude-instant-1.2": {
|
||||
"claude-1-100k": {
|
||||
"fn_with_ui": claude_ui,
|
||||
"fn_without_ui": claude_noui,
|
||||
"endpoint": claude_endpoint,
|
||||
"max_token": 100000,
|
||||
"endpoint": None,
|
||||
"max_token": 8196,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
})
|
||||
model_info.update({
|
||||
"claude-2.0": {
|
||||
"claude-2": {
|
||||
"fn_with_ui": claude_ui,
|
||||
"fn_without_ui": claude_noui,
|
||||
"endpoint": claude_endpoint,
|
||||
"max_token": 100000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
})
|
||||
model_info.update({
|
||||
"claude-2.1": {
|
||||
"fn_with_ui": claude_ui,
|
||||
"fn_without_ui": claude_noui,
|
||||
"endpoint": claude_endpoint,
|
||||
"max_token": 200000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
})
|
||||
model_info.update({
|
||||
"claude-3-haiku-20240307": {
|
||||
"fn_with_ui": claude_ui,
|
||||
"fn_without_ui": claude_noui,
|
||||
"endpoint": claude_endpoint,
|
||||
"max_token": 200000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
})
|
||||
model_info.update({
|
||||
"claude-3-sonnet-20240229": {
|
||||
"fn_with_ui": claude_ui,
|
||||
"fn_without_ui": claude_noui,
|
||||
"endpoint": claude_endpoint,
|
||||
"max_token": 200000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
})
|
||||
model_info.update({
|
||||
"claude-3-opus-20240229": {
|
||||
"fn_with_ui": claude_ui,
|
||||
"fn_without_ui": claude_noui,
|
||||
"endpoint": claude_endpoint,
|
||||
"max_token": 200000,
|
||||
"endpoint": None,
|
||||
"max_token": 8196,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
@@ -604,6 +370,22 @@ if "stack-claude" in AVAIL_LLM_MODELS:
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
}
|
||||
})
|
||||
if "newbing-free" in AVAIL_LLM_MODELS:
|
||||
try:
|
||||
from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
|
||||
from .bridge_newbingfree import predict as newbingfree_ui
|
||||
model_info.update({
|
||||
"newbing-free": {
|
||||
"fn_with_ui": newbingfree_ui,
|
||||
"fn_without_ui": newbingfree_noui,
|
||||
"endpoint": newbing_endpoint,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
}
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
if "newbing" in AVAIL_LLM_MODELS: # same with newbing-free
|
||||
try:
|
||||
from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
|
||||
@@ -636,7 +418,6 @@ if "chatglmft" in AVAIL_LLM_MODELS: # same with newbing-free
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 上海AI-LAB书生大模型 -=-=-=-=-=-=-
|
||||
if "internlm" in AVAIL_LLM_MODELS:
|
||||
try:
|
||||
from .bridge_internlm import predict_no_ui_long_connection as internlm_noui
|
||||
@@ -669,7 +450,6 @@ if "chatglm_onnx" in AVAIL_LLM_MODELS:
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 通义-本地模型 -=-=-=-=-=-=-
|
||||
if "qwen-local" in AVAIL_LLM_MODELS:
|
||||
try:
|
||||
from .bridge_qwen_local import predict_no_ui_long_connection as qwen_local_noui
|
||||
@@ -678,7 +458,6 @@ if "qwen-local" in AVAIL_LLM_MODELS:
|
||||
"qwen-local": {
|
||||
"fn_with_ui": qwen_local_ui,
|
||||
"fn_without_ui": qwen_local_noui,
|
||||
"can_multi_thread": False,
|
||||
"endpoint": None,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
@@ -687,7 +466,6 @@ if "qwen-local" in AVAIL_LLM_MODELS:
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 通义-在线模型 -=-=-=-=-=-=-
|
||||
if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-max" in AVAIL_LLM_MODELS: # zhipuai
|
||||
try:
|
||||
from .bridge_qwen import predict_no_ui_long_connection as qwen_noui
|
||||
@@ -696,7 +474,6 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
|
||||
"qwen-turbo": {
|
||||
"fn_with_ui": qwen_ui,
|
||||
"fn_without_ui": qwen_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 6144,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
@@ -705,7 +482,6 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
|
||||
"qwen-plus": {
|
||||
"fn_with_ui": qwen_ui,
|
||||
"fn_without_ui": qwen_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 30720,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
@@ -714,7 +490,6 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
|
||||
"qwen-max": {
|
||||
"fn_with_ui": qwen_ui,
|
||||
"fn_without_ui": qwen_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 28672,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
@@ -723,88 +498,7 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 零一万物模型 -=-=-=-=-=-=-
|
||||
yi_models = ["yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview"]
|
||||
if any(item in yi_models for item in AVAIL_LLM_MODELS):
|
||||
try:
|
||||
yimodel_4k_noui, yimodel_4k_ui = get_predict_function(
|
||||
api_key_conf_name="YIMODEL_API_KEY", max_output_token=600, disable_proxy=False
|
||||
)
|
||||
yimodel_16k_noui, yimodel_16k_ui = get_predict_function(
|
||||
api_key_conf_name="YIMODEL_API_KEY", max_output_token=4000, disable_proxy=False
|
||||
)
|
||||
yimodel_200k_noui, yimodel_200k_ui = get_predict_function(
|
||||
api_key_conf_name="YIMODEL_API_KEY", max_output_token=4096, disable_proxy=False
|
||||
)
|
||||
model_info.update({
|
||||
"yi-34b-chat-0205": {
|
||||
"fn_with_ui": yimodel_4k_ui,
|
||||
"fn_without_ui": yimodel_4k_noui,
|
||||
"can_multi_thread": False, # 目前来说，默认情况下并发量极低，因此禁用
|
||||
"endpoint": yimodel_endpoint,
|
||||
"max_token": 4000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"yi-34b-chat-200k": {
|
||||
"fn_with_ui": yimodel_200k_ui,
|
||||
"fn_without_ui": yimodel_200k_noui,
|
||||
"can_multi_thread": False, # 目前来说，默认情况下并发量极低，因此禁用
|
||||
"endpoint": yimodel_endpoint,
|
||||
"max_token": 200000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"yi-large": {
|
||||
"fn_with_ui": yimodel_16k_ui,
|
||||
"fn_without_ui": yimodel_16k_noui,
|
||||
"can_multi_thread": False, # 目前来说，默认情况下并发量极低，因此禁用
|
||||
"endpoint": yimodel_endpoint,
|
||||
"max_token": 16000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"yi-medium": {
|
||||
"fn_with_ui": yimodel_16k_ui,
|
||||
"fn_without_ui": yimodel_16k_noui,
|
||||
"can_multi_thread": True, # 这个并发量稍微大一点
|
||||
"endpoint": yimodel_endpoint,
|
||||
"max_token": 16000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"yi-spark": {
|
||||
"fn_with_ui": yimodel_16k_ui,
|
||||
"fn_without_ui": yimodel_16k_noui,
|
||||
"can_multi_thread": True, # 这个并发量稍微大一点
|
||||
"endpoint": yimodel_endpoint,
|
||||
"max_token": 16000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"yi-large-turbo": {
|
||||
"fn_with_ui": yimodel_16k_ui,
|
||||
"fn_without_ui": yimodel_16k_noui,
|
||||
"can_multi_thread": False, # 目前来说，默认情况下并发量极低，因此禁用
|
||||
"endpoint": yimodel_endpoint,
|
||||
"max_token": 16000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"yi-large-preview": {
|
||||
"fn_with_ui": yimodel_16k_ui,
|
||||
"fn_without_ui": yimodel_16k_noui,
|
||||
"can_multi_thread": False, # 目前来说，默认情况下并发量极低，因此禁用
|
||||
"endpoint": yimodel_endpoint,
|
||||
"max_token": 16000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 讯飞星火认知大模型 -=-=-=-=-=-=-
|
||||
if "spark" in AVAIL_LLM_MODELS:
|
||||
if "spark" in AVAIL_LLM_MODELS: # 讯飞星火认知大模型
|
||||
try:
|
||||
from .bridge_spark import predict_no_ui_long_connection as spark_noui
|
||||
from .bridge_spark import predict as spark_ui
|
||||
@@ -812,7 +506,6 @@ if "spark" in AVAIL_LLM_MODELS:
|
||||
"spark": {
|
||||
"fn_with_ui": spark_ui,
|
||||
"fn_without_ui": spark_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
@@ -829,7 +522,6 @@ if "sparkv2" in AVAIL_LLM_MODELS: # 讯飞星火认知大模型
|
||||
"sparkv2": {
|
||||
"fn_with_ui": spark_ui,
|
||||
"fn_without_ui": spark_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
@@ -838,7 +530,7 @@ if "sparkv2" in AVAIL_LLM_MODELS: # 讯飞星火认知大模型
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS: # 讯飞星火认知大模型
|
||||
if "sparkv3" in AVAIL_LLM_MODELS: # 讯飞星火认知大模型
|
||||
try:
|
||||
from .bridge_spark import predict_no_ui_long_connection as spark_noui
|
||||
from .bridge_spark import predict as spark_ui
|
||||
@@ -846,25 +538,6 @@ if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS: # 讯飞
|
||||
"sparkv3": {
|
||||
"fn_with_ui": spark_ui,
|
||||
"fn_without_ui": spark_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"sparkv3.5": {
|
||||
"fn_with_ui": spark_ui,
|
||||
"fn_without_ui": spark_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"sparkv4":{
|
||||
"fn_with_ui": spark_ui,
|
||||
"fn_without_ui": spark_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
@@ -889,22 +562,22 @@ if "llama2" in AVAIL_LLM_MODELS: # llama2
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 智谱 -=-=-=-=-=-=-
|
||||
if "zhipuai" in AVAIL_LLM_MODELS: # zhipuai 是glm-4的别名，向后兼容配置
|
||||
if "zhipuai" in AVAIL_LLM_MODELS: # zhipuai
|
||||
try:
|
||||
from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
|
||||
from .bridge_zhipu import predict as zhipu_ui
|
||||
model_info.update({
|
||||
"zhipuai": {
|
||||
"fn_with_ui": zhipu_ui,
|
||||
"fn_without_ui": zhipu_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 10124 * 8,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
}
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 幻方-深度求索大模型 -=-=-=-=-=-=-
|
||||
if "deepseekcoder" in AVAIL_LLM_MODELS: # deepseekcoder
|
||||
try:
|
||||
from .bridge_deepseekcoder import predict_no_ui_long_connection as deepseekcoder_noui
|
||||
@@ -921,119 +594,26 @@ if "deepseekcoder" in AVAIL_LLM_MODELS: # deepseekcoder
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 幻方-深度求索大模型在线API -=-=-=-=-=-=-
|
||||
if "deepseek-chat" in AVAIL_LLM_MODELS or "deepseek-coder" in AVAIL_LLM_MODELS:
|
||||
try:
|
||||
deepseekapi_noui, deepseekapi_ui = get_predict_function(
|
||||
api_key_conf_name="DEEPSEEK_API_KEY", max_output_token=4096, disable_proxy=False
|
||||
)
|
||||
model_info.update({
|
||||
"deepseek-chat":{
|
||||
"fn_with_ui": deepseekapi_ui,
|
||||
"fn_without_ui": deepseekapi_noui,
|
||||
"endpoint": deepseekapi_endpoint,
|
||||
"can_multi_thread": True,
|
||||
"max_token": 32000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"deepseek-coder":{
|
||||
"fn_with_ui": deepseekapi_ui,
|
||||
"fn_without_ui": deepseekapi_noui,
|
||||
"endpoint": deepseekapi_endpoint,
|
||||
"can_multi_thread": True,
|
||||
"max_token": 16000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- one-api 对齐支持 -=-=-=-=-=-=-
|
||||
for model in [m for m in AVAIL_LLM_MODELS if m.startswith("one-api-")]:
|
||||
# 为了更灵活地接入one-api多模型管理界面，设计了此接口，例子：AVAIL_LLM_MODELS = ["one-api-mixtral-8x7b(max_token=6666)"]
|
||||
# 其中
|
||||
# "one-api-" 是前缀（必要）
|
||||
# "mixtral-8x7b" 是模型名（必要）
|
||||
# "(max_token=6666)" 是配置（非必要）
|
||||
try:
|
||||
origin_model_name, max_token_tmp = read_one_api_model_name(model)
|
||||
# 如果是已知模型，则尝试获取其信息
|
||||
original_model_info = model_info.get(origin_model_name.replace("one-api-", "", 1), None)
|
||||
except:
|
||||
print(f"one-api模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
|
||||
continue
|
||||
this_model_info = {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": max_token_tmp,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
}
|
||||
# if "skylark" in AVAIL_LLM_MODELS:
|
||||
# try:
|
||||
# from .bridge_skylark2 import predict_no_ui_long_connection as skylark_noui
|
||||
# from .bridge_skylark2 import predict as skylark_ui
|
||||
# model_info.update({
|
||||
# "skylark": {
|
||||
# "fn_with_ui": skylark_ui,
|
||||
# "fn_without_ui": skylark_noui,
|
||||
# "endpoint": None,
|
||||
# "max_token": 4096,
|
||||
# "tokenizer": tokenizer_gpt35,
|
||||
# "token_cnt": get_token_num_gpt35,
|
||||
# }
|
||||
# })
|
||||
# except:
|
||||
# print(trimmed_format_exc())
|
||||
|
||||
# 同步已知模型的其他信息
|
||||
attribute = "has_multimodal_capacity"
|
||||
if original_model_info is not None and original_model_info.get(attribute, None) is not None: this_model_info.update({attribute: original_model_info.get(attribute, None)})
|
||||
# attribute = "attribute2"
|
||||
# if original_model_info is not None and original_model_info.get(attribute, None) is not None: this_model_info.update({attribute: original_model_info.get(attribute, None)})
|
||||
# attribute = "attribute3"
|
||||
# if original_model_info is not None and original_model_info.get(attribute, None) is not None: this_model_info.update({attribute: original_model_info.get(attribute, None)})
|
||||
model_info.update({model: this_model_info})
|
||||
|
||||
# -=-=-=-=-=-=- vllm 对齐支持 -=-=-=-=-=-=-
|
||||
for model in [m for m in AVAIL_LLM_MODELS if m.startswith("vllm-")]:
|
||||
# 为了更灵活地接入vllm多模型管理界面，设计了此接口，例子：AVAIL_LLM_MODELS = ["vllm-/home/hmp/llm/cache/Qwen1___5-32B-Chat(max_token=6666)"]
|
||||
# 其中
|
||||
# "vllm-" 是前缀（必要）
|
||||
# "mixtral-8x7b" 是模型名（必要）
|
||||
# "(max_token=6666)" 是配置（非必要）
|
||||
try:
|
||||
_, max_token_tmp = read_one_api_model_name(model)
|
||||
except:
|
||||
print(f"vllm模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
|
||||
continue
|
||||
model_info.update({
|
||||
model: {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": max_token_tmp,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
})
|
||||
# -=-=-=-=-=-=- ollama 对齐支持 -=-=-=-=-=-=-
|
||||
for model in [m for m in AVAIL_LLM_MODELS if m.startswith("ollama-")]:
|
||||
from .bridge_ollama import predict_no_ui_long_connection as ollama_noui
|
||||
from .bridge_ollama import predict as ollama_ui
|
||||
break
|
||||
for model in [m for m in AVAIL_LLM_MODELS if m.startswith("ollama-")]:
|
||||
# 为了更灵活地接入ollama多模型管理界面，设计了此接口，例子：AVAIL_LLM_MODELS = ["ollama-phi3(max_token=6666)"]
|
||||
# 其中
|
||||
# "ollama-" 是前缀（必要）
|
||||
# "phi3" 是模型名（必要）
|
||||
# "(max_token=6666)" 是配置（非必要）
|
||||
try:
|
||||
_, max_token_tmp = read_one_api_model_name(model)
|
||||
except:
|
||||
print(f"ollama模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
|
||||
continue
|
||||
model_info.update({
|
||||
model: {
|
||||
"fn_with_ui": ollama_ui,
|
||||
"fn_without_ui": ollama_noui,
|
||||
"endpoint": ollama_endpoint,
|
||||
"max_token": max_token_tmp,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
})
|
||||
|
||||
# -=-=-=-=-=-=- azure模型对齐支持 -=-=-=-=-=-=-
|
||||
AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY") # <-- 用于定义和切换多个azure模型 -->
|
||||
# <-- 用于定义和切换多个azure模型 -->
|
||||
AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY")
|
||||
if len(AZURE_CFG_ARRAY) > 0:
|
||||
for azure_model_name, azure_cfg_dict in AZURE_CFG_ARRAY.items():
|
||||
# 可能会覆盖之前的配置，但这是意料之中的
|
||||
@@ -1056,20 +636,13 @@ if len(AZURE_CFG_ARRAY) > 0:
|
||||
AVAIL_LLM_MODELS += [azure_model_name]
|
||||
|
||||
|
||||
# -=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=-=-=
|
||||
# -=-=-=-=-=-=-=-=-=- ☝️ 以上是模型路由 -=-=-=-=-=-=-=-=-=
|
||||
# -=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=-=-=
|
||||
|
||||
# -=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=-=-=
|
||||
# -=-=-=-=-=-=-= 👇 以下是多模型路由切换函数 -=-=-=-=-=-=-=
|
||||
# -=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=-=-=
|
||||
|
||||
|
||||
def LLM_CATCH_EXCEPTION(f):
|
||||
"""
|
||||
装饰器函数，将错误显示出来
|
||||
"""
|
||||
def decorated(inputs:str, llm_kwargs:dict, history:list, sys_prompt:str, observe_window:list, console_slience:bool):
|
||||
def decorated(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience):
|
||||
try:
|
||||
return f(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience)
|
||||
except Exception as e:
|
||||
@@ -1079,9 +652,9 @@ def LLM_CATCH_EXCEPTION(f):
|
||||
return decorated
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys_prompt:str, observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, observe_window=[], console_slience=False):
|
||||
"""
|
||||
发送至LLM，等待回复，一次性完成，不显示中间过程。但内部（尽可能地）用stream的方法避免中途网线被掐。
|
||||
发送至LLM，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
是本次问询的输入
|
||||
sys_prompt:
|
||||
@@ -1099,11 +672,14 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys
|
||||
model = llm_kwargs['llm_model']
|
||||
n_model = 1
|
||||
if '&' not in model:
|
||||
# 如果只询问“一个”大语言模型（多数情况）：
|
||||
assert not model.startswith("tgui"), "TGUI不支持函数插件的实现"
|
||||
|
||||
# 如果只询问1个大语言模型：
|
||||
method = model_info[model]["fn_without_ui"]
|
||||
return method(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience)
|
||||
else:
|
||||
# 如果同时询问“多个”大语言模型，这个稍微啰嗦一点，但思路相同，您不必读这个else分支
|
||||
|
||||
# 如果同时询问多个大语言模型，这个稍微啰嗦一点，但思路相同，您不必读这个else分支
|
||||
executor = ThreadPoolExecutor(max_workers=4)
|
||||
models = model.split('&')
|
||||
n_model = len(models)
|
||||
@@ -1131,8 +707,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys
|
||||
# 观察窗（window）
|
||||
chat_string = []
|
||||
for i in range(n_model):
|
||||
color = colors[i%len(colors)]
|
||||
chat_string.append( f"【{str(models[i])} 说】: <font color=\"{color}\"> {window_mutex[i][0]} </font>" )
|
||||
chat_string.append( f"【{str(models[i])} 说】: <font color=\"{colors[i]}\"> {window_mutex[i][0]} </font>" )
|
||||
res = '<br/><br/>\n\n---\n\n'.join(chat_string)
|
||||
# # # # # # # # # # #
|
||||
observe_window[0] = res
|
||||
@@ -1149,56 +724,25 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys
|
||||
time.sleep(1)
|
||||
|
||||
for i, future in enumerate(futures): # wait and get
|
||||
color = colors[i%len(colors)]
|
||||
return_string_collect.append( f"【{str(models[i])} 说】: <font color=\"{color}\"> {future.result()} </font>" )
|
||||
return_string_collect.append( f"【{str(models[i])} 说】: <font color=\"{colors[i]}\"> {future.result()} </font>" )
|
||||
|
||||
window_mutex[-1] = False # stop mutex thread
|
||||
res = '<br/><br/>\n\n---\n\n'.join(return_string_collect)
|
||||
return res
|
||||
|
||||
# 根据基础功能区 ModelOverride 参数调整模型类型，用于 `predict` 中
|
||||
import importlib
|
||||
import core_functional
|
||||
def execute_model_override(llm_kwargs, additional_fn, method):
|
||||
functional = core_functional.get_core_functions()
|
||||
if (additional_fn in functional) and 'ModelOverride' in functional[additional_fn]:
|
||||
# 热更新Prompt & ModelOverride
|
||||
importlib.reload(core_functional)
|
||||
functional = core_functional.get_core_functions()
|
||||
model_override = functional[additional_fn]['ModelOverride']
|
||||
if model_override not in model_info:
|
||||
raise ValueError(f"模型覆盖参数 '{model_override}' 指向一个暂不支持的模型，请检查配置文件。")
|
||||
method = model_info[model_override]["fn_with_ui"]
|
||||
llm_kwargs['llm_model'] = model_override
|
||||
return llm_kwargs, additional_fn, method
|
||||
# 默认返回原参数
|
||||
return llm_kwargs, additional_fn, method
|
||||
|
||||
def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot,
|
||||
history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
|
||||
def predict(inputs, llm_kwargs, *args, **kwargs):
|
||||
"""
|
||||
发送至LLM，流式获取输出。
|
||||
用于基础的对话功能。
|
||||
|
||||
完整参数列表：
|
||||
predict(
|
||||
inputs:str, # 是本次问询的输入
|
||||
llm_kwargs:dict, # 是LLM的内部调优参数
|
||||
plugin_kwargs:dict, # 是插件的内部参数
|
||||
chatbot:ChatBotWithCookies, # 原样传递，负责向用户前端展示对话，兼顾前端状态的功能
|
||||
history:list=[], # 是之前的对话列表
|
||||
system_prompt:str='', # 系统静默prompt
|
||||
stream:bool=True, # 是否流式输出（已弃用）
|
||||
additional_fn:str=None # 基础功能区按钮的附加功能
|
||||
):
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是LLM的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
|
||||
inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")
|
||||
|
||||
method = model_info[llm_kwargs['llm_model']]["fn_with_ui"] # 如果这里报错，检查config中的AVAIL_LLM_MODELS选项
|
||||
|
||||
if additional_fn: # 根据基础功能区 ModelOverride 参数调整模型类型
|
||||
llm_kwargs, additional_fn, method = execute_model_override(llm_kwargs, additional_fn, method)
|
||||
|
||||
yield from method(inputs, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, stream, additional_fn)
|
||||
yield from method(inputs, llm_kwargs, *args, **kwargs)
|
||||
|
||||
|
||||
@@ -6,6 +6,7 @@ from toolbox import get_conf, ProxyNetworkActivate
|
||||
from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
|
||||
|
||||
|
||||
|
||||
# ------------------------------------------------------------------------------------------------------------------------
|
||||
# 🔌💻 Local Model
|
||||
# ------------------------------------------------------------------------------------------------------------------------
|
||||
@@ -22,45 +23,20 @@ class GetGLM3Handle(LocalLLMHandle):
|
||||
import os, glob
|
||||
import os
|
||||
import platform
|
||||
LOCAL_MODEL_QUANT, device = get_conf('LOCAL_MODEL_QUANT', 'LOCAL_MODEL_DEVICE')
|
||||
|
||||
LOCAL_MODEL_QUANT, device = get_conf("LOCAL_MODEL_QUANT", "LOCAL_MODEL_DEVICE")
|
||||
_model_name_ = "THUDM/chatglm3-6b"
|
||||
# if LOCAL_MODEL_QUANT == "INT4": # INT4
|
||||
# _model_name_ = "THUDM/chatglm3-6b-int4"
|
||||
# elif LOCAL_MODEL_QUANT == "INT8": # INT8
|
||||
# _model_name_ = "THUDM/chatglm3-6b-int8"
|
||||
# else:
|
||||
# _model_name_ = "THUDM/chatglm3-6b" # FP16
|
||||
with ProxyNetworkActivate("Download_LLM"):
|
||||
chatglm_tokenizer = AutoTokenizer.from_pretrained(
|
||||
_model_name_, trust_remote_code=True
|
||||
)
|
||||
if device == "cpu":
|
||||
chatglm_model = AutoModel.from_pretrained(
|
||||
_model_name_,
|
||||
trust_remote_code=True,
|
||||
device="cpu",
|
||||
).float()
|
||||
elif LOCAL_MODEL_QUANT == "INT4": # INT4
|
||||
chatglm_model = AutoModel.from_pretrained(
|
||||
pretrained_model_name_or_path=_model_name_,
|
||||
trust_remote_code=True,
|
||||
device="cuda",
|
||||
load_in_4bit=True,
|
||||
)
|
||||
if LOCAL_MODEL_QUANT == "INT4": # INT4
|
||||
_model_name_ = "THUDM/chatglm3-6b-int4"
|
||||
elif LOCAL_MODEL_QUANT == "INT8": # INT8
|
||||
chatglm_model = AutoModel.from_pretrained(
|
||||
pretrained_model_name_or_path=_model_name_,
|
||||
trust_remote_code=True,
|
||||
device="cuda",
|
||||
load_in_8bit=True,
|
||||
)
|
||||
_model_name_ = "THUDM/chatglm3-6b-int8"
|
||||
else:
|
||||
chatglm_model = AutoModel.from_pretrained(
|
||||
pretrained_model_name_or_path=_model_name_,
|
||||
trust_remote_code=True,
|
||||
device="cuda",
|
||||
)
|
||||
_model_name_ = "THUDM/chatglm3-6b" # FP16
|
||||
with ProxyNetworkActivate('Download_LLM'):
|
||||
chatglm_tokenizer = AutoTokenizer.from_pretrained(_model_name_, trust_remote_code=True)
|
||||
if device=='cpu':
|
||||
chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True, device='cpu').float()
|
||||
else:
|
||||
chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True, device='cuda')
|
||||
chatglm_model = chatglm_model.eval()
|
||||
|
||||
self._model = chatglm_model
|
||||
@@ -70,17 +46,16 @@ class GetGLM3Handle(LocalLLMHandle):
|
||||
def llm_stream_generator(self, **kwargs):
|
||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
||||
def adaptor(kwargs):
|
||||
query = kwargs["query"]
|
||||
max_length = kwargs["max_length"]
|
||||
top_p = kwargs["top_p"]
|
||||
temperature = kwargs["temperature"]
|
||||
history = kwargs["history"]
|
||||
query = kwargs['query']
|
||||
max_length = kwargs['max_length']
|
||||
top_p = kwargs['top_p']
|
||||
temperature = kwargs['temperature']
|
||||
history = kwargs['history']
|
||||
return query, max_length, top_p, temperature, history
|
||||
|
||||
query, max_length, top_p, temperature, history = adaptor(kwargs)
|
||||
|
||||
for response, history in self._model.stream_chat(
|
||||
self._tokenizer,
|
||||
for response, history in self._model.stream_chat(self._tokenizer,
|
||||
query,
|
||||
history,
|
||||
max_length=max_length,
|
||||
@@ -93,13 +68,10 @@ class GetGLM3Handle(LocalLLMHandle):
|
||||
# import something that will raise error if the user does not install requirement_*.txt
|
||||
# 🏃♂️🏃♂️🏃♂️ 主进程执行
|
||||
import importlib
|
||||
|
||||
# importlib.import_module('modelscope')
|
||||
|
||||
|
||||
# ------------------------------------------------------------------------------------------------------------------------
|
||||
# 🔌💻 GPT-Academic Interface
|
||||
# ------------------------------------------------------------------------------------------------------------------------
|
||||
predict_no_ui_long_connection, predict = get_local_llm_predict_fns(
|
||||
GetGLM3Handle, model_name, history_format="chatglm3"
|
||||
)
|
||||
predict_no_ui_long_connection, predict = get_local_llm_predict_fns(GetGLM3Handle, model_name, history_format='chatglm3')
|
||||
@@ -137,8 +137,7 @@ class GetGLMFTHandle(Process):
|
||||
global glmft_handle
|
||||
glmft_handle = None
|
||||
#################################################################################
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
# 借鉴了 https://github.com/GaiZhenbiao/ChuanhuChatGPT 项目
|
||||
|
||||
"""
|
||||
该文件中主要包含三个函数
|
||||
|
||||
@@ -9,19 +11,17 @@
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
import gradio as gr
|
||||
import logging
|
||||
import traceback
|
||||
import requests
|
||||
import importlib
|
||||
import random
|
||||
|
||||
# config_private.py放自己的秘密如API和代理网址
|
||||
# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
|
||||
from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history
|
||||
from toolbox import trimmed_format_exc, is_the_upload_folder, read_one_api_model_name, log_chat
|
||||
from toolbox import ChatBotWithCookies, have_any_recent_upload_image_files, encode_image
|
||||
from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history, trimmed_format_exc, is_the_upload_folder
|
||||
proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
|
||||
get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
|
||||
|
||||
@@ -39,57 +39,6 @@ def get_full_error(chunk, stream_response):
|
||||
break
|
||||
return chunk
|
||||
|
||||
def make_multimodal_input(inputs, image_paths):
|
||||
image_base64_array = []
|
||||
for image_path in image_paths:
|
||||
path = os.path.abspath(image_path)
|
||||
base64 = encode_image(path)
|
||||
inputs = inputs + f'<br/><br/><div align="center"><img src="file={path}" base64="{base64}"></div>'
|
||||
image_base64_array.append(base64)
|
||||
return inputs, image_base64_array
|
||||
|
||||
def reverse_base64_from_input(inputs):
|
||||
# 定义一个正则表达式来匹配 Base64 字符串（假设格式为 base64="<Base64编码>"）
|
||||
# pattern = re.compile(r'base64="([^"]+)"></div>')
|
||||
pattern = re.compile(r'<br/><br/><div align="center"><img[^<>]+base64="([^"]+)"></div>')
|
||||
# 使用 findall 方法查找所有匹配的 Base64 字符串
|
||||
base64_strings = pattern.findall(inputs)
|
||||
# 返回反转后的 Base64 字符串列表
|
||||
return base64_strings
|
||||
|
||||
def contain_base64(inputs):
|
||||
base64_strings = reverse_base64_from_input(inputs)
|
||||
return len(base64_strings) > 0
|
||||
|
||||
def append_image_if_contain_base64(inputs):
|
||||
if not contain_base64(inputs):
|
||||
return inputs
|
||||
else:
|
||||
image_base64_array = reverse_base64_from_input(inputs)
|
||||
pattern = re.compile(r'<br/><br/><div align="center"><img[^><]+></div>')
|
||||
inputs = re.sub(pattern, '', inputs)
|
||||
res = []
|
||||
res.append({
|
||||
"type": "text",
|
||||
"text": inputs
|
||||
})
|
||||
for image_base64 in image_base64_array:
|
||||
res.append({
|
||||
"type": "image_url",
|
||||
"image_url": {
|
||||
"url": f"data:image/jpeg;base64,{image_base64}"
|
||||
}
|
||||
})
|
||||
return res
|
||||
|
||||
def remove_image_if_contain_base64(inputs):
|
||||
if not contain_base64(inputs):
|
||||
return inputs
|
||||
else:
|
||||
pattern = re.compile(r'<br/><br/><div align="center"><img[^><]+></div>')
|
||||
inputs = re.sub(pattern, '', inputs)
|
||||
return inputs
|
||||
|
||||
def decode_chunk(chunk):
|
||||
# 提前读取一些信息 （用于判断异常）
|
||||
chunk_decoded = chunk.decode()
|
||||
@@ -119,7 +68,7 @@ def verify_endpoint(endpoint):
|
||||
raise ValueError("Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:" + endpoint)
|
||||
return endpoint
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
|
||||
"""
|
||||
发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
@@ -164,8 +113,6 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
||||
error_msg = get_full_error(chunk, stream_response).decode()
|
||||
if "reduce the length" in error_msg:
|
||||
raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
|
||||
elif """type":"upstream_error","param":"307""" in error_msg:
|
||||
raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
|
||||
else:
|
||||
raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
|
||||
if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成
|
||||
@@ -176,9 +123,8 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
||||
json_data = chunkjson['choices'][0]
|
||||
delta = json_data["delta"]
|
||||
if len(delta) == 0: break
|
||||
if (not has_content) and has_role: continue
|
||||
if (not has_content) and (not has_role): continue # raise RuntimeError("发现不标准的第三方接口："+delta)
|
||||
if has_content: # has_role = True/False
|
||||
if "role" in delta: continue
|
||||
if "content" in delta:
|
||||
result += delta["content"]
|
||||
if not console_slience: print(delta["content"], end='')
|
||||
if observe_window is not None:
|
||||
@@ -197,8 +143,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
||||
return result
|
||||
|
||||
|
||||
def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
|
||||
history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
|
||||
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
|
||||
"""
|
||||
发送至chatGPT，流式获取输出。
|
||||
用于基础的对话功能。
|
||||
@@ -208,7 +153,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
from .bridge_all import model_info
|
||||
if is_any_api_key(inputs):
|
||||
chatbot._cookies['api_key'] = inputs
|
||||
chatbot.append(("输入已识别为openai的api_key", what_keys(inputs)))
|
||||
@@ -224,17 +168,9 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
from core_functional import handle_core_functionality
|
||||
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
|
||||
|
||||
# 多模态模型
|
||||
has_multimodal_capacity = model_info[llm_kwargs['llm_model']].get('has_multimodal_capacity', False)
|
||||
if has_multimodal_capacity:
|
||||
has_recent_image_upload, image_paths = have_any_recent_upload_image_files(chatbot, pop=True)
|
||||
else:
|
||||
has_recent_image_upload, image_paths = False, []
|
||||
if has_recent_image_upload:
|
||||
_inputs, image_base64_array = make_multimodal_input(inputs, image_paths)
|
||||
else:
|
||||
_inputs, image_base64_array = inputs, []
|
||||
chatbot.append((_inputs, ""))
|
||||
raw_input = inputs
|
||||
logging.info(f'[raw_input] {raw_input}')
|
||||
chatbot.append((inputs, ""))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
|
||||
|
||||
# check mis-behavior
|
||||
@@ -244,7 +180,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
time.sleep(2)
|
||||
|
||||
try:
|
||||
headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, image_base64_array, has_multimodal_capacity, stream)
|
||||
headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
|
||||
except RuntimeError as e:
|
||||
chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
|
||||
@@ -252,6 +188,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
|
||||
# 检查endpoint是否合法
|
||||
try:
|
||||
from .bridge_all import model_info
|
||||
endpoint = verify_endpoint(model_info[llm_kwargs['llm_model']]['endpoint'])
|
||||
except:
|
||||
tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
@@ -259,11 +196,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Endpoint不满足要求") # 刷新界面
|
||||
return
|
||||
|
||||
# 加入历史
|
||||
if has_recent_image_upload:
|
||||
history.extend([_inputs, ""])
|
||||
else:
|
||||
history.extend([inputs, ""])
|
||||
history.append(inputs); history.append("")
|
||||
|
||||
retry = 0
|
||||
while True:
|
||||
@@ -317,8 +250,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
# 前者是API2D的结束条件，后者是OPENAI的结束条件
|
||||
if ('data: [DONE]' in chunk_decoded) or (len(chunkjson['choices'][0]["delta"]) == 0):
|
||||
# 判定为数据流的结束，gpt_replying_buffer也写完了
|
||||
# logging.info(f'[response] {gpt_replying_buffer}')
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
|
||||
logging.info(f'[response] {gpt_replying_buffer}')
|
||||
break
|
||||
# 处理数据流的主体
|
||||
status_text = f"finish_reason: {chunkjson['choices'][0].get('finish_reason', 'null')}"
|
||||
@@ -330,8 +262,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
# 一些第三方接口的出现这样的错误，兼容一下吧
|
||||
continue
|
||||
else:
|
||||
# 至此已经超出了正常接口应该进入的范围，一些垃圾第三方接口会出现这样的错误
|
||||
if chunkjson['choices'][0]["delta"]["content"] is None: continue # 一些垃圾第三方接口出现这样的错误，兼容一下吧
|
||||
# 一些垃圾第三方接口的出现这样的错误
|
||||
gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]
|
||||
|
||||
history[-1] = gpt_replying_buffer
|
||||
@@ -377,16 +308,13 @@ def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
||||
chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
|
||||
return chatbot, history
|
||||
|
||||
def generate_payload(inputs:str, llm_kwargs:dict, history:list, system_prompt:str, image_base64_array:list=[], has_multimodal_capacity:bool=False, stream:bool=True):
|
||||
def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
|
||||
"""
|
||||
整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
|
||||
"""
|
||||
if not is_any_api_key(llm_kwargs['api_key']):
|
||||
raise AssertionError("你提供了错误的API_KEY。\n\n1. 临时解决方案：直接在输入区键入api_key，然后回车提交。\n\n2. 长效解决方案：在config.py中配置。")
|
||||
|
||||
if llm_kwargs['llm_model'].startswith('vllm-'):
|
||||
api_key = 'no-api-key'
|
||||
else:
|
||||
api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
|
||||
|
||||
headers = {
|
||||
@@ -400,27 +328,17 @@ def generate_payload(inputs:str, llm_kwargs:dict, history:list, system_prompt:st
|
||||
azure_api_key_unshared = AZURE_CFG_ARRAY[llm_kwargs['llm_model']]["AZURE_API_KEY"]
|
||||
headers.update({"api-key": azure_api_key_unshared})
|
||||
|
||||
if has_multimodal_capacity:
|
||||
# 当以下条件满足时，启用多模态能力：
|
||||
# 1. 模型本身是多模态模型（has_multimodal_capacity）
|
||||
# 2. 输入包含图像（len(image_base64_array) > 0）
|
||||
# 3. 历史输入包含图像（ any([contain_base64(h) for h in history]) ）
|
||||
enable_multimodal_capacity = (len(image_base64_array) > 0) or any([contain_base64(h) for h in history])
|
||||
else:
|
||||
enable_multimodal_capacity = False
|
||||
|
||||
if not enable_multimodal_capacity:
|
||||
# 不使用多模态能力
|
||||
conversation_cnt = len(history) // 2
|
||||
|
||||
messages = [{"role": "system", "content": system_prompt}]
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2*conversation_cnt, 2):
|
||||
what_i_have_asked = {}
|
||||
what_i_have_asked["role"] = "user"
|
||||
what_i_have_asked["content"] = remove_image_if_contain_base64(history[index])
|
||||
what_i_have_asked["content"] = history[index]
|
||||
what_gpt_answer = {}
|
||||
what_gpt_answer["role"] = "assistant"
|
||||
what_gpt_answer["content"] = remove_image_if_contain_base64(history[index+1])
|
||||
what_gpt_answer["content"] = history[index+1]
|
||||
if what_i_have_asked["content"] != "":
|
||||
if what_gpt_answer["content"] == "": continue
|
||||
if what_gpt_answer["content"] == timeout_bot_msg: continue
|
||||
@@ -428,55 +346,15 @@ def generate_payload(inputs:str, llm_kwargs:dict, history:list, system_prompt:st
|
||||
messages.append(what_gpt_answer)
|
||||
else:
|
||||
messages[-1]['content'] = what_gpt_answer['content']
|
||||
|
||||
what_i_ask_now = {}
|
||||
what_i_ask_now["role"] = "user"
|
||||
what_i_ask_now["content"] = inputs
|
||||
messages.append(what_i_ask_now)
|
||||
else:
|
||||
# 多模态能力
|
||||
conversation_cnt = len(history) // 2
|
||||
messages = [{"role": "system", "content": system_prompt}]
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2*conversation_cnt, 2):
|
||||
what_i_have_asked = {}
|
||||
what_i_have_asked["role"] = "user"
|
||||
what_i_have_asked["content"] = append_image_if_contain_base64(history[index])
|
||||
what_gpt_answer = {}
|
||||
what_gpt_answer["role"] = "assistant"
|
||||
what_gpt_answer["content"] = append_image_if_contain_base64(history[index+1])
|
||||
if what_i_have_asked["content"] != "":
|
||||
if what_gpt_answer["content"] == "": continue
|
||||
if what_gpt_answer["content"] == timeout_bot_msg: continue
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
else:
|
||||
messages[-1]['content'] = what_gpt_answer['content']
|
||||
what_i_ask_now = {}
|
||||
what_i_ask_now["role"] = "user"
|
||||
what_i_ask_now["content"] = []
|
||||
what_i_ask_now["content"].append({
|
||||
"type": "text",
|
||||
"text": inputs
|
||||
})
|
||||
for image_base64 in image_base64_array:
|
||||
what_i_ask_now["content"].append({
|
||||
"type": "image_url",
|
||||
"image_url": {
|
||||
"url": f"data:image/jpeg;base64,{image_base64}"
|
||||
}
|
||||
})
|
||||
messages.append(what_i_ask_now)
|
||||
|
||||
|
||||
model = llm_kwargs['llm_model']
|
||||
if llm_kwargs['llm_model'].startswith('api2d-'):
|
||||
model = llm_kwargs['llm_model'][len('api2d-'):]
|
||||
if llm_kwargs['llm_model'].startswith('one-api-'):
|
||||
model = llm_kwargs['llm_model'][len('one-api-'):]
|
||||
model, _ = read_one_api_model_name(model)
|
||||
if llm_kwargs['llm_model'].startswith('vllm-'):
|
||||
model = llm_kwargs['llm_model'][len('vllm-'):]
|
||||
model, _ = read_one_api_model_name(model)
|
||||
|
||||
if model == "gpt-3.5-random": # 随机选择, 绕过openai访问频率限制
|
||||
model = random.choice([
|
||||
"gpt-3.5-turbo",
|
||||
@@ -495,6 +373,8 @@ def generate_payload(inputs:str, llm_kwargs:dict, history:list, system_prompt:st
|
||||
"top_p": llm_kwargs['top_p'], # 1.0,
|
||||
"n": 1,
|
||||
"stream": stream,
|
||||
"presence_penalty": 0,
|
||||
"frequency_penalty": 0,
|
||||
}
|
||||
try:
|
||||
print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
|
||||
|
||||
@@ -27,8 +27,10 @@ timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check
|
||||
|
||||
|
||||
def report_invalid_key(key):
|
||||
# 弃用功能
|
||||
return
|
||||
if get_conf("BLOCK_INVALID_APIKEY"):
|
||||
# 实验性功能，自动检测并屏蔽失效的KEY，请勿使用
|
||||
from request_llms.key_manager import ApiKeyManager
|
||||
api_key = ApiKeyManager().add_key_to_blacklist(key)
|
||||
|
||||
def get_full_error(chunk, stream_response):
|
||||
"""
|
||||
|
||||
@@ -9,15 +9,15 @@
|
||||
具备多线程调用能力的函数
|
||||
2. predict_no_ui_long_connection：支持多线程
|
||||
"""
|
||||
import logging
|
||||
|
||||
import os
|
||||
import time
|
||||
import traceback
|
||||
import json
|
||||
import time
|
||||
import gradio as gr
|
||||
import logging
|
||||
import traceback
|
||||
import requests
|
||||
from toolbox import get_conf, update_ui, trimmed_format_exc, encode_image, every_image_file_in_path, log_chat
|
||||
picture_system_prompt = "\n当回复图像时,必须说明正在回复哪张图像。所有图像仅在最后一个问题中提供,即使它们在历史记录中被提及。请使用'这是第X张图像:'的格式来指明您正在描述的是哪张图像。"
|
||||
Claude_3_Models = ["claude-3-haiku-20240307", "claude-3-sonnet-20240229", "claude-3-opus-20240229"]
|
||||
import importlib
|
||||
|
||||
# config_private.py放自己的秘密如API和代理网址
|
||||
# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
|
||||
@@ -39,34 +39,6 @@ def get_full_error(chunk, stream_response):
|
||||
break
|
||||
return chunk
|
||||
|
||||
def decode_chunk(chunk):
|
||||
# 提前读取一些信息（用于判断异常）
|
||||
chunk_decoded = chunk.decode()
|
||||
chunkjson = None
|
||||
is_last_chunk = False
|
||||
need_to_pass = False
|
||||
if chunk_decoded.startswith('data:'):
|
||||
try:
|
||||
chunkjson = json.loads(chunk_decoded[6:])
|
||||
except:
|
||||
need_to_pass = True
|
||||
pass
|
||||
elif chunk_decoded.startswith('event:'):
|
||||
try:
|
||||
event_type = chunk_decoded.split(':')[1].strip()
|
||||
if event_type == 'content_block_stop' or event_type == 'message_stop':
|
||||
is_last_chunk = True
|
||||
elif event_type == 'content_block_start' or event_type == 'message_start':
|
||||
need_to_pass = True
|
||||
pass
|
||||
except:
|
||||
need_to_pass = True
|
||||
pass
|
||||
else:
|
||||
need_to_pass = True
|
||||
pass
|
||||
return need_to_pass, chunkjson, is_last_chunk
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
|
||||
"""
|
||||
@@ -82,67 +54,50 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
|
||||
observe_window = None：
|
||||
用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
|
||||
"""
|
||||
from anthropic import Anthropic
|
||||
watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
|
||||
prompt = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
|
||||
retry = 0
|
||||
if len(ANTHROPIC_API_KEY) == 0:
|
||||
raise RuntimeError("没有设置ANTHROPIC_API_KEY选项")
|
||||
if inputs == "": inputs = "空空如也的输入栏"
|
||||
headers, message = generate_payload(inputs, llm_kwargs, history, sys_prompt, image_paths=None)
|
||||
retry = 0
|
||||
|
||||
|
||||
while True:
|
||||
try:
|
||||
# make a POST request to the API endpoint, stream=False
|
||||
from .bridge_all import model_info
|
||||
endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
||||
response = requests.post(endpoint, headers=headers, json=message,
|
||||
proxies=proxies, stream=True, timeout=TIMEOUT_SECONDS);break
|
||||
except requests.exceptions.ReadTimeout as e:
|
||||
anthropic = Anthropic(api_key=ANTHROPIC_API_KEY)
|
||||
# endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
||||
# with ProxyNetworkActivate()
|
||||
stream = anthropic.completions.create(
|
||||
prompt=prompt,
|
||||
max_tokens_to_sample=4096, # The maximum number of tokens to generate before stopping.
|
||||
model=llm_kwargs['llm_model'],
|
||||
stream=True,
|
||||
temperature = llm_kwargs['temperature']
|
||||
)
|
||||
break
|
||||
except Exception as e:
|
||||
retry += 1
|
||||
traceback.print_exc()
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
|
||||
stream_response = response.iter_lines()
|
||||
result = ''
|
||||
while True:
|
||||
try: chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
break
|
||||
except requests.exceptions.ConnectionError:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
need_to_pass, chunkjson, is_last_chunk = decode_chunk(chunk)
|
||||
if chunk:
|
||||
try:
|
||||
if need_to_pass:
|
||||
pass
|
||||
elif is_last_chunk:
|
||||
# logging.info(f'[response] {result}')
|
||||
break
|
||||
else:
|
||||
if chunkjson and chunkjson['type'] == 'content_block_delta':
|
||||
result += chunkjson['delta']['text']
|
||||
print(chunkjson['delta']['text'], end='')
|
||||
for completion in stream:
|
||||
result += completion.completion
|
||||
if not console_slience: print(completion.completion, end='')
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1:
|
||||
observe_window[0] += chunkjson['delta']['text']
|
||||
if len(observe_window) >= 1: observe_window[0] += completion.completion
|
||||
# 看门狗，如果超过期限没有喂狗，则终止
|
||||
if len(observe_window) >= 2:
|
||||
if (time.time()-observe_window[1]) > watch_dog_patience:
|
||||
raise RuntimeError("用户取消了程序。")
|
||||
except Exception as e:
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
chunk_decoded = chunk.decode()
|
||||
error_msg = chunk_decoded
|
||||
print(error_msg)
|
||||
raise RuntimeError("Json解析不合常规")
|
||||
traceback.print_exc()
|
||||
|
||||
return result
|
||||
|
||||
def make_media_input(history,inputs,image_paths):
|
||||
for image_path in image_paths:
|
||||
inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
|
||||
return inputs
|
||||
|
||||
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
|
||||
"""
|
||||
@@ -154,7 +109,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
if inputs == "": inputs = "空空如也的输入栏"
|
||||
from anthropic import Anthropic
|
||||
if len(ANTHROPIC_API_KEY) == 0:
|
||||
chatbot.append((inputs, "没有设置ANTHROPIC_API_KEY"))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
|
||||
@@ -164,23 +119,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
from core_functional import handle_core_functionality
|
||||
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
|
||||
|
||||
have_recent_file, image_paths = every_image_file_in_path(chatbot)
|
||||
if len(image_paths) > 20:
|
||||
chatbot.append((inputs, "图片数量超过api上限(20张)"))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应")
|
||||
return
|
||||
|
||||
if any([llm_kwargs['llm_model'] == model for model in Claude_3_Models]) and have_recent_file:
|
||||
if inputs == "" or inputs == "空空如也的输入栏": inputs = "请描述给出的图片"
|
||||
system_prompt += picture_system_prompt # 由于没有单独的参数保存包含图片的历史，所以只能通过提示词对第几张图片进行定位
|
||||
chatbot.append((make_media_input(history,inputs, image_paths), ""))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
|
||||
else:
|
||||
raw_input = inputs
|
||||
logging.info(f'[raw_input] {raw_input}')
|
||||
chatbot.append((inputs, ""))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
|
||||
|
||||
try:
|
||||
headers, message = generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths)
|
||||
prompt = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
|
||||
except RuntimeError as e:
|
||||
chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
|
||||
@@ -193,117 +138,91 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
try:
|
||||
# make a POST request to the API endpoint, stream=True
|
||||
from .bridge_all import model_info
|
||||
endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
||||
response = requests.post(endpoint, headers=headers, json=message,
|
||||
proxies=proxies, stream=True, timeout=TIMEOUT_SECONDS);break
|
||||
except requests.exceptions.ReadTimeout as e:
|
||||
anthropic = Anthropic(api_key=ANTHROPIC_API_KEY)
|
||||
# endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
||||
# with ProxyNetworkActivate()
|
||||
stream = anthropic.completions.create(
|
||||
prompt=prompt,
|
||||
max_tokens_to_sample=4096, # The maximum number of tokens to generate before stopping.
|
||||
model=llm_kwargs['llm_model'],
|
||||
stream=True,
|
||||
temperature = llm_kwargs['temperature']
|
||||
)
|
||||
|
||||
break
|
||||
except:
|
||||
retry += 1
|
||||
traceback.print_exc()
|
||||
chatbot[-1] = ((chatbot[-1][0], timeout_bot_msg))
|
||||
retry_msg = f"，正在重试 ({retry}/{MAX_RETRY}) ……" if MAX_RETRY > 0 else ""
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
|
||||
stream_response = response.iter_lines()
|
||||
|
||||
gpt_replying_buffer = ""
|
||||
|
||||
while True:
|
||||
try: chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
break
|
||||
except requests.exceptions.ConnectionError:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
need_to_pass, chunkjson, is_last_chunk = decode_chunk(chunk)
|
||||
if chunk:
|
||||
for completion in stream:
|
||||
try:
|
||||
if need_to_pass:
|
||||
pass
|
||||
elif is_last_chunk:
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
|
||||
# logging.info(f'[response] {gpt_replying_buffer}')
|
||||
break
|
||||
else:
|
||||
if chunkjson and chunkjson['type'] == 'content_block_delta':
|
||||
gpt_replying_buffer += chunkjson['delta']['text']
|
||||
gpt_replying_buffer = gpt_replying_buffer + completion.completion
|
||||
history[-1] = gpt_replying_buffer
|
||||
chatbot[-1] = (history[-2], history[-1])
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg='正常') # 刷新界面
|
||||
|
||||
except Exception as e:
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
chunk_decoded = chunk.decode()
|
||||
error_msg = chunk_decoded
|
||||
print(error_msg)
|
||||
raise RuntimeError("Json解析不合常规")
|
||||
from toolbox import regular_txt_to_markdown
|
||||
tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str}")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + tb_str) # 刷新界面
|
||||
return
|
||||
|
||||
def multiple_picture_types(image_paths):
|
||||
"""
|
||||
根据图片类型返回image/jpeg, image/png, image/gif, image/webp，无法判断则返回image/jpeg
|
||||
"""
|
||||
for image_path in image_paths:
|
||||
if image_path.endswith('.jpeg') or image_path.endswith('.jpg'):
|
||||
return 'image/jpeg'
|
||||
elif image_path.endswith('.png'):
|
||||
return 'image/png'
|
||||
elif image_path.endswith('.gif'):
|
||||
return 'image/gif'
|
||||
elif image_path.endswith('.webp'):
|
||||
return 'image/webp'
|
||||
return 'image/jpeg'
|
||||
|
||||
def generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths):
|
||||
|
||||
|
||||
# https://github.com/jtsang4/claude-to-chatgpt/blob/main/claude_to_chatgpt/adapter.py
|
||||
def convert_messages_to_prompt(messages):
|
||||
prompt = ""
|
||||
role_map = {
|
||||
"system": "Human",
|
||||
"user": "Human",
|
||||
"assistant": "Assistant",
|
||||
}
|
||||
for message in messages:
|
||||
role = message["role"]
|
||||
content = message["content"]
|
||||
transformed_role = role_map[role]
|
||||
prompt += f"\n\n{transformed_role.capitalize()}: {content}"
|
||||
prompt += "\n\nAssistant: "
|
||||
return prompt
|
||||
|
||||
def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
|
||||
"""
|
||||
整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
|
||||
"""
|
||||
from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT
|
||||
|
||||
conversation_cnt = len(history) // 2
|
||||
|
||||
messages = []
|
||||
|
||||
messages = [{"role": "system", "content": system_prompt}]
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2*conversation_cnt, 2):
|
||||
what_i_have_asked = {}
|
||||
what_i_have_asked["role"] = "user"
|
||||
what_i_have_asked["content"] = [{"type": "text", "text": history[index]}]
|
||||
what_i_have_asked["content"] = history[index]
|
||||
what_gpt_answer = {}
|
||||
what_gpt_answer["role"] = "assistant"
|
||||
what_gpt_answer["content"] = [{"type": "text", "text": history[index+1]}]
|
||||
if what_i_have_asked["content"][0]["text"] != "":
|
||||
if what_i_have_asked["content"][0]["text"] == "": continue
|
||||
if what_i_have_asked["content"][0]["text"] == timeout_bot_msg: continue
|
||||
what_gpt_answer["content"] = history[index+1]
|
||||
if what_i_have_asked["content"] != "":
|
||||
if what_gpt_answer["content"] == "": continue
|
||||
if what_gpt_answer["content"] == timeout_bot_msg: continue
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
else:
|
||||
messages[-1]['content'][0]['text'] = what_gpt_answer['content'][0]['text']
|
||||
messages[-1]['content'] = what_gpt_answer['content']
|
||||
|
||||
if any([llm_kwargs['llm_model'] == model for model in Claude_3_Models]) and image_paths:
|
||||
what_i_ask_now = {}
|
||||
what_i_ask_now["role"] = "user"
|
||||
what_i_ask_now["content"] = []
|
||||
for image_path in image_paths:
|
||||
what_i_ask_now["content"].append({
|
||||
"type": "image",
|
||||
"source": {
|
||||
"type": "base64",
|
||||
"media_type": multiple_picture_types(image_paths),
|
||||
"data": encode_image(image_path),
|
||||
}
|
||||
})
|
||||
what_i_ask_now["content"].append({"type": "text", "text": inputs})
|
||||
else:
|
||||
what_i_ask_now = {}
|
||||
what_i_ask_now["role"] = "user"
|
||||
what_i_ask_now["content"] = [{"type": "text", "text": inputs}]
|
||||
what_i_ask_now["content"] = inputs
|
||||
messages.append(what_i_ask_now)
|
||||
# 开始整理headers与message
|
||||
headers = {
|
||||
'x-api-key': ANTHROPIC_API_KEY,
|
||||
'anthropic-version': '2023-06-01',
|
||||
'content-type': 'application/json'
|
||||
}
|
||||
payload = {
|
||||
'model': llm_kwargs['llm_model'],
|
||||
'max_tokens': 4096,
|
||||
'messages': messages,
|
||||
'temperature': llm_kwargs['temperature'],
|
||||
'stream': True,
|
||||
'system': system_prompt
|
||||
}
|
||||
return headers, payload
|
||||
prompt = convert_messages_to_prompt(messages)
|
||||
|
||||
return prompt
|
||||
|
||||
|
||||
|
||||
@@ -1,328 +0,0 @@
|
||||
# 借鉴了 https://github.com/GaiZhenbiao/ChuanhuChatGPT 项目
|
||||
|
||||
"""
|
||||
该文件中主要包含三个函数
|
||||
|
||||
不具备多线程能力的函数：
|
||||
1. predict: 正常对话时使用，具备完备的交互功能，不可多线程
|
||||
|
||||
具备多线程调用能力的函数
|
||||
2. predict_no_ui_long_connection：支持多线程
|
||||
"""
|
||||
|
||||
import json
|
||||
import time
|
||||
import gradio as gr
|
||||
import logging
|
||||
import traceback
|
||||
import requests
|
||||
import importlib
|
||||
import random
|
||||
|
||||
# config_private.py放自己的秘密如API和代理网址
|
||||
# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
|
||||
from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history
|
||||
from toolbox import trimmed_format_exc, is_the_upload_folder, read_one_api_model_name, log_chat
|
||||
from toolbox import ChatBotWithCookies
|
||||
proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
|
||||
get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
|
||||
|
||||
timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
|
||||
'网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
|
||||
|
||||
def get_full_error(chunk, stream_response):
|
||||
"""
|
||||
获取完整的从Cohere返回的报错
|
||||
"""
|
||||
while True:
|
||||
try:
|
||||
chunk += next(stream_response)
|
||||
except:
|
||||
break
|
||||
return chunk
|
||||
|
||||
def decode_chunk(chunk):
|
||||
# 提前读取一些信息 （用于判断异常）
|
||||
chunk_decoded = chunk.decode()
|
||||
chunkjson = None
|
||||
has_choices = False
|
||||
choice_valid = False
|
||||
has_content = False
|
||||
has_role = False
|
||||
try:
|
||||
chunkjson = json.loads(chunk_decoded)
|
||||
has_choices = 'choices' in chunkjson
|
||||
if has_choices: choice_valid = (len(chunkjson['choices']) > 0)
|
||||
if has_choices and choice_valid: has_content = ("content" in chunkjson['choices'][0]["delta"])
|
||||
if has_content: has_content = (chunkjson['choices'][0]["delta"]["content"] is not None)
|
||||
if has_choices and choice_valid: has_role = "role" in chunkjson['choices'][0]["delta"]
|
||||
except:
|
||||
pass
|
||||
return chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role
|
||||
|
||||
from functools import lru_cache
|
||||
@lru_cache(maxsize=32)
|
||||
def verify_endpoint(endpoint):
|
||||
"""
|
||||
检查endpoint是否可用
|
||||
"""
|
||||
if "你亲手写的api名称" in endpoint:
|
||||
raise ValueError("Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:" + endpoint)
|
||||
return endpoint
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_slience:bool=False):
|
||||
"""
|
||||
发送，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
是本次问询的输入
|
||||
sys_prompt:
|
||||
系统静默prompt
|
||||
llm_kwargs：
|
||||
内部调优参数
|
||||
history：
|
||||
是之前的对话列表
|
||||
observe_window = None：
|
||||
用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
|
||||
"""
|
||||
watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
|
||||
headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
# make a POST request to the API endpoint, stream=False
|
||||
from .bridge_all import model_info
|
||||
endpoint = verify_endpoint(model_info[llm_kwargs['llm_model']]['endpoint'])
|
||||
response = requests.post(endpoint, headers=headers, proxies=proxies,
|
||||
json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
|
||||
except requests.exceptions.ReadTimeout as e:
|
||||
retry += 1
|
||||
traceback.print_exc()
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
|
||||
|
||||
stream_response = response.iter_lines()
|
||||
result = ''
|
||||
json_data = None
|
||||
while True:
|
||||
try: chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
break
|
||||
except requests.exceptions.ConnectionError:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
|
||||
if chunkjson['event_type'] == 'stream-start': continue
|
||||
if chunkjson['event_type'] == 'text-generation':
|
||||
result += chunkjson["text"]
|
||||
if not console_slience: print(chunkjson["text"], end='')
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1:
|
||||
observe_window[0] += chunkjson["text"]
|
||||
# 看门狗，如果超过期限没有喂狗，则终止
|
||||
if len(observe_window) >= 2:
|
||||
if (time.time()-observe_window[1]) > watch_dog_patience:
|
||||
raise RuntimeError("用户取消了程序。")
|
||||
if chunkjson['event_type'] == 'stream-end': break
|
||||
return result
|
||||
|
||||
|
||||
def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
|
||||
history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
|
||||
"""
|
||||
发送至chatGPT，流式获取输出。
|
||||
用于基础的对话功能。
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
# if is_any_api_key(inputs):
|
||||
# chatbot._cookies['api_key'] = inputs
|
||||
# chatbot.append(("输入已识别为Cohere的api_key", what_keys(inputs)))
|
||||
# yield from update_ui(chatbot=chatbot, history=history, msg="api_key已导入") # 刷新界面
|
||||
# return
|
||||
# elif not is_any_api_key(chatbot._cookies['api_key']):
|
||||
# chatbot.append((inputs, "缺少api_key。\n\n1. 临时解决方案：直接在输入区键入api_key，然后回车提交。\n\n2. 长效解决方案：在config.py中配置。"))
|
||||
# yield from update_ui(chatbot=chatbot, history=history, msg="缺少api_key") # 刷新界面
|
||||
# return
|
||||
|
||||
user_input = inputs
|
||||
if additional_fn is not None:
|
||||
from core_functional import handle_core_functionality
|
||||
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
|
||||
|
||||
raw_input = inputs
|
||||
# logging.info(f'[raw_input] {raw_input}')
|
||||
chatbot.append((inputs, ""))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
|
||||
|
||||
# check mis-behavior
|
||||
if is_the_upload_folder(user_input):
|
||||
chatbot[-1] = (inputs, f"[Local Message] 检测到操作错误！当您上传文档之后，需点击“**函数插件区**”按钮进行处理，请勿点击“提交”按钮或者“基础功能区”按钮。")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="正常") # 刷新界面
|
||||
time.sleep(2)
|
||||
|
||||
try:
|
||||
headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
|
||||
except RuntimeError as e:
|
||||
chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
|
||||
return
|
||||
|
||||
# 检查endpoint是否合法
|
||||
try:
|
||||
from .bridge_all import model_info
|
||||
endpoint = verify_endpoint(model_info[llm_kwargs['llm_model']]['endpoint'])
|
||||
except:
|
||||
tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
chatbot[-1] = (inputs, tb_str)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Endpoint不满足要求") # 刷新界面
|
||||
return
|
||||
|
||||
history.append(inputs); history.append("")
|
||||
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
# make a POST request to the API endpoint, stream=True
|
||||
response = requests.post(endpoint, headers=headers, proxies=proxies,
|
||||
json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
|
||||
except:
|
||||
retry += 1
|
||||
chatbot[-1] = ((chatbot[-1][0], timeout_bot_msg))
|
||||
retry_msg = f"，正在重试 ({retry}/{MAX_RETRY}) ……" if MAX_RETRY > 0 else ""
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
|
||||
gpt_replying_buffer = ""
|
||||
|
||||
is_head_of_the_stream = True
|
||||
if stream:
|
||||
stream_response = response.iter_lines()
|
||||
while True:
|
||||
try:
|
||||
chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
# 非Cohere官方接口的出现这样的报错，Cohere和API2D不会走这里
|
||||
chunk_decoded = chunk.decode()
|
||||
error_msg = chunk_decoded
|
||||
# 其他情况，直接返回报错
|
||||
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="非Cohere官方接口返回了错误:" + chunk.decode()) # 刷新界面
|
||||
return
|
||||
|
||||
# 提前读取一些信息 （用于判断异常）
|
||||
chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
|
||||
|
||||
if chunkjson:
|
||||
try:
|
||||
if chunkjson['event_type'] == 'stream-start':
|
||||
continue
|
||||
if chunkjson['event_type'] == 'text-generation':
|
||||
gpt_replying_buffer = gpt_replying_buffer + chunkjson["text"]
|
||||
history[-1] = gpt_replying_buffer
|
||||
chatbot[-1] = (history[-2], history[-1])
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="正常") # 刷新界面
|
||||
if chunkjson['event_type'] == 'stream-end':
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
|
||||
history[-1] = gpt_replying_buffer
|
||||
chatbot[-1] = (history[-2], history[-1])
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="正常") # 刷新界面
|
||||
break
|
||||
except Exception as e:
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
chunk_decoded = chunk.decode()
|
||||
error_msg = chunk_decoded
|
||||
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
|
||||
print(error_msg)
|
||||
return
|
||||
|
||||
def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
|
||||
from .bridge_all import model_info
|
||||
Cohere_website = ' 请登录Cohere查看详情 https://platform.Cohere.com/signup'
|
||||
if "reduce the length" in error_msg:
|
||||
if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
|
||||
history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
|
||||
max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
|
||||
elif "does not exist" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格.")
|
||||
elif "Incorrect API key" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. Cohere以提供了不正确的API_KEY为由, 拒绝服务. " + Cohere_website)
|
||||
elif "exceeded your current quota" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] You exceeded your current quota. Cohere以账户额度不足为由, 拒绝服务." + Cohere_website)
|
||||
elif "account is not active" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] Your account is not active. Cohere以账户失效为由, 拒绝服务." + Cohere_website)
|
||||
elif "associated with a deactivated account" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] You are associated with a deactivated account. Cohere以账户失效为由, 拒绝服务." + Cohere_website)
|
||||
elif "API key has been deactivated" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] API key has been deactivated. Cohere以账户失效为由, 拒绝服务." + Cohere_website)
|
||||
elif "bad forward key" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] Bad forward key. API2D账户额度不足.")
|
||||
elif "Not enough point" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] Not enough point. API2D账户点数不足.")
|
||||
else:
|
||||
from toolbox import regular_txt_to_markdown
|
||||
tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
|
||||
return chatbot, history
|
||||
|
||||
def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
|
||||
"""
|
||||
整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
|
||||
"""
|
||||
# if not is_any_api_key(llm_kwargs['api_key']):
|
||||
# raise AssertionError("你提供了错误的API_KEY。\n\n1. 临时解决方案：直接在输入区键入api_key，然后回车提交。\n\n2. 长效解决方案：在config.py中配置。")
|
||||
|
||||
api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
|
||||
|
||||
headers = {
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {api_key}"
|
||||
}
|
||||
if API_ORG.startswith('org-'): headers.update({"Cohere-Organization": API_ORG})
|
||||
if llm_kwargs['llm_model'].startswith('azure-'):
|
||||
headers.update({"api-key": api_key})
|
||||
if llm_kwargs['llm_model'] in AZURE_CFG_ARRAY.keys():
|
||||
azure_api_key_unshared = AZURE_CFG_ARRAY[llm_kwargs['llm_model']]["AZURE_API_KEY"]
|
||||
headers.update({"api-key": azure_api_key_unshared})
|
||||
|
||||
conversation_cnt = len(history) // 2
|
||||
|
||||
messages = [{"role": "SYSTEM", "message": system_prompt}]
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2*conversation_cnt, 2):
|
||||
what_i_have_asked = {}
|
||||
what_i_have_asked["role"] = "USER"
|
||||
what_i_have_asked["message"] = history[index]
|
||||
what_gpt_answer = {}
|
||||
what_gpt_answer["role"] = "CHATBOT"
|
||||
what_gpt_answer["message"] = history[index+1]
|
||||
if what_i_have_asked["message"] != "":
|
||||
if what_gpt_answer["message"] == "": continue
|
||||
if what_gpt_answer["message"] == timeout_bot_msg: continue
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
else:
|
||||
messages[-1]['message'] = what_gpt_answer['message']
|
||||
|
||||
model = llm_kwargs['llm_model']
|
||||
if model.startswith('cohere-'): model = model[len('cohere-'):]
|
||||
payload = {
|
||||
"model": model,
|
||||
"message": inputs,
|
||||
"chat_history": messages,
|
||||
"temperature": llm_kwargs['temperature'], # 1.0,
|
||||
"top_p": llm_kwargs['top_p'], # 1.0,
|
||||
"n": 1,
|
||||
"stream": stream,
|
||||
"presence_penalty": 0,
|
||||
"frequency_penalty": 0,
|
||||
}
|
||||
|
||||
return headers,payload
|
||||
|
||||
|
||||
@@ -7,8 +7,7 @@ import re
|
||||
import os
|
||||
import time
|
||||
from request_llms.com_google import GoogleChatInit
|
||||
from toolbox import ChatBotWithCookies
|
||||
from toolbox import get_conf, update_ui, update_ui_lastest_msg, have_any_recent_upload_image_files, trimmed_format_exc, log_chat
|
||||
from toolbox import get_conf, update_ui, update_ui_lastest_msg, have_any_recent_upload_image_files, trimmed_format_exc
|
||||
|
||||
proxies, TIMEOUT_SECONDS, MAX_RETRY = get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY')
|
||||
timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
|
||||
@@ -21,7 +20,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
|
||||
if get_conf("GEMINI_API_KEY") == "":
|
||||
raise ValueError(f"请配置 GEMINI_API_KEY。")
|
||||
|
||||
genai = GoogleChatInit(llm_kwargs)
|
||||
genai = GoogleChatInit()
|
||||
watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
|
||||
gpt_replying_buffer = ''
|
||||
stream_response = genai.generate_chat(inputs, llm_kwargs, history, sys_prompt)
|
||||
@@ -45,8 +44,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
|
||||
return gpt_replying_buffer
|
||||
|
||||
|
||||
def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
|
||||
history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
|
||||
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream=True, additional_fn=None):
|
||||
# 检查API_KEY
|
||||
if get_conf("GEMINI_API_KEY") == "":
|
||||
yield from update_ui_lastest_msg(f"请配置 GEMINI_API_KEY。", chatbot=chatbot, history=history, delay=0)
|
||||
@@ -59,10 +57,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
|
||||
if "vision" in llm_kwargs["llm_model"]:
|
||||
have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
|
||||
if not have_recent_file:
|
||||
chatbot.append((inputs, "没有检测到任何近期上传的图像文件，请上传jpg格式的图片，此外，请注意拓展名需要小写"))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
|
||||
return
|
||||
def make_media_input(inputs, image_paths):
|
||||
for image_path in image_paths:
|
||||
inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
|
||||
@@ -72,7 +66,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
|
||||
chatbot.append((inputs, ""))
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
genai = GoogleChatInit(llm_kwargs)
|
||||
genai = GoogleChatInit()
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
@@ -99,7 +93,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
gpt_replying_buffer += paraphrase['text'] # 使用 json 解析库进行处理
|
||||
chatbot[-1] = (inputs, gpt_replying_buffer)
|
||||
history[-1] = gpt_replying_buffer
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
if error_match:
|
||||
history = history[-2] # 错误的不纳入对话
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
|
||||
from transformers import AutoModel, AutoTokenizer
|
||||
import time
|
||||
import threading
|
||||
import importlib
|
||||
from toolbox import update_ui, get_conf
|
||||
from multiprocessing import Process, Pipe
|
||||
from transformers import AutoModel, AutoTokenizer
|
||||
|
||||
load_message = "jittorllms尚未加载，加载需要一段时间。注意，请避免混用多种jittor模型，否则可能导致显存溢出而造成卡顿，取决于`config.py`的配置，jittorllms消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
|
||||
|
||||
@@ -106,8 +106,7 @@ class GetGLMHandle(Process):
|
||||
global llama_glm_handle
|
||||
llama_glm_handle = None
|
||||
#################################################################################
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
|
||||
from transformers import AutoModel, AutoTokenizer
|
||||
import time
|
||||
import threading
|
||||
import importlib
|
||||
from toolbox import update_ui, get_conf
|
||||
from multiprocessing import Process, Pipe
|
||||
from transformers import AutoModel, AutoTokenizer
|
||||
|
||||
load_message = "jittorllms尚未加载，加载需要一段时间。注意，请避免混用多种jittor模型，否则可能导致显存溢出而造成卡顿，取决于`config.py`的配置，jittorllms消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
|
||||
|
||||
@@ -106,8 +106,7 @@ class GetGLMHandle(Process):
|
||||
global pangu_glm_handle
|
||||
pangu_glm_handle = None
|
||||
#################################################################################
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -106,8 +106,7 @@ class GetGLMHandle(Process):
|
||||
global rwkv_glm_handle
|
||||
rwkv_glm_handle = None
|
||||
#################################################################################
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -1,197 +0,0 @@
|
||||
# encoding: utf-8
|
||||
# @Time : 2024/3/3
|
||||
# @Author : Spike
|
||||
# @Descr :
|
||||
import json
|
||||
import os
|
||||
import time
|
||||
import logging
|
||||
|
||||
from toolbox import get_conf, update_ui, log_chat
|
||||
from toolbox import ChatBotWithCookies
|
||||
|
||||
import requests
|
||||
|
||||
|
||||
class MoonShotInit:
|
||||
|
||||
def __init__(self):
|
||||
self.llm_model = None
|
||||
self.url = 'https://api.moonshot.cn/v1/chat/completions'
|
||||
self.api_key = get_conf('MOONSHOT_API_KEY')
|
||||
|
||||
def __converter_file(self, user_input: str):
|
||||
what_ask = []
|
||||
for f in user_input.splitlines():
|
||||
if os.path.exists(f):
|
||||
files = []
|
||||
if os.path.isdir(f):
|
||||
file_list = os.listdir(f)
|
||||
files.extend([os.path.join(f, file) for file in file_list])
|
||||
else:
|
||||
files.append(f)
|
||||
for file in files:
|
||||
if file.split('.')[-1] in ['pdf']:
|
||||
with open(file, 'r') as fp:
|
||||
from crazy_functions.crazy_utils import read_and_clean_pdf_text
|
||||
file_content, _ = read_and_clean_pdf_text(fp)
|
||||
what_ask.append({"role": "system", "content": file_content})
|
||||
return what_ask
|
||||
|
||||
def __converter_user(self, user_input: str):
|
||||
what_i_ask_now = {"role": "user", "content": user_input}
|
||||
return what_i_ask_now
|
||||
|
||||
def __conversation_history(self, history):
|
||||
conversation_cnt = len(history) // 2
|
||||
messages = []
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2 * conversation_cnt, 2):
|
||||
what_i_have_asked = {
|
||||
"role": "user",
|
||||
"content": str(history[index])
|
||||
}
|
||||
what_gpt_answer = {
|
||||
"role": "assistant",
|
||||
"content": str(history[index + 1])
|
||||
}
|
||||
if what_i_have_asked["content"] != "":
|
||||
if what_gpt_answer["content"] == "": continue
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
else:
|
||||
messages[-1]['content'] = what_gpt_answer['content']
|
||||
return messages
|
||||
|
||||
def _analysis_content(self, chuck):
|
||||
chunk_decoded = chuck.decode("utf-8")
|
||||
chunk_json = {}
|
||||
content = ""
|
||||
try:
|
||||
chunk_json = json.loads(chunk_decoded[6:])
|
||||
content = chunk_json['choices'][0]["delta"].get("content", "")
|
||||
except:
|
||||
pass
|
||||
return chunk_decoded, chunk_json, content
|
||||
|
||||
def generate_payload(self, inputs, llm_kwargs, history, system_prompt, stream):
|
||||
self.llm_model = llm_kwargs['llm_model']
|
||||
llm_kwargs.update({'use-key': self.api_key})
|
||||
messages = []
|
||||
if system_prompt:
|
||||
messages.append({"role": "system", "content": system_prompt})
|
||||
messages.extend(self.__converter_file(inputs))
|
||||
for i in history[0::2]: # 历史文件继续上传
|
||||
messages.extend(self.__converter_file(i))
|
||||
messages.extend(self.__conversation_history(history))
|
||||
messages.append(self.__converter_user(inputs))
|
||||
header = {
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {self.api_key}",
|
||||
}
|
||||
payload = {
|
||||
"model": self.llm_model,
|
||||
"messages": messages,
|
||||
"temperature": llm_kwargs.get('temperature', 0.3), # 1.0,
|
||||
"top_p": llm_kwargs.get('top_p', 1.0), # 1.0,
|
||||
"n": llm_kwargs.get('n_choices', 1),
|
||||
"stream": stream
|
||||
}
|
||||
return payload, header
|
||||
|
||||
def generate_messages(self, inputs, llm_kwargs, history, system_prompt, stream):
|
||||
payload, headers = self.generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
|
||||
response = requests.post(self.url, headers=headers, json=payload, stream=stream)
|
||||
|
||||
chunk_content = ""
|
||||
gpt_bro_result = ""
|
||||
for chuck in response.iter_lines():
|
||||
chunk_decoded, check_json, content = self._analysis_content(chuck)
|
||||
chunk_content += chunk_decoded
|
||||
if content:
|
||||
gpt_bro_result += content
|
||||
yield content, gpt_bro_result, ''
|
||||
else:
|
||||
error_msg = msg_handle_error(llm_kwargs, chunk_decoded)
|
||||
if error_msg:
|
||||
yield error_msg, gpt_bro_result, error_msg
|
||||
break
|
||||
|
||||
|
||||
def msg_handle_error(llm_kwargs, chunk_decoded):
|
||||
use_ket = llm_kwargs.get('use-key', '')
|
||||
api_key_encryption = use_ket[:8] + '****' + use_ket[-5:]
|
||||
openai_website = f' 请登录OpenAI查看详情 https://platform.openai.com/signup api-key: `{api_key_encryption}`'
|
||||
error_msg = ''
|
||||
if "does not exist" in chunk_decoded:
|
||||
error_msg = f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格."
|
||||
elif "Incorrect API key" in chunk_decoded:
|
||||
error_msg = f"[Local Message] Incorrect API key. OpenAI以提供了不正确的API_KEY为由, 拒绝服务." + openai_website
|
||||
elif "exceeded your current quota" in chunk_decoded:
|
||||
error_msg = "[Local Message] You exceeded your current quota. OpenAI以账户额度不足为由, 拒绝服务." + openai_website
|
||||
elif "account is not active" in chunk_decoded:
|
||||
error_msg = "[Local Message] Your account is not active. OpenAI以账户失效为由, 拒绝服务." + openai_website
|
||||
elif "associated with a deactivated account" in chunk_decoded:
|
||||
error_msg = "[Local Message] You are associated with a deactivated account. OpenAI以账户失效为由, 拒绝服务." + openai_website
|
||||
elif "API key has been deactivated" in chunk_decoded:
|
||||
error_msg = "[Local Message] API key has been deactivated. OpenAI以账户失效为由, 拒绝服务." + openai_website
|
||||
elif "bad forward key" in chunk_decoded:
|
||||
error_msg = "[Local Message] Bad forward key. API2D账户额度不足."
|
||||
elif "Not enough point" in chunk_decoded:
|
||||
error_msg = "[Local Message] Not enough point. API2D账户点数不足."
|
||||
elif 'error' in str(chunk_decoded).lower():
|
||||
try:
|
||||
error_msg = json.dumps(json.loads(chunk_decoded[:6]), indent=4, ensure_ascii=False)
|
||||
except:
|
||||
error_msg = chunk_decoded
|
||||
return error_msg
|
||||
|
||||
|
||||
def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
|
||||
history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
|
||||
chatbot.append([inputs, ""])
|
||||
|
||||
if additional_fn is not None:
|
||||
from core_functional import handle_core_functionality
|
||||
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
|
||||
gpt_bro_init = MoonShotInit()
|
||||
history.extend([inputs, ''])
|
||||
stream_response = gpt_bro_init.generate_messages(inputs, llm_kwargs, history, system_prompt, stream)
|
||||
for content, gpt_bro_result, error_bro_meg in stream_response:
|
||||
chatbot[-1] = [inputs, gpt_bro_result]
|
||||
history[-1] = gpt_bro_result
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
if error_bro_meg:
|
||||
chatbot[-1] = [inputs, error_bro_meg]
|
||||
history = history[:-2]
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
break
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_bro_result)
|
||||
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None,
|
||||
console_slience=False):
|
||||
gpt_bro_init = MoonShotInit()
|
||||
watch_dog_patience = 60 # 看门狗的耐心, 设置10秒即可
|
||||
stream_response = gpt_bro_init.generate_messages(inputs, llm_kwargs, history, sys_prompt, True)
|
||||
moonshot_bro_result = ''
|
||||
for content, moonshot_bro_result, error_bro_meg in stream_response:
|
||||
moonshot_bro_result = moonshot_bro_result
|
||||
if error_bro_meg:
|
||||
if len(observe_window) >= 3:
|
||||
observe_window[2] = error_bro_meg
|
||||
return f'{moonshot_bro_result} 对话错误'
|
||||
# 观测窗
|
||||
if len(observe_window) >= 1:
|
||||
observe_window[0] = moonshot_bro_result
|
||||
if len(observe_window) >= 2:
|
||||
if (time.time() - observe_window[1]) > watch_dog_patience:
|
||||
observe_window[2] = "请求超时，程序终止。"
|
||||
raise RuntimeError(f"{moonshot_bro_result} 程序终止。")
|
||||
return moonshot_bro_result
|
||||
|
||||
if __name__ == '__main__':
|
||||
moon_ai = MoonShotInit()
|
||||
for g in moon_ai.generate_messages('hello', {'llm_model': 'moonshot-v1-8k'},
|
||||
[], '', True):
|
||||
print(g)
|
||||
@@ -171,8 +171,7 @@ class GetGLMHandle(Process):
|
||||
global moss_handle
|
||||
moss_handle = None
|
||||
#################################################################################
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -1,272 +0,0 @@
|
||||
# 借鉴自同目录下的bridge_chatgpt.py
|
||||
|
||||
"""
|
||||
该文件中主要包含三个函数
|
||||
|
||||
不具备多线程能力的函数：
|
||||
1. predict: 正常对话时使用，具备完备的交互功能，不可多线程
|
||||
|
||||
具备多线程调用能力的函数
|
||||
2. predict_no_ui_long_connection：支持多线程
|
||||
"""
|
||||
|
||||
import json
|
||||
import time
|
||||
import gradio as gr
|
||||
import logging
|
||||
import traceback
|
||||
import requests
|
||||
import importlib
|
||||
import random
|
||||
|
||||
# config_private.py放自己的秘密如API和代理网址
|
||||
# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
|
||||
from toolbox import get_conf, update_ui, trimmed_format_exc, is_the_upload_folder, read_one_api_model_name
|
||||
proxies, TIMEOUT_SECONDS, MAX_RETRY = get_conf(
|
||||
"proxies", "TIMEOUT_SECONDS", "MAX_RETRY"
|
||||
)
|
||||
|
||||
timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
|
||||
'网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
|
||||
|
||||
def get_full_error(chunk, stream_response):
|
||||
"""
|
||||
获取完整的从Openai返回的报错
|
||||
"""
|
||||
while True:
|
||||
try:
|
||||
chunk += next(stream_response)
|
||||
except:
|
||||
break
|
||||
return chunk
|
||||
|
||||
def decode_chunk(chunk):
|
||||
# 提前读取一些信息（用于判断异常）
|
||||
chunk_decoded = chunk.decode()
|
||||
chunkjson = None
|
||||
is_last_chunk = False
|
||||
try:
|
||||
chunkjson = json.loads(chunk_decoded)
|
||||
is_last_chunk = chunkjson.get("done", False)
|
||||
except:
|
||||
pass
|
||||
return chunk_decoded, chunkjson, is_last_chunk
|
||||
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
|
||||
"""
|
||||
发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
是本次问询的输入
|
||||
sys_prompt:
|
||||
系统静默prompt
|
||||
llm_kwargs：
|
||||
chatGPT的内部调优参数
|
||||
history：
|
||||
是之前的对话列表
|
||||
observe_window = None：
|
||||
用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
|
||||
"""
|
||||
watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
|
||||
if inputs == "": inputs = "空空如也的输入栏"
|
||||
headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
# make a POST request to the API endpoint, stream=False
|
||||
from .bridge_all import model_info
|
||||
endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
||||
response = requests.post(endpoint, headers=headers, proxies=proxies,
|
||||
json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
|
||||
except requests.exceptions.ReadTimeout as e:
|
||||
retry += 1
|
||||
traceback.print_exc()
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
|
||||
|
||||
stream_response = response.iter_lines()
|
||||
result = ''
|
||||
while True:
|
||||
try: chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
break
|
||||
except requests.exceptions.ConnectionError:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
chunk_decoded, chunkjson, is_last_chunk = decode_chunk(chunk)
|
||||
if chunk:
|
||||
try:
|
||||
if is_last_chunk:
|
||||
# 判定为数据流的结束，gpt_replying_buffer也写完了
|
||||
logging.info(f'[response] {result}')
|
||||
break
|
||||
result += chunkjson['message']["content"]
|
||||
if not console_slience: print(chunkjson['message']["content"], end='')
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1:
|
||||
observe_window[0] += chunkjson['message']["content"]
|
||||
# 看门狗，如果超过期限没有喂狗，则终止
|
||||
if len(observe_window) >= 2:
|
||||
if (time.time()-observe_window[1]) > watch_dog_patience:
|
||||
raise RuntimeError("用户取消了程序。")
|
||||
except Exception as e:
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
chunk_decoded = chunk.decode()
|
||||
error_msg = chunk_decoded
|
||||
print(error_msg)
|
||||
raise RuntimeError("Json解析不合常规")
|
||||
return result
|
||||
|
||||
|
||||
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
|
||||
"""
|
||||
发送至chatGPT，流式获取输出。
|
||||
用于基础的对话功能。
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
if inputs == "": inputs = "空空如也的输入栏"
|
||||
user_input = inputs
|
||||
if additional_fn is not None:
|
||||
from core_functional import handle_core_functionality
|
||||
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
|
||||
|
||||
raw_input = inputs
|
||||
logging.info(f'[raw_input] {raw_input}')
|
||||
chatbot.append((inputs, ""))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
|
||||
|
||||
# check mis-behavior
|
||||
if is_the_upload_folder(user_input):
|
||||
chatbot[-1] = (inputs, f"[Local Message] 检测到操作错误！当您上传文档之后，需点击“**函数插件区**”按钮进行处理，请勿点击“提交”按钮或者“基础功能区”按钮。")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="正常") # 刷新界面
|
||||
time.sleep(2)
|
||||
|
||||
headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
|
||||
|
||||
from .bridge_all import model_info
|
||||
endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
||||
|
||||
history.append(inputs); history.append("")
|
||||
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
# make a POST request to the API endpoint, stream=True
|
||||
response = requests.post(endpoint, headers=headers, proxies=proxies,
|
||||
json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
|
||||
except:
|
||||
retry += 1
|
||||
chatbot[-1] = ((chatbot[-1][0], timeout_bot_msg))
|
||||
retry_msg = f"，正在重试 ({retry}/{MAX_RETRY}) ……" if MAX_RETRY > 0 else ""
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
|
||||
gpt_replying_buffer = ""
|
||||
|
||||
if stream:
|
||||
stream_response = response.iter_lines()
|
||||
while True:
|
||||
try:
|
||||
chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
break
|
||||
except requests.exceptions.ConnectionError:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
|
||||
# 提前读取一些信息 （用于判断异常）
|
||||
chunk_decoded, chunkjson, is_last_chunk = decode_chunk(chunk)
|
||||
|
||||
if chunk:
|
||||
try:
|
||||
if is_last_chunk:
|
||||
# 判定为数据流的结束，gpt_replying_buffer也写完了
|
||||
logging.info(f'[response] {gpt_replying_buffer}')
|
||||
break
|
||||
# 处理数据流的主体
|
||||
try:
|
||||
status_text = f"finish_reason: {chunkjson['error'].get('message', 'null')}"
|
||||
except:
|
||||
status_text = "finish_reason: null"
|
||||
gpt_replying_buffer = gpt_replying_buffer + chunkjson['message']["content"]
|
||||
# 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
|
||||
history[-1] = gpt_replying_buffer
|
||||
chatbot[-1] = (history[-2], history[-1])
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg=status_text) # 刷新界面
|
||||
except Exception as e:
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
chunk_decoded = chunk.decode()
|
||||
error_msg = chunk_decoded
|
||||
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
|
||||
print(error_msg)
|
||||
return
|
||||
|
||||
def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
|
||||
from .bridge_all import model_info
|
||||
if "bad_request" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] 已经超过了模型的最大上下文或是模型格式错误,请尝试削减单次输入的文本量。")
|
||||
elif "authentication_error" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. 请确保API key有效。")
|
||||
elif "not_found" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], f"[Local Message] {llm_kwargs['llm_model']} 无效，请确保使用小写的模型名称。")
|
||||
elif "rate_limit" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] 遇到了控制请求速率限制，请一分钟后重试。")
|
||||
elif "system_busy" in error_msg:
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] 系统繁忙，请一分钟后重试。")
|
||||
else:
|
||||
from toolbox import regular_txt_to_markdown
|
||||
tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
|
||||
return chatbot, history
|
||||
|
||||
def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
|
||||
"""
|
||||
整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
|
||||
"""
|
||||
|
||||
headers = {
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
|
||||
conversation_cnt = len(history) // 2
|
||||
|
||||
messages = [{"role": "system", "content": system_prompt}]
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2*conversation_cnt, 2):
|
||||
what_i_have_asked = {}
|
||||
what_i_have_asked["role"] = "user"
|
||||
what_i_have_asked["content"] = history[index]
|
||||
what_gpt_answer = {}
|
||||
what_gpt_answer["role"] = "assistant"
|
||||
what_gpt_answer["content"] = history[index+1]
|
||||
if what_i_have_asked["content"] != "":
|
||||
if what_gpt_answer["content"] == "": continue
|
||||
if what_gpt_answer["content"] == timeout_bot_msg: continue
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
else:
|
||||
messages[-1]['content'] = what_gpt_answer['content']
|
||||
|
||||
what_i_ask_now = {}
|
||||
what_i_ask_now["role"] = "user"
|
||||
what_i_ask_now["content"] = inputs
|
||||
messages.append(what_i_ask_now)
|
||||
model = llm_kwargs['llm_model']
|
||||
if llm_kwargs['llm_model'].startswith('ollama-'):
|
||||
model = llm_kwargs['llm_model'][len('ollama-'):]
|
||||
model, _ = read_one_api_model_name(model)
|
||||
options = {"temperature": llm_kwargs['temperature']}
|
||||
payload = {
|
||||
"model": model,
|
||||
"messages": messages,
|
||||
"options": options,
|
||||
}
|
||||
try:
|
||||
print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
|
||||
except:
|
||||
print('输入中可能存在乱码。')
|
||||
return headers,payload
|
||||
@@ -82,9 +82,6 @@ def generate_from_baidu_qianfan(inputs, llm_kwargs, history, system_prompt):
|
||||
"ERNIE-Bot": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions",
|
||||
"ERNIE-Bot-turbo": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant",
|
||||
"BLOOMZ-7B": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1",
|
||||
"ERNIE-Speed-128K": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-speed-128k",
|
||||
"ERNIE-Speed-8K": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed",
|
||||
"ERNIE-Lite-8K": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-lite-8k",
|
||||
|
||||
"Llama-2-70B-Chat": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/llama_2_70b",
|
||||
"Llama-2-13B-Chat": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/llama_2_13b",
|
||||
@@ -120,8 +117,7 @@ def generate_from_baidu_qianfan(inputs, llm_kwargs, history, system_prompt):
|
||||
raise RuntimeError(dec['error_msg'])
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
@@ -150,12 +146,9 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
# 开始接收回复
|
||||
try:
|
||||
response = f"[Local Message] 等待{model_name}响应中 ..."
|
||||
for response in generate_from_baidu_qianfan(inputs, llm_kwargs, history, system_prompt):
|
||||
chatbot[-1] = (inputs, response)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
history.extend([inputs, response])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
except ConnectionAbortedError as e:
|
||||
from .bridge_all import model_info
|
||||
if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
|
||||
@@ -164,8 +157,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="异常") # 刷新界面
|
||||
return
|
||||
except RuntimeError as e:
|
||||
tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
chatbot[-1] = (chatbot[-1][0], tb_str)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="异常") # 刷新界面
|
||||
return
|
||||
|
||||
# 总结输出
|
||||
response = f"[Local Message] {model_name}响应异常 ..."
|
||||
if response == f"[Local Message] 等待{model_name}响应中 ...":
|
||||
response = f"[Local Message] {model_name}响应异常 ..."
|
||||
history.extend([inputs, response])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
@@ -1,12 +1,11 @@
|
||||
import time
|
||||
import os
|
||||
from toolbox import update_ui, get_conf, update_ui_lastest_msg
|
||||
from toolbox import check_packages, report_exception, log_chat
|
||||
from toolbox import check_packages, report_exception
|
||||
|
||||
model_name = 'Qwen'
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
@@ -48,18 +47,14 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
if additional_fn is not None:
|
||||
from core_functional import handle_core_functionality
|
||||
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
|
||||
chatbot[-1] = (inputs, "")
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
# 开始接收回复
|
||||
from .com_qwenapi import QwenRequestInstance
|
||||
sri = QwenRequestInstance()
|
||||
response = f"[Local Message] 等待{model_name}响应中 ..."
|
||||
for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
|
||||
chatbot[-1] = (inputs, response)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=response)
|
||||
# 总结输出
|
||||
if response == f"[Local Message] 等待{model_name}响应中 ...":
|
||||
response = f"[Local Message] {model_name}响应异常 ..."
|
||||
|
||||
@@ -9,8 +9,7 @@ def validate_key():
|
||||
if YUNQUE_SECRET_KEY == '': return False
|
||||
return True
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
⭐ 多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
@@ -57,7 +56,6 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
# 开始接收回复
|
||||
from .com_skylark2api import YUNQUERequestInstance
|
||||
sri = YUNQUERequestInstance()
|
||||
response = f"[Local Message] 等待{model_name}响应中 ..."
|
||||
for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
|
||||
chatbot[-1] = (inputs, response)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
@@ -13,8 +13,7 @@ def validate_key():
|
||||
return False
|
||||
return True
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
@@ -53,7 +52,6 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
# 开始接收回复
|
||||
from .com_sparkapi import SparkRequestInstance
|
||||
sri = SparkRequestInstance()
|
||||
response = f"[Local Message] 等待{model_name}响应中 ..."
|
||||
for response in sri.generate(inputs, llm_kwargs, history, system_prompt, use_image_api=True):
|
||||
chatbot[-1] = (inputs, response)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
@@ -1,72 +0,0 @@
|
||||
import time
|
||||
import os
|
||||
from toolbox import update_ui, get_conf, update_ui_lastest_msg, log_chat
|
||||
from toolbox import check_packages, report_exception, have_any_recent_upload_image_files
|
||||
from toolbox import ChatBotWithCookies
|
||||
|
||||
# model_name = 'Taichu-2.0'
|
||||
# taichu_default_model = 'taichu_llm'
|
||||
|
||||
def validate_key():
|
||||
TAICHU_API_KEY = get_conf("TAICHU_API_KEY")
|
||||
if TAICHU_API_KEY == '': return False
|
||||
return True
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
"""
|
||||
watch_dog_patience = 5
|
||||
response = ""
|
||||
|
||||
# if llm_kwargs["llm_model"] == "taichu":
|
||||
# llm_kwargs["llm_model"] = "taichu"
|
||||
|
||||
if validate_key() is False:
|
||||
raise RuntimeError('请配置 TAICHU_API_KEY')
|
||||
|
||||
# 开始接收回复
|
||||
from .com_taichu import TaichuChatInit
|
||||
zhipu_bro_init = TaichuChatInit()
|
||||
for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, sys_prompt):
|
||||
if len(observe_window) >= 1:
|
||||
observe_window[0] = response
|
||||
if len(observe_window) >= 2:
|
||||
if (time.time() - observe_window[1]) > watch_dog_patience:
|
||||
raise RuntimeError("程序终止。")
|
||||
return response
|
||||
|
||||
|
||||
def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
|
||||
history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
|
||||
"""
|
||||
⭐单线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
"""
|
||||
chatbot.append([inputs, ""])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
if validate_key() is False:
|
||||
yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置ZHIPUAI_API_KEY", chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
if additional_fn is not None:
|
||||
from core_functional import handle_core_functionality
|
||||
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
|
||||
chatbot[-1] = [inputs, ""]
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
# if llm_kwargs["llm_model"] == "taichu":
|
||||
# llm_kwargs["llm_model"] = taichu_default_model
|
||||
|
||||
# 开始接收回复
|
||||
from .com_taichu import TaichuChatInit
|
||||
zhipu_bro_init = TaichuChatInit()
|
||||
for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, system_prompt):
|
||||
chatbot[-1] = [inputs, response]
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
history.extend([inputs, response])
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=response)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
@@ -1,24 +1,16 @@
|
||||
|
||||
import time
|
||||
import os
|
||||
from toolbox import update_ui, get_conf, update_ui_lastest_msg, log_chat
|
||||
from toolbox import check_packages, report_exception, have_any_recent_upload_image_files
|
||||
from toolbox import ChatBotWithCookies
|
||||
from toolbox import update_ui, get_conf, update_ui_lastest_msg
|
||||
from toolbox import check_packages, report_exception
|
||||
|
||||
model_name = '智谱AI大模型'
|
||||
zhipuai_default_model = 'glm-4'
|
||||
|
||||
def validate_key():
|
||||
ZHIPUAI_API_KEY = get_conf("ZHIPUAI_API_KEY")
|
||||
if ZHIPUAI_API_KEY == '': return False
|
||||
return True
|
||||
|
||||
def make_media_input(inputs, image_paths):
|
||||
for image_path in image_paths:
|
||||
inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
|
||||
return inputs
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
@@ -26,38 +18,31 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
||||
watch_dog_patience = 5
|
||||
response = ""
|
||||
|
||||
if llm_kwargs["llm_model"] == "zhipuai":
|
||||
llm_kwargs["llm_model"] = zhipuai_default_model
|
||||
|
||||
if validate_key() is False:
|
||||
raise RuntimeError('请配置ZHIPUAI_API_KEY')
|
||||
|
||||
# 开始接收回复
|
||||
from .com_zhipuglm import ZhipuChatInit
|
||||
zhipu_bro_init = ZhipuChatInit()
|
||||
for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, sys_prompt):
|
||||
from .com_zhipuapi import ZhipuRequestInstance
|
||||
sri = ZhipuRequestInstance()
|
||||
for response in sri.generate(inputs, llm_kwargs, history, sys_prompt):
|
||||
if len(observe_window) >= 1:
|
||||
observe_window[0] = response
|
||||
if len(observe_window) >= 2:
|
||||
if (time.time() - observe_window[1]) > watch_dog_patience:
|
||||
raise RuntimeError("程序终止。")
|
||||
if (time.time()-observe_window[1]) > watch_dog_patience: raise RuntimeError("程序终止。")
|
||||
return response
|
||||
|
||||
|
||||
def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
|
||||
history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
|
||||
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
|
||||
"""
|
||||
⭐单线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
"""
|
||||
chatbot.append([inputs, ""])
|
||||
chatbot.append((inputs, ""))
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
# 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
try:
|
||||
check_packages(["zhipuai"])
|
||||
except:
|
||||
yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install --upgrade zhipuai```。",
|
||||
yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install zhipuai==1.0.7```。",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
@@ -68,34 +53,16 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
if additional_fn is not None:
|
||||
from core_functional import handle_core_functionality
|
||||
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
|
||||
chatbot[-1] = [inputs, ""]
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
if llm_kwargs["llm_model"] == "zhipuai":
|
||||
llm_kwargs["llm_model"] = zhipuai_default_model
|
||||
|
||||
if llm_kwargs["llm_model"] in ["glm-4v"]:
|
||||
if (len(inputs) + sum(len(temp) for temp in history) + 1047) > 2000:
|
||||
chatbot.append((inputs, "上下文长度超过glm-4v上限2000tokens，注意图片大约占用1,047个tokens"))
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
return
|
||||
have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
|
||||
if not have_recent_file:
|
||||
chatbot.append((inputs, "没有检测到任何近期上传的图像文件，请上传jpg格式的图片，此外，请注意拓展名需要小写"))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
|
||||
return
|
||||
if have_recent_file:
|
||||
inputs = make_media_input(inputs, image_paths)
|
||||
chatbot[-1] = [inputs, ""]
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
|
||||
# 开始接收回复
|
||||
from .com_zhipuglm import ZhipuChatInit
|
||||
zhipu_bro_init = ZhipuChatInit()
|
||||
for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, system_prompt):
|
||||
chatbot[-1] = [inputs, response]
|
||||
from .com_zhipuapi import ZhipuRequestInstance
|
||||
sri = ZhipuRequestInstance()
|
||||
for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
|
||||
chatbot[-1] = (inputs, response)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
# 总结输出
|
||||
if response == f"[Local Message] 等待{model_name}响应中 ...":
|
||||
response = f"[Local Message] {model_name}响应异常 ..."
|
||||
history.extend([inputs, response])
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=response)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
@@ -7,7 +7,7 @@ import os
|
||||
import re
|
||||
import requests
|
||||
from typing import List, Dict, Tuple
|
||||
from toolbox import get_conf, encode_image, get_pictures_list, to_markdown_tabs
|
||||
from toolbox import get_conf, encode_image, get_pictures_list
|
||||
|
||||
proxies, TIMEOUT_SECONDS = get_conf("proxies", "TIMEOUT_SECONDS")
|
||||
|
||||
@@ -112,12 +112,38 @@ def html_local_img(__file, layout="left", max_width=None, max_height=None, md=Tr
|
||||
return a
|
||||
|
||||
|
||||
def to_markdown_tabs(head: list, tabs: list, alignment=":---:", column=False):
|
||||
"""
|
||||
Args:
|
||||
head: 表头：[]
|
||||
tabs: 表值：[[列1], [列2], [列3], [列4]]
|
||||
alignment: :--- 左对齐， :---: 居中对齐， ---: 右对齐
|
||||
column: True to keep data in columns, False to keep data in rows (default).
|
||||
Returns:
|
||||
A string representation of the markdown table.
|
||||
"""
|
||||
if column:
|
||||
transposed_tabs = list(map(list, zip(*tabs)))
|
||||
else:
|
||||
transposed_tabs = tabs
|
||||
# Find the maximum length among the columns
|
||||
max_len = max(len(column) for column in transposed_tabs)
|
||||
|
||||
tab_format = "| %s "
|
||||
tabs_list = "".join([tab_format % i for i in head]) + "|\n"
|
||||
tabs_list += "".join([tab_format % alignment for i in head]) + "|\n"
|
||||
|
||||
for i in range(max_len):
|
||||
row_data = [tab[i] if i < len(tab) else "" for tab in transposed_tabs]
|
||||
row_data = file_manifest_filter_html(row_data, filter_=None)
|
||||
tabs_list += "".join([tab_format % i for i in row_data]) + "|\n"
|
||||
|
||||
return tabs_list
|
||||
|
||||
|
||||
class GoogleChatInit:
|
||||
def __init__(self, llm_kwargs):
|
||||
from .bridge_all import model_info
|
||||
endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
||||
self.url_gemini = endpoint + "/%m:streamGenerateContent?key=%k"
|
||||
def __init__(self):
|
||||
self.url_gemini = "https://generativelanguage.googleapis.com/v1beta/models/%m:streamGenerateContent?key=%k"
|
||||
|
||||
def generate_chat(self, inputs, llm_kwargs, history, system_prompt):
|
||||
headers, payload = self.generate_message_payload(
|
||||
|
||||
@@ -48,10 +48,6 @@ class QwenRequestInstance():
|
||||
for response in responses:
|
||||
if response.status_code == HTTPStatus.OK:
|
||||
if response.output.choices[0].finish_reason == 'stop':
|
||||
try:
|
||||
self.result_buf += response.output.choices[0].message.content
|
||||
except:
|
||||
pass
|
||||
yield self.result_buf
|
||||
break
|
||||
elif response.output.choices[0].finish_reason == 'length':
|
||||
@@ -65,12 +61,8 @@ class QwenRequestInstance():
|
||||
self.result_buf += f"[Local Message] 请求错误：状态码：{response.status_code}，错误码:{response.code}，消息：{response.message}"
|
||||
yield self.result_buf
|
||||
break
|
||||
|
||||
# 耗尽generator避免报错
|
||||
while True:
|
||||
try: next(responses)
|
||||
except: break
|
||||
|
||||
logging.info(f'[raw_input] {inputs}')
|
||||
logging.info(f'[response] {self.result_buf}')
|
||||
return self.result_buf
|
||||
|
||||
|
||||
|
||||
@@ -65,9 +65,7 @@ class SparkRequestInstance():
|
||||
self.gpt_url = "ws://spark-api.xf-yun.com/v1.1/chat"
|
||||
self.gpt_url_v2 = "ws://spark-api.xf-yun.com/v2.1/chat"
|
||||
self.gpt_url_v3 = "ws://spark-api.xf-yun.com/v3.1/chat"
|
||||
self.gpt_url_v35 = "wss://spark-api.xf-yun.com/v3.5/chat"
|
||||
self.gpt_url_img = "wss://spark-api.cn-huabei-1.xf-yun.com/v2.1/image"
|
||||
self.gpt_url_v4 = "wss://spark-api.xf-yun.com/v4.0/chat"
|
||||
|
||||
self.time_to_yield_event = threading.Event()
|
||||
self.time_to_exit_event = threading.Event()
|
||||
@@ -93,10 +91,6 @@ class SparkRequestInstance():
|
||||
gpt_url = self.gpt_url_v2
|
||||
elif llm_kwargs['llm_model'] == 'sparkv3':
|
||||
gpt_url = self.gpt_url_v3
|
||||
elif llm_kwargs['llm_model'] == 'sparkv3.5':
|
||||
gpt_url = self.gpt_url_v35
|
||||
elif llm_kwargs['llm_model'] == 'sparkv4':
|
||||
gpt_url = self.gpt_url_v4
|
||||
else:
|
||||
gpt_url = self.gpt_url
|
||||
file_manifest = []
|
||||
@@ -196,8 +190,6 @@ def gen_params(appid, inputs, llm_kwargs, history, system_prompt, file_manifest)
|
||||
"spark": "general",
|
||||
"sparkv2": "generalv2",
|
||||
"sparkv3": "generalv3",
|
||||
"sparkv3.5": "generalv3.5",
|
||||
"sparkv4": "4.0Ultra"
|
||||
}
|
||||
domains_select = domains[llm_kwargs['llm_model']]
|
||||
if file_manifest: domains_select = 'image'
|
||||
|
||||
@@ -1,55 +0,0 @@
|
||||
# encoding: utf-8
|
||||
# @Time : 2024/1/22
|
||||
# @Author : Kilig947 & binary husky
|
||||
# @Descr : 兼容最新的智谱Ai
|
||||
from toolbox import get_conf
|
||||
from toolbox import get_conf, encode_image, get_pictures_list
|
||||
import logging, os, requests
|
||||
import json
|
||||
class TaichuChatInit:
|
||||
def __init__(self): ...
|
||||
|
||||
def __conversation_user(self, user_input: str, llm_kwargs:dict):
|
||||
return {"role": "user", "content": user_input}
|
||||
|
||||
def __conversation_history(self, history:list, llm_kwargs:dict):
|
||||
messages = []
|
||||
conversation_cnt = len(history) // 2
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2 * conversation_cnt, 2):
|
||||
what_i_have_asked = self.__conversation_user(history[index], llm_kwargs)
|
||||
what_gpt_answer = {
|
||||
"role": "assistant",
|
||||
"content": history[index + 1]
|
||||
}
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
return messages
|
||||
|
||||
def generate_chat(self, inputs:str, llm_kwargs:dict, history:list, system_prompt:str):
|
||||
TAICHU_API_KEY = get_conf("TAICHU_API_KEY")
|
||||
params = {
|
||||
'api_key': TAICHU_API_KEY,
|
||||
'model_code': 'taichu_llm',
|
||||
'question': '\n\n'.join(history) + inputs,
|
||||
'prefix': system_prompt,
|
||||
'temperature': llm_kwargs.get('temperature', 0.95),
|
||||
'stream_format': 'json'
|
||||
}
|
||||
|
||||
api = 'https://ai-maas.wair.ac.cn/maas/v1/model_api/invoke'
|
||||
response = requests.post(api, json=params, stream=True)
|
||||
results = ""
|
||||
if response.status_code == 200:
|
||||
response.encoding = 'utf-8'
|
||||
for line in response.iter_lines(decode_unicode=True):
|
||||
delta = json.loads(line)['choices'][0]['text']
|
||||
results += delta
|
||||
yield delta, results
|
||||
else:
|
||||
raise ValueError
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
zhipu = TaichuChatInit()
|
||||
zhipu.generate_chat('你好', {'llm_model': 'glm-4'}, [], '你是WPSAi')
|
||||
70
request_llms/com_zhipuapi.py
Normal file
70
request_llms/com_zhipuapi.py
Normal file
@@ -0,0 +1,70 @@
|
||||
from toolbox import get_conf
|
||||
import threading
|
||||
import logging
|
||||
|
||||
timeout_bot_msg = '[Local Message] Request timeout. Network error.'
|
||||
|
||||
class ZhipuRequestInstance():
|
||||
def __init__(self):
|
||||
|
||||
self.time_to_yield_event = threading.Event()
|
||||
self.time_to_exit_event = threading.Event()
|
||||
|
||||
self.result_buf = ""
|
||||
|
||||
def generate(self, inputs, llm_kwargs, history, system_prompt):
|
||||
# import _thread as thread
|
||||
import zhipuai
|
||||
ZHIPUAI_API_KEY, ZHIPUAI_MODEL = get_conf("ZHIPUAI_API_KEY", "ZHIPUAI_MODEL")
|
||||
zhipuai.api_key = ZHIPUAI_API_KEY
|
||||
self.result_buf = ""
|
||||
response = zhipuai.model_api.sse_invoke(
|
||||
model=ZHIPUAI_MODEL,
|
||||
prompt=generate_message_payload(inputs, llm_kwargs, history, system_prompt),
|
||||
top_p=llm_kwargs['top_p']*0.7, # 智谱的API抽风，手动*0.7给做个线性变换
|
||||
temperature=llm_kwargs['temperature']*0.95, # 智谱的API抽风，手动*0.7给做个线性变换
|
||||
)
|
||||
for event in response.events():
|
||||
if event.event == "add":
|
||||
# if self.result_buf == "" and event.data.startswith(" "):
|
||||
# event.data = event.data.lstrip(" ") # 每次智谱为啥都要带个空格开头呢？
|
||||
self.result_buf += event.data
|
||||
yield self.result_buf
|
||||
elif event.event == "error" or event.event == "interrupted":
|
||||
raise RuntimeError("Unknown error:" + event.data)
|
||||
elif event.event == "finish":
|
||||
yield self.result_buf
|
||||
break
|
||||
else:
|
||||
raise RuntimeError("Unknown error:" + str(event))
|
||||
if self.result_buf == "":
|
||||
yield "智谱没有返回任何数据, 请检查ZHIPUAI_API_KEY和ZHIPUAI_MODEL是否填写正确."
|
||||
logging.info(f'[raw_input] {inputs}')
|
||||
logging.info(f'[response] {self.result_buf}')
|
||||
return self.result_buf
|
||||
|
||||
def generate_message_payload(inputs, llm_kwargs, history, system_prompt):
|
||||
conversation_cnt = len(history) // 2
|
||||
messages = [{"role": "user", "content": system_prompt}, {"role": "assistant", "content": "Certainly!"}]
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2*conversation_cnt, 2):
|
||||
what_i_have_asked = {}
|
||||
what_i_have_asked["role"] = "user"
|
||||
what_i_have_asked["content"] = history[index]
|
||||
what_gpt_answer = {}
|
||||
what_gpt_answer["role"] = "assistant"
|
||||
what_gpt_answer["content"] = history[index+1]
|
||||
if what_i_have_asked["content"] != "":
|
||||
if what_gpt_answer["content"] == "":
|
||||
continue
|
||||
if what_gpt_answer["content"] == timeout_bot_msg:
|
||||
continue
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
else:
|
||||
messages[-1]['content'] = what_gpt_answer['content']
|
||||
what_i_ask_now = {}
|
||||
what_i_ask_now["role"] = "user"
|
||||
what_i_ask_now["content"] = inputs
|
||||
messages.append(what_i_ask_now)
|
||||
return messages
|
||||
@@ -1,135 +0,0 @@
|
||||
# encoding: utf-8
|
||||
# @Time : 2024/1/22
|
||||
# @Author : Kilig947 & binary husky
|
||||
# @Descr : 兼容最新的智谱Ai
|
||||
from toolbox import get_conf
|
||||
from zhipuai import ZhipuAI
|
||||
from toolbox import get_conf, encode_image, get_pictures_list
|
||||
import logging, os
|
||||
|
||||
|
||||
def input_encode_handler(inputs:str, llm_kwargs:dict):
|
||||
if llm_kwargs["most_recent_uploaded"].get("path"):
|
||||
image_paths = get_pictures_list(llm_kwargs["most_recent_uploaded"]["path"])
|
||||
md_encode = []
|
||||
for md_path in image_paths:
|
||||
type_ = os.path.splitext(md_path)[1].replace(".", "")
|
||||
type_ = "jpeg" if type_ == "jpg" else type_
|
||||
md_encode.append({"data": encode_image(md_path), "type": type_})
|
||||
return inputs, md_encode
|
||||
|
||||
|
||||
class ZhipuChatInit:
|
||||
|
||||
def __init__(self):
|
||||
ZHIPUAI_API_KEY, ZHIPUAI_MODEL = get_conf("ZHIPUAI_API_KEY", "ZHIPUAI_MODEL")
|
||||
if len(ZHIPUAI_MODEL) > 0:
|
||||
logging.error('ZHIPUAI_MODEL 配置项选项已经弃用，请在LLM_MODEL中配置')
|
||||
self.zhipu_bro = ZhipuAI(api_key=ZHIPUAI_API_KEY)
|
||||
self.model = ''
|
||||
|
||||
def __conversation_user(self, user_input: str, llm_kwargs:dict):
|
||||
if self.model not in ["glm-4v"]:
|
||||
return {"role": "user", "content": user_input}
|
||||
else:
|
||||
input_, encode_img = input_encode_handler(user_input, llm_kwargs=llm_kwargs)
|
||||
what_i_have_asked = {"role": "user", "content": []}
|
||||
what_i_have_asked['content'].append({"type": 'text', "text": user_input})
|
||||
if encode_img:
|
||||
if len(encode_img) > 1:
|
||||
logging.warning("glm-4v只支持一张图片,将只取第一张图片进行处理")
|
||||
print("glm-4v只支持一张图片,将只取第一张图片进行处理")
|
||||
img_d = {"type": "image_url",
|
||||
"image_url": {
|
||||
"url": encode_img[0]['data']
|
||||
}
|
||||
}
|
||||
what_i_have_asked['content'].append(img_d)
|
||||
return what_i_have_asked
|
||||
|
||||
def __conversation_history(self, history:list, llm_kwargs:dict):
|
||||
messages = []
|
||||
conversation_cnt = len(history) // 2
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2 * conversation_cnt, 2):
|
||||
what_i_have_asked = self.__conversation_user(history[index], llm_kwargs)
|
||||
what_gpt_answer = {
|
||||
"role": "assistant",
|
||||
"content": history[index + 1]
|
||||
}
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
return messages
|
||||
|
||||
@staticmethod
|
||||
def preprocess_param(param, default=0.95, min_val=0.01, max_val=0.99):
|
||||
"""预处理参数，保证其在允许范围内，并处理精度问题"""
|
||||
try:
|
||||
param = float(param)
|
||||
except ValueError:
|
||||
return default
|
||||
|
||||
if param <= min_val:
|
||||
return min_val
|
||||
elif param >= max_val:
|
||||
return max_val
|
||||
else:
|
||||
return round(param, 2) # 可挑选精度，目前是两位小数
|
||||
|
||||
def __conversation_message_payload(self, inputs:str, llm_kwargs:dict, history:list, system_prompt:str):
|
||||
messages = []
|
||||
if system_prompt:
|
||||
messages.append({"role": "system", "content": system_prompt})
|
||||
self.model = llm_kwargs['llm_model']
|
||||
messages.extend(self.__conversation_history(history, llm_kwargs)) # 处理 history
|
||||
if inputs.strip() == "": # 处理空输入导致报错的问题 https://github.com/binary-husky/gpt_academic/issues/1640 提示 {"error":{"code":"1214","message":"messages[1]:content和tool_calls 字段不能同时为空"}
|
||||
inputs = "." # 空格、换行、空字符串都会报错，所以用最没有意义的一个点代替
|
||||
messages.append(self.__conversation_user(inputs, llm_kwargs)) # 处理用户对话
|
||||
"""
|
||||
采样温度，控制输出的随机性，必须为正数
|
||||
取值范围是：(0.0, 1.0)，不能等于 0，默认值为 0.95，
|
||||
值越大，会使输出更随机，更具创造性；
|
||||
值越小，输出会更加稳定或确定
|
||||
建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数
|
||||
"""
|
||||
temperature = self.preprocess_param(
|
||||
param=llm_kwargs.get('temperature', 0.95),
|
||||
default=0.95,
|
||||
min_val=0.01,
|
||||
max_val=0.99
|
||||
)
|
||||
"""
|
||||
用温度取样的另一种方法，称为核取样
|
||||
取值范围是：(0.0, 1.0) 开区间，
|
||||
不能等于 0 或 1，默认值为 0.7
|
||||
模型考虑具有 top_p 概率质量 tokens 的结果
|
||||
例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens
|
||||
建议您根据应用场景调整 top_p 或 temperature 参数，
|
||||
但不要同时调整两个参数
|
||||
"""
|
||||
top_p = self.preprocess_param(
|
||||
param=llm_kwargs.get('top_p', 0.70),
|
||||
default=0.70,
|
||||
min_val=0.01,
|
||||
max_val=0.99
|
||||
)
|
||||
response = self.zhipu_bro.chat.completions.create(
|
||||
model=self.model, messages=messages, stream=True,
|
||||
temperature=temperature,
|
||||
top_p=top_p,
|
||||
max_tokens=llm_kwargs.get('max_tokens', 1024 * 4),
|
||||
)
|
||||
return response
|
||||
|
||||
def generate_chat(self, inputs:str, llm_kwargs:dict, history:list, system_prompt:str):
|
||||
self.model = llm_kwargs['llm_model']
|
||||
response = self.__conversation_message_payload(inputs, llm_kwargs, history, system_prompt)
|
||||
bro_results = ''
|
||||
for chunk in response:
|
||||
bro_results += chunk.choices[0].delta.content
|
||||
yield chunk.choices[0].delta.content, bro_results
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
zhipu = ZhipuChatInit()
|
||||
zhipu.generate_chat('你好', {'llm_model': 'glm-4'}, [], '你是WPSAi')
|
||||
@@ -1,7 +1,6 @@
|
||||
import time
|
||||
import threading
|
||||
from toolbox import update_ui, Singleton
|
||||
from toolbox import ChatBotWithCookies
|
||||
from multiprocessing import Process, Pipe
|
||||
from contextlib import redirect_stdout
|
||||
from request_llms.queued_pipe import create_queue_pipe
|
||||
@@ -215,7 +214,7 @@ class LocalLLMHandle(Process):
|
||||
def get_local_llm_predict_fns(LLMSingletonClass, model_name, history_format='classic'):
|
||||
load_message = f"{model_name}尚未加载，加载需要一段时间。注意，取决于`config.py`的配置，{model_name}消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=[], console_slience:bool=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
refer to request_llms/bridge_all.py
|
||||
"""
|
||||
@@ -261,8 +260,7 @@ def get_local_llm_predict_fns(LLMSingletonClass, model_name, history_format='cla
|
||||
raise RuntimeError("程序终止。")
|
||||
return response
|
||||
|
||||
def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
|
||||
history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
|
||||
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream=True, additional_fn=None):
|
||||
"""
|
||||
refer to request_llms/bridge_all.py
|
||||
"""
|
||||
|
||||
@@ -1,402 +0,0 @@
|
||||
import json
|
||||
import time
|
||||
import logging
|
||||
import traceback
|
||||
import requests
|
||||
|
||||
# config_private.py放自己的秘密如API和代理网址
|
||||
# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
|
||||
from toolbox import (
|
||||
get_conf,
|
||||
update_ui,
|
||||
is_the_upload_folder,
|
||||
)
|
||||
|
||||
proxies, TIMEOUT_SECONDS, MAX_RETRY = get_conf(
|
||||
"proxies", "TIMEOUT_SECONDS", "MAX_RETRY"
|
||||
)
|
||||
|
||||
timeout_bot_msg = (
|
||||
"[Local Message] Request timeout. Network error. Please check proxy settings in config.py."
|
||||
+ "网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。"
|
||||
)
|
||||
|
||||
|
||||
def get_full_error(chunk, stream_response):
|
||||
"""
|
||||
尝试获取完整的错误信息
|
||||
"""
|
||||
while True:
|
||||
try:
|
||||
chunk += next(stream_response)
|
||||
except:
|
||||
break
|
||||
return chunk
|
||||
|
||||
|
||||
def decode_chunk(chunk):
|
||||
"""
|
||||
用于解读"content"和"finish_reason"的内容
|
||||
"""
|
||||
chunk = chunk.decode()
|
||||
respose = ""
|
||||
finish_reason = "False"
|
||||
try:
|
||||
chunk = json.loads(chunk[6:])
|
||||
except:
|
||||
respose = "API_ERROR"
|
||||
finish_reason = chunk
|
||||
# 错误处理部分
|
||||
if "error" in chunk:
|
||||
respose = "API_ERROR"
|
||||
try:
|
||||
chunk = json.loads(chunk)
|
||||
finish_reason = chunk["error"]["code"]
|
||||
except:
|
||||
finish_reason = "API_ERROR"
|
||||
return respose, finish_reason
|
||||
|
||||
try:
|
||||
respose = chunk["choices"][0]["delta"]["content"]
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
finish_reason = chunk["choices"][0]["finish_reason"]
|
||||
except:
|
||||
pass
|
||||
return respose, finish_reason
|
||||
|
||||
|
||||
def generate_message(input, model, key, history, max_output_token, system_prompt, temperature):
|
||||
"""
|
||||
整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
|
||||
"""
|
||||
api_key = f"Bearer {key}"
|
||||
|
||||
headers = {"Content-Type": "application/json", "Authorization": api_key}
|
||||
|
||||
conversation_cnt = len(history) // 2
|
||||
|
||||
messages = [{"role": "system", "content": system_prompt}]
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2 * conversation_cnt, 2):
|
||||
what_i_have_asked = {}
|
||||
what_i_have_asked["role"] = "user"
|
||||
what_i_have_asked["content"] = history[index]
|
||||
what_gpt_answer = {}
|
||||
what_gpt_answer["role"] = "assistant"
|
||||
what_gpt_answer["content"] = history[index + 1]
|
||||
if what_i_have_asked["content"] != "":
|
||||
if what_gpt_answer["content"] == "":
|
||||
continue
|
||||
if what_gpt_answer["content"] == timeout_bot_msg:
|
||||
continue
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
else:
|
||||
messages[-1]["content"] = what_gpt_answer["content"]
|
||||
what_i_ask_now = {}
|
||||
what_i_ask_now["role"] = "user"
|
||||
what_i_ask_now["content"] = input
|
||||
messages.append(what_i_ask_now)
|
||||
playload = {
|
||||
"model": model,
|
||||
"messages": messages,
|
||||
"temperature": temperature,
|
||||
"stream": True,
|
||||
"max_tokens": max_output_token,
|
||||
}
|
||||
try:
|
||||
print(f" {model} : {conversation_cnt} : {input[:100]} ..........")
|
||||
except:
|
||||
print("输入中可能存在乱码。")
|
||||
return headers, playload
|
||||
|
||||
|
||||
def get_predict_function(
|
||||
api_key_conf_name,
|
||||
max_output_token,
|
||||
disable_proxy = False
|
||||
):
|
||||
"""
|
||||
为openai格式的API生成响应函数，其中传入参数：
|
||||
api_key_conf_name：
|
||||
`config.py`中此模型的APIKEY的名字，例如"YIMODEL_API_KEY"
|
||||
max_output_token：
|
||||
每次请求的最大token数量，例如对于01万物的yi-34b-chat-200k，其最大请求数为4096
|
||||
⚠️请不要与模型的最大token数量相混淆。
|
||||
disable_proxy：
|
||||
是否使用代理，True为不使用，False为使用。
|
||||
"""
|
||||
|
||||
APIKEY = get_conf(api_key_conf_name)
|
||||
|
||||
def predict_no_ui_long_connection(
|
||||
inputs,
|
||||
llm_kwargs,
|
||||
history=[],
|
||||
sys_prompt="",
|
||||
observe_window=None,
|
||||
console_slience=False,
|
||||
):
|
||||
"""
|
||||
发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
是本次问询的输入
|
||||
sys_prompt:
|
||||
系统静默prompt
|
||||
llm_kwargs：
|
||||
chatGPT的内部调优参数
|
||||
history：
|
||||
是之前的对话列表
|
||||
observe_window = None：
|
||||
用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
|
||||
"""
|
||||
watch_dog_patience = 5 # 看门狗的耐心，设置5秒不准咬人(咬的也不是人
|
||||
if len(APIKEY) == 0:
|
||||
raise RuntimeError(f"APIKEY为空,请检查配置文件的{APIKEY}")
|
||||
if inputs == "":
|
||||
inputs = "你好👋"
|
||||
headers, playload = generate_message(
|
||||
input=inputs,
|
||||
model=llm_kwargs["llm_model"],
|
||||
key=APIKEY,
|
||||
history=history,
|
||||
max_output_token=max_output_token,
|
||||
system_prompt=sys_prompt,
|
||||
temperature=llm_kwargs["temperature"],
|
||||
)
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
from .bridge_all import model_info
|
||||
|
||||
endpoint = model_info[llm_kwargs["llm_model"]]["endpoint"]
|
||||
if not disable_proxy:
|
||||
response = requests.post(
|
||||
endpoint,
|
||||
headers=headers,
|
||||
proxies=proxies,
|
||||
json=playload,
|
||||
stream=True,
|
||||
timeout=TIMEOUT_SECONDS,
|
||||
)
|
||||
else:
|
||||
response = requests.post(
|
||||
endpoint,
|
||||
headers=headers,
|
||||
json=playload,
|
||||
stream=True,
|
||||
timeout=TIMEOUT_SECONDS,
|
||||
)
|
||||
break
|
||||
except:
|
||||
retry += 1
|
||||
traceback.print_exc()
|
||||
if retry > MAX_RETRY:
|
||||
raise TimeoutError
|
||||
if MAX_RETRY != 0:
|
||||
print(f"请求超时，正在重试 ({retry}/{MAX_RETRY}) ……")
|
||||
|
||||
stream_response = response.iter_lines()
|
||||
result = ""
|
||||
while True:
|
||||
try:
|
||||
chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
break
|
||||
except requests.exceptions.ConnectionError:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
response_text, finish_reason = decode_chunk(chunk)
|
||||
# 返回的数据流第一次为空，继续等待
|
||||
if response_text == "" and finish_reason != "False":
|
||||
continue
|
||||
if response_text == "API_ERROR" and (
|
||||
finish_reason != "False" or finish_reason != "stop"
|
||||
):
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
chunk_decoded = chunk.decode()
|
||||
print(chunk_decoded)
|
||||
raise RuntimeError(
|
||||
f"API异常,请检测终端输出。可能的原因是:{finish_reason}"
|
||||
)
|
||||
if chunk:
|
||||
try:
|
||||
if finish_reason == "stop":
|
||||
logging.info(f"[response] {result}")
|
||||
break
|
||||
result += response_text
|
||||
if not console_slience:
|
||||
print(response_text, end="")
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1:
|
||||
observe_window[0] += response_text
|
||||
# 看门狗，如果超过期限没有喂狗，则终止
|
||||
if len(observe_window) >= 2:
|
||||
if (time.time() - observe_window[1]) > watch_dog_patience:
|
||||
raise RuntimeError("用户取消了程序。")
|
||||
except Exception as e:
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
chunk_decoded = chunk.decode()
|
||||
error_msg = chunk_decoded
|
||||
print(error_msg)
|
||||
raise RuntimeError("Json解析不合常规")
|
||||
return result
|
||||
|
||||
def predict(
|
||||
inputs,
|
||||
llm_kwargs,
|
||||
plugin_kwargs,
|
||||
chatbot,
|
||||
history=[],
|
||||
system_prompt="",
|
||||
stream=True,
|
||||
additional_fn=None,
|
||||
):
|
||||
"""
|
||||
发送至chatGPT，流式获取输出。
|
||||
用于基础的对话功能。
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
if len(APIKEY) == 0:
|
||||
raise RuntimeError(f"APIKEY为空,请检查配置文件的{APIKEY}")
|
||||
if inputs == "":
|
||||
inputs = "你好👋"
|
||||
if additional_fn is not None:
|
||||
from core_functional import handle_core_functionality
|
||||
|
||||
inputs, history = handle_core_functionality(
|
||||
additional_fn, inputs, history, chatbot
|
||||
)
|
||||
logging.info(f"[raw_input] {inputs}")
|
||||
chatbot.append((inputs, ""))
|
||||
yield from update_ui(
|
||||
chatbot=chatbot, history=history, msg="等待响应"
|
||||
) # 刷新界面
|
||||
|
||||
# check mis-behavior
|
||||
if is_the_upload_folder(inputs):
|
||||
chatbot[-1] = (
|
||||
inputs,
|
||||
f"[Local Message] 检测到操作错误！当您上传文档之后，需点击“**函数插件区**”按钮进行处理，请勿点击“提交”按钮或者“基础功能区”按钮。",
|
||||
)
|
||||
yield from update_ui(
|
||||
chatbot=chatbot, history=history, msg="正常"
|
||||
) # 刷新界面
|
||||
time.sleep(2)
|
||||
|
||||
headers, playload = generate_message(
|
||||
input=inputs,
|
||||
model=llm_kwargs["llm_model"],
|
||||
key=APIKEY,
|
||||
history=history,
|
||||
max_output_token=max_output_token,
|
||||
system_prompt=system_prompt,
|
||||
temperature=llm_kwargs["temperature"],
|
||||
)
|
||||
|
||||
history.append(inputs)
|
||||
history.append("")
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
from .bridge_all import model_info
|
||||
|
||||
endpoint = model_info[llm_kwargs["llm_model"]]["endpoint"]
|
||||
if not disable_proxy:
|
||||
response = requests.post(
|
||||
endpoint,
|
||||
headers=headers,
|
||||
proxies=proxies,
|
||||
json=playload,
|
||||
stream=True,
|
||||
timeout=TIMEOUT_SECONDS,
|
||||
)
|
||||
else:
|
||||
response = requests.post(
|
||||
endpoint,
|
||||
headers=headers,
|
||||
json=playload,
|
||||
stream=True,
|
||||
timeout=TIMEOUT_SECONDS,
|
||||
)
|
||||
break
|
||||
except:
|
||||
retry += 1
|
||||
chatbot[-1] = (chatbot[-1][0], timeout_bot_msg)
|
||||
retry_msg = (
|
||||
f"，正在重试 ({retry}/{MAX_RETRY}) ……" if MAX_RETRY > 0 else ""
|
||||
)
|
||||
yield from update_ui(
|
||||
chatbot=chatbot, history=history, msg="请求超时" + retry_msg
|
||||
) # 刷新界面
|
||||
if retry > MAX_RETRY:
|
||||
raise TimeoutError
|
||||
|
||||
gpt_replying_buffer = ""
|
||||
|
||||
stream_response = response.iter_lines()
|
||||
while True:
|
||||
try:
|
||||
chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
break
|
||||
except requests.exceptions.ConnectionError:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
response_text, finish_reason = decode_chunk(chunk)
|
||||
# 返回的数据流第一次为空，继续等待
|
||||
if response_text == "" and finish_reason != "False":
|
||||
continue
|
||||
if chunk:
|
||||
try:
|
||||
if response_text == "API_ERROR" and (
|
||||
finish_reason != "False" or finish_reason != "stop"
|
||||
):
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
chunk_decoded = chunk.decode()
|
||||
chatbot[-1] = (
|
||||
chatbot[-1][0],
|
||||
"[Local Message] {finish_reason},获得以下报错信息：\n"
|
||||
+ chunk_decoded,
|
||||
)
|
||||
yield from update_ui(
|
||||
chatbot=chatbot,
|
||||
history=history,
|
||||
msg="API异常:" + chunk_decoded,
|
||||
) # 刷新界面
|
||||
print(chunk_decoded)
|
||||
return
|
||||
|
||||
if finish_reason == "stop":
|
||||
logging.info(f"[response] {gpt_replying_buffer}")
|
||||
break
|
||||
status_text = f"finish_reason: {finish_reason}"
|
||||
gpt_replying_buffer += response_text
|
||||
# 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
|
||||
history[-1] = gpt_replying_buffer
|
||||
chatbot[-1] = (history[-2], history[-1])
|
||||
yield from update_ui(
|
||||
chatbot=chatbot, history=history, msg=status_text
|
||||
) # 刷新界面
|
||||
except Exception as e:
|
||||
yield from update_ui(
|
||||
chatbot=chatbot, history=history, msg="Json解析不合常规"
|
||||
) # 刷新界面
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
chunk_decoded = chunk.decode()
|
||||
chatbot[-1] = (
|
||||
chatbot[-1][0],
|
||||
"[Local Message] 解析错误,获得以下报错信息：\n" + chunk_decoded,
|
||||
)
|
||||
yield from update_ui(
|
||||
chatbot=chatbot, history=history, msg="Json异常" + chunk_decoded
|
||||
) # 刷新界面
|
||||
print(chunk_decoded)
|
||||
return
|
||||
|
||||
return predict_no_ui_long_connection, predict
|
||||
@@ -1,15 +1,12 @@
|
||||
https://public.agent-matrix.com/publish/gradio-3.32.10-py3-none-any.whl
|
||||
fastapi==0.110
|
||||
gradio-client==0.8
|
||||
https://fastly.jsdelivr.net/gh/binary-husky/gradio-fix@gpt-academic/release/gradio-3.32.7-py3-none-any.whl
|
||||
pypdf2==2.12.1
|
||||
zhipuai==2.0.1
|
||||
zhipuai<2
|
||||
tiktoken>=0.3.3
|
||||
requests[socks]
|
||||
pydantic==2.5.2
|
||||
pydantic==1.10.11
|
||||
protobuf==3.18
|
||||
transformers>=4.27.1
|
||||
scipdf_parser>=0.52
|
||||
anthropic>=0.18.1
|
||||
python-markdown-math
|
||||
pymdown-extensions
|
||||
websocket-client
|
||||
@@ -18,15 +15,13 @@ prompt_toolkit
|
||||
latex2mathml
|
||||
python-docx
|
||||
mdtex2html
|
||||
dashscope
|
||||
anthropic
|
||||
pyautogen
|
||||
colorama
|
||||
Markdown
|
||||
pygments
|
||||
edge-tts
|
||||
pymupdf
|
||||
openai
|
||||
rjsmin
|
||||
arxiv
|
||||
numpy
|
||||
rich
|
||||
|
||||
@@ -46,16 +46,6 @@ code_highlight_configs_block_mermaid = {
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
mathpatterns = {
|
||||
r"(?<!\\|\$)(\$)([^\$]+)(\$)": {"allow_multi_lines": False}, # $...$
|
||||
r"(?<!\\)(\$\$)([^\$]+)(\$\$)": {"allow_multi_lines": True}, # $$...$$
|
||||
r"(?<!\\)(\\\[)(.+?)(\\\])": {"allow_multi_lines": False}, # \[...\]
|
||||
r'(?<!\\)(\\\()(.+?)(\\\))': {'allow_multi_lines': False}, # \(...\)
|
||||
# r'(?<!\\)(\\begin{([a-z]+?\*?)})(.+?)(\\end{\2})': {'allow_multi_lines': True}, # \begin...\end
|
||||
# r'(?<!\\)(\$`)([^`]+)(`\$)': {'allow_multi_lines': False}, # $`...`$
|
||||
}
|
||||
|
||||
def tex2mathml_catch_exception(content, *args, **kwargs):
|
||||
try:
|
||||
content = tex2mathml(content, *args, **kwargs)
|
||||
@@ -106,7 +96,14 @@ def is_equation(txt):
|
||||
return False
|
||||
if "$" not in txt and "\\[" not in txt:
|
||||
return False
|
||||
|
||||
mathpatterns = {
|
||||
r"(?<!\\|\$)(\$)([^\$]+)(\$)": {"allow_multi_lines": False}, # $...$
|
||||
r"(?<!\\)(\$\$)([^\$]+)(\$\$)": {"allow_multi_lines": True}, # $$...$$
|
||||
r"(?<!\\)(\\\[)(.+?)(\\\])": {"allow_multi_lines": False}, # \[...\]
|
||||
# r'(?<!\\)(\\\()(.+?)(\\\))': {'allow_multi_lines': False}, # \(...\)
|
||||
# r'(?<!\\)(\\begin{([a-z]+?\*?)})(.+?)(\\end{\2})': {'allow_multi_lines': True}, # \begin...\end
|
||||
# r'(?<!\\)(\$`)([^`]+)(`\$)': {'allow_multi_lines': False}, # $`...`$
|
||||
}
|
||||
matches = []
|
||||
for pattern, property in mathpatterns.items():
|
||||
flags = re.ASCII | re.DOTALL if property["allow_multi_lines"] else re.ASCII
|
||||
@@ -210,118 +207,6 @@ def fix_code_segment_indent(txt):
|
||||
return txt
|
||||
|
||||
|
||||
def fix_dollar_sticking_bug(txt):
|
||||
"""
|
||||
修复不标准的dollar公式符号的问题
|
||||
"""
|
||||
txt_result = ""
|
||||
single_stack_height = 0
|
||||
double_stack_height = 0
|
||||
while True:
|
||||
while True:
|
||||
index = txt.find('$')
|
||||
|
||||
if index == -1:
|
||||
txt_result += txt
|
||||
return txt_result
|
||||
|
||||
if single_stack_height > 0:
|
||||
if txt[:(index+1)].find('\n') > 0 or txt[:(index+1)].find('<td>') > 0 or txt[:(index+1)].find('</td>') > 0:
|
||||
print('公式之中出现了异常 (Unexpect element in equation)')
|
||||
single_stack_height = 0
|
||||
txt_result += ' $'
|
||||
continue
|
||||
|
||||
if double_stack_height > 0:
|
||||
if txt[:(index+1)].find('\n\n') > 0:
|
||||
print('公式之中出现了异常 (Unexpect element in equation)')
|
||||
double_stack_height = 0
|
||||
txt_result += '$$'
|
||||
continue
|
||||
|
||||
is_double = (txt[index+1] == '$')
|
||||
if is_double:
|
||||
if single_stack_height != 0:
|
||||
# add a padding
|
||||
txt = txt[:(index+1)] + " " + txt[(index+1):]
|
||||
continue
|
||||
if double_stack_height == 0:
|
||||
double_stack_height = 1
|
||||
else:
|
||||
double_stack_height = 0
|
||||
txt_result += txt[:(index+2)]
|
||||
txt = txt[(index+2):]
|
||||
else:
|
||||
if double_stack_height != 0:
|
||||
# print(txt[:(index)])
|
||||
print('发现异常嵌套公式')
|
||||
if single_stack_height == 0:
|
||||
single_stack_height = 1
|
||||
else:
|
||||
single_stack_height = 0
|
||||
# print(txt[:(index)])
|
||||
txt_result += txt[:(index+1)]
|
||||
txt = txt[(index+1):]
|
||||
break
|
||||
|
||||
|
||||
def markdown_convertion_for_file(txt):
|
||||
"""
|
||||
将Markdown格式的文本转换为HTML格式。如果包含数学公式，则先将公式转换为HTML格式。
|
||||
"""
|
||||
from themes.theme import advanced_css
|
||||
pre = f"""
|
||||
<!DOCTYPE html><head><meta charset="utf-8"><title>PDF文档翻译</title><style>{advanced_css}</style></head>
|
||||
<body>
|
||||
<div class="test_temp1" style="width:10%; height: 500px; float:left;"></div>
|
||||
<div class="test_temp2" style="width:80%;padding: 40px;float:left;padding-left: 20px;padding-right: 20px;box-shadow: rgba(0, 0, 0, 0.2) 0px 0px 8px 8px;border-radius: 10px;">
|
||||
<div class="markdown-body">
|
||||
"""
|
||||
suf = """
|
||||
</div>
|
||||
</div>
|
||||
<div class="test_temp3" style="width:10%; height: 500px; float:left;"></div>
|
||||
</body>
|
||||
"""
|
||||
|
||||
if txt.startswith(pre) and txt.endswith(suf):
|
||||
# print('警告，输入了已经经过转化的字符串，二次转化可能出问题')
|
||||
return txt # 已经被转化过，不需要再次转化
|
||||
|
||||
find_equation_pattern = r'<script type="math/tex(?:.*?)>(.*?)</script>'
|
||||
txt = fix_markdown_indent(txt)
|
||||
convert_stage_1 = fix_dollar_sticking_bug(txt)
|
||||
# convert everything to html format
|
||||
convert_stage_2 = markdown.markdown(
|
||||
text=convert_stage_1,
|
||||
extensions=[
|
||||
"sane_lists",
|
||||
"tables",
|
||||
"mdx_math",
|
||||
"pymdownx.superfences",
|
||||
"pymdownx.highlight",
|
||||
],
|
||||
extension_configs={**markdown_extension_configs, **code_highlight_configs},
|
||||
)
|
||||
|
||||
|
||||
def repl_fn(match):
|
||||
content = match.group(2)
|
||||
return f'<script type="math/tex">{content}</script>'
|
||||
|
||||
pattern = "|".join([pattern for pattern, property in mathpatterns.items() if not property["allow_multi_lines"]])
|
||||
pattern = re.compile(pattern, flags=re.ASCII)
|
||||
convert_stage_3 = pattern.sub(repl_fn, convert_stage_2)
|
||||
|
||||
convert_stage_4 = markdown_bug_hunt(convert_stage_3)
|
||||
|
||||
# 2. convert to rendered equation
|
||||
convert_stage_5, n = re.subn(
|
||||
find_equation_pattern, replace_math_render, convert_stage_4, flags=re.DOTALL
|
||||
)
|
||||
# cat them together
|
||||
return pre + convert_stage_5 + suf
|
||||
|
||||
@lru_cache(maxsize=128) # 使用 lru缓存 加快转换速度
|
||||
def markdown_convertion(txt):
|
||||
"""
|
||||
|
||||
@@ -1,25 +0,0 @@
|
||||
def is_full_width_char(ch):
|
||||
"""判断给定的单个字符是否是全角字符"""
|
||||
if '\u4e00' <= ch <= '\u9fff':
|
||||
return True # 中文字符
|
||||
if '\uff01' <= ch <= '\uff5e':
|
||||
return True # 全角符号
|
||||
if '\u3000' <= ch <= '\u303f':
|
||||
return True # CJK标点符号
|
||||
return False
|
||||
|
||||
def scolling_visual_effect(text, scroller_max_len):
|
||||
text = text.\
|
||||
replace('\n', '').replace('`', '.').replace(' ', '.').replace('<br/>', '.....').replace('$', '.')
|
||||
place_take_cnt = 0
|
||||
pointer = len(text) - 1
|
||||
|
||||
if len(text) < scroller_max_len:
|
||||
return text
|
||||
|
||||
while place_take_cnt < scroller_max_len and pointer > 0:
|
||||
if is_full_width_char(text[pointer]): place_take_cnt += 2
|
||||
else: place_take_cnt += 1
|
||||
pointer -= 1
|
||||
|
||||
return text[pointer:]
|
||||
@@ -2,7 +2,7 @@ import importlib
|
||||
import time
|
||||
import os
|
||||
from functools import lru_cache
|
||||
from shared_utils.colorful import print亮红, print亮绿, print亮蓝
|
||||
from colorful import print亮红, print亮绿, print亮蓝
|
||||
|
||||
pj = os.path.join
|
||||
default_user_name = 'default_user'
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user