Compare commits
2 Commits
GHSA-3jrq-
...
binary-hus
| Author | SHA1 | Date | |
|---|---|---|---|
|
b8d1eabd46 | ||
|
|
de9bc50ac4 |
3
.gitignore
vendored
3
.gitignore
vendored
@@ -153,6 +153,3 @@ media
|
||||
flagged
|
||||
request_llms/ChatGLM-6b-onnx-u8s8
|
||||
.pre-commit-config.yaml
|
||||
themes/common.js.min.*.js
|
||||
test*
|
||||
objdump*
|
||||
@@ -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
|
||||
|
||||
|
||||
17
README.md
17
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/)
|
||||
> [!IMPORTANT]
|
||||
> 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": {
|
||||
|
||||
@@ -47,7 +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)
|
||||
@@ -71,7 +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，',
|
||||
@@ -81,7 +81,7 @@ def patch_and_restart(path):
|
||||
dir_util.copy_tree(path_new_version, './')
|
||||
print亮绿('代码已经更新，即将更新pip包依赖……')
|
||||
for i in reversed(range(5)): time.sleep(1); print(i)
|
||||
try:
|
||||
try:
|
||||
import subprocess
|
||||
subprocess.check_call([sys.executable, '-m', 'pip', 'install', '-r', 'requirements.txt'])
|
||||
except:
|
||||
@@ -113,7 +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"]:
|
||||
@@ -124,7 +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）？')
|
||||
@@ -159,7 +159,7 @@ def warm_up_modules():
|
||||
enc.encode("模块预热", disallowed_special=())
|
||||
enc = model_info["gpt-4"]['tokenizer']
|
||||
enc.encode("模块预热", disallowed_special=())
|
||||
|
||||
|
||||
def warm_up_vectordb():
|
||||
print('正在执行一些模块的预热 ...')
|
||||
from toolbox import ProxyNetworkActivate
|
||||
@@ -167,7 +167,7 @@ def warm_up_vectordb():
|
||||
import nltk
|
||||
with ProxyNetworkActivate("Warmup_Modules"): nltk.download("punkt")
|
||||
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
import os
|
||||
os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
|
||||
|
||||
@@ -3,7 +3,7 @@ from sys import stdout
|
||||
|
||||
if platform.system()=="Linux":
|
||||
pass
|
||||
else:
|
||||
else:
|
||||
from colorama import init
|
||||
init()
|
||||
|
||||
144
config.py
144
config.py
@@ -2,8 +2,8 @@
|
||||
以下所有配置也都支持利用环境变量覆写，环境变量配置格式见docker-compose.yml。
|
||||
读取优先级：环境变量 > config_private.py > config.py
|
||||
--- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---
|
||||
All the following configurations also support using environment variables to override,
|
||||
and the environment variable configuration format can be seen in docker-compose.yml.
|
||||
All the following configurations also support using environment variables to override,
|
||||
and the environment variable configuration format can be seen in docker-compose.yml.
|
||||
Configuration reading priority: environment variable > config_private.py > 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",
|
||||
# "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"}
|
||||
# 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"}
|
||||
API_URL_REDIRECT = {}
|
||||
|
||||
|
||||
@@ -95,7 +66,7 @@ LAYOUT = "LEFT-RIGHT" # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下
|
||||
|
||||
|
||||
# 暗色模式 / 亮色模式
|
||||
DARK_MODE = True
|
||||
DARK_MODE = True
|
||||
|
||||
|
||||
# 发送请求到OpenAI后，等待多久判定为超时
|
||||
@@ -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" # 可选 ↓↓↓
|
||||
AVAIL_LLM_MODELS = ["gpt-3.5-turbo-1106","gpt-4-1106-preview","gpt-4-vision-preview",
|
||||
"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 = "/"
|
||||
|
||||
|
||||
@@ -179,7 +158,7 @@ API_ORG = ""
|
||||
|
||||
|
||||
# 如果需要使用Slack Claude，使用教程详情见 request_llms/README.md
|
||||
SLACK_CLAUDE_BOT_ID = ''
|
||||
SLACK_CLAUDE_BOT_ID = ''
|
||||
SLACK_CLAUDE_USER_TOKEN = ''
|
||||
|
||||
|
||||
@@ -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"
|
||||
@@ -216,32 +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 = ""
|
||||
|
||||
# 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 = ""
|
||||
|
||||
@@ -258,8 +224,8 @@ HUGGINGFACE_ACCESS_TOKEN = "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"
|
||||
# 获取方法：复制以下空间https://huggingface.co/spaces/qingxu98/grobid，设为public，然后GROBID_URL = "https://(你的hf用户名如qingxu98)-(你的填写的空间名如grobid).hf.space"
|
||||
GROBID_URLS = [
|
||||
"https://qingxu98-grobid.hf.space","https://qingxu98-grobid2.hf.space","https://qingxu98-grobid3.hf.space",
|
||||
"https://qingxu98-grobid4.hf.space","https://qingxu98-grobid5.hf.space", "https://qingxu98-grobid6.hf.space",
|
||||
"https://qingxu98-grobid7.hf.space", "https://qingxu98-grobid8.hf.space",
|
||||
"https://qingxu98-grobid4.hf.space","https://qingxu98-grobid5.hf.space", "https://qingxu98-grobid6.hf.space",
|
||||
"https://qingxu98-grobid7.hf.space", "https://qingxu98-grobid8.hf.space",
|
||||
]
|
||||
|
||||
|
||||
@@ -280,7 +246,7 @@ PATH_LOGGING = "gpt_log"
|
||||
|
||||
|
||||
# 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",
|
||||
WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
|
||||
"Warmup_Modules", "Nougat_Download", "AutoGen"]
|
||||
|
||||
|
||||
@@ -295,11 +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
|
||||
@@ -323,7 +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"
|
||||
@@ -335,11 +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
|
||||
@@ -347,12 +307,11 @@ 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
|
||||
│
|
||||
├── "chatglm3"
|
||||
@@ -392,9 +351,6 @@ NUM_CUSTOM_BASIC_BTN = 4
|
||||
│ └── ALIYUN_SECRET
|
||||
│
|
||||
└── PDF文档精准解析
|
||||
├── GROBID_URLS
|
||||
├── MATHPIX_APPID
|
||||
└── MATHPIX_APPKEY
|
||||
|
||||
└── GROBID_URLS
|
||||
|
||||
"""
|
||||
|
||||
@@ -3,27 +3,18 @@
|
||||
# 'stop' 颜色对应 theme.py 中的 color_er
|
||||
import importlib
|
||||
from toolbox import clear_line_break
|
||||
from toolbox import apply_gpt_academic_string_mask_langbased
|
||||
from toolbox import build_gpt_academic_masked_string_langbased
|
||||
from textwrap import dedent
|
||||
|
||||
def get_core_functions():
|
||||
return {
|
||||
|
||||
"学术语料润色": {
|
||||
# [1*] 前缀字符串，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。
|
||||
# 这里填一个提示词字符串就行了，这里为了区分中英文情景搞复杂了一点
|
||||
"Prefix": build_gpt_academic_masked_string_langbased(
|
||||
text_show_english=
|
||||
r"Below is a paragraph from an academic paper. Polish the writing to meet the academic style, "
|
||||
r"improve the spelling, grammar, clarity, concision and overall readability. When necessary, rewrite the whole sentence. "
|
||||
r"Firstly, you should provide the polished paragraph. "
|
||||
r"Secondly, you should list all your modification and explain the reasons to do so in markdown table.",
|
||||
text_show_chinese=
|
||||
r"作为一名中文学术论文写作改进助理，你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性，"
|
||||
r"同时分解长句，减少重复，并提供改进建议。请先提供文本的更正版本，然后在markdown表格中列出修改的内容，并给出修改的理由:"
|
||||
) + "\n\n",
|
||||
# [2*] 后缀字符串，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
|
||||
"英语学术润色": {
|
||||
# [1*] 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": r"Below is a paragraph from an academic paper. Polish the writing to meet the academic style, "
|
||||
r"improve the spelling, grammar, clarity, concision and overall readability. When necessary, rewrite the whole sentence. "
|
||||
r"Firstly, you should provide the polished paragraph. "
|
||||
r"Secondly, you should list all your modification and explain the reasons to do so in markdown table." + "\n\n",
|
||||
# [2*] 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": r"",
|
||||
# [3] 按钮颜色 (可选参数，默认 secondary)
|
||||
"Color": r"secondary",
|
||||
@@ -33,20 +24,16 @@ 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：
|
||||
|
||||
以下是对以上文本的总结，以mermaid flowchart的形式展示：
|
||||
@@ -59,15 +46,15 @@ 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
|
||||
（4）根据情况选择flowchart LR（从左到右）或者flowchart TD（从上到下）
|
||||
'''),
|
||||
},
|
||||
|
||||
|
||||
|
||||
|
||||
"查找语法错误": {
|
||||
"Prefix": r"Help me ensure that the grammar and the spelling is correct. "
|
||||
r"Do not try to polish the text, if no mistake is found, tell me that this paragraph is good. "
|
||||
@@ -87,56 +74,48 @@ def get_core_functions():
|
||||
"Suffix": r"",
|
||||
"PreProcess": clear_line_break, # 预处理：清除换行符
|
||||
},
|
||||
|
||||
|
||||
|
||||
|
||||
"中译英": {
|
||||
"Prefix": r"Please translate following sentence to English:" + "\n\n",
|
||||
"Suffix": r"",
|
||||
},
|
||||
|
||||
|
||||
|
||||
|
||||
"学术英中互译": {
|
||||
"Prefix": build_gpt_academic_masked_string_langbased(
|
||||
text_show_chinese=
|
||||
r"I want you to act as a scientific English-Chinese translator, "
|
||||
r"I will provide you with some paragraphs in one language "
|
||||
r"and your task is to accurately and academically translate the paragraphs only into the other language. "
|
||||
r"Do not repeat the original provided paragraphs after translation. "
|
||||
r"You should use artificial intelligence tools, "
|
||||
r"such as natural language processing, and rhetorical knowledge "
|
||||
r"and experience about effective writing techniques to reply. "
|
||||
r"I'll give you my paragraphs as follows, tell me what language it is written in, and then translate:",
|
||||
text_show_english=
|
||||
r"你是经验丰富的翻译，请把以下学术文章段落翻译成中文，"
|
||||
r"并同时充分考虑中文的语法、清晰、简洁和整体可读性，"
|
||||
r"必要时，你可以修改整个句子的顺序以确保翻译后的段落符合中文的语言习惯。"
|
||||
r"你需要翻译的文本如下："
|
||||
) + "\n\n",
|
||||
"Prefix": r"I want you to act as a scientific English-Chinese translator, " +
|
||||
r"I will provide you with some paragraphs in one language " +
|
||||
r"and your task is to accurately and academically translate the paragraphs only into the other language. " +
|
||||
r"Do not repeat the original provided paragraphs after translation. " +
|
||||
r"You should use artificial intelligence tools, " +
|
||||
r"such as natural language processing, and rhetorical knowledge " +
|
||||
r"and experience about effective writing techniques to reply. " +
|
||||
r"I'll give you my paragraphs as follows, tell me what language it is written in, and then translate:" + "\n\n",
|
||||
"Suffix": r"",
|
||||
},
|
||||
|
||||
|
||||
|
||||
|
||||
"英译中": {
|
||||
"Prefix": r"翻译成地道的中文：" + "\n\n",
|
||||
"Suffix": r"",
|
||||
"Visible": False,
|
||||
},
|
||||
|
||||
|
||||
|
||||
|
||||
"找图片": {
|
||||
"Prefix": r"我需要你找一张网络图片。使用Unsplash API(https://source.unsplash.com/960x640/?<英语关键词>)获取图片URL，"
|
||||
r"然后请使用Markdown格式封装，并且不要有反斜线，不要用代码块。现在，请按以下描述给我发送图片：" + "\n\n",
|
||||
"Suffix": r"",
|
||||
"Visible": False,
|
||||
},
|
||||
|
||||
|
||||
|
||||
|
||||
"解释代码": {
|
||||
"Prefix": r"请解释以下代码：" + "\n```\n",
|
||||
"Suffix": "\n```\n",
|
||||
},
|
||||
|
||||
|
||||
|
||||
|
||||
"参考文献转Bib": {
|
||||
"Prefix": r"Here are some bibliography items, please transform them into bibtex style."
|
||||
r"Note that, reference styles maybe more than one kind, you should transform each item correctly."
|
||||
@@ -161,11 +140,7 @@ def handle_core_functionality(additional_fn, inputs, history, chatbot):
|
||||
if "PreProcess" in core_functional[additional_fn]:
|
||||
if core_functional[additional_fn]["PreProcess"] is not None:
|
||||
inputs = core_functional[additional_fn]["PreProcess"](inputs) # 获取预处理函数（如果有的话）
|
||||
# 为字符串加上上面定义的前缀和后缀。
|
||||
inputs = apply_gpt_academic_string_mask_langbased(
|
||||
string = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"],
|
||||
lang_reference = inputs,
|
||||
)
|
||||
inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
|
||||
if core_functional[additional_fn].get("AutoClearHistory", False):
|
||||
history = []
|
||||
return inputs, history
|
||||
|
||||
@@ -15,35 +15,27 @@ 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.Latex全文翻译 import Latex中译英
|
||||
from crazy_functions.Latex全文翻译 import Latex英译中
|
||||
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
|
||||
|
||||
|
||||
function_plugins = {
|
||||
"虚空终端": {
|
||||
@@ -79,14 +71,6 @@ 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）": {
|
||||
"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
|
||||
},
|
||||
"批量总结Word文档": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
@@ -198,8 +182,7 @@ def get_crazy_functions():
|
||||
"Group": "对话",
|
||||
"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",
|
||||
@@ -211,16 +194,14 @@ def get_crazy_functions():
|
||||
"Group": "对话",
|
||||
"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",
|
||||
@@ -256,7 +237,13 @@ def get_crazy_functions():
|
||||
"Info": "对英文Latex项目全文进行润色处理 | 输入参数为路径或上传压缩包",
|
||||
"Function": HotReload(Latex英文润色),
|
||||
},
|
||||
|
||||
"英文Latex项目全文纠错（输入路径或上传压缩包）": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Info": "对英文Latex项目全文进行纠错处理 | 输入参数为路径或上传压缩包",
|
||||
"Function": HotReload(Latex英文纠错),
|
||||
},
|
||||
"中文Latex项目全文润色（输入路径或上传压缩包）": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
@@ -265,14 +252,6 @@ def get_crazy_functions():
|
||||
"Function": HotReload(Latex中文润色),
|
||||
},
|
||||
# 已经被新插件取代
|
||||
# "英文Latex项目全文纠错（输入路径或上传压缩包）": {
|
||||
# "Group": "学术",
|
||||
# "Color": "stop",
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Info": "对英文Latex项目全文进行纠错处理 | 输入参数为路径或上传压缩包",
|
||||
# "Function": HotReload(Latex英文纠错),
|
||||
# },
|
||||
# 已经被新插件取代
|
||||
# "Latex项目全文中译英（输入路径或上传压缩包）": {
|
||||
# "Group": "学术",
|
||||
# "Color": "stop",
|
||||
@@ -295,52 +274,8 @@ 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:
|
||||
from crazy_functions.下载arxiv论文翻译摘要 import 下载arxiv论文并翻译摘要
|
||||
@@ -513,7 +448,7 @@ 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(
|
||||
{
|
||||
@@ -586,6 +521,56 @@ 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
|
||||
|
||||
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),
|
||||
}
|
||||
}
|
||||
)
|
||||
from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
|
||||
|
||||
function_plugins.update(
|
||||
{
|
||||
"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),
|
||||
}
|
||||
}
|
||||
)
|
||||
function_plugins.update(
|
||||
{
|
||||
"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, 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
|
||||
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
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
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
|
||||
"""
|
||||
@@ -1,222 +0,0 @@
|
||||
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'
|
||||
|
||||
def write_chat_to_file(chatbot, history=None, file_name=None):
|
||||
"""
|
||||
将对话记录history以Markdown格式写入文件中。如果没有指定文件名，则使用当前时间生成文件名。
|
||||
"""
|
||||
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 = ""
|
||||
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 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)
|
||||
|
||||
promote_file_to_downloadzone(fp, rename_file=file_name, chatbot=chatbot)
|
||||
return '对话历史写入：' + fp
|
||||
|
||||
def gen_file_preview(file_name):
|
||||
try:
|
||||
with open(file_name, 'r', encoding='utf8') as f:
|
||||
file_content = f.read()
|
||||
# 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')
|
||||
history = history.strip('<code>')
|
||||
history = history.strip('</code>')
|
||||
history = history.split("\n>>>")
|
||||
return list(filter(lambda x:x!="", history))[0][:100]
|
||||
except:
|
||||
return ""
|
||||
|
||||
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
|
||||
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。"])
|
||||
return chatbot, history
|
||||
|
||||
@CatchException
|
||||
def 对话历史存档(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）
|
||||
"""
|
||||
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。"))
|
||||
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()
|
||||
replace_path = "."
|
||||
return str.replace(current_path, replace_path)
|
||||
|
||||
@CatchException
|
||||
def 载入对话历史存档(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）
|
||||
"""
|
||||
from .crazy_utils import get_files_from_everything
|
||||
success, file_manifest, _ = get_files_from_everything(txt, type='.html')
|
||||
|
||||
if not success:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
import glob
|
||||
local_history = "<br/>".join([
|
||||
"`"+hide_cwd(f)+f" ({gen_file_preview(f)})"+"`"
|
||||
for f in glob.glob(
|
||||
f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html',
|
||||
recursive=True
|
||||
)])
|
||||
chatbot.append([f"正在查找对话历史文件（html格式）: {txt}", f"找不到任何html文件: {txt}。但本地存储了以下历史文件，您可以将任意一个文件路径粘贴到输入区，然后重试：<br/>{local_history}"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
try:
|
||||
chatbot, history = read_file_to_chat(chatbot, history, file_manifest[0])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
except:
|
||||
chatbot.append([f"载入对话历史文件", f"对话历史文件损坏！"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
@CatchException
|
||||
def 删除所有本地对话历史记录(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）
|
||||
"""
|
||||
|
||||
import glob, os
|
||||
local_history = "<br/>".join([
|
||||
"`"+hide_cwd(f)+"`"
|
||||
for f in glob.glob(
|
||||
f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html', recursive=True
|
||||
)])
|
||||
for f in glob.glob(f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html', recursive=True):
|
||||
os.remove(f)
|
||||
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
|
||||
|
||||
|
||||
@@ -1,122 +0,0 @@
|
||||
from toolbox import CatchException, update_ui
|
||||
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
|
||||
from functools import lru_cache
|
||||
|
||||
|
||||
@lru_cache
|
||||
def get_auth_ip():
|
||||
try:
|
||||
external_ip = urllib.request.urlopen('https://v4.ident.me/').read().decode('utf8')
|
||||
return external_ip
|
||||
except:
|
||||
return '114.114.114.114'
|
||||
|
||||
def searxng_request(query, proxies):
|
||||
url = 'https://cloud-1.agent-matrix.com/' # 请替换为实际的API URL
|
||||
params = {
|
||||
'q': query, # 搜索查询
|
||||
'format': 'json', # 输出格式为JSON
|
||||
'language': 'zh', # 搜索语言
|
||||
}
|
||||
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)
|
||||
if response.status_code == 200:
|
||||
json_result = response.json()
|
||||
for result in json_result['results']:
|
||||
item = {
|
||||
"title": result["title"],
|
||||
"content": result["content"],
|
||||
"link": result["url"],
|
||||
}
|
||||
results.append(item)
|
||||
return results
|
||||
else:
|
||||
raise ValueError("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):
|
||||
"""
|
||||
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）
|
||||
"""
|
||||
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}",
|
||||
"[Local Message] 请注意，您正在调用一个[函数插件]的模板，该模板可以实现ChatGPT联网信息综合。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。您若希望分享新的功能模组，请不吝PR！"))
|
||||
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
|
||||
|
||||
# ------------- < 第1步：爬取搜索引擎的结果 > -------------
|
||||
from toolbox import get_conf
|
||||
proxies = get_conf('proxies')
|
||||
urls = searxng_request(txt, proxies)
|
||||
history = []
|
||||
if len(urls) == 0:
|
||||
chatbot.append((f"结论：{txt}",
|
||||
"[Local Message] 受到google限制，无法从google获取信息！"))
|
||||
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
|
||||
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
|
||||
for index, url in enumerate(urls[:max_search_result]):
|
||||
res = scrape_text(url['link'], proxies)
|
||||
history.extend([f"第{index}份搜索结果：", res])
|
||||
chatbot.append([f"第{index}份搜索结果：", res[:500]+"......"])
|
||||
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
|
||||
|
||||
# ------------- < 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=model_info[llm_kwargs['llm_model']]['max_token']*3//4
|
||||
)
|
||||
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
|
||||
|
||||
@@ -1,548 +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 = 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 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 ------------->
|
||||
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 ------------->
|
||||
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 ------------->
|
||||
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)
|
||||
@@ -46,7 +46,7 @@ class PaperFileGroup():
|
||||
manifest.append(path + '.polish.tex')
|
||||
f.write(res)
|
||||
return manifest
|
||||
|
||||
|
||||
def zip_result(self):
|
||||
import os, time
|
||||
folder = os.path.dirname(self.file_paths[0])
|
||||
@@ -59,7 +59,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
|
||||
|
||||
# <-------- 读取Latex文件，删除其中的所有注释 ---------->
|
||||
# <-------- 读取Latex文件，删除其中的所有注释 ---------->
|
||||
pfg = PaperFileGroup()
|
||||
|
||||
for index, fp in enumerate(file_manifest):
|
||||
@@ -73,31 +73,31 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
pfg.file_paths.append(fp)
|
||||
pfg.file_contents.append(clean_tex_content)
|
||||
|
||||
# <-------- 拆分过长的latex文件 ---------->
|
||||
# <-------- 拆分过长的latex文件 ---------->
|
||||
pfg.run_file_split(max_token_limit=1024)
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
|
||||
|
||||
# <-------- 多线程润色开始 ---------->
|
||||
# <-------- 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." +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
|
||||
r"Answer me only with the revised text:" +
|
||||
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. " +
|
||||
r"Answer me only with the revised text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
inputs_show_user_array = [f"Polish {f}" for f in pfg.sp_file_tag]
|
||||
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：" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
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)]
|
||||
|
||||
@@ -113,7 +113,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
scroller_max_len = 80
|
||||
)
|
||||
|
||||
# <-------- 文本碎片重组为完整的tex文件，整理结果为压缩包 ---------->
|
||||
# <-------- 文本碎片重组为完整的tex文件，整理结果为压缩包 ---------->
|
||||
try:
|
||||
pfg.sp_file_result = []
|
||||
for i_say, gpt_say in zip(gpt_response_collection[0::2], gpt_response_collection[1::2]):
|
||||
@@ -124,7 +124,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
|
||||
# <-------- 整理结果，退出 ---------->
|
||||
# <-------- 整理结果，退出 ---------->
|
||||
create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
|
||||
res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
|
||||
promote_file_to_downloadzone(res, chatbot=chatbot)
|
||||
@@ -135,11 +135,11 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
|
||||
|
||||
@CatchException
|
||||
def Latex英文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def Latex英文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"对整个Latex项目进行润色。函数插件贡献者: Binary-Husky。（注意，此插件不调用Latex，如果有Latex环境，请使用「Latex英文纠错+高亮修正位置(需Latex)插件」"])
|
||||
"对整个Latex项目进行润色。函数插件贡献者: Binary-Husky。（注意，此插件不调用Latex，如果有Latex环境，请使用“Latex英文纠错+高亮”插件）"])
|
||||
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
|
||||
@@ -173,7 +173,7 @@ def Latex英文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
|
||||
|
||||
|
||||
@CatchException
|
||||
def Latex中文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def Latex中文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
@@ -209,7 +209,7 @@ def Latex中文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
|
||||
|
||||
|
||||
@CatchException
|
||||
def Latex英文纠错(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def Latex英文纠错(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
|
||||
@@ -39,7 +39,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
import time, os, re
|
||||
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
|
||||
# <-------- 读取Latex文件，删除其中的所有注释 ---------->
|
||||
# <-------- 读取Latex文件，删除其中的所有注释 ---------->
|
||||
pfg = PaperFileGroup()
|
||||
|
||||
for index, fp in enumerate(file_manifest):
|
||||
@@ -53,11 +53,11 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
pfg.file_paths.append(fp)
|
||||
pfg.file_contents.append(clean_tex_content)
|
||||
|
||||
# <-------- 拆分过长的latex文件 ---------->
|
||||
# <-------- 拆分过长的latex文件 ---------->
|
||||
pfg.run_file_split(max_token_limit=1024)
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
|
||||
# <-------- 抽取摘要 ---------->
|
||||
# <-------- 抽取摘要 ---------->
|
||||
# if language == 'en':
|
||||
# abs_extract_inputs = f"Please write an abstract for this paper"
|
||||
|
||||
@@ -70,14 +70,14 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
# sys_prompt="Your job is to collect information from materials。",
|
||||
# )
|
||||
|
||||
# <-------- 多线程润色开始 ---------->
|
||||
# <-------- 多线程润色开始 ---------->
|
||||
if language == 'en->zh':
|
||||
inputs_array = ["Below is a section from an English academic paper, translate it into Chinese, do not modify any latex command such as \section, \cite and equations:" +
|
||||
inputs_array = ["Below is a section from an English academic paper, translate it into Chinese, do not modify any latex command such as \section, \cite and equations:" +
|
||||
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." for _ in range(n_split)]
|
||||
elif language == 'zh->en':
|
||||
inputs_array = [f"Below is a section from a Chinese academic paper, translate it into English, do not modify any latex command such as \section, \cite and equations:" +
|
||||
inputs_array = [f"Below is a section from a Chinese academic paper, translate it into English, do not modify any latex command such as \section, \cite and equations:" +
|
||||
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." for _ in range(n_split)]
|
||||
@@ -93,7 +93,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
scroller_max_len = 80
|
||||
)
|
||||
|
||||
# <-------- 整理结果，退出 ---------->
|
||||
# <-------- 整理结果，退出 ---------->
|
||||
create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
|
||||
res = write_history_to_file(gpt_response_collection, create_report_file_name)
|
||||
promote_file_to_downloadzone(res, chatbot=chatbot)
|
||||
@@ -106,7 +106,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
|
||||
|
||||
@CatchException
|
||||
def Latex英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def Latex英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
@@ -143,7 +143,7 @@ def Latex英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
|
||||
|
||||
|
||||
@CatchException
|
||||
def Latex中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def Latex中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
|
||||
306
crazy_functions/Latex输出PDF结果.py
Normal file
306
crazy_functions/Latex输出PDF结果.py
Normal file
@@ -0,0 +1,306 @@
|
||||
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
|
||||
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
|
||||
|
||||
# <-------------- 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, web_port):
|
||||
# <-------------- 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, web_port):
|
||||
# <-------------- 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 = []
|
||||
txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
|
||||
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)
|
||||
@@ -35,11 +35,7 @@ def gpt_academic_generate_oai_reply(
|
||||
class AutoGenGeneral(PluginMultiprocessManager):
|
||||
def gpt_academic_print_override(self, user_proxy, message, sender):
|
||||
# ⭐⭐ run in subprocess
|
||||
try:
|
||||
print_msg = sender.name + "\n\n---\n\n" + message["content"]
|
||||
except:
|
||||
print_msg = sender.name + "\n\n---\n\n" + message
|
||||
self.child_conn.send(PipeCom("show", print_msg))
|
||||
self.child_conn.send(PipeCom("show", sender.name + "\n\n---\n\n" + message["content"]))
|
||||
|
||||
def gpt_academic_get_human_input(self, user_proxy, message):
|
||||
# ⭐⭐ run in subprocess
|
||||
@@ -66,33 +62,33 @@ class AutoGenGeneral(PluginMultiprocessManager):
|
||||
def exe_autogen(self, input):
|
||||
# ⭐⭐ run in subprocess
|
||||
input = input.content
|
||||
code_execution_config = {"work_dir": self.autogen_work_dir, "use_docker": self.use_docker}
|
||||
agents = self.define_agents()
|
||||
user_proxy = None
|
||||
assistant = None
|
||||
for agent_kwargs in agents:
|
||||
agent_cls = agent_kwargs.pop('cls')
|
||||
kwargs = {
|
||||
'llm_config':self.llm_kwargs,
|
||||
'code_execution_config':code_execution_config
|
||||
}
|
||||
kwargs.update(agent_kwargs)
|
||||
agent_handle = agent_cls(**kwargs)
|
||||
agent_handle._print_received_message = lambda a,b: self.gpt_academic_print_override(agent_kwargs, a, b)
|
||||
for d in agent_handle._reply_func_list:
|
||||
if hasattr(d['reply_func'],'__name__') and d['reply_func'].__name__ == 'generate_oai_reply':
|
||||
d['reply_func'] = gpt_academic_generate_oai_reply
|
||||
if agent_kwargs['name'] == 'user_proxy':
|
||||
agent_handle.get_human_input = lambda a: self.gpt_academic_get_human_input(user_proxy, a)
|
||||
user_proxy = agent_handle
|
||||
if agent_kwargs['name'] == 'assistant': assistant = agent_handle
|
||||
try:
|
||||
if user_proxy is None or assistant is None: raise Exception("用户代理或助理代理未定义")
|
||||
with ProxyNetworkActivate("AutoGen"):
|
||||
with ProxyNetworkActivate("AutoGen"):
|
||||
code_execution_config = {"work_dir": self.autogen_work_dir, "use_docker": self.use_docker}
|
||||
agents = self.define_agents()
|
||||
user_proxy = None
|
||||
assistant = None
|
||||
for agent_kwargs in agents:
|
||||
agent_cls = agent_kwargs.pop('cls')
|
||||
kwargs = {
|
||||
'llm_config':self.llm_kwargs,
|
||||
'code_execution_config':code_execution_config
|
||||
}
|
||||
kwargs.update(agent_kwargs)
|
||||
agent_handle = agent_cls(**kwargs)
|
||||
agent_handle._print_received_message = lambda a,b: self.gpt_academic_print_override(agent_kwargs, a, b)
|
||||
for d in agent_handle._reply_func_list:
|
||||
if hasattr(d['reply_func'],'__name__') and d['reply_func'].__name__ == 'generate_oai_reply':
|
||||
d['reply_func'] = gpt_academic_generate_oai_reply
|
||||
if agent_kwargs['name'] == 'user_proxy':
|
||||
agent_handle.get_human_input = lambda a: self.gpt_academic_get_human_input(user_proxy, a)
|
||||
user_proxy = agent_handle
|
||||
if agent_kwargs['name'] == 'assistant': assistant = agent_handle
|
||||
try:
|
||||
if user_proxy is None or assistant is None: raise Exception("用户代理或助理代理未定义")
|
||||
user_proxy.initiate_chat(assistant, message=input)
|
||||
except Exception as e:
|
||||
tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
self.child_conn.send(PipeCom("done", "AutoGen 执行失败: \n\n" + tb_str))
|
||||
except Exception as e:
|
||||
tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
self.child_conn.send(PipeCom("done", "AutoGen 执行失败: \n\n" + tb_str))
|
||||
|
||||
def subprocess_worker(self, child_conn):
|
||||
# ⭐⭐ run in subprocess
|
||||
|
||||
@@ -9,7 +9,7 @@ class PipeCom:
|
||||
|
||||
|
||||
class PluginMultiprocessManager:
|
||||
def __init__(self, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def __init__(self, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# ⭐ run in main process
|
||||
self.autogen_work_dir = os.path.join(get_log_folder("autogen"), gen_time_str())
|
||||
self.previous_work_dir_files = {}
|
||||
@@ -18,7 +18,7 @@ class PluginMultiprocessManager:
|
||||
self.chatbot = chatbot
|
||||
self.history = history
|
||||
self.system_prompt = system_prompt
|
||||
# self.user_request = user_request
|
||||
# self.web_port = web_port
|
||||
self.alive = True
|
||||
self.use_docker = get_conf("AUTOGEN_USE_DOCKER")
|
||||
self.last_user_input = ""
|
||||
@@ -72,7 +72,7 @@ class PluginMultiprocessManager:
|
||||
if file_type.lower() in ['png', 'jpg']:
|
||||
image_path = os.path.abspath(fp)
|
||||
self.chatbot.append([
|
||||
'检测到新生图像:',
|
||||
'检测到新生图像:',
|
||||
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
|
||||
])
|
||||
yield from update_ui(chatbot=self.chatbot, history=self.history)
|
||||
@@ -114,21 +114,21 @@ class PluginMultiprocessManager:
|
||||
self.cnt = 1
|
||||
self.parent_conn = self.launch_subprocess_with_pipe() # ⭐⭐⭐
|
||||
repeated, cmd_to_autogen = self.send_command(txt)
|
||||
if txt == 'exit':
|
||||
if txt == 'exit':
|
||||
self.chatbot.append([f"结束", "结束信号已明确，终止AutoGen程序。"])
|
||||
yield from update_ui(chatbot=self.chatbot, history=self.history)
|
||||
self.terminate()
|
||||
return "terminate"
|
||||
|
||||
|
||||
# patience = 10
|
||||
|
||||
|
||||
while True:
|
||||
time.sleep(0.5)
|
||||
if not self.alive:
|
||||
# the heartbeat watchdog might have it killed
|
||||
self.terminate()
|
||||
return "terminate"
|
||||
if self.parent_conn.poll():
|
||||
if self.parent_conn.poll():
|
||||
self.feed_heartbeat_watchdog()
|
||||
if "[GPT-Academic] 等待中" in self.chatbot[-1][-1]:
|
||||
self.chatbot.pop(-1) # remove the last line
|
||||
@@ -152,8 +152,8 @@ class PluginMultiprocessManager:
|
||||
yield from update_ui(chatbot=self.chatbot, history=self.history)
|
||||
if msg.cmd == "interact":
|
||||
yield from self.overwatch_workdir_file_change()
|
||||
self.chatbot.append([f"程序抵达用户反馈节点.", msg.content +
|
||||
"\n\n等待您的进一步指令." +
|
||||
self.chatbot.append([f"程序抵达用户反馈节点.", msg.content +
|
||||
"\n\n等待您的进一步指令." +
|
||||
"\n\n(1) 一般情况下您不需要说什么, 清空输入区, 然后直接点击“提交”以继续. " +
|
||||
"\n\n(2) 如果您需要补充些什么, 输入要反馈的内容, 直接点击“提交”以继续. " +
|
||||
"\n\n(3) 如果您想终止程序, 输入exit, 直接点击“提交”以终止AutoGen并解锁. "
|
||||
|
||||
@@ -8,7 +8,7 @@ class WatchDog():
|
||||
self.interval = interval
|
||||
self.msg = msg
|
||||
self.kill_dog = False
|
||||
|
||||
|
||||
def watch(self):
|
||||
while True:
|
||||
if self.kill_dog: break
|
||||
|
||||
@@ -32,7 +32,7 @@ def string_to_options(arguments):
|
||||
return args
|
||||
|
||||
@CatchException
|
||||
def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 微调数据集生成(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
|
||||
@@ -40,13 +40,13 @@ def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
args = plugin_kwargs.get("advanced_arg", None)
|
||||
if args is None:
|
||||
if args is None:
|
||||
chatbot.append(("没给定指令", "退出"))
|
||||
yield from update_ui(chatbot=chatbot, history=history); return
|
||||
else:
|
||||
@@ -69,7 +69,7 @@ def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
sys_prompt_array=[arguments.system_prompt for _ in (batch)],
|
||||
max_workers=10 # OpenAI所允许的最大并行过载
|
||||
)
|
||||
|
||||
|
||||
with open(txt+'.generated.json', 'a+', encoding='utf8') as f:
|
||||
for b, r in zip(batch, res[1::2]):
|
||||
f.write(json.dumps({"content":b, "summary":r}, ensure_ascii=False)+'\n')
|
||||
@@ -80,7 +80,7 @@ def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
|
||||
|
||||
@CatchException
|
||||
def 启动微调(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 启动微调(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
|
||||
@@ -88,19 +88,19 @@ def 启动微调(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
import subprocess
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
args = plugin_kwargs.get("advanced_arg", None)
|
||||
if args is None:
|
||||
if args is None:
|
||||
chatbot.append(("没给定指令", "退出"))
|
||||
yield from update_ui(chatbot=chatbot, history=history); return
|
||||
else:
|
||||
arguments = string_to_options(arguments=args)
|
||||
|
||||
|
||||
|
||||
|
||||
pre_seq_len = arguments.pre_seq_len # 128
|
||||
|
||||
@@ -12,7 +12,7 @@ def input_clipping(inputs, history, max_token_limit):
|
||||
mode = 'input-and-history'
|
||||
# 当 输入部分的token占比 小于 全文的一半时，只裁剪历史
|
||||
input_token_num = get_token_num(inputs)
|
||||
if input_token_num < max_token_limit//2:
|
||||
if input_token_num < max_token_limit//2:
|
||||
mode = 'only-history'
|
||||
max_token_limit = max_token_limit - input_token_num
|
||||
|
||||
@@ -21,7 +21,7 @@ def input_clipping(inputs, history, max_token_limit):
|
||||
n_token = get_token_num('\n'.join(everything))
|
||||
everything_token = [get_token_num(e) for e in everything]
|
||||
delta = max(everything_token) // 16 # 截断时的颗粒度
|
||||
|
||||
|
||||
while n_token > max_token_limit:
|
||||
where = np.argmax(everything_token)
|
||||
encoded = enc.encode(everything[where], disallowed_special=())
|
||||
@@ -38,9 +38,9 @@ def input_clipping(inputs, history, max_token_limit):
|
||||
return inputs, history
|
||||
|
||||
def request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs, inputs_show_user, llm_kwargs,
|
||||
inputs, inputs_show_user, llm_kwargs,
|
||||
chatbot, history, sys_prompt, refresh_interval=0.2,
|
||||
handle_token_exceed=True,
|
||||
handle_token_exceed=True,
|
||||
retry_times_at_unknown_error=2,
|
||||
):
|
||||
"""
|
||||
@@ -77,7 +77,7 @@ def request_gpt_model_in_new_thread_with_ui_alive(
|
||||
exceeded_cnt = 0
|
||||
while True:
|
||||
# watchdog error
|
||||
if len(mutable) >= 2 and (time.time()-mutable[1]) > watch_dog_patience:
|
||||
if len(mutable) >= 2 and (time.time()-mutable[1]) > watch_dog_patience:
|
||||
raise RuntimeError("检测到程序终止。")
|
||||
try:
|
||||
# 【第一种情况】：顺利完成
|
||||
@@ -135,29 +135,17 @@ 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
|
||||
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
|
||||
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 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'): return True
|
||||
return False
|
||||
|
||||
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,
|
||||
inputs_array, inputs_show_user_array, llm_kwargs,
|
||||
chatbot, history_array, sys_prompt_array,
|
||||
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,
|
||||
@@ -201,7 +189,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
# 屏蔽掉 chatglm的多线程，可能会导致严重卡顿
|
||||
if not can_multi_process(llm_kwargs['llm_model']):
|
||||
max_workers = 1
|
||||
|
||||
|
||||
executor = ThreadPoolExecutor(max_workers=max_workers)
|
||||
n_frag = len(inputs_array)
|
||||
# 用户反馈
|
||||
@@ -226,7 +214,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
try:
|
||||
# 【第一种情况】：顺利完成
|
||||
gpt_say = predict_no_ui_long_connection(
|
||||
inputs=inputs, llm_kwargs=llm_kwargs, history=history,
|
||||
inputs=inputs, llm_kwargs=llm_kwargs, history=history,
|
||||
sys_prompt=sys_prompt, observe_window=mutable[index], console_slience=True
|
||||
)
|
||||
mutable[index][2] = "已成功"
|
||||
@@ -258,7 +246,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
print(tb_str)
|
||||
gpt_say += f"[Local Message] 警告，线程{index}在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n"
|
||||
if len(mutable[index][0]) > 0: gpt_say += "此线程失败前收到的回答：\n\n" + mutable[index][0]
|
||||
if retry_op > 0:
|
||||
if retry_op > 0:
|
||||
retry_op -= 1
|
||||
wait = random.randint(5, 20)
|
||||
if ("Rate limit reached" in tb_str) or ("Too Many Requests" in tb_str):
|
||||
@@ -296,11 +284,12 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
# 在前端打印些好玩的东西
|
||||
for thread_index, _ in enumerate(worker_done):
|
||||
print_something_really_funny = "[ ...`"+mutable[thread_index][0][-scroller_max_len:].\
|
||||
replace('\n', '').replace('`', '.').replace(' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
|
||||
replace('\n', '').replace('`', '.').replace(
|
||||
' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
|
||||
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'
|
||||
if not done else f'`{mutable[thread_index][2]}`\n\n'
|
||||
stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
|
||||
if not done else f'`{mutable[thread_index][2]}`\n\n'
|
||||
for thread_index, done, obs in zip(range(len(worker_done)), worker_done, observe_win)])
|
||||
# 在前端打印些好玩的东西
|
||||
chatbot[-1] = [chatbot[-1][0], f'多线程操作已经开始，完成情况: \n\n{stat_str}' + ''.join(['.']*(cnt % 10+1))]
|
||||
@@ -314,7 +303,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
for inputs_show_user, f in zip(inputs_show_user_array, futures):
|
||||
gpt_res = f.result()
|
||||
gpt_response_collection.extend([inputs_show_user, gpt_res])
|
||||
|
||||
|
||||
# 是否在结束时，在界面上显示结果
|
||||
if show_user_at_complete:
|
||||
for inputs_show_user, f in zip(inputs_show_user_array, futures):
|
||||
@@ -349,7 +338,7 @@ 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
|
||||
@@ -364,7 +353,7 @@ def read_and_clean_pdf_text(fp):
|
||||
if wtf['size'] not in fsize_statiscs: fsize_statiscs[wtf['size']] = 0
|
||||
fsize_statiscs[wtf['size']] += len(wtf['text'])
|
||||
return max(fsize_statiscs, key=fsize_statiscs.get)
|
||||
|
||||
|
||||
def ffsize_same(a,b):
|
||||
"""
|
||||
提取字体大小是否近似相等
|
||||
@@ -400,7 +389,7 @@ def read_and_clean_pdf_text(fp):
|
||||
if index == 0:
|
||||
page_one_meta = [" ".join(["".join([wtf['text'] for wtf in l['spans']]) for l in t['lines']]).replace(
|
||||
'- ', '') for t in text_areas['blocks'] if 'lines' in t]
|
||||
|
||||
|
||||
############################## <第 2 步，获取正文主字体> ##################################
|
||||
try:
|
||||
fsize_statiscs = {}
|
||||
@@ -416,7 +405,7 @@ def read_and_clean_pdf_text(fp):
|
||||
mega_sec = []
|
||||
sec = []
|
||||
for index, line in enumerate(meta_line):
|
||||
if index == 0:
|
||||
if index == 0:
|
||||
sec.append(line[fc])
|
||||
continue
|
||||
if REMOVE_FOOT_NOTE:
|
||||
@@ -513,12 +502,12 @@ def get_files_from_everything(txt, type): # type='.md'
|
||||
"""
|
||||
这个函数是用来获取指定目录下所有指定类型（如.md）的文件，并且对于网络上的文件，也可以获取它。
|
||||
下面是对每个参数和返回值的说明：
|
||||
参数
|
||||
- txt: 路径或网址，表示要搜索的文件或者文件夹路径或网络上的文件。
|
||||
参数
|
||||
- txt: 路径或网址，表示要搜索的文件或者文件夹路径或网络上的文件。
|
||||
- type: 字符串，表示要搜索的文件类型。默认是.md。
|
||||
返回值
|
||||
- success: 布尔值，表示函数是否成功执行。
|
||||
- file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。
|
||||
返回值
|
||||
- success: 布尔值，表示函数是否成功执行。
|
||||
- file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。
|
||||
- project_folder: 字符串，表示文件所在的文件夹路径。如果是网络上的文件，就是临时文件夹的路径。
|
||||
该函数详细注释已添加，请确认是否满足您的需要。
|
||||
"""
|
||||
@@ -568,7 +557,7 @@ 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:
|
||||
@@ -582,7 +571,7 @@ class nougat_interface():
|
||||
def NOUGAT_parse_pdf(self, fp, chatbot, history):
|
||||
from toolbox import update_ui_lastest_msg
|
||||
|
||||
yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
|
||||
yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
self.threadLock.acquire()
|
||||
import glob, threading, os
|
||||
@@ -590,10 +579,9 @@ class nougat_interface():
|
||||
dst = os.path.join(get_log_folder(plugin_name='nougat'), gen_time_str())
|
||||
os.makedirs(dst)
|
||||
|
||||
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）",
|
||||
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()
|
||||
|
||||
@@ -1,122 +0,0 @@
|
||||
import os
|
||||
from textwrap import indent
|
||||
|
||||
class FileNode:
|
||||
def __init__(self, name):
|
||||
self.name = name
|
||||
self.children = []
|
||||
self.is_leaf = False
|
||||
self.level = 0
|
||||
self.parenting_ship = []
|
||||
self.comment = ""
|
||||
self.comment_maxlen_show = 50
|
||||
|
||||
@staticmethod
|
||||
def add_linebreaks_at_spaces(string, interval=10):
|
||||
return '\n'.join(string[i:i+interval] for i in range(0, len(string), interval))
|
||||
|
||||
def sanitize_comment(self, comment):
|
||||
if len(comment) > self.comment_maxlen_show: suf = '...'
|
||||
else: suf = ''
|
||||
comment = comment[:self.comment_maxlen_show]
|
||||
comment = comment.replace('\"', '').replace('`', '').replace('\n', '').replace('`', '').replace('$', '')
|
||||
comment = self.add_linebreaks_at_spaces(comment, 10)
|
||||
return '`' + comment + suf + '`'
|
||||
|
||||
def add_file(self, file_path, file_comment):
|
||||
directory_names, file_name = os.path.split(file_path)
|
||||
current_node = self
|
||||
level = 1
|
||||
if directory_names == "":
|
||||
new_node = FileNode(file_name)
|
||||
current_node.children.append(new_node)
|
||||
new_node.is_leaf = True
|
||||
new_node.comment = self.sanitize_comment(file_comment)
|
||||
new_node.level = level
|
||||
current_node = new_node
|
||||
else:
|
||||
dnamesplit = directory_names.split(os.sep)
|
||||
for i, directory_name in enumerate(dnamesplit):
|
||||
found_child = False
|
||||
level += 1
|
||||
for child in current_node.children:
|
||||
if child.name == directory_name:
|
||||
current_node = child
|
||||
found_child = True
|
||||
break
|
||||
if not found_child:
|
||||
new_node = FileNode(directory_name)
|
||||
current_node.children.append(new_node)
|
||||
new_node.level = level - 1
|
||||
current_node = new_node
|
||||
term = FileNode(file_name)
|
||||
term.level = level
|
||||
term.comment = self.sanitize_comment(file_comment)
|
||||
term.is_leaf = True
|
||||
current_node.children.append(term)
|
||||
|
||||
def print_files_recursively(self, level=0, code="R0"):
|
||||
print(' '*level + self.name + ' ' + str(self.is_leaf) + ' ' + str(self.level))
|
||||
for j, child in enumerate(self.children):
|
||||
child.print_files_recursively(level=level+1, code=code+str(j))
|
||||
self.parenting_ship.extend(child.parenting_ship)
|
||||
p1 = f"""{code}[\"🗎{self.name}\"]""" if self.is_leaf else f"""{code}[[\"📁{self.name}\"]]"""
|
||||
p2 = """ --> """
|
||||
p3 = f"""{code+str(j)}[\"🗎{child.name}\"]""" if child.is_leaf else f"""{code+str(j)}[[\"📁{child.name}\"]]"""
|
||||
edge_code = p1 + p2 + p3
|
||||
if edge_code in self.parenting_ship:
|
||||
continue
|
||||
self.parenting_ship.append(edge_code)
|
||||
if self.comment != "":
|
||||
pc1 = f"""{code}[\"🗎{self.name}\"]""" if self.is_leaf else f"""{code}[[\"📁{self.name}\"]]"""
|
||||
pc2 = f""" -.-x """
|
||||
pc3 = f"""C{code}[\"{self.comment}\"]:::Comment"""
|
||||
edge_code = pc1 + pc2 + pc3
|
||||
self.parenting_ship.append(edge_code)
|
||||
|
||||
|
||||
MERMAID_TEMPLATE = r"""
|
||||
```mermaid
|
||||
flowchart LR
|
||||
%% <gpt_academic_hide_mermaid_code> 一个特殊标记，用于在生成mermaid图表时隐藏代码块
|
||||
classDef Comment stroke-dasharray: 5 5
|
||||
subgraph {graph_name}
|
||||
{relationship}
|
||||
end
|
||||
```
|
||||
"""
|
||||
|
||||
def build_file_tree_mermaid_diagram(file_manifest, file_comments, graph_name):
|
||||
# Create the root node
|
||||
file_tree_struct = FileNode("root")
|
||||
# Build the tree structure
|
||||
for file_path, file_comment in zip(file_manifest, file_comments):
|
||||
file_tree_struct.add_file(file_path, file_comment)
|
||||
file_tree_struct.print_files_recursively()
|
||||
cc = "\n".join(file_tree_struct.parenting_ship)
|
||||
ccc = indent(cc, prefix=" "*8)
|
||||
return MERMAID_TEMPLATE.format(graph_name=graph_name, relationship=ccc)
|
||||
|
||||
if __name__ == "__main__":
|
||||
# File manifest
|
||||
file_manifest = [
|
||||
"cradle_void_terminal.ipynb",
|
||||
"tests/test_utils.py",
|
||||
"tests/test_plugins.py",
|
||||
"tests/test_llms.py",
|
||||
"config.py",
|
||||
"build/ChatGLM-6b-onnx-u8s8/chatglm-6b-int8-onnx-merged/model_weights_0.bin",
|
||||
"crazy_functions/latex_fns/latex_actions.py",
|
||||
"crazy_functions/latex_fns/latex_toolbox.py"
|
||||
]
|
||||
file_comments = [
|
||||
"根据位置和名称，可能是一个模块的初始化文件根据位置和名称，可能是一个模块的初始化文件根据位置和名称，可能是一个模块的初始化文件",
|
||||
"包含一些用于文本处理和模型微调的函数和装饰器包含一些用于文本处理和模型微调的函数和装饰器包含一些用于文本处理和模型微调的函数和装饰器",
|
||||
"用于构建HTML报告的类和方法用于构建HTML报告的类和方法用于构建HTML报告的类和方法",
|
||||
"包含了用于文本切分的函数，以及处理PDF文件的示例代码包含了用于文本切分的函数，以及处理PDF文件的示例代码包含了用于文本切分的函数，以及处理PDF文件的示例代码",
|
||||
"用于解析和翻译PDF文件的功能和相关辅助函数用于解析和翻译PDF文件的功能和相关辅助函数用于解析和翻译PDF文件的功能和相关辅助函数",
|
||||
"是一个包的初始化文件，用于初始化包的属性和导入模块是一个包的初始化文件，用于初始化包的属性和导入模块是一个包的初始化文件，用于初始化包的属性和导入模块",
|
||||
"用于加载和分割文件中的文本的通用文件加载器用于加载和分割文件中的文本的通用文件加载器用于加载和分割文件中的文本的通用文件加载器",
|
||||
"包含了用于构建和管理向量数据库的函数和类包含了用于构建和管理向量数据库的函数和类包含了用于构建和管理向量数据库的函数和类",
|
||||
]
|
||||
print(build_file_tree_mermaid_diagram(file_manifest, file_comments, "项目文件树"))
|
||||
@@ -8,7 +8,7 @@ import random
|
||||
|
||||
class MiniGame_ASCII_Art(GptAcademicGameBaseState):
|
||||
def step(self, prompt, chatbot, history):
|
||||
if self.step_cnt == 0:
|
||||
if self.step_cnt == 0:
|
||||
chatbot.append(["我画你猜（动物）", "请稍等..."])
|
||||
else:
|
||||
if prompt.strip() == 'exit':
|
||||
|
||||
@@ -88,8 +88,8 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
self.story = []
|
||||
chatbot.append(["互动写故事", f"这次的故事开头是：{self.headstart}"])
|
||||
self.sys_prompt_ = '你是一个想象力丰富的杰出作家。正在与你的朋友互动，一起写故事，因此你每次写的故事段落应少于300字（结局除外）。'
|
||||
|
||||
|
||||
|
||||
|
||||
def generate_story_image(self, story_paragraph):
|
||||
try:
|
||||
from crazy_functions.图片生成 import gen_image
|
||||
@@ -98,13 +98,13 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
return f'<br/><div align="center"><img src="file={image_path}"></div>'
|
||||
except:
|
||||
return ''
|
||||
|
||||
|
||||
def step(self, prompt, chatbot, history):
|
||||
|
||||
|
||||
"""
|
||||
首先，处理游戏初始化等特殊情况
|
||||
"""
|
||||
if self.step_cnt == 0:
|
||||
if self.step_cnt == 0:
|
||||
self.begin_game_step_0(prompt, chatbot, history)
|
||||
self.lock_plugin(chatbot)
|
||||
self.cur_task = 'head_start'
|
||||
@@ -132,7 +132,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
inputs_ = prompts_hs.format(headstart=self.headstart)
|
||||
history_ = []
|
||||
story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs_, '故事开头', self.llm_kwargs,
|
||||
inputs_, '故事开头', self.llm_kwargs,
|
||||
chatbot, history_, self.sys_prompt_
|
||||
)
|
||||
self.story.append(story_paragraph)
|
||||
@@ -147,7 +147,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
|
||||
history_ = []
|
||||
self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs_, '请在以下几种故事走向中，选择一种（当然，您也可以选择给出其他故事走向）：', self.llm_kwargs,
|
||||
inputs_, '请在以下几种故事走向中，选择一种（当然，您也可以选择给出其他故事走向）：', self.llm_kwargs,
|
||||
chatbot,
|
||||
history_,
|
||||
self.sys_prompt_
|
||||
@@ -166,7 +166,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
inputs_ = prompts_resume.format(previously_on_story=previously_on_story, choice=self.next_choices, user_choice=prompt)
|
||||
history_ = []
|
||||
story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs_, f'下一段故事（您的选择是：{prompt}）。', self.llm_kwargs,
|
||||
inputs_, f'下一段故事（您的选择是：{prompt}）。', self.llm_kwargs,
|
||||
chatbot, history_, self.sys_prompt_
|
||||
)
|
||||
self.story.append(story_paragraph)
|
||||
@@ -181,10 +181,10 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
|
||||
history_ = []
|
||||
self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs_,
|
||||
'请在以下几种故事走向中，选择一种。当然，您也可以给出您心中的其他故事走向。另外，如果您希望剧情立即收尾，请输入剧情走向，并以“剧情收尾”四个字提示程序。', self.llm_kwargs,
|
||||
chatbot,
|
||||
history_,
|
||||
inputs_,
|
||||
'请在以下几种故事走向中，选择一种。当然，您也可以给出您心中的其他故事走向。另外，如果您希望剧情立即收尾，请输入剧情走向，并以“剧情收尾”四个字提示程序。', self.llm_kwargs,
|
||||
chatbot,
|
||||
history_,
|
||||
self.sys_prompt_
|
||||
)
|
||||
self.cur_task = 'user_choice'
|
||||
@@ -200,7 +200,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
inputs_ = prompts_terminate.format(previously_on_story=previously_on_story, user_choice=prompt)
|
||||
history_ = []
|
||||
story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs_, f'故事收尾（您的选择是：{prompt}）。', self.llm_kwargs,
|
||||
inputs_, f'故事收尾（您的选择是：{prompt}）。', self.llm_kwargs,
|
||||
chatbot, history_, self.sys_prompt_
|
||||
)
|
||||
# # 配图
|
||||
|
||||
@@ -5,7 +5,7 @@ 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:
|
||||
if len(matches) == 1:
|
||||
return "```" + matches[0] + "```" # code block
|
||||
raise RuntimeError("GPT is not generating proper code.")
|
||||
|
||||
@@ -13,10 +13,10 @@ def is_same_thing(a, b, llm_kwargs):
|
||||
from pydantic import BaseModel, Field
|
||||
class IsSameThing(BaseModel):
|
||||
is_same_thing: bool = Field(description="determine whether two objects are same thing.", default=False)
|
||||
|
||||
def run_gpt_fn(inputs, sys_prompt, history=[]):
|
||||
|
||||
def run_gpt_fn(inputs, sys_prompt, history=[]):
|
||||
return predict_no_ui_long_connection(
|
||||
inputs=inputs, llm_kwargs=llm_kwargs,
|
||||
inputs=inputs, llm_kwargs=llm_kwargs,
|
||||
history=history, sys_prompt=sys_prompt, observe_window=[]
|
||||
)
|
||||
|
||||
@@ -24,7 +24,7 @@ def is_same_thing(a, b, llm_kwargs):
|
||||
inputs_01 = "Identity whether the user input and the target is the same thing: \n target object: {a} \n user input object: {b} \n\n\n".format(a=a, b=b)
|
||||
inputs_01 += "\n\n\n Note that the user may describe the target object with a different language, e.g. cat and 猫 are the same thing."
|
||||
analyze_res_cot_01 = run_gpt_fn(inputs_01, "", [])
|
||||
|
||||
|
||||
inputs_02 = inputs_01 + gpt_json_io.format_instructions
|
||||
analyze_res = run_gpt_fn(inputs_02, "", [inputs_01, analyze_res_cot_01])
|
||||
|
||||
|
||||
@@ -41,11 +41,11 @@ def is_function_successfully_generated(fn_path, class_name, return_dict):
|
||||
# Now you can create an instance of the class
|
||||
instance = some_class()
|
||||
return_dict['success'] = True
|
||||
return
|
||||
return
|
||||
except:
|
||||
return_dict['traceback'] = trimmed_format_exc()
|
||||
return
|
||||
|
||||
|
||||
def subprocess_worker(code, file_path, return_dict):
|
||||
return_dict['result'] = None
|
||||
return_dict['success'] = False
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import platform
|
||||
import platform
|
||||
import pickle
|
||||
import multiprocessing
|
||||
|
||||
|
||||
@@ -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)
|
||||
@@ -89,7 +89,7 @@ class GptJsonIO():
|
||||
error + "\n\n" + \
|
||||
"Now, fix this json string. \n\n"
|
||||
return prompt
|
||||
|
||||
|
||||
def generate_output_auto_repair(self, response, gpt_gen_fn):
|
||||
"""
|
||||
response: string containing canidate json
|
||||
|
||||
@@ -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
|
||||
@@ -91,16 +90,16 @@ class LatexPaperSplit():
|
||||
"版权归原文作者所有。翻译内容可靠性无保障，请仔细鉴别并以原文为准。" + \
|
||||
"项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
|
||||
# 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加REAME中的QQ联系开发者）
|
||||
self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\"
|
||||
self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\"
|
||||
self.title = "unknown"
|
||||
self.abstract = "unknown"
|
||||
|
||||
def read_title_and_abstract(self, txt):
|
||||
try:
|
||||
title, abstract = find_title_and_abs(txt)
|
||||
if title is not None:
|
||||
if title is not None:
|
||||
self.title = title.replace('\n', ' ').replace('\\\\', ' ').replace(' ', '').replace(' ', '')
|
||||
if abstract is not None:
|
||||
if abstract is not None:
|
||||
self.abstract = abstract.replace('\n', ' ').replace('\\\\', ' ').replace(' ', '').replace(' ', '')
|
||||
except:
|
||||
pass
|
||||
@@ -112,7 +111,7 @@ class LatexPaperSplit():
|
||||
result_string = ""
|
||||
node_cnt = 0
|
||||
line_cnt = 0
|
||||
|
||||
|
||||
for node in self.nodes:
|
||||
if node.preserve:
|
||||
line_cnt += node.string.count('\n')
|
||||
@@ -145,7 +144,7 @@ class LatexPaperSplit():
|
||||
return result_string
|
||||
|
||||
|
||||
def split(self, txt, project_folder, opts):
|
||||
def split(self, txt, project_folder, opts):
|
||||
"""
|
||||
break down latex file to a linked list,
|
||||
each node use a preserve flag to indicate whether it should
|
||||
@@ -156,7 +155,7 @@ class LatexPaperSplit():
|
||||
manager = multiprocessing.Manager()
|
||||
return_dict = manager.dict()
|
||||
p = multiprocessing.Process(
|
||||
target=split_subprocess,
|
||||
target=split_subprocess,
|
||||
args=(txt, project_folder, return_dict, opts))
|
||||
p.start()
|
||||
p.join()
|
||||
@@ -218,13 +217,13 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
|
||||
from ..crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
from .latex_actions import LatexPaperFileGroup, LatexPaperSplit
|
||||
|
||||
# <-------- 寻找主tex文件 ---------->
|
||||
# <-------- 寻找主tex文件 ---------->
|
||||
maintex = find_main_tex_file(file_manifest, mode)
|
||||
chatbot.append((f"定位主Latex文件", f'[Local Message] 分析结果：该项目的Latex主文件是{maintex}, 如果分析错误, 请立即终止程序, 删除或修改歧义文件, 然后重试。主程序即将开始, 请稍候。'))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
time.sleep(3)
|
||||
|
||||
# <-------- 读取Latex文件, 将多文件tex工程融合为一个巨型tex ---------->
|
||||
# <-------- 读取Latex文件, 将多文件tex工程融合为一个巨型tex ---------->
|
||||
main_tex_basename = os.path.basename(maintex)
|
||||
assert main_tex_basename.endswith('.tex')
|
||||
main_tex_basename_bare = main_tex_basename[:-4]
|
||||
@@ -241,13 +240,13 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
|
||||
with open(project_folder + '/merge.tex', 'w', encoding='utf-8', errors='replace') as f:
|
||||
f.write(merged_content)
|
||||
|
||||
# <-------- 精细切分latex文件 ---------->
|
||||
# <-------- 精细切分latex文件 ---------->
|
||||
chatbot.append((f"Latex文件融合完成", f'[Local Message] 正在精细切分latex文件，这需要一段时间计算，文档越长耗时越长，请耐心等待。'))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
lps = LatexPaperSplit()
|
||||
lps.read_title_and_abstract(merged_content)
|
||||
res = lps.split(merged_content, project_folder, opts) # 消耗时间的函数
|
||||
# <-------- 拆分过长的latex片段 ---------->
|
||||
# <-------- 拆分过长的latex片段 ---------->
|
||||
pfg = LatexPaperFileGroup()
|
||||
for index, r in enumerate(res):
|
||||
pfg.file_paths.append('segment-' + str(index))
|
||||
@@ -256,17 +255,17 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
|
||||
pfg.run_file_split(max_token_limit=1024)
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
|
||||
# <-------- 根据需要切换prompt ---------->
|
||||
# <-------- 根据需要切换prompt ---------->
|
||||
inputs_array, sys_prompt_array = switch_prompt(pfg, mode)
|
||||
inputs_show_user_array = [f"{mode} {f}" for f in pfg.sp_file_tag]
|
||||
|
||||
if os.path.exists(pj(project_folder,'temp.pkl')):
|
||||
|
||||
# <-------- 【仅调试】如果存在调试缓存文件，则跳过GPT请求环节 ---------->
|
||||
# <-------- 【仅调试】如果存在调试缓存文件，则跳过GPT请求环节 ---------->
|
||||
pfg = objload(file=pj(project_folder,'temp.pkl'))
|
||||
|
||||
else:
|
||||
# <-------- gpt 多线程请求 ---------->
|
||||
# <-------- gpt 多线程请求 ---------->
|
||||
history_array = [[""] for _ in range(n_split)]
|
||||
# LATEX_EXPERIMENTAL, = get_conf('LATEX_EXPERIMENTAL')
|
||||
# if LATEX_EXPERIMENTAL:
|
||||
@@ -285,32 +284,32 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
|
||||
scroller_max_len = 40
|
||||
)
|
||||
|
||||
# <-------- 文本碎片重组为完整的tex片段 ---------->
|
||||
# <-------- 文本碎片重组为完整的tex片段 ---------->
|
||||
pfg.sp_file_result = []
|
||||
for i_say, gpt_say, orig_content in zip(gpt_response_collection[0::2], gpt_response_collection[1::2], pfg.sp_file_contents):
|
||||
pfg.sp_file_result.append(gpt_say)
|
||||
pfg.merge_result()
|
||||
|
||||
# <-------- 临时存储用于调试 ---------->
|
||||
# <-------- 临时存储用于调试 ---------->
|
||||
pfg.get_token_num = None
|
||||
objdump(pfg, file=pj(project_folder,'temp.pkl'))
|
||||
|
||||
write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
|
||||
|
||||
# <-------- 写出文件 ---------->
|
||||
# <-------- 写出文件 ---------->
|
||||
msg = f"当前大语言模型: {llm_kwargs['llm_model']}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
|
||||
final_tex = lps.merge_result(pfg.file_result, mode, msg)
|
||||
objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl'))
|
||||
|
||||
with open(project_folder + f'/merge_{mode}.tex', 'w', encoding='utf-8', errors='replace') as f:
|
||||
if mode != 'translate_zh' or "binary" in final_tex: f.write(final_tex)
|
||||
|
||||
|
||||
|
||||
# <-------- 整理结果, 退出 ---------->
|
||||
# <-------- 整理结果, 退出 ---------->
|
||||
chatbot.append((f"完成了吗？", 'GPT结果已输出, 即将编译PDF'))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------- 返回 ---------->
|
||||
# <-------- 返回 ---------->
|
||||
return project_folder + f'/merge_{mode}.tex'
|
||||
|
||||
|
||||
@@ -363,7 +362,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
|
||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history) # 刷新Gradio前端界面
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
|
||||
|
||||
|
||||
if ok and os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf')):
|
||||
# 只有第二步成功，才能继续下面的步骤
|
||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history) # 刷新Gradio前端界面
|
||||
@@ -394,9 +393,9 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
original_pdf_success = os.path.exists(pj(work_folder_original, f'{main_file_original}.pdf'))
|
||||
modified_pdf_success = os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf'))
|
||||
diff_pdf_success = os.path.exists(pj(work_folder, f'merge_diff.pdf'))
|
||||
results_ += f"原始PDF编译是否成功: {original_pdf_success};"
|
||||
results_ += f"转化PDF编译是否成功: {modified_pdf_success};"
|
||||
results_ += f"对比PDF编译是否成功: {diff_pdf_success};"
|
||||
results_ += f"原始PDF编译是否成功: {original_pdf_success};"
|
||||
results_ += f"转化PDF编译是否成功: {modified_pdf_success};"
|
||||
results_ += f"对比PDF编译是否成功: {diff_pdf_success};"
|
||||
yield from update_ui_lastest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
|
||||
|
||||
if diff_pdf_success:
|
||||
@@ -410,7 +409,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
shutil.copyfile(result_pdf, pj(work_folder, '..', 'translation', 'translate_zh.pdf'))
|
||||
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI
|
||||
# 将两个PDF拼接
|
||||
if original_pdf_success:
|
||||
if original_pdf_success:
|
||||
try:
|
||||
from .latex_toolbox import merge_pdfs
|
||||
concat_pdf = pj(work_folder_modified, f'comparison.pdf')
|
||||
@@ -426,7 +425,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
if n_fix>=max_try: break
|
||||
n_fix += 1
|
||||
can_retry, main_file_modified, buggy_lines = remove_buggy_lines(
|
||||
file_path=pj(work_folder_modified, f'{main_file_modified}.tex'),
|
||||
file_path=pj(work_folder_modified, f'{main_file_modified}.tex'),
|
||||
log_path=pj(work_folder_modified, f'{main_file_modified}.log'),
|
||||
tex_name=f'{main_file_modified}.tex',
|
||||
tex_name_pure=f'{main_file_modified}',
|
||||
@@ -446,14 +445,14 @@ def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
|
||||
import shutil
|
||||
from crazy_functions.pdf_fns.report_gen_html import construct_html
|
||||
from toolbox import gen_time_str
|
||||
ch = construct_html()
|
||||
ch = construct_html()
|
||||
orig = ""
|
||||
trans = ""
|
||||
final = []
|
||||
for c,r in zip(sp_file_contents, sp_file_result):
|
||||
for c,r in zip(sp_file_contents, sp_file_result):
|
||||
final.append(c)
|
||||
final.append(r)
|
||||
for i, k in enumerate(final):
|
||||
for i, k in enumerate(final):
|
||||
if i%2==0:
|
||||
orig = k
|
||||
if i%2==1:
|
||||
|
||||
@@ -1,38 +0,0 @@
|
||||
import pickle
|
||||
|
||||
|
||||
class SafeUnpickler(pickle.Unpickler):
|
||||
|
||||
def get_safe_classes(self):
|
||||
from .latex_actions import LatexPaperFileGroup, LatexPaperSplit
|
||||
# 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,
|
||||
}
|
||||
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()
|
||||
if f'{module}.{name}' in self.safe_classes:
|
||||
return self.safe_classes[f'{module}.{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()
|
||||
@@ -85,8 +85,8 @@ def write_numpy_to_wave(filename, rate, data, add_header=False):
|
||||
|
||||
def is_speaker_speaking(vad, data, sample_rate):
|
||||
# Function to detect if the speaker is speaking
|
||||
# The WebRTC VAD only accepts 16-bit mono PCM audio,
|
||||
# sampled at 8000, 16000, 32000 or 48000 Hz.
|
||||
# The WebRTC VAD only accepts 16-bit mono PCM audio,
|
||||
# sampled at 8000, 16000, 32000 or 48000 Hz.
|
||||
# A frame must be either 10, 20, or 30 ms in duration:
|
||||
frame_duration = 30
|
||||
n_bit_each = int(sample_rate * frame_duration / 1000)*2 # x2 because audio is 16 bit (2 bytes)
|
||||
@@ -94,7 +94,7 @@ def is_speaker_speaking(vad, data, sample_rate):
|
||||
for t in range(len(data)):
|
||||
if t!=0 and t % n_bit_each == 0:
|
||||
res_list.append(vad.is_speech(data[t-n_bit_each:t], sample_rate))
|
||||
|
||||
|
||||
info = ''.join(['^' if r else '.' for r in res_list])
|
||||
info = info[:10]
|
||||
if any(res_list):
|
||||
@@ -186,10 +186,10 @@ class AliyunASR():
|
||||
keep_alive_last_send_time = time.time()
|
||||
while not self.stop:
|
||||
# time.sleep(self.capture_interval)
|
||||
audio = rad.read(uuid.hex)
|
||||
audio = rad.read(uuid.hex)
|
||||
if audio is not None:
|
||||
# convert to pcm file
|
||||
temp_file = f'{temp_folder}/{uuid.hex}.pcm' #
|
||||
temp_file = f'{temp_folder}/{uuid.hex}.pcm' #
|
||||
dsdata = change_sample_rate(audio, rad.rate, NEW_SAMPLERATE) # 48000 --> 16000
|
||||
write_numpy_to_wave(temp_file, NEW_SAMPLERATE, dsdata)
|
||||
# read pcm binary
|
||||
|
||||
@@ -3,12 +3,12 @@ from scipy import interpolate
|
||||
|
||||
def Singleton(cls):
|
||||
_instance = {}
|
||||
|
||||
|
||||
def _singleton(*args, **kargs):
|
||||
if cls not in _instance:
|
||||
_instance[cls] = cls(*args, **kargs)
|
||||
return _instance[cls]
|
||||
|
||||
|
||||
return _singleton
|
||||
|
||||
|
||||
@@ -39,7 +39,7 @@ class RealtimeAudioDistribution():
|
||||
else:
|
||||
res = None
|
||||
return res
|
||||
|
||||
|
||||
def change_sample_rate(audio, old_sr, new_sr):
|
||||
duration = audio.shape[0] / old_sr
|
||||
|
||||
|
||||
@@ -40,7 +40,7 @@ class GptAcademicState():
|
||||
|
||||
class GptAcademicGameBaseState():
|
||||
"""
|
||||
1. first init: __init__ ->
|
||||
1. first init: __init__ ->
|
||||
"""
|
||||
def init_game(self, chatbot, lock_plugin):
|
||||
self.plugin_name = None
|
||||
@@ -53,7 +53,7 @@ class GptAcademicGameBaseState():
|
||||
raise ValueError("callback_fn is None")
|
||||
chatbot._cookies['lock_plugin'] = self.callback_fn
|
||||
self.dump_state(chatbot)
|
||||
|
||||
|
||||
def get_plugin_name(self):
|
||||
if self.plugin_name is None:
|
||||
raise ValueError("plugin_name is None")
|
||||
@@ -71,7 +71,7 @@ class GptAcademicGameBaseState():
|
||||
state = chatbot._cookies.get(f'plugin_state/{plugin_name}', None)
|
||||
if state is not None:
|
||||
state = pickle.loads(state)
|
||||
else:
|
||||
else:
|
||||
state = cls()
|
||||
state.init_game(chatbot, lock_plugin)
|
||||
state.plugin_name = plugin_name
|
||||
@@ -79,7 +79,7 @@ class GptAcademicGameBaseState():
|
||||
state.chatbot = chatbot
|
||||
state.callback_fn = callback_fn
|
||||
return state
|
||||
|
||||
|
||||
def continue_game(self, prompt, chatbot, history):
|
||||
# 游戏主体
|
||||
yield from self.step(prompt, chatbot, history)
|
||||
|
||||
@@ -35,7 +35,7 @@ def cut(limit, get_token_fn, txt_tocut, must_break_at_empty_line, break_anyway=F
|
||||
remain_txt_to_cut_storage = ""
|
||||
# 为了加速计算，我们采样一个特殊的手段。当 remain_txt_to_cut > `_max` 时， 我们把 _max 后的文字转存至 remain_txt_to_cut_storage
|
||||
remain_txt_to_cut, remain_txt_to_cut_storage = maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage)
|
||||
|
||||
|
||||
while True:
|
||||
if get_token_fn(remain_txt_to_cut) <= limit:
|
||||
# 如果剩余文本的token数小于限制，那么就不用切了
|
||||
|
||||
@@ -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
|
||||
@@ -64,15 +64,15 @@ def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chat
|
||||
# 再做一个小修改：重新修改当前part的标题，默认用英文的
|
||||
cur_value += value
|
||||
translated_res_array.append(cur_value)
|
||||
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + translated_res_array,
|
||||
file_basename = f"{gen_time_str()}-translated_only.md",
|
||||
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + translated_res_array,
|
||||
file_basename = f"{gen_time_str()}-translated_only.md",
|
||||
file_fullname = None,
|
||||
auto_caption = False)
|
||||
promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot)
|
||||
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
|
||||
@@ -138,17 +138,17 @@ 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)
|
||||
|
||||
# -=-=-=-=-=-=-=-= 写出HTML文件 -=-=-=-=-=-=-=-=
|
||||
ch = construct_html()
|
||||
ch = construct_html()
|
||||
orig = ""
|
||||
trans = ""
|
||||
gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
|
||||
for i,k in enumerate(gpt_response_collection_html):
|
||||
for i,k in enumerate(gpt_response_collection_html):
|
||||
if i%2==0:
|
||||
gpt_response_collection_html[i] = inputs_show_user_array[i//2]
|
||||
else:
|
||||
@@ -159,7 +159,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
|
||||
|
||||
final = ["", "", "一、论文概况", "", "Abstract", paper_meta_info, "二、论文翻译", ""]
|
||||
final.extend(gpt_response_collection_html)
|
||||
for i, k in enumerate(final):
|
||||
for i, k in enumerate(final):
|
||||
if i%2==0:
|
||||
orig = k
|
||||
if i%2==1:
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
@@ -1,211 +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)
|
||||
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")
|
||||
@@ -28,7 +28,7 @@ EMBEDDING_DEVICE = "cpu"
|
||||
|
||||
# 基于上下文的prompt模版，请务必保留"{question}"和"{context}"
|
||||
PROMPT_TEMPLATE = """已知信息：
|
||||
{context}
|
||||
{context}
|
||||
|
||||
根据上述已知信息，简洁和专业的来回答用户的问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题” 或 “没有提供足够的相关信息”，不允许在答案中添加编造成分，答案请使用中文。 问题是：{question}"""
|
||||
|
||||
@@ -58,7 +58,7 @@ OPEN_CROSS_DOMAIN = False
|
||||
def similarity_search_with_score_by_vector(
|
||||
self, embedding: List[float], k: int = 4
|
||||
) -> List[Tuple[Document, float]]:
|
||||
|
||||
|
||||
def seperate_list(ls: List[int]) -> List[List[int]]:
|
||||
lists = []
|
||||
ls1 = [ls[0]]
|
||||
@@ -200,7 +200,7 @@ class LocalDocQA:
|
||||
return vs_path, loaded_files
|
||||
else:
|
||||
raise RuntimeError("文件加载失败，请检查文件格式是否正确")
|
||||
|
||||
|
||||
def get_loaded_file(self, vs_path):
|
||||
ds = self.vector_store.docstore
|
||||
return set([ds._dict[k].metadata['source'].split(vs_path)[-1] for k in ds._dict])
|
||||
@@ -290,10 +290,10 @@ class knowledge_archive_interface():
|
||||
self.threadLock.acquire()
|
||||
# import uuid
|
||||
self.current_id = id
|
||||
self.qa_handle, self.kai_path = construct_vector_store(
|
||||
vs_id=self.current_id,
|
||||
self.qa_handle, self.kai_path = construct_vector_store(
|
||||
vs_id=self.current_id,
|
||||
vs_path=vs_path,
|
||||
files=file_manifest,
|
||||
files=file_manifest,
|
||||
sentence_size=100,
|
||||
history=[],
|
||||
one_conent="",
|
||||
@@ -304,7 +304,7 @@ class knowledge_archive_interface():
|
||||
|
||||
def get_current_archive_id(self):
|
||||
return self.current_id
|
||||
|
||||
|
||||
def get_loaded_file(self, vs_path):
|
||||
return self.qa_handle.get_loaded_file(vs_path)
|
||||
|
||||
@@ -312,10 +312,10 @@ class knowledge_archive_interface():
|
||||
self.threadLock.acquire()
|
||||
if not self.current_id == id:
|
||||
self.current_id = id
|
||||
self.qa_handle, self.kai_path = construct_vector_store(
|
||||
vs_id=self.current_id,
|
||||
self.qa_handle, self.kai_path = construct_vector_store(
|
||||
vs_id=self.current_id,
|
||||
vs_path=vs_path,
|
||||
files=[],
|
||||
files=[],
|
||||
sentence_size=100,
|
||||
history=[],
|
||||
one_conent="",
|
||||
@@ -329,7 +329,7 @@ class knowledge_archive_interface():
|
||||
query = txt,
|
||||
vs_path = self.kai_path,
|
||||
score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
|
||||
vector_search_top_k=VECTOR_SEARCH_TOP_K,
|
||||
vector_search_top_k=VECTOR_SEARCH_TOP_K,
|
||||
chunk_conent=True,
|
||||
chunk_size=CHUNK_SIZE,
|
||||
text2vec = self.get_chinese_text2vec(),
|
||||
|
||||
@@ -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)}
|
||||
@@ -35,9 +35,9 @@ def get_recent_file_prompt_support(chatbot):
|
||||
most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
|
||||
path = most_recent_uploaded['path']
|
||||
prompt = "\nAdditional Information:\n"
|
||||
prompt = "In case that this plugin requires a path or a file as argument,"
|
||||
prompt += f"it is important for you to know that the user has recently uploaded a file, located at: `{path}`"
|
||||
prompt += f"Only use it when necessary, otherwise, you can ignore this file."
|
||||
prompt = "In case that this plugin requires a path or a file as argument,"
|
||||
prompt += f"it is important for you to know that the user has recently uploaded a file, located at: `{path}`"
|
||||
prompt += f"Only use it when necessary, otherwise, you can ignore this file."
|
||||
return prompt
|
||||
|
||||
def get_inputs_show_user(inputs, plugin_arr_enum_prompt):
|
||||
@@ -82,7 +82,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
|
||||
msg += "\n但您可以尝试再试一次\n"
|
||||
yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
|
||||
return
|
||||
|
||||
|
||||
# ⭐ ⭐ ⭐ 确认插件参数
|
||||
if not have_any_recent_upload_files(chatbot):
|
||||
appendix_info = ""
|
||||
@@ -99,7 +99,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
|
||||
inputs = f"A plugin named {plugin_sel.plugin_selection} is selected, " + \
|
||||
"you should extract plugin_arg from the user requirement, the user requirement is: \n\n" + \
|
||||
">> " + (txt + appendix_info).rstrip('\n').replace('\n','\n>> ') + '\n\n' + \
|
||||
gpt_json_io.format_instructions
|
||||
gpt_json_io.format_instructions
|
||||
run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(
|
||||
inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
|
||||
plugin_sel = gpt_json_io.generate_output_auto_repair(run_gpt_fn(inputs, ""), run_gpt_fn)
|
||||
|
||||
@@ -10,7 +10,7 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
|
||||
if not ALLOW_RESET_CONFIG:
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
|
||||
lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
|
||||
chatbot=chatbot, history=history, delay=2
|
||||
)
|
||||
return
|
||||
@@ -35,7 +35,7 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
inputs = "Analyze how to change configuration according to following user input, answer me with json: \n\n" + \
|
||||
">> " + txt.rstrip('\n').replace('\n','\n>> ') + '\n\n' + \
|
||||
gpt_json_io.format_instructions
|
||||
|
||||
|
||||
run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(
|
||||
inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
|
||||
user_intention = gpt_json_io.generate_output_auto_repair(run_gpt_fn(inputs, ""), run_gpt_fn)
|
||||
@@ -45,11 +45,11 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
ok = (explicit_conf in txt)
|
||||
if ok:
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}",
|
||||
lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}",
|
||||
chatbot=chatbot, history=history, delay=1
|
||||
)
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}\n\n正在修改配置中",
|
||||
lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}\n\n正在修改配置中",
|
||||
chatbot=chatbot, history=history, delay=2
|
||||
)
|
||||
|
||||
@@ -69,7 +69,7 @@ def modify_configuration_reboot(txt, llm_kwargs, plugin_kwargs, chatbot, history
|
||||
ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
|
||||
if not ALLOW_RESET_CONFIG:
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
|
||||
lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
|
||||
chatbot=chatbot, history=history, delay=2
|
||||
)
|
||||
return
|
||||
|
||||
@@ -6,7 +6,7 @@ class VoidTerminalState():
|
||||
|
||||
def reset_state(self):
|
||||
self.has_provided_explaination = False
|
||||
|
||||
|
||||
def lock_plugin(self, chatbot):
|
||||
chatbot._cookies['lock_plugin'] = 'crazy_functions.虚空终端->虚空终端'
|
||||
chatbot._cookies['plugin_state'] = pickle.dumps(self)
|
||||
|
||||
@@ -130,7 +130,7 @@ def get_name(_url_):
|
||||
|
||||
|
||||
@CatchException
|
||||
def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
|
||||
CRAZY_FUNCTION_INFO = "下载arxiv论文并翻译摘要，函数插件作者[binary-husky]。正在提取摘要并下载PDF文档……"
|
||||
import glob
|
||||
@@ -144,8 +144,8 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
|
||||
try:
|
||||
import bs4
|
||||
except:
|
||||
report_exception(chatbot, history,
|
||||
a = f"解析项目: {txt}",
|
||||
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 beautifulsoup4```。")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
@@ -157,12 +157,12 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
|
||||
try:
|
||||
pdf_path, info = download_arxiv_(txt)
|
||||
except:
|
||||
report_exception(chatbot, history,
|
||||
a = f"解析项目: {txt}",
|
||||
report_exception(chatbot, history,
|
||||
a = f"解析项目: {txt}",
|
||||
b = f"下载pdf文件未成功")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# 翻译摘要等
|
||||
i_say = f"请你阅读以下学术论文相关的材料，提取摘要，翻译为中文。材料如下：{str(info)}"
|
||||
i_say_show_user = f'请你阅读以下学术论文相关的材料，提取摘要，翻译为中文。论文：{pdf_path}'
|
||||
|
||||
@@ -5,16 +5,16 @@ from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
from crazy_functions.game_fns.game_utils import get_code_block, is_same_thing
|
||||
|
||||
@CatchException
|
||||
def 随机小游戏(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 随机小游戏(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
from crazy_functions.game_fns.game_interactive_story import MiniGame_ResumeStory
|
||||
# 清空历史
|
||||
history = []
|
||||
# 选择游戏
|
||||
cls = MiniGame_ResumeStory
|
||||
# 如果之前已经初始化了游戏实例，则继续该实例；否则重新初始化
|
||||
state = cls.sync_state(chatbot,
|
||||
llm_kwargs,
|
||||
cls,
|
||||
state = cls.sync_state(chatbot,
|
||||
llm_kwargs,
|
||||
cls,
|
||||
plugin_name='MiniGame_ResumeStory',
|
||||
callback_fn='crazy_functions.互动小游戏->随机小游戏',
|
||||
lock_plugin=True
|
||||
@@ -23,16 +23,16 @@ def 随机小游戏(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
|
||||
|
||||
@CatchException
|
||||
def 随机小游戏1(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 随机小游戏1(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
from crazy_functions.game_fns.game_ascii_art import MiniGame_ASCII_Art
|
||||
# 清空历史
|
||||
history = []
|
||||
# 选择游戏
|
||||
cls = MiniGame_ASCII_Art
|
||||
# 如果之前已经初始化了游戏实例，则继续该实例；否则重新初始化
|
||||
state = cls.sync_state(chatbot,
|
||||
llm_kwargs,
|
||||
cls,
|
||||
state = cls.sync_state(chatbot,
|
||||
llm_kwargs,
|
||||
cls,
|
||||
plugin_name='MiniGame_ASCII_Art',
|
||||
callback_fn='crazy_functions.互动小游戏->随机小游戏1',
|
||||
lock_plugin=True
|
||||
|
||||
@@ -3,7 +3,7 @@ from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
|
||||
|
||||
@CatchException
|
||||
def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 交互功能模板函数(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
|
||||
@@ -11,7 +11,7 @@ def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
chatbot.append(("这是什么功能？", "交互功能函数模板。在执行完成之后, 可以将自身的状态存储到cookie中, 等待用户的再次调用。"))
|
||||
@@ -38,7 +38,7 @@ def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
inputs=inputs_show_user=f"Extract all image urls in this html page, pick the first 5 images and show them with markdown format: \n\n {page_return}"
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=inputs, inputs_show_user=inputs_show_user,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt="When you want to show an image, use markdown format. e.g. . If there are no image url provided, answer 'no image url provided'"
|
||||
)
|
||||
chatbot[-1] = [chatbot[-1][0], gpt_say]
|
||||
|
||||
@@ -6,10 +6,10 @@
|
||||
- 将图像转为灰度图像
|
||||
- 将csv文件转excel表格
|
||||
|
||||
Testing:
|
||||
- Crop the image, keeping the bottom half.
|
||||
- Swap the blue channel and red channel of the image.
|
||||
- Convert the image to grayscale.
|
||||
Testing:
|
||||
- Crop the image, keeping the bottom half.
|
||||
- Swap the blue channel and red channel of the image.
|
||||
- Convert the image to grayscale.
|
||||
- Convert the CSV file to an Excel spreadsheet.
|
||||
"""
|
||||
|
||||
@@ -29,12 +29,12 @@ import multiprocessing
|
||||
|
||||
templete = """
|
||||
```python
|
||||
import ... # Put dependencies here, e.g. import numpy as np.
|
||||
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
|
||||
# rewrite the function you have just written here
|
||||
...
|
||||
return generated_file_path
|
||||
```
|
||||
@@ -48,7 +48,7 @@ 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:
|
||||
if len(matches) == 1:
|
||||
return matches[0].strip('python') # code block
|
||||
for match in matches:
|
||||
if 'class TerminalFunction' in match:
|
||||
@@ -68,8 +68,8 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
|
||||
|
||||
# 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,
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
|
||||
sys_prompt= r"You are a world-class programmer."
|
||||
)
|
||||
history.extend([i_say, gpt_say])
|
||||
@@ -82,33 +82,33 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
|
||||
]
|
||||
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,
|
||||
inputs=i_say, inputs_show_user=inputs_show_user,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
sys_prompt= r"You are a programmer. You need to replace `...` with valid packages, do not give `...` in your answer!"
|
||||
)
|
||||
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,
|
||||
# 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
|
||||
# # # 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,
|
||||
# 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
|
||||
|
||||
|
||||
@@ -117,7 +117,7 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
|
||||
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:',
|
||||
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>'
|
||||
])
|
||||
@@ -139,7 +139,7 @@ def get_recent_file_prompt_support(chatbot):
|
||||
return path
|
||||
|
||||
@CatchException
|
||||
def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 函数动态生成(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
|
||||
@@ -147,7 +147,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
|
||||
# 清空历史
|
||||
@@ -177,7 +177,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
|
||||
yield from update_ui_lastest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
|
||||
return # 2. 如果没有文件
|
||||
|
||||
|
||||
# 读取文件
|
||||
file_type = file_list[0].split('.')[-1]
|
||||
|
||||
@@ -185,7 +185,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
if is_the_upload_folder(txt):
|
||||
yield from update_ui_lastest_msg(f"请在输入框内填写需求, 然后再次点击该插件! 至于您的文件，不用担心, 文件路径 {txt} 已经被记忆. ", chatbot, history, 1)
|
||||
return
|
||||
|
||||
|
||||
# 开始干正事
|
||||
MAX_TRY = 3
|
||||
for j in range(MAX_TRY): # 最多重试5次
|
||||
@@ -238,7 +238,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
# 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):
|
||||
@@ -248,5 +248,5 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
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
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ from .crazy_utils import input_clipping
|
||||
import copy, json
|
||||
|
||||
@CatchException
|
||||
def 命令行助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 命令行助手(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
|
||||
@@ -12,7 +12,7 @@ def 命令行助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
# 清空历史, 以免输入溢出
|
||||
history = []
|
||||
@@ -21,8 +21,8 @@ def 命令行助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
|
||||
i_say = "请写bash命令实现以下功能：" + txt
|
||||
# 开始
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=txt,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
inputs=i_say, inputs_show_user=txt,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt="你是一个Linux大师级用户。注意，当我要求你写bash命令时，尽可能地仅用一行命令解决我的要求。"
|
||||
)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
@@ -7,7 +7,7 @@ def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2", qual
|
||||
from request_llms.bridge_all import model_info
|
||||
|
||||
proxies = get_conf('proxies')
|
||||
# Set up OpenAI API key and model
|
||||
# Set up OpenAI API key and model
|
||||
api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
|
||||
chat_endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
||||
# 'https://api.openai.com/v1/chat/completions'
|
||||
@@ -93,7 +93,7 @@ def edit_image(llm_kwargs, prompt, image_path, resolution="1024x1024", model="da
|
||||
|
||||
|
||||
@CatchException
|
||||
def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 图片生成_DALLE2(prompt, 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
|
||||
@@ -101,7 +101,7 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
history = [] # 清空历史,以免输入溢出
|
||||
if prompt.strip() == "":
|
||||
@@ -113,7 +113,7 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
resolution = plugin_kwargs.get("advanced_arg", '1024x1024')
|
||||
image_url, image_path = gen_image(llm_kwargs, prompt, resolution)
|
||||
chatbot.append([prompt,
|
||||
chatbot.append([prompt,
|
||||
f'图像中转网址: <br/>`{image_url}`<br/>'+
|
||||
f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
|
||||
f'本地文件地址: <br/>`{image_path}`<br/>'+
|
||||
@@ -123,7 +123,7 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
|
||||
|
||||
|
||||
@CatchException
|
||||
def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史,以免输入溢出
|
||||
if prompt.strip() == "":
|
||||
chatbot.append((prompt, "[Local Message] 图像生成提示为空白，请在“输入区”输入图像生成提示。"))
|
||||
@@ -144,7 +144,7 @@ def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
|
||||
elif part in ['vivid', 'natural']:
|
||||
style = part
|
||||
image_url, image_path = gen_image(llm_kwargs, prompt, resolution, model="dall-e-3", quality=quality, style=style)
|
||||
chatbot.append([prompt,
|
||||
chatbot.append([prompt,
|
||||
f'图像中转网址: <br/>`{image_url}`<br/>'+
|
||||
f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
|
||||
f'本地文件地址: <br/>`{image_path}`<br/>'+
|
||||
@@ -164,7 +164,7 @@ class ImageEditState(GptAcademicState):
|
||||
confirm = (len(file_manifest) >= 1 and file_manifest[0].endswith('.png') and os.path.exists(file_manifest[0]))
|
||||
file = None if not confirm else file_manifest[0]
|
||||
return confirm, file
|
||||
|
||||
|
||||
def lock_plugin(self, chatbot):
|
||||
chatbot._cookies['lock_plugin'] = 'crazy_functions.图片生成->图片修改_DALLE2'
|
||||
self.dump_state(chatbot)
|
||||
@@ -209,7 +209,7 @@ class ImageEditState(GptAcademicState):
|
||||
return all([x['value'] is not None for x in self.req])
|
||||
|
||||
@CatchException
|
||||
def 图片修改_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 图片修改_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# 尚未完成
|
||||
history = [] # 清空历史
|
||||
state = ImageEditState.get_state(chatbot, ImageEditState)
|
||||
|
||||
@@ -21,7 +21,7 @@ def remove_model_prefix(llm):
|
||||
|
||||
|
||||
@CatchException
|
||||
def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 多智能体终端(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
|
||||
@@ -29,7 +29,7 @@ def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
# 检查当前的模型是否符合要求
|
||||
supported_llms = [
|
||||
@@ -50,18 +50,25 @@ def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
return
|
||||
if model_info[llm_kwargs['llm_model']]["endpoint"] is not None: # 如果不是本地模型，加载API_KEY
|
||||
llm_kwargs['api_key'] = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
|
||||
|
||||
|
||||
# 检查当前的模型是否符合要求
|
||||
API_URL_REDIRECT = get_conf('API_URL_REDIRECT')
|
||||
if len(API_URL_REDIRECT) > 0:
|
||||
chatbot.append([f"处理任务: {txt}", f"暂不支持中转."])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
try:
|
||||
import autogen
|
||||
if get_conf("AUTOGEN_USE_DOCKER"):
|
||||
import docker
|
||||
except:
|
||||
chatbot.append([ f"处理任务: {txt}",
|
||||
chatbot.append([ f"处理任务: {txt}",
|
||||
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 pyautogen docker```。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
try:
|
||||
import autogen
|
||||
@@ -72,7 +79,7 @@ def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
chatbot.append([f"处理任务: {txt}", f"缺少docker运行环境！"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# 解锁插件
|
||||
chatbot.get_cookies()['lock_plugin'] = None
|
||||
persistent_class_multi_user_manager = GradioMultiuserManagerForPersistentClasses()
|
||||
@@ -89,7 +96,7 @@ def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
history = []
|
||||
chatbot.append(["正在启动: 多智能体终端", "插件动态生成, 执行开始, 作者 Microsoft & Binary-Husky."])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
executor = AutoGenMath(llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
executor = AutoGenMath(llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port)
|
||||
persistent_class_multi_user_manager.set(persistent_key, executor)
|
||||
exit_reason = yield from executor.main_process_ui_control(txt, create_or_resume="create")
|
||||
|
||||
|
||||
152
crazy_functions/对话历史存档.py
Normal file
152
crazy_functions/对话历史存档.py
Normal file
@@ -0,0 +1,152 @@
|
||||
from toolbox import CatchException, update_ui, promote_file_to_downloadzone, get_log_folder, get_user
|
||||
import re
|
||||
|
||||
f_prefix = 'GPT-Academic对话存档'
|
||||
|
||||
def write_chat_to_file(chatbot, history=None, file_name=None):
|
||||
"""
|
||||
将对话记录history以Markdown格式写入文件中。如果没有指定文件名，则使用当前时间生成文件名。
|
||||
"""
|
||||
import os
|
||||
import time
|
||||
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 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):
|
||||
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:
|
||||
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
|
||||
|
||||
def gen_file_preview(file_name):
|
||||
try:
|
||||
with open(file_name, 'r', encoding='utf8') as f:
|
||||
file_content = f.read()
|
||||
# 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>>>")
|
||||
return list(filter(lambda x:x!="", history))[0][:100]
|
||||
except:
|
||||
return ""
|
||||
|
||||
def read_file_to_chat(chatbot, history, file_name):
|
||||
with open(file_name, 'r', encoding='utf8') as f:
|
||||
file_content = f.read()
|
||||
# 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()
|
||||
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
|
||||
def 对话历史存档(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
|
||||
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
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
|
||||
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
|
||||
|
||||
def hide_cwd(str):
|
||||
import os
|
||||
current_path = os.getcwd()
|
||||
replace_path = "."
|
||||
return str.replace(current_path, replace_path)
|
||||
|
||||
@CatchException
|
||||
def 载入对话历史存档(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
|
||||
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
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
from .crazy_utils import get_files_from_everything
|
||||
success, file_manifest, _ = get_files_from_everything(txt, type='.html')
|
||||
|
||||
if not success:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
import glob
|
||||
local_history = "<br/>".join([
|
||||
"`"+hide_cwd(f)+f" ({gen_file_preview(f)})"+"`"
|
||||
for f in glob.glob(
|
||||
f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html',
|
||||
recursive=True
|
||||
)])
|
||||
chatbot.append([f"正在查找对话历史文件（html格式）: {txt}", f"找不到任何html文件: {txt}。但本地存储了以下历史文件，您可以将任意一个文件路径粘贴到输入区，然后重试：<br/>{local_history}"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
try:
|
||||
chatbot, history = read_file_to_chat(chatbot, history, file_manifest[0])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
except:
|
||||
chatbot.append([f"载入对话历史文件", f"对话历史文件损坏！"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
@CatchException
|
||||
def 删除所有本地对话历史记录(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
|
||||
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
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
|
||||
import glob, os
|
||||
local_history = "<br/>".join([
|
||||
"`"+hide_cwd(f)+"`"
|
||||
for f in glob.glob(
|
||||
f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html', recursive=True
|
||||
)])
|
||||
for f in glob.glob(f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html', recursive=True):
|
||||
os.remove(f)
|
||||
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
|
||||
|
||||
|
||||
@@ -40,10 +40,10 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
|
||||
i_say = f'请对下面的文章片段用中文做概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{paper_frag}```'
|
||||
i_say_show_user = f'请对下面的文章片段做概述: {os.path.abspath(fp)}的第{i+1}/{len(paper_fragments)}个片段。'
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say_show_user,
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say_show_user,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
chatbot=chatbot,
|
||||
history=[],
|
||||
sys_prompt="总结文章。"
|
||||
)
|
||||
@@ -56,10 +56,10 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
|
||||
if len(paper_fragments) > 1:
|
||||
i_say = f"根据以上的对话，总结文章{os.path.abspath(fp)}的主要内容。"
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say,
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
chatbot=chatbot,
|
||||
history=this_paper_history,
|
||||
sys_prompt="总结文章。"
|
||||
)
|
||||
@@ -79,7 +79,7 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
|
||||
|
||||
|
||||
@CatchException
|
||||
def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
import glob, os
|
||||
|
||||
# 基本信息：功能、贡献者
|
||||
|
||||
@@ -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
|
||||
"""
|
||||
@@ -53,7 +53,7 @@ class PaperFileGroup():
|
||||
def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
|
||||
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
|
||||
# <-------- 读取Markdown文件，删除其中的所有注释 ---------->
|
||||
# <-------- 读取Markdown文件，删除其中的所有注释 ---------->
|
||||
pfg = PaperFileGroup()
|
||||
|
||||
for index, fp in enumerate(file_manifest):
|
||||
@@ -63,26 +63,26 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
pfg.file_paths.append(fp)
|
||||
pfg.file_contents.append(file_content)
|
||||
|
||||
# <-------- 拆分过长的Markdown文件 ---------->
|
||||
pfg.run_file_split(max_token_limit=2048)
|
||||
# <-------- 拆分过长的Markdown文件 ---------->
|
||||
pfg.run_file_split(max_token_limit=1500)
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
|
||||
# <-------- 多线程翻译开始 ---------->
|
||||
# <-------- 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,
|
||||
@@ -99,16 +99,11 @@ 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())
|
||||
|
||||
# <-------- 整理结果，退出 ---------->
|
||||
# <-------- 整理结果，退出 ---------->
|
||||
create_report_file_name = gen_time_str() + f"-chatgpt.md"
|
||||
res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
|
||||
promote_file_to_downloadzone(res, chatbot=chatbot)
|
||||
@@ -158,12 +153,13 @@ def get_files_from_everything(txt, preference=''):
|
||||
|
||||
|
||||
@CatchException
|
||||
def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"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:
|
||||
@@ -197,12 +193,13 @@ def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
|
||||
|
||||
|
||||
@CatchException
|
||||
def Markdown中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def Markdown中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"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:
|
||||
@@ -229,12 +226,13 @@ def Markdown中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
|
||||
|
||||
|
||||
@CatchException
|
||||
def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"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:
|
||||
@@ -257,7 +255,7 @@ def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history,
|
||||
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
language = plugin_kwargs.get("advanced_arg", 'Chinese')
|
||||
yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language=language)
|
||||
@@ -17,7 +17,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
|
||||
file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
page_one = str(page_one).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
|
||||
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 2500
|
||||
|
||||
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
|
||||
@@ -25,7 +25,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
|
||||
page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
|
||||
# 为了更好的效果，我们剥离Introduction之后的部分（如果有）
|
||||
paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
|
||||
|
||||
|
||||
############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
|
||||
final_results = []
|
||||
final_results.append(paper_meta)
|
||||
@@ -44,10 +44,10 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
|
||||
i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[i]}"
|
||||
i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[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,
|
||||
llm_kwargs, chatbot,
|
||||
history=["The main idea of the previous section is?", last_iteration_result], # 迭代上一次的结果
|
||||
sys_prompt="Extract the main idea of this section with Chinese." # 提示
|
||||
)
|
||||
)
|
||||
iteration_results.append(gpt_say)
|
||||
last_iteration_result = gpt_say
|
||||
|
||||
@@ -67,15 +67,15 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
|
||||
- (2):What are the past methods? What are the problems with them? Is the approach well motivated?
|
||||
- (3):What is the research methodology proposed in this paper?
|
||||
- (4):On what task and what performance is achieved by the methods in this paper? Can the performance support their goals?
|
||||
Follow the format of the output that follows:
|
||||
Follow the format of the output that follows:
|
||||
1. Title: xxx\n\n
|
||||
2. Authors: xxx\n\n
|
||||
3. Affiliation: xxx\n\n
|
||||
4. Keywords: xxx\n\n
|
||||
5. Urls: xxx or xxx , xxx \n\n
|
||||
6. Summary: \n\n
|
||||
- (1):xxx;\n
|
||||
- (2):xxx;\n
|
||||
- (1):xxx;\n
|
||||
- (2):xxx;\n
|
||||
- (3):xxx;\n
|
||||
- (4):xxx.\n\n
|
||||
Be sure to use Chinese answers (proper nouns need to be marked in English), statements as concise and academic as possible,
|
||||
@@ -85,8 +85,8 @@ do not have too much repetitive information, numerical values using the original
|
||||
file_write_buffer.extend(final_results)
|
||||
i_say, final_results = input_clipping(i_say, final_results, max_token_limit=2000)
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user='开始最终总结',
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=final_results,
|
||||
inputs=i_say, inputs_show_user='开始最终总结',
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=final_results,
|
||||
sys_prompt= f"Extract the main idea of this paper with less than {NUM_OF_WORD} Chinese characters"
|
||||
)
|
||||
final_results.append(gpt_say)
|
||||
@@ -101,7 +101,7 @@ do not have too much repetitive information, numerical values using the original
|
||||
|
||||
|
||||
@CatchException
|
||||
def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
import glob, os
|
||||
|
||||
# 基本信息：功能、贡献者
|
||||
@@ -114,8 +114,8 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
try:
|
||||
import fitz
|
||||
except:
|
||||
report_exception(chatbot, history,
|
||||
a = f"解析项目: {txt}",
|
||||
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
|
||||
@@ -134,7 +134,7 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
|
||||
# 搜索需要处理的文件清单
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
|
||||
|
||||
|
||||
# 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.tex或.pdf文件: {txt}")
|
||||
|
||||
@@ -85,10 +85,10 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
|
||||
msg = '正常'
|
||||
# ** gpt request **
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say_show_user,
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say_show_user,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
chatbot=chatbot,
|
||||
history=[],
|
||||
sys_prompt="总结文章。"
|
||||
) # 带超时倒计时
|
||||
@@ -106,10 +106,10 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
|
||||
msg = '正常'
|
||||
# ** gpt request **
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say,
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
chatbot=chatbot,
|
||||
history=history,
|
||||
sys_prompt="总结文章。"
|
||||
) # 带超时倒计时
|
||||
@@ -124,7 +124,7 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
|
||||
|
||||
|
||||
@CatchException
|
||||
def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
import glob, os
|
||||
|
||||
@@ -138,8 +138,8 @@ def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, histo
|
||||
try:
|
||||
import pdfminer, bs4
|
||||
except:
|
||||
report_exception(chatbot, history,
|
||||
a = f"解析项目: {txt}",
|
||||
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 pdfminer beautifulsoup4```。")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
@@ -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
|
||||
@@ -48,7 +48,7 @@ def markdown_to_dict(article_content):
|
||||
|
||||
|
||||
@CatchException
|
||||
def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
|
||||
disable_auto_promotion(chatbot)
|
||||
# 基本信息：功能、贡献者
|
||||
@@ -76,8 +76,8 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
success_mmd, file_manifest_mmd, _ = get_files_from_everything(txt, type='.mmd')
|
||||
success = success or success_mmd
|
||||
file_manifest += file_manifest_mmd
|
||||
chatbot.append(["文件列表：", ", ".join([e.split('/')[-1] for e in file_manifest])]);
|
||||
yield from update_ui( chatbot=chatbot, history=history)
|
||||
chatbot.append(["文件列表：", ", ".join([e.split('/')[-1] for e in file_manifest])]);
|
||||
yield from update_ui( chatbot=chatbot, history=history)
|
||||
# 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'
|
||||
|
||||
@@ -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, web_port):
|
||||
|
||||
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
|
||||
@@ -29,7 +97,7 @@ def 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwa
|
||||
|
||||
# 为了更好的效果，我们剥离Introduction之后的部分（如果有）
|
||||
paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
|
||||
|
||||
|
||||
# 单线，获取文章meta信息
|
||||
paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=f"以下是一篇学术论文的基础信息，请从中提取出“标题”、“收录会议或期刊”、“作者”、“摘要”、“编号”、“作者邮箱”这六个部分。请用markdown格式输出，最后用中文翻译摘要部分。请提取：{paper_meta}",
|
||||
@@ -48,13 +116,12 @@ 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)
|
||||
# 整理报告的格式
|
||||
for i,k in enumerate(gpt_response_collection_md):
|
||||
for i,k in enumerate(gpt_response_collection_md):
|
||||
if i%2==0:
|
||||
gpt_response_collection_md[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection_md)//2}]： \n\n {paper_fragments[i//2].replace('#', '')} \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection_md)//2}]：\n "
|
||||
else:
|
||||
@@ -72,18 +139,18 @@ def 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwa
|
||||
|
||||
# write html
|
||||
try:
|
||||
ch = construct_html()
|
||||
ch = construct_html()
|
||||
orig = ""
|
||||
trans = ""
|
||||
gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
|
||||
for i,k in enumerate(gpt_response_collection_html):
|
||||
for i,k in enumerate(gpt_response_collection_html):
|
||||
if i%2==0:
|
||||
gpt_response_collection_html[i] = paper_fragments[i//2].replace('#', '')
|
||||
else:
|
||||
gpt_response_collection_html[i] = gpt_response_collection_html[i]
|
||||
final = ["论文概况", paper_meta_info.replace('# ', '### '), "二、论文翻译", ""]
|
||||
final.extend(gpt_response_collection_html)
|
||||
for i, k in enumerate(final):
|
||||
for i, k in enumerate(final):
|
||||
if i%2==0:
|
||||
orig = k
|
||||
if i%2==1:
|
||||
@@ -27,7 +27,7 @@ def eval_manim(code):
|
||||
|
||||
class_name = get_class_name(code)
|
||||
|
||||
try:
|
||||
try:
|
||||
time_str = gen_time_str()
|
||||
subprocess.check_output([sys.executable, '-c', f"from gpt_log.MyAnimation import {class_name}; {class_name}().render()"])
|
||||
shutil.move(f'media/videos/1080p60/{class_name}.mp4', f'gpt_log/{class_name}-{time_str}.mp4')
|
||||
@@ -36,7 +36,7 @@ def eval_manim(code):
|
||||
output = e.output.decode()
|
||||
print(f"Command returned non-zero exit status {e.returncode}: {output}.")
|
||||
return f"Evaluating python script failed: {e.output}."
|
||||
except:
|
||||
except:
|
||||
print('generating mp4 failed')
|
||||
return "Generating mp4 failed."
|
||||
|
||||
@@ -45,12 +45,12 @@ 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:
|
||||
if len(matches) != 1:
|
||||
raise RuntimeError("GPT is not generating proper code.")
|
||||
return matches[0].strip('python') # code block
|
||||
|
||||
@CatchException
|
||||
def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 动画生成(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
|
||||
@@ -58,10 +58,10 @@ def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
# 清空历史，以免输入溢出
|
||||
history = []
|
||||
history = []
|
||||
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
@@ -73,24 +73,24 @@ def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
|
||||
# 尝试导入依赖, 如果缺少依赖, 则给出安装建议
|
||||
dep_ok = yield from inspect_dependency(chatbot=chatbot, history=history) # 刷新界面
|
||||
if not dep_ok: return
|
||||
|
||||
|
||||
# 输入
|
||||
i_say = f'Generate a animation to show: ' + txt
|
||||
demo = ["Here is some examples of manim", examples_of_manim()]
|
||||
_, demo = input_clipping(inputs="", history=demo, max_token_limit=2560)
|
||||
# 开始
|
||||
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,
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
|
||||
sys_prompt=
|
||||
r"Write a animation script with 3blue1brown's manim. "+
|
||||
r"Please begin with `from manim import *`. " +
|
||||
r"Please begin with `from manim import *`. " +
|
||||
r"Answer me with a code block wrapped by ```."
|
||||
)
|
||||
chatbot.append(["开始生成动画", "..."])
|
||||
history.extend([i_say, gpt_say])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
|
||||
# 将代码转为动画
|
||||
code = get_code_block(gpt_say)
|
||||
res = eval_manim(code)
|
||||
|
||||
@@ -15,7 +15,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
|
||||
file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
page_one = str(page_one).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
|
||||
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 2500
|
||||
|
||||
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
|
||||
@@ -23,7 +23,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
|
||||
page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
|
||||
# 为了更好的效果，我们剥离Introduction之后的部分（如果有）
|
||||
paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
|
||||
|
||||
|
||||
############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
|
||||
final_results = []
|
||||
final_results.append(paper_meta)
|
||||
@@ -42,10 +42,10 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
|
||||
i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i]}"
|
||||
i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[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,
|
||||
llm_kwargs, chatbot,
|
||||
history=["The main idea of the previous section is?", last_iteration_result], # 迭代上一次的结果
|
||||
sys_prompt="Extract the main idea of this section, answer me with Chinese." # 提示
|
||||
)
|
||||
)
|
||||
iteration_results.append(gpt_say)
|
||||
last_iteration_result = gpt_say
|
||||
|
||||
@@ -63,7 +63,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
|
||||
|
||||
|
||||
@CatchException
|
||||
def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
import glob, os
|
||||
|
||||
# 基本信息：功能、贡献者
|
||||
@@ -76,8 +76,8 @@ def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chat
|
||||
try:
|
||||
import fitz
|
||||
except:
|
||||
report_exception(chatbot, history,
|
||||
a = f"解析项目: {txt}",
|
||||
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
|
||||
|
||||
@@ -16,7 +16,7 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
if not fast_debug:
|
||||
if not fast_debug:
|
||||
msg = '正常'
|
||||
# ** gpt request **
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
@@ -27,7 +27,7 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
|
||||
if not fast_debug: time.sleep(2)
|
||||
|
||||
if not fast_debug:
|
||||
if not fast_debug:
|
||||
res = write_history_to_file(history)
|
||||
promote_file_to_downloadzone(res, chatbot=chatbot)
|
||||
chatbot.append(("完成了吗？", res))
|
||||
@@ -36,7 +36,7 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
|
||||
|
||||
@CatchException
|
||||
def 批量生成函数注释(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 批量生成函数注释(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
|
||||
@@ -1,438 +0,0 @@
|
||||
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
|
||||
|
||||
# 以下是每类图表的PROMPT
|
||||
SELECT_PROMPT = """
|
||||
“{subject}”
|
||||
=============
|
||||
以上是从文章中提取的摘要,将会使用这些摘要绘制图表。请你选择一个合适的图表类型:
|
||||
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
|
||||
不需要解释原因，仅需要输出单个不带任何标点符号的数字。
|
||||
"""
|
||||
# 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：
|
||||
```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")
|
||||
```
|
||||
"""
|
||||
# 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：
|
||||
```mermaid
|
||||
sequenceDiagram
|
||||
participant A as 用户
|
||||
participant B as 系统
|
||||
A->>B: 登录请求
|
||||
B->>A: 登录成功
|
||||
A->>B: 获取数据
|
||||
B->>A: 返回数据
|
||||
```
|
||||
"""
|
||||
# 类图
|
||||
PROMPT_3 = """
|
||||
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
|
||||
Class03 *-- Class04
|
||||
Class05 o-- Class06
|
||||
Class07 .. Class08
|
||||
Class09 --> C2 : Where am i?
|
||||
Class09 --* C3
|
||||
Class09 --|> Class07
|
||||
Class07 : equals()
|
||||
Class07 : Object[] elementData
|
||||
Class01 : size()
|
||||
Class01 : int chimp
|
||||
Class01 : int gorilla
|
||||
Class08 <--> C2: Cool label
|
||||
```
|
||||
"""
|
||||
# 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：
|
||||
```mermaid
|
||||
pie title Pets adopted by volunteers
|
||||
"狗" : 386
|
||||
"猫" : 85
|
||||
"兔子" : 15
|
||||
```
|
||||
"""
|
||||
# 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：
|
||||
```mermaid
|
||||
gantt
|
||||
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
|
||||
```
|
||||
"""
|
||||
# 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：
|
||||
```mermaid
|
||||
stateDiagram-v2
|
||||
[*] --> "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：
|
||||
```mermaid
|
||||
erDiagram
|
||||
CUSTOMER ||--o{ ORDER : places
|
||||
ORDER ||--|{ LINE-ITEM : contains
|
||||
CUSTOMER {
|
||||
string name
|
||||
string id
|
||||
}
|
||||
ORDER {
|
||||
string orderNumber
|
||||
date orderDate
|
||||
string customerID
|
||||
}
|
||||
LINE-ITEM {
|
||||
number quantity
|
||||
string productID
|
||||
}
|
||||
```
|
||||
"""
|
||||
# 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：
|
||||
```mermaid
|
||||
graph LR
|
||||
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：
|
||||
```mermaid
|
||||
mindmap
|
||||
root((mindmap))
|
||||
("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)
|
||||
```
|
||||
"""
|
||||
|
||||
|
||||
def 解析历史输入(history, llm_kwargs, file_manifest, 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"]
|
||||
)
|
||||
############################## <第 1 步，迭代地历遍整个文章，提取精炼信息> ##################################
|
||||
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")
|
||||
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_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
|
||||
)
|
||||
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
|
||||
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="",
|
||||
)
|
||||
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"
|
||||
############################## <第 3 步，根据选择的图表类型绘制图表> ##################################
|
||||
if gpt_say == "1":
|
||||
i_say = PROMPT_1.format(subject=results_txt)
|
||||
elif gpt_say == "2":
|
||||
i_say = PROMPT_2.format(subject=results_txt)
|
||||
elif gpt_say == "3":
|
||||
i_say = PROMPT_3.format(subject=results_txt)
|
||||
elif gpt_say == "4":
|
||||
i_say = PROMPT_4.format(subject=results_txt)
|
||||
elif gpt_say == "5":
|
||||
i_say = PROMPT_5.format(subject=results_txt)
|
||||
elif gpt_say == "6":
|
||||
i_say = PROMPT_6.format(subject=results_txt)
|
||||
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":
|
||||
i_say = PROMPT_8.format(subject=results_txt)
|
||||
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。"
|
||||
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="",
|
||||
)
|
||||
history.append(gpt_say)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
|
||||
@CatchException
|
||||
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
|
||||
plugin_kwargs 插件模型的参数，用于灵活调整复杂功能的各种参数
|
||||
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
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
import os
|
||||
|
||||
# 基本信息：功能、贡献者
|
||||
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",
|
||||
]
|
||||
)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
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)
|
||||
)
|
||||
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。",
|
||||
)
|
||||
|
||||
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,
|
||||
)
|
||||
@@ -9,11 +9,11 @@ install_msg ="""
|
||||
|
||||
3. python -m pip install unstructured[all-docs] --upgrade
|
||||
|
||||
4. python -c 'import nltk; nltk.download("punkt")'
|
||||
4. python -c 'import nltk; nltk.download("punkt")'
|
||||
"""
|
||||
|
||||
@CatchException
|
||||
def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 知识库文件注入(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
|
||||
@@ -21,7 +21,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
|
||||
@@ -56,7 +56,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
chatbot.append(["没有找到任何可读取文件", "当前支持的格式包括: txt, md, docx, pptx, pdf, json等"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# < -------------------预热文本向量化模组--------------- >
|
||||
chatbot.append(['<br/>'.join(file_manifest), "正在预热文本向量化模组, 如果是第一次运行, 将消耗较长时间下载中文向量化模型..."])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
@@ -84,7 +84,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
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
|
||||
|
||||
@CatchException
|
||||
def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request=-1):
|
||||
def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port=-1):
|
||||
# resolve deps
|
||||
try:
|
||||
# from zh_langchain import construct_vector_store
|
||||
@@ -109,8 +109,8 @@ def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
chatbot.append((txt, f'[知识库 {kai_id}] ' + prompt))
|
||||
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
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=prompt, inputs_show_user=txt,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
inputs=prompt, inputs_show_user=txt,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt=system_prompt
|
||||
)
|
||||
history.extend((prompt, gpt_say))
|
||||
|
||||
@@ -40,10 +40,10 @@ def scrape_text(url, proxies) -> str:
|
||||
'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:
|
||||
try:
|
||||
response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
|
||||
if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
|
||||
except:
|
||||
except:
|
||||
return "无法连接到该网页"
|
||||
soup = BeautifulSoup(response.text, "html.parser")
|
||||
for script in soup(["script", "style"]):
|
||||
@@ -55,7 +55,7 @@ def scrape_text(url, proxies) -> str:
|
||||
return text
|
||||
|
||||
@CatchException
|
||||
def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 连接网络回答问题(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
|
||||
@@ -63,10 +63,10 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
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}",
|
||||
chatbot.append((f"请结合互联网信息回答以下问题：{txt}",
|
||||
"[Local Message] 请注意，您正在调用一个[函数插件]的模板，该模板可以实现ChatGPT联网信息综合。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。您若希望分享新的功能模组，请不吝PR！"))
|
||||
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
|
||||
|
||||
@@ -91,13 +91,13 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
# ------------- < 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,
|
||||
inputs=i_say,
|
||||
history=history,
|
||||
max_token_limit=model_info[llm_kwargs['llm_model']]['max_token']*3//4
|
||||
)
|
||||
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,
|
||||
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)
|
||||
|
||||
@@ -55,7 +55,7 @@ def scrape_text(url, proxies) -> str:
|
||||
return text
|
||||
|
||||
@CatchException
|
||||
def 连接bing搜索回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 连接bing搜索回答问题(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
|
||||
@@ -63,7 +63,7 @@ def 连接bing搜索回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, histor
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
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}",
|
||||
|
||||
@@ -33,7 +33,7 @@ explain_msg = """
|
||||
- 「请调用插件，解析python源代码项目，代码我刚刚打包拖到上传区了」
|
||||
- 「请问Transformer网络的结构是怎样的？」
|
||||
|
||||
2. 您可以打开插件下拉菜单以了解本项目的各种能力。
|
||||
2. 您可以打开插件下拉菜单以了解本项目的各种能力。
|
||||
|
||||
3. 如果您使用「调用插件xxx」、「修改配置xxx」、「请问」等关键词，您的意图可以被识别的更准确。
|
||||
|
||||
@@ -67,7 +67,7 @@ class UserIntention(BaseModel):
|
||||
def chat(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=txt, inputs_show_user=txt,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt=system_prompt
|
||||
)
|
||||
chatbot[-1] = [txt, gpt_say]
|
||||
@@ -104,7 +104,7 @@ def analyze_intention_with_simple_rules(txt):
|
||||
|
||||
|
||||
@CatchException
|
||||
def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
disable_auto_promotion(chatbot=chatbot)
|
||||
# 获取当前虚空终端状态
|
||||
state = VoidTerminalState.get_state(chatbot)
|
||||
@@ -115,13 +115,13 @@ def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
|
||||
if is_the_upload_folder(txt):
|
||||
state.set_state(chatbot=chatbot, key='has_provided_explaination', value=False)
|
||||
appendix_msg = "\n\n**很好，您已经上传了文件**，现在请您描述您的需求。"
|
||||
|
||||
|
||||
if is_certain or (state.has_provided_explaination):
|
||||
# 如果意图明确，跳过提示环节
|
||||
state.set_state(chatbot=chatbot, key='has_provided_explaination', value=True)
|
||||
state.unlock_plugin(chatbot=chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
yield from 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
yield from 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port)
|
||||
return
|
||||
else:
|
||||
# 如果意图模糊，提示
|
||||
@@ -133,7 +133,7 @@ def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
|
||||
|
||||
|
||||
|
||||
def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = []
|
||||
chatbot.append(("虚空终端状态: ", f"正在执行任务: {txt}"))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
@@ -152,7 +152,7 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
analyze_res = run_gpt_fn(inputs, "")
|
||||
try:
|
||||
user_intention = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
|
||||
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
|
||||
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
|
||||
except JsonStringError as e:
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 失败 当前语言模型（{llm_kwargs['llm_model']}）不能理解您的意图", chatbot=chatbot, history=history, delay=0)
|
||||
@@ -161,7 +161,7 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
pass
|
||||
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
|
||||
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
|
||||
# 用户意图: 修改本项目的配置
|
||||
|
||||
@@ -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
|
||||
@@ -60,7 +54,7 @@ def parseNotebook(filename, enable_markdown=1):
|
||||
Code += f"This is {idx+1}th code block: \n"
|
||||
Code += code+"\n"
|
||||
|
||||
return Code
|
||||
return Code
|
||||
|
||||
|
||||
def ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
|
||||
@@ -115,7 +109,7 @@ def ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
@CatchException
|
||||
def 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"对IPynb文件进行解析。Contributor: codycjy."])
|
||||
|
||||
@@ -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
|
||||
@@ -83,13 +82,12 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
inputs=inputs, inputs_show_user=inputs_show_user, llm_kwargs=llm_kwargs, chatbot=chatbot,
|
||||
history=this_iteration_history_feed, # 迭代之前的分析
|
||||
sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。" + sys_prompt_additional)
|
||||
|
||||
diagram_code = make_diagram(this_iteration_files, result, this_iteration_history_feed)
|
||||
summary = "请用一句话概括这些文件的整体功能。\n\n" + diagram_code
|
||||
|
||||
summary = "请用一句话概括这些文件的整体功能"
|
||||
summary_result = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=summary,
|
||||
inputs_show_user=summary,
|
||||
llm_kwargs=llm_kwargs,
|
||||
inputs=summary,
|
||||
inputs_show_user=summary,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
history=[i_say, result], # 迭代之前的分析
|
||||
sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。" + sys_prompt_additional)
|
||||
@@ -106,12 +104,9 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot.append(("完成了吗？", res))
|
||||
yield from update_ui(chatbot=chatbot, history=history_to_return) # 刷新界面
|
||||
|
||||
def make_diagram(this_iteration_files, result, this_iteration_history_feed):
|
||||
from crazy_functions.diagram_fns.file_tree import build_file_tree_mermaid_diagram
|
||||
return build_file_tree_mermaid_diagram(this_iteration_history_feed[0::2], this_iteration_history_feed[1::2], "项目示意图")
|
||||
|
||||
@CatchException
|
||||
def 解析项目本身(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析项目本身(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
import glob
|
||||
file_manifest = [f for f in glob.glob('./*.py')] + \
|
||||
@@ -124,12 +119,11 @@ def 解析项目本身(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
|
||||
@CatchException
|
||||
def 解析一个Python项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析一个Python项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
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}")
|
||||
@@ -143,12 +137,11 @@ def 解析一个Python项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
|
||||
@CatchException
|
||||
def 解析一个Matlab项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析一个Matlab项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
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}")
|
||||
@@ -162,12 +155,11 @@ def 解析一个Matlab项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
|
||||
@CatchException
|
||||
def 解析一个C项目的头文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析一个C项目的头文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
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}")
|
||||
@@ -183,12 +175,11 @@ def 解析一个C项目的头文件(txt, llm_kwargs, plugin_kwargs, chatbot, his
|
||||
yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
|
||||
@CatchException
|
||||
def 解析一个C项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析一个C项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
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}")
|
||||
@@ -206,12 +197,11 @@ def 解析一个C项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system
|
||||
|
||||
|
||||
@CatchException
|
||||
def 解析一个Java项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析一个Java项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
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}")
|
||||
@@ -229,12 +219,11 @@ def 解析一个Java项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
|
||||
|
||||
|
||||
@CatchException
|
||||
def 解析一个前端项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析一个前端项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
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}")
|
||||
@@ -259,12 +248,11 @@ def 解析一个前端项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
|
||||
|
||||
@CatchException
|
||||
def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
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}")
|
||||
@@ -281,12 +269,11 @@ def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
|
||||
@CatchException
|
||||
def 解析一个Rust项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析一个Rust项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
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}")
|
||||
@@ -302,12 +289,11 @@ def 解析一个Rust项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
|
||||
yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
|
||||
@CatchException
|
||||
def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
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}")
|
||||
@@ -325,12 +311,11 @@ def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
|
||||
|
||||
@CatchException
|
||||
def 解析一个CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析一个CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
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}")
|
||||
@@ -346,7 +331,7 @@ def 解析一个CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
|
||||
|
||||
@CatchException
|
||||
def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
txt_pattern = plugin_kwargs.get("advanced_arg")
|
||||
txt_pattern = txt_pattern.replace("，", ",")
|
||||
# 将要匹配的模式(例如: *.c, *.cpp, *.py, config.toml)
|
||||
@@ -356,19 +341,15 @@ 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}")
|
||||
|
||||
@@ -2,7 +2,7 @@ from toolbox import CatchException, update_ui, get_conf
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
import datetime
|
||||
@CatchException
|
||||
def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 同时问询(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
|
||||
@@ -10,7 +10,7 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
MULTI_QUERY_LLM_MODELS = get_conf('MULTI_QUERY_LLM_MODELS')
|
||||
@@ -20,8 +20,8 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
|
||||
# llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo&api2d-gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
|
||||
llm_kwargs['llm_model'] = MULTI_QUERY_LLM_MODELS # 支持任意数量的llm接口，用&符号分隔
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=txt, inputs_show_user=txt,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
inputs=txt, inputs_show_user=txt,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
sys_prompt=system_prompt,
|
||||
retry_times_at_unknown_error=0
|
||||
)
|
||||
@@ -32,7 +32,7 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
|
||||
|
||||
|
||||
@CatchException
|
||||
def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 同时问询_指定模型(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
|
||||
@@ -40,7 +40,7 @@ def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history,
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
|
||||
@@ -52,8 +52,8 @@ def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history,
|
||||
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
|
||||
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=txt, inputs_show_user=txt,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
inputs=txt, inputs_show_user=txt,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
sys_prompt=system_prompt,
|
||||
retry_times_at_unknown_error=0
|
||||
)
|
||||
|
||||
@@ -39,7 +39,7 @@ class AsyncGptTask():
|
||||
try:
|
||||
MAX_TOKEN_ALLO = 2560
|
||||
i_say, history = input_clipping(i_say, history, max_token_limit=MAX_TOKEN_ALLO)
|
||||
gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt,
|
||||
gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt,
|
||||
observe_window=observe_window[index], console_slience=True)
|
||||
except ConnectionAbortedError as token_exceed_err:
|
||||
print('至少一个线程任务Token溢出而失败', e)
|
||||
@@ -120,7 +120,7 @@ class InterviewAssistant(AliyunASR):
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
self.plugin_wd.feed()
|
||||
|
||||
if self.event_on_result_chg.is_set():
|
||||
if self.event_on_result_chg.is_set():
|
||||
# called when some words have finished
|
||||
self.event_on_result_chg.clear()
|
||||
chatbot[-1] = list(chatbot[-1])
|
||||
@@ -151,7 +151,7 @@ class InterviewAssistant(AliyunASR):
|
||||
# add gpt task 创建子线程请求gpt，避免线程阻塞
|
||||
history = chatbot2history(chatbot)
|
||||
self.agt.add_async_gpt_task(self.buffered_sentence, len(chatbot)-1, llm_kwargs, history, system_prompt)
|
||||
|
||||
|
||||
self.buffered_sentence = ""
|
||||
chatbot.append(["[ 请讲话 ]", "[ 正在等您说完问题 ]"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
@@ -166,7 +166,7 @@ class InterviewAssistant(AliyunASR):
|
||||
|
||||
|
||||
@CatchException
|
||||
def 语音助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 语音助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# pip install -U openai-whisper
|
||||
chatbot.append(["对话助手函数插件：使用时，双手离开鼠标键盘吧", "音频助手, 正在听您讲话（点击“停止”键可终止程序）..."])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
@@ -44,7 +44,7 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
|
||||
|
||||
|
||||
@CatchException
|
||||
def 读文章写摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 读文章写摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
import glob, os
|
||||
if os.path.exists(txt):
|
||||
|
||||
@@ -20,10 +20,10 @@ def get_meta_information(url, chatbot, history):
|
||||
proxies = get_conf('proxies')
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
|
||||
'Accept-Encoding': 'gzip, deflate, br',
|
||||
'Accept-Encoding': 'gzip, deflate, br',
|
||||
'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
|
||||
'Cache-Control':'max-age=0',
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
|
||||
'Connection': 'keep-alive'
|
||||
}
|
||||
try:
|
||||
@@ -95,7 +95,7 @@ def get_meta_information(url, chatbot, history):
|
||||
)
|
||||
try: paper = next(search.results())
|
||||
except: paper = None
|
||||
|
||||
|
||||
is_match = paper is not None and string_similar(title, paper.title) > 0.90
|
||||
|
||||
# 如果在Arxiv上匹配失败，检索文章的历史版本的题目
|
||||
@@ -132,7 +132,7 @@ def get_meta_information(url, chatbot, history):
|
||||
return profile
|
||||
|
||||
@CatchException
|
||||
def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
disable_auto_promotion(chatbot=chatbot)
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
@@ -146,8 +146,8 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
import math
|
||||
from bs4 import BeautifulSoup
|
||||
except:
|
||||
report_exception(chatbot, history,
|
||||
a = f"解析项目: {txt}",
|
||||
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 beautifulsoup4 arxiv```。")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
@@ -163,7 +163,7 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
if len(meta_paper_info_list[:batchsize]) > 0:
|
||||
i_say = "下面是一些学术文献的数据，提取出以下内容：" + \
|
||||
"1、英文题目；2、中文题目翻译；3、作者；4、arxiv公开（is_paper_in_arxiv）；4、引用数量（cite）；5、中文摘要翻译。" + \
|
||||
f"以下是信息源：{str(meta_paper_info_list[:batchsize])}"
|
||||
f"以下是信息源：{str(meta_paper_info_list[:batchsize])}"
|
||||
|
||||
inputs_show_user = f"请分析此页面中出现的所有文章：{txt}，这是第{batch+1}批"
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
@@ -175,11 +175,11 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
history.extend([ f"第{batch+1}批", gpt_say ])
|
||||
meta_paper_info_list = meta_paper_info_list[batchsize:]
|
||||
|
||||
chatbot.append(["状态？",
|
||||
chatbot.append(["状态？",
|
||||
"已经全部完成，您可以试试让AI写一个Related Works，例如您可以继续输入Write a \"Related Works\" section about \"你搜索的研究领域\" for me."])
|
||||
msg = '正常'
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
|
||||
path = write_history_to_file(history)
|
||||
promote_file_to_downloadzone(path, chatbot=chatbot)
|
||||
chatbot.append(("完成了吗？", path));
|
||||
chatbot.append(("完成了吗？", path));
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
|
||||
|
||||
@@ -11,7 +11,7 @@ import os
|
||||
|
||||
|
||||
@CatchException
|
||||
def 猜你想问(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 猜你想问(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
if txt:
|
||||
show_say = txt
|
||||
prompt = txt+'\n回答完问题后，再列出用户可能提出的三个问题。'
|
||||
@@ -32,7 +32,7 @@ def 猜你想问(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
|
||||
|
||||
|
||||
@CatchException
|
||||
def 清除缓存(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 清除缓存(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
chatbot.append(['清除本地缓存数据', '执行中. 删除数据'])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
|
||||
@@ -1,59 +1,27 @@
|
||||
from toolbox import CatchException, update_ui
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from .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
|
||||
%% <gpt_academic_hide_mermaid_code> 一个特殊标记，用于在生成mermaid图表时隐藏代码块
|
||||
subgraph 函数调用["函数调用过程"]
|
||||
AA["输入栏用户输入的文本(txt)"] --> BB["gpt模型参数(llm_kwargs)"]
|
||||
BB --> CC["插件模型参数(plugin_kwargs)"]
|
||||
CC --> DD["对话显示框的句柄(chatbot)"]
|
||||
DD --> EE["对话历史(history)"]
|
||||
EE --> FF["系统提示词(system_prompt)"]
|
||||
FF --> GG["当前用户信息(web_port)"]
|
||||
|
||||
A["开始(查询5天历史事件)"]
|
||||
A --> B["获取当前月份和日期"]
|
||||
B --> C["生成历史事件查询提示词"]
|
||||
C --> D["调用大模型"]
|
||||
D --> E["更新界面"]
|
||||
E --> F["记录历史"]
|
||||
F --> |"下一天"| B
|
||||
end
|
||||
```
|
||||
"""
|
||||
|
||||
@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, web_port):
|
||||
"""
|
||||
# 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
|
||||
|
||||
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，用于灵活调整复杂功能的各种参数
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
chatbot.append((
|
||||
"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))
|
||||
chatbot.append(("这是什么功能？", "[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！"))
|
||||
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。'
|
||||
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=[],
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt="当你想发送一张照片时，请使用Markdown, 并且不要有反斜线, 不要用代码块。使用 Unsplash API (https://source.unsplash.com/1280x720/? < PUT_YOUR_QUERY_HERE >)。"
|
||||
)
|
||||
chatbot[-1] = (i_say, gpt_say)
|
||||
@@ -63,56 +31,6 @@ 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
|
||||
@@ -125,7 +43,7 @@ graph TD
|
||||
```
|
||||
"""
|
||||
@CatchException
|
||||
def 测试图表渲染(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 测试图表渲染(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
|
||||
@@ -133,20 +51,20 @@ def 测试图表渲染(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
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）
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
chatbot.append(("这是什么功能？", "一个测试mermaid绘制图表的功能，您可以在输入框中输入一些关键词，然后使用mermaid+llm绘制图表。"))
|
||||
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
|
||||
|
||||
|
||||
if txt == "": txt = "空白的输入栏" # 调皮一下
|
||||
|
||||
|
||||
i_say_show_user = f'请绘制有关“{txt}”的逻辑关系图。'
|
||||
i_say = PROMPT.format(subject=txt)
|
||||
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=[],
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt=""
|
||||
)
|
||||
history.append(i_say); history.append(gpt_say)
|
||||
|
||||
@@ -1,12 +1,12 @@
|
||||
## ===================================================
|
||||
# docker-compose.yml
|
||||
# docker-compose.yml
|
||||
## ===================================================
|
||||
# 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"
|
||||
|
||||
@@ -28,8 +28,6 @@ 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
|
||||
|
||||
# edge-tts需要的依赖
|
||||
RUN apt update && apt install ffmpeg -y
|
||||
|
||||
# 预热Tiktoken模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
@@ -36,9 +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
|
||||
|
||||
# edge-tts需要的依赖
|
||||
RUN apt update && apt install ffmpeg -y
|
||||
|
||||
# 预热Tiktoken模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
|
||||
@@ -21,8 +21,7 @@ RUN python3 -m pip install -r request_llms/requirements_qwen.txt
|
||||
RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
|
||||
RUN python3 -m pip install -r request_llms/requirements_newbing.txt
|
||||
|
||||
# edge-tts需要的依赖
|
||||
RUN apt update && apt install ffmpeg -y
|
||||
|
||||
|
||||
# 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, web_port)：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 |
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user