Compare commits
2 Commits
e9de41b7e8
...
batch-file
| Author | SHA1 | Date | |
|---|---|---|---|
|
36e50d490d | ||
|
|
9172337695 |
56
.github/workflows/conda-pack-windows.yml
vendored
56
.github/workflows/conda-pack-windows.yml
vendored
@@ -1,56 +0,0 @@
|
|||||||
name: Create Conda Environment Package
|
|
||||||
|
|
||||||
on:
|
|
||||||
workflow_dispatch:
|
|
||||||
|
|
||||||
jobs:
|
|
||||||
build:
|
|
||||||
runs-on: windows-latest
|
|
||||||
|
|
||||||
steps:
|
|
||||||
- name: Checkout repository
|
|
||||||
uses: actions/checkout@v4
|
|
||||||
|
|
||||||
- name: Setup Miniconda
|
|
||||||
uses: conda-incubator/setup-miniconda@v3
|
|
||||||
with:
|
|
||||||
auto-activate-base: true
|
|
||||||
activate-environment: ""
|
|
||||||
|
|
||||||
- name: Create new Conda environment
|
|
||||||
shell: bash -l {0}
|
|
||||||
run: |
|
|
||||||
conda create -n gpt python=3.11 -y
|
|
||||||
conda activate gpt
|
|
||||||
|
|
||||||
- name: Install requirements
|
|
||||||
shell: bash -l {0}
|
|
||||||
run: |
|
|
||||||
conda activate gpt
|
|
||||||
pip install -r requirements.txt
|
|
||||||
|
|
||||||
- name: Install conda-pack
|
|
||||||
shell: bash -l {0}
|
|
||||||
run: |
|
|
||||||
conda activate gpt
|
|
||||||
conda install conda-pack -y
|
|
||||||
|
|
||||||
- name: Pack conda environment
|
|
||||||
shell: bash -l {0}
|
|
||||||
run: |
|
|
||||||
conda activate gpt
|
|
||||||
conda pack -n gpt -o gpt.tar.gz
|
|
||||||
|
|
||||||
- name: Create workspace zip
|
|
||||||
shell: pwsh
|
|
||||||
run: |
|
|
||||||
mkdir workspace
|
|
||||||
Get-ChildItem -Exclude "workspace" | Copy-Item -Destination workspace -Recurse
|
|
||||||
Remove-Item -Path workspace/.git* -Recurse -Force -ErrorAction SilentlyContinue
|
|
||||||
Copy-Item gpt.tar.gz workspace/ -Force
|
|
||||||
|
|
||||||
- name: Upload packed files
|
|
||||||
uses: actions/upload-artifact@v4
|
|
||||||
with:
|
|
||||||
name: gpt-academic-package
|
|
||||||
path: workspace
|
|
||||||
7
.github/workflows/stale.yml
vendored
7
.github/workflows/stale.yml
vendored
@@ -7,7 +7,7 @@
|
|||||||
name: 'Close stale issues and PRs'
|
name: 'Close stale issues and PRs'
|
||||||
on:
|
on:
|
||||||
schedule:
|
schedule:
|
||||||
- cron: '*/30 * * * *'
|
- cron: '*/5 * * * *'
|
||||||
|
|
||||||
jobs:
|
jobs:
|
||||||
stale:
|
stale:
|
||||||
@@ -19,6 +19,7 @@ jobs:
|
|||||||
steps:
|
steps:
|
||||||
- uses: actions/stale@v8
|
- uses: actions/stale@v8
|
||||||
with:
|
with:
|
||||||
stale-issue-message: 'This issue is stale because it has been open 100 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
|
stale-issue-message: 'This issue is stale because it has been open 100 days with no activity. Remove stale label or comment or this will be closed in 1 days.'
|
||||||
days-before-stale: 100
|
days-before-stale: 100
|
||||||
days-before-close: 7
|
days-before-close: 1
|
||||||
|
debug-only: true
|
||||||
|
|||||||
4
.gitignore
vendored
4
.gitignore
vendored
@@ -160,6 +160,4 @@ test.*
|
|||||||
temp.*
|
temp.*
|
||||||
objdump*
|
objdump*
|
||||||
*.min.*.js
|
*.min.*.js
|
||||||
TODO
|
TODO
|
||||||
experimental_mods
|
|
||||||
search_results
|
|
||||||
@@ -15,7 +15,6 @@ RUN echo '[global]' > /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）
|
# 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/ $UBUNTU_VERSION main non-free contrib" > /etc/apt/sources.list; apt-get update
|
RUN UBUNTU_VERSION=$(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
|
RUN apt-get install ffmpeg -y
|
||||||
RUN apt-get clean
|
|
||||||
|
|
||||||
|
|
||||||
# 进入工作路径（必要）
|
# 进入工作路径（必要）
|
||||||
@@ -34,7 +33,6 @@ RUN pip3 install -r requirements.txt
|
|||||||
|
|
||||||
# 非必要步骤，用于预热模块（可以删除）
|
# 非必要步骤，用于预热模块（可以删除）
|
||||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||||
RUN python3 -m pip cache purge
|
|
||||||
|
|
||||||
|
|
||||||
# 启动（必要）
|
# 启动（必要）
|
||||||
|
|||||||
49
README.md
49
README.md
@@ -1,11 +1,6 @@
|
|||||||
> [!IMPORTANT]
|
> [!IMPORTANT]
|
||||||
> `master主分支`最新动态(2025.2.4): 增加deepseek-r1支持
|
> 2024.10.10: 突发停电，紧急恢复了提供[whl包](https://drive.google.com/file/d/19U_hsLoMrjOlQSzYS3pzWX9fTzyusArP/view?usp=sharing)的文件服务器
|
||||||
> `frontier开发分支`最新动态(2024.12.9): 更新对话时间线功能，优化xelatex论文翻译
|
> 2024.10.8: 版本3.90加入对llama-index的初步支持，版本3.80加入插件二级菜单功能（详见wiki）
|
||||||
> `wiki文档`最新动态(2024.12.5): 更新ollama接入指南
|
|
||||||
>
|
|
||||||
> 2025.2.2: 三分钟快速接入最强qwen2.5-max[视频](https://www.bilibili.com/video/BV1LeFuerEG4)
|
|
||||||
> 2025.2.1: 支持自定义字体
|
|
||||||
> 2024.10.10: 突发停电，紧急恢复了提供[whl包](https://drive.google.com/drive/folders/14kR-3V-lIbvGxri4AHc8TpiA1fqsw7SK?usp=sharing)的文件服务器
|
|
||||||
> 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)
|
> 2024.5.1: 加入Doc2x翻译PDF论文的功能，[查看详情](https://github.com/binary-husky/gpt_academic/wiki/Doc2x)
|
||||||
> 2024.3.11: 全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！ SoVits语音克隆模块，[查看详情](https://www.bilibili.com/video/BV1Rp421S7tF/)
|
> 2024.3.11: 全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！ SoVits语音克隆模块，[查看详情](https://www.bilibili.com/video/BV1Rp421S7tF/)
|
||||||
> 2024.1.17: 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。
|
> 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。
|
||||||
@@ -129,20 +124,20 @@ Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼
|
|||||||
|
|
||||||
```mermaid
|
```mermaid
|
||||||
flowchart TD
|
flowchart TD
|
||||||
A{"安装方法"} --> W1("I 🔑直接运行 (Windows, Linux or MacOS)")
|
A{"安装方法"} --> W1("I. 🔑直接运行 (Windows, Linux or MacOS)")
|
||||||
W1 --> W11["1 Python pip包管理依赖"]
|
W1 --> W11["1. Python pip包管理依赖"]
|
||||||
W1 --> W12["2 Anaconda包管理依赖（推荐⭐）"]
|
W1 --> W12["2. Anaconda包管理依赖（推荐⭐）"]
|
||||||
|
|
||||||
A --> W2["II 🐳使用Docker (Windows, Linux or MacOS)"]
|
A --> W2["II. 🐳使用Docker (Windows, Linux or MacOS)"]
|
||||||
|
|
||||||
W2 --> k1["1 部署项目全部能力的大镜像（推荐⭐）"]
|
W2 --> k1["1. 部署项目全部能力的大镜像（推荐⭐）"]
|
||||||
W2 --> k2["2 仅在线模型（GPT, GLM4等）镜像"]
|
W2 --> k2["2. 仅在线模型（GPT, GLM4等）镜像"]
|
||||||
W2 --> k3["3 在线模型 + Latex的大镜像"]
|
W2 --> k3["3. 在线模型 + Latex的大镜像"]
|
||||||
|
|
||||||
A --> W4["IV 🚀其他部署方法"]
|
A --> W4["IV. 🚀其他部署方法"]
|
||||||
W4 --> C1["1 Windows/MacOS 一键安装运行脚本（推荐⭐）"]
|
W4 --> C1["1. Windows/MacOS 一键安装运行脚本（推荐⭐）"]
|
||||||
W4 --> C2["2 Huggingface, Sealos远程部署"]
|
W4 --> C2["2. Huggingface, Sealos远程部署"]
|
||||||
W4 --> C4["3 其他 ..."]
|
W4 --> C4["3. ... 其他 ..."]
|
||||||
```
|
```
|
||||||
|
|
||||||
### 安装方法I：直接运行 (Windows, Linux or MacOS)
|
### 安装方法I：直接运行 (Windows, Linux or MacOS)
|
||||||
@@ -175,32 +170,26 @@ flowchart TD
|
|||||||
```
|
```
|
||||||
|
|
||||||
|
|
||||||
<details><summary>如果需要支持清华ChatGLM系列/复旦MOSS/RWKV作为后端，请点击展开此处</summary>
|
<details><summary>如果需要支持清华ChatGLM2/复旦MOSS/RWKV作为后端，请点击展开此处</summary>
|
||||||
<p>
|
<p>
|
||||||
|
|
||||||
【可选步骤】如果需要支持清华ChatGLM系列/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
|
【可选步骤】如果需要支持清华ChatGLM3/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
|
||||||
|
|
||||||
```sh
|
```sh
|
||||||
# 【可选步骤I】支持清华ChatGLM3。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
|
# 【可选步骤I】支持清华ChatGLM3。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
|
||||||
python -m pip install -r request_llms/requirements_chatglm.txt
|
python -m pip install -r request_llms/requirements_chatglm.txt
|
||||||
|
|
||||||
# 【可选步骤II】支持清华ChatGLM4 注意：此模型至少需要24G显存
|
# 【可选步骤II】支持复旦MOSS
|
||||||
python -m pip install -r request_llms/requirements_chatglm4.txt
|
|
||||||
# 可使用modelscope下载ChatGLM4模型
|
|
||||||
# pip install modelscope
|
|
||||||
# modelscope download --model ZhipuAI/glm-4-9b-chat --local_dir ./THUDM/glm-4-9b-chat
|
|
||||||
|
|
||||||
# 【可选步骤III】支持复旦MOSS
|
|
||||||
python -m pip install -r request_llms/requirements_moss.txt
|
python -m pip install -r request_llms/requirements_moss.txt
|
||||||
git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss # 注意执行此行代码时，必须处于项目根路径
|
git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss # 注意执行此行代码时，必须处于项目根路径
|
||||||
|
|
||||||
# 【可选步骤IV】支持RWKV Runner
|
# 【可选步骤III】支持RWKV Runner
|
||||||
参考wiki：https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
|
参考wiki：https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
|
||||||
|
|
||||||
# 【可选步骤V】确保config.py配置文件的AVAIL_LLM_MODELS包含了期望的模型，目前支持的全部模型如下(jittorllms系列目前仅支持docker方案)：
|
# 【可选步骤IV】确保config.py配置文件的AVAIL_LLM_MODELS包含了期望的模型，目前支持的全部模型如下(jittorllms系列目前仅支持docker方案)：
|
||||||
AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
|
AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
|
||||||
|
|
||||||
# 【可选步骤VI】支持本地模型INT8,INT4量化（这里所指的模型本身不是量化版本，目前deepseek-coder支持，后面测试后会加入更多模型量化选择）
|
# 【可选步骤V】支持本地模型INT8,INT4量化（这里所指的模型本身不是量化版本，目前deepseek-coder支持，后面测试后会加入更多模型量化选择）
|
||||||
pip install bitsandbyte
|
pip install bitsandbyte
|
||||||
# windows用户安装bitsandbytes需要使用下面bitsandbytes-windows-webui
|
# windows用户安装bitsandbytes需要使用下面bitsandbytes-windows-webui
|
||||||
python -m pip install bitsandbytes --prefer-binary --extra-index-url=https://jllllll.github.io/bitsandbytes-windows-webui
|
python -m pip install bitsandbytes --prefer-binary --extra-index-url=https://jllllll.github.io/bitsandbytes-windows-webui
|
||||||
|
|||||||
70
config.py
70
config.py
@@ -7,16 +7,11 @@
|
|||||||
Configuration reading priority: environment variable > config_private.py > config.py
|
Configuration reading priority: environment variable > config_private.py > config.py
|
||||||
"""
|
"""
|
||||||
|
|
||||||
# [step 1-1]>> ( 接入GPT等模型 ) API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
|
# [step 1]>> API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
|
||||||
API_KEY = "在此处填写APIKEY" # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
|
API_KEY = "此处填API密钥" # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
|
||||||
|
|
||||||
# [step 1-2]>> ( 接入通义 qwen-max ) 接入通义千问在线大模型，api-key获取地址 https://dashscope.console.aliyun.com/
|
|
||||||
DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
|
|
||||||
|
|
||||||
# [step 1-3]>> ( 接入 deepseek-reasoner, 即 deepseek-r1 ) 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
|
# [step 2]>> 改为True应用代理，如果直接在海外服务器部署，此处不修改；如果使用本地或无地域限制的大模型时，此处也不需要修改
|
||||||
DEEPSEEK_API_KEY = "sk-d99b8cc6b7414cc88a5d950a3ff7585e"
|
|
||||||
|
|
||||||
# [step 2]>> 改为True应用代理。如果使用本地或无地域限制的大模型时，此处不修改；如果直接在海外服务器部署，此处不修改
|
|
||||||
USE_PROXY = False
|
USE_PROXY = False
|
||||||
if USE_PROXY:
|
if USE_PROXY:
|
||||||
"""
|
"""
|
||||||
@@ -37,13 +32,11 @@ else:
|
|||||||
|
|
||||||
# [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 )
|
# [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 ↓↓↓
|
LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
|
||||||
AVAIL_LLM_MODELS = ["qwen-max", "o1-mini", "o1-mini-2024-09-12", "o1", "o1-2024-12-17", "o1-preview", "o1-preview-2024-09-12",
|
AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
|
||||||
"gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
|
|
||||||
"gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
|
"gpt-4o", "gpt-4o-mini", "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-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",
|
"gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
|
||||||
"gemini-1.5-pro", "chatglm3", "chatglm4",
|
"gemini-1.5-pro", "chatglm3"
|
||||||
"deepseek-chat", "deepseek-coder", "deepseek-reasoner"
|
|
||||||
]
|
]
|
||||||
|
|
||||||
EMBEDDING_MODEL = "text-embedding-3-small"
|
EMBEDDING_MODEL = "text-embedding-3-small"
|
||||||
@@ -54,7 +47,7 @@ EMBEDDING_MODEL = "text-embedding-3-small"
|
|||||||
# "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-flash",
|
# "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-flash",
|
||||||
# "qianfan", "deepseekcoder",
|
# "qianfan", "deepseekcoder",
|
||||||
# "spark", "sparkv2", "sparkv3", "sparkv3.5", "sparkv4",
|
# "spark", "sparkv2", "sparkv3", "sparkv3.5", "sparkv4",
|
||||||
# "qwen-turbo", "qwen-plus", "qwen-local",
|
# "qwen-turbo", "qwen-plus", "qwen-max", "qwen-local",
|
||||||
# "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
|
# "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"
|
# "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",
|
# "claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
|
||||||
@@ -62,7 +55,6 @@ EMBEDDING_MODEL = "text-embedding-3-small"
|
|||||||
# "deepseek-chat" ,"deepseek-coder",
|
# "deepseek-chat" ,"deepseek-coder",
|
||||||
# "gemini-1.5-flash",
|
# "gemini-1.5-flash",
|
||||||
# "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
|
# "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
|
||||||
# "grok-beta",
|
|
||||||
# ]
|
# ]
|
||||||
# --- --- --- ---
|
# --- --- --- ---
|
||||||
# 此外，您还可以在接入one-api/vllm/ollama/Openroute时，
|
# 此外，您还可以在接入one-api/vllm/ollama/Openroute时，
|
||||||
@@ -89,30 +81,6 @@ DEFAULT_WORKER_NUM = 3
|
|||||||
THEME = "Default"
|
THEME = "Default"
|
||||||
AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gstaff/Xkcd", "NoCrypt/Miku"]
|
AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gstaff/Xkcd", "NoCrypt/Miku"]
|
||||||
|
|
||||||
FONT = "Theme-Default-Font"
|
|
||||||
AVAIL_FONTS = [
|
|
||||||
"默认值(Theme-Default-Font)",
|
|
||||||
"宋体(SimSun)",
|
|
||||||
"黑体(SimHei)",
|
|
||||||
"楷体(KaiTi)",
|
|
||||||
"仿宋(FangSong)",
|
|
||||||
"华文细黑(STHeiti Light)",
|
|
||||||
"华文楷体(STKaiti)",
|
|
||||||
"华文仿宋(STFangsong)",
|
|
||||||
"华文宋体(STSong)",
|
|
||||||
"华文中宋(STZhongsong)",
|
|
||||||
"华文新魏(STXinwei)",
|
|
||||||
"华文隶书(STLiti)",
|
|
||||||
"思源宋体(Source Han Serif CN VF@https://chinese-fonts-cdn.deno.dev/packages/syst/dist/SourceHanSerifCN/result.css)",
|
|
||||||
"月星楷(Moon Stars Kai HW@https://chinese-fonts-cdn.deno.dev/packages/moon-stars-kai/dist/MoonStarsKaiHW-Regular/result.css)",
|
|
||||||
"珠圆体(MaokenZhuyuanTi@https://chinese-fonts-cdn.deno.dev/packages/mkzyt/dist/猫啃珠圆体/result.css)",
|
|
||||||
"平方萌萌哒(PING FANG MENG MNEG DA@https://chinese-fonts-cdn.deno.dev/packages/pfmmd/dist/平方萌萌哒/result.css)",
|
|
||||||
"Helvetica",
|
|
||||||
"ui-sans-serif",
|
|
||||||
"sans-serif",
|
|
||||||
"system-ui"
|
|
||||||
]
|
|
||||||
|
|
||||||
|
|
||||||
# 默认的系统提示词（system prompt）
|
# 默认的系统提示词（system prompt）
|
||||||
INIT_SYS_PROMPT = "Serve me as a writing and programming assistant."
|
INIT_SYS_PROMPT = "Serve me as a writing and programming assistant."
|
||||||
@@ -164,15 +132,16 @@ MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
|
|||||||
QWEN_LOCAL_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
|
QWEN_LOCAL_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
|
||||||
|
|
||||||
|
|
||||||
|
# 接入通义千问在线大模型 https://dashscope.console.aliyun.com/
|
||||||
|
DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
|
||||||
|
|
||||||
|
|
||||||
# 百度千帆（LLM_MODEL="qianfan"）
|
# 百度千帆（LLM_MODEL="qianfan"）
|
||||||
BAIDU_CLOUD_API_KEY = ''
|
BAIDU_CLOUD_API_KEY = ''
|
||||||
BAIDU_CLOUD_SECRET_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", "ERNIE-Speed-128K", "ERNIE-Speed-8K", "ERNIE-Lite-8K"
|
||||||
|
|
||||||
|
|
||||||
# 如果使用ChatGLM3或ChatGLM4本地模型，请把 LLM_MODEL="chatglm3" 或LLM_MODEL="chatglm4"，并在此处指定模型路径
|
|
||||||
CHATGLM_LOCAL_MODEL_PATH = "THUDM/glm-4-9b-chat" # 例如"/home/hmp/ChatGLM3-6B/"
|
|
||||||
|
|
||||||
# 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
|
# 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
|
||||||
CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b-pt-128-1e-2/checkpoint-100"
|
CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b-pt-128-1e-2/checkpoint-100"
|
||||||
|
|
||||||
@@ -266,11 +235,13 @@ MOONSHOT_API_KEY = ""
|
|||||||
YIMODEL_API_KEY = ""
|
YIMODEL_API_KEY = ""
|
||||||
|
|
||||||
|
|
||||||
|
# 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
|
||||||
|
DEEPSEEK_API_KEY = ""
|
||||||
|
|
||||||
|
|
||||||
# 紫东太初大模型 https://ai-maas.wair.ac.cn
|
# 紫东太初大模型 https://ai-maas.wair.ac.cn
|
||||||
TAICHU_API_KEY = ""
|
TAICHU_API_KEY = ""
|
||||||
|
|
||||||
# Grok API KEY
|
|
||||||
GROK_API_KEY = ""
|
|
||||||
|
|
||||||
# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
|
# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
|
||||||
MATHPIX_APPID = ""
|
MATHPIX_APPID = ""
|
||||||
@@ -302,8 +273,8 @@ GROBID_URLS = [
|
|||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
# Searxng互联网检索服务（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
|
# Searxng互联网检索服务
|
||||||
SEARXNG_URLS = [ f"https://kaletianlre-beardvs{i}dd.hf.space/" for i in range(1,5) ]
|
SEARXNG_URL = "https://cloud-1.agent-matrix.com/"
|
||||||
|
|
||||||
|
|
||||||
# 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
|
# 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
|
||||||
@@ -327,7 +298,7 @@ ARXIV_CACHE_DIR = "gpt_log/arxiv_cache"
|
|||||||
|
|
||||||
|
|
||||||
# 除了连接OpenAI之外，还有哪些场合允许使用代理，请尽量不要修改
|
# 除了连接OpenAI之外，还有哪些场合允许使用代理，请尽量不要修改
|
||||||
WHEN_TO_USE_PROXY = ["Connect_OpenAI", "Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
|
WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
|
||||||
"Warmup_Modules", "Nougat_Download", "AutoGen", "Connect_OpenAI_Embedding"]
|
"Warmup_Modules", "Nougat_Download", "AutoGen", "Connect_OpenAI_Embedding"]
|
||||||
|
|
||||||
|
|
||||||
@@ -339,10 +310,6 @@ PLUGIN_HOT_RELOAD = False
|
|||||||
NUM_CUSTOM_BASIC_BTN = 4
|
NUM_CUSTOM_BASIC_BTN = 4
|
||||||
|
|
||||||
|
|
||||||
# 媒体智能体的服务地址（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
|
|
||||||
DAAS_SERVER_URLS = [ f"https://niuziniu-biligpt{i}.hf.space/stream" for i in range(1,5) ]
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
"""
|
"""
|
||||||
--------------- 配置关联关系说明 ---------------
|
--------------- 配置关联关系说明 ---------------
|
||||||
@@ -402,7 +369,6 @@ DAAS_SERVER_URLS = [ f"https://niuziniu-biligpt{i}.hf.space/stream" for i in ran
|
|||||||
|
|
||||||
本地大模型示意图
|
本地大模型示意图
|
||||||
│
|
│
|
||||||
├── "chatglm4"
|
|
||||||
├── "chatglm3"
|
├── "chatglm3"
|
||||||
├── "chatglm"
|
├── "chatglm"
|
||||||
├── "chatglm_onnx"
|
├── "chatglm_onnx"
|
||||||
@@ -433,7 +399,7 @@ DAAS_SERVER_URLS = [ f"https://niuziniu-biligpt{i}.hf.space/stream" for i in ran
|
|||||||
插件在线服务配置依赖关系示意图
|
插件在线服务配置依赖关系示意图
|
||||||
│
|
│
|
||||||
├── 互联网检索
|
├── 互联网检索
|
||||||
│ └── SEARXNG_URLS
|
│ └── SEARXNG_URL
|
||||||
│
|
│
|
||||||
├── 语音功能
|
├── 语音功能
|
||||||
│ ├── ENABLE_AUDIO
|
│ ├── ENABLE_AUDIO
|
||||||
|
|||||||
@@ -1,444 +0,0 @@
|
|||||||
"""
|
|
||||||
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.
|
|
||||||
Configuration reading priority: environment variable > config_private.py > config.py
|
|
||||||
"""
|
|
||||||
|
|
||||||
# [step 1-1]>> ( 接入GPT等模型 ) API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
|
|
||||||
API_KEY = "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" # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey1,fkxxxx-api2dkey2"
|
|
||||||
|
|
||||||
# [step 1-2]>> ( 接入通义 qwen-max ) 接入通义千问在线大模型，api-key获取地址 https://dashscope.console.aliyun.com/
|
|
||||||
DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
|
|
||||||
|
|
||||||
# [step 1-3]>> ( 接入 deepseek-reasoner, 即 deepseek-r1 ) 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
|
|
||||||
DEEPSEEK_API_KEY = "sk-d99b8cc6b7414cc88a5d950a3ff7585e"
|
|
||||||
|
|
||||||
# [step 2]>> 改为True应用代理。如果使用本地或无地域限制的大模型时，此处不修改；如果直接在海外服务器部署，此处不修改
|
|
||||||
USE_PROXY = True
|
|
||||||
if USE_PROXY:
|
|
||||||
proxies = {
|
|
||||||
"http":"socks5h://192.168.8.9:1070", # 再例如 "http": "http://127.0.0.1:7890",
|
|
||||||
"https":"socks5h://192.168.8.9:1070", # 再例如 "https": "http://127.0.0.1:7890",
|
|
||||||
}
|
|
||||||
else:
|
|
||||||
proxies = None
|
|
||||||
DEFAULT_WORKER_NUM = 256
|
|
||||||
|
|
||||||
# [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-4-32k" # 可选 ↓↓↓
|
|
||||||
AVAIL_LLM_MODELS = ["deepseek-chat", "deepseek-coder", "deepseek-reasoner",
|
|
||||||
"gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
|
|
||||||
"gpt-4o", "gpt-4o-mini", "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-1.5-pro", "chatglm3", "chatglm4",
|
|
||||||
]
|
|
||||||
|
|
||||||
EMBEDDING_MODEL = "text-embedding-3-small"
|
|
||||||
|
|
||||||
# --- --- --- ---
|
|
||||||
# P.S. 其他可用的模型还包括
|
|
||||||
# AVAIL_LLM_MODELS = [
|
|
||||||
# "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-flash",
|
|
||||||
# "qianfan", "deepseekcoder",
|
|
||||||
# "spark", "sparkv2", "sparkv3", "sparkv3.5", "sparkv4",
|
|
||||||
# "qwen-turbo", "qwen-plus", "qwen-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",
|
|
||||||
# "gemini-1.5-flash",
|
|
||||||
# "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
|
|
||||||
# "grok-beta",
|
|
||||||
# ]
|
|
||||||
# --- --- --- ---
|
|
||||||
# 此外，您还可以在接入one-api/vllm/ollama/Openroute时，
|
|
||||||
# 使用"one-api-*","vllm-*","ollama-*","openrouter-*"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)","openrouter-openai/gpt-4o-mini","openrouter-openai/chatgpt-4o-latest"]
|
|
||||||
# --- --- --- ---
|
|
||||||
|
|
||||||
|
|
||||||
# --------------- 以下配置可以优化体验 ---------------
|
|
||||||
|
|
||||||
# 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"}
|
|
||||||
API_URL_REDIRECT = {}
|
|
||||||
|
|
||||||
|
|
||||||
# 多线程函数插件中，默认允许多少路线程同时访问OpenAI。Free trial users的限制是每分钟3次，Pay-as-you-go users的限制是每分钟3500次
|
|
||||||
# 一言以蔽之：免费（5刀）用户填3，OpenAI绑了信用卡的用户可以填 16 或者更高。提高限制请查询：https://platform.openai.com/docs/guides/rate-limits/overview
|
|
||||||
DEFAULT_WORKER_NUM = 64
|
|
||||||
|
|
||||||
|
|
||||||
# 色彩主题, 可选 ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast"]
|
|
||||||
# 更多主题, 请查阅Gradio主题商店: https://huggingface.co/spaces/gradio/theme-gallery 可选 ["Gstaff/Xkcd", "NoCrypt/Miku", ...]
|
|
||||||
THEME = "Default"
|
|
||||||
AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gstaff/Xkcd", "NoCrypt/Miku"]
|
|
||||||
|
|
||||||
FONT = "Theme-Default-Font"
|
|
||||||
AVAIL_FONTS = [
|
|
||||||
"默认值(Theme-Default-Font)",
|
|
||||||
"宋体(SimSun)",
|
|
||||||
"黑体(SimHei)",
|
|
||||||
"楷体(KaiTi)",
|
|
||||||
"仿宋(FangSong)",
|
|
||||||
"华文细黑(STHeiti Light)",
|
|
||||||
"华文楷体(STKaiti)",
|
|
||||||
"华文仿宋(STFangsong)",
|
|
||||||
"华文宋体(STSong)",
|
|
||||||
"华文中宋(STZhongsong)",
|
|
||||||
"华文新魏(STXinwei)",
|
|
||||||
"华文隶书(STLiti)",
|
|
||||||
"思源宋体(Source Han Serif CN VF@https://chinese-fonts-cdn.deno.dev/packages/syst/dist/SourceHanSerifCN/result.css)",
|
|
||||||
"月星楷(Moon Stars Kai HW@https://chinese-fonts-cdn.deno.dev/packages/moon-stars-kai/dist/MoonStarsKaiHW-Regular/result.css)",
|
|
||||||
"珠圆体(MaokenZhuyuanTi@https://chinese-fonts-cdn.deno.dev/packages/mkzyt/dist/猫啃珠圆体/result.css)",
|
|
||||||
"平方萌萌哒(PING FANG MENG MNEG DA@https://chinese-fonts-cdn.deno.dev/packages/pfmmd/dist/平方萌萌哒/result.css)",
|
|
||||||
"Helvetica",
|
|
||||||
"ui-sans-serif",
|
|
||||||
"sans-serif",
|
|
||||||
"system-ui"
|
|
||||||
]
|
|
||||||
|
|
||||||
|
|
||||||
# 默认的系统提示词（system prompt）
|
|
||||||
INIT_SYS_PROMPT = "Serve me as a writing and programming assistant."
|
|
||||||
|
|
||||||
|
|
||||||
# 对话窗的高度 （仅在LAYOUT="TOP-DOWN"时生效）
|
|
||||||
CHATBOT_HEIGHT = 1115
|
|
||||||
|
|
||||||
|
|
||||||
# 代码高亮
|
|
||||||
CODE_HIGHLIGHT = True
|
|
||||||
|
|
||||||
|
|
||||||
# 窗口布局
|
|
||||||
LAYOUT = "LEFT-RIGHT" # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下布局）
|
|
||||||
|
|
||||||
|
|
||||||
# 暗色模式 / 亮色模式
|
|
||||||
DARK_MODE = True
|
|
||||||
|
|
||||||
|
|
||||||
# 发送请求到OpenAI后，等待多久判定为超时
|
|
||||||
TIMEOUT_SECONDS = 60
|
|
||||||
|
|
||||||
|
|
||||||
# 网页的端口, -1代表随机端口
|
|
||||||
WEB_PORT = 19998
|
|
||||||
|
|
||||||
# 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 = 5
|
|
||||||
|
|
||||||
|
|
||||||
# 插件分类默认选项
|
|
||||||
DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
|
|
||||||
|
|
||||||
|
|
||||||
# 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"
|
|
||||||
|
|
||||||
|
|
||||||
# 选择本地模型变体（只有当AVAIL_LLM_MODELS包含了对应本地模型时，才会起作用）
|
|
||||||
# 如果你选择Qwen系列的模型，那么请在下面的QWEN_MODEL_SELECTION中指定具体的模型
|
|
||||||
# 也可以是具体的模型路径
|
|
||||||
QWEN_LOCAL_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
|
|
||||||
|
|
||||||
|
|
||||||
# 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"
|
|
||||||
|
|
||||||
|
|
||||||
# 如果使用ChatGLM3或ChatGLM4本地模型，请把 LLM_MODEL="chatglm3" 或LLM_MODEL="chatglm4"，并在此处指定模型路径
|
|
||||||
CHATGLM_LOCAL_MODEL_PATH = "THUDM/glm-4-9b-chat" # 例如"/home/hmp/ChatGLM3-6B/"
|
|
||||||
|
|
||||||
# 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
|
|
||||||
CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b-pt-128-1e-2/checkpoint-100"
|
|
||||||
|
|
||||||
|
|
||||||
# 本地LLM模型如ChatGLM的执行方式 CPU/GPU
|
|
||||||
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
|
|
||||||
|
|
||||||
|
|
||||||
# 是否在提交时自动清空输入框
|
|
||||||
AUTO_CLEAR_TXT = False
|
|
||||||
|
|
||||||
|
|
||||||
# 加一个live2d装饰
|
|
||||||
ADD_WAIFU = False
|
|
||||||
|
|
||||||
|
|
||||||
# 设置用户名和密码（不需要修改）（相关功能不稳定，与gradio版本和网络都相关，如果本地使用不建议加这个）
|
|
||||||
# [("username", "password"), ("username2", "password2"), ...]
|
|
||||||
AUTHENTICATION = [("van", "L807878712"),("林", "L807878712"),("源", "L807878712"),("欣", "L807878712"),("z", "czh123456789")]
|
|
||||||
|
|
||||||
|
|
||||||
# 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。）
|
|
||||||
CUSTOM_PATH = "/"
|
|
||||||
|
|
||||||
|
|
||||||
# HTTPS 秘钥和证书（不需要修改）
|
|
||||||
SSL_KEYFILE = ""
|
|
||||||
SSL_CERTFILE = ""
|
|
||||||
|
|
||||||
|
|
||||||
# 极少数情况下，openai的官方KEY需要伴随组织编码（格式如org-xxxxxxxxxxxxxxxxxxxxxxxx）使用
|
|
||||||
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_USER_TOKEN = ''
|
|
||||||
|
|
||||||
|
|
||||||
# 如果需要使用AZURE（方法一：单个azure模型部署）详情请见额外文档 docs\use_azure.md
|
|
||||||
AZURE_ENDPOINT = "https://你亲手写的api名称.openai.azure.com/"
|
|
||||||
AZURE_API_KEY = "填入azure openai api的密钥" # 建议直接在API_KEY处填写，该选项即将被弃用
|
|
||||||
AZURE_ENGINE = "填入你亲手写的部署名" # 读 docs\use_azure.md
|
|
||||||
|
|
||||||
|
|
||||||
# 如果需要使用AZURE（方法二：多个azure模型部署+动态切换）详情请见额外文档 docs\use_azure.md
|
|
||||||
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
|
|
||||||
ENABLE_AUDIO = False
|
|
||||||
ALIYUN_TOKEN="" # 例如 f37f30e0f9934c34a992f6f64f7eba4f
|
|
||||||
ALIYUN_APPKEY="" # 例如 RoPlZrM88DnAFkZK
|
|
||||||
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 = "DISABLE" # 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"
|
|
||||||
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
|
|
||||||
|
|
||||||
|
|
||||||
# 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 = ""
|
|
||||||
|
|
||||||
|
|
||||||
# 紫东太初大模型 https://ai-maas.wair.ac.cn
|
|
||||||
TAICHU_API_KEY = ""
|
|
||||||
|
|
||||||
# Grok API KEY
|
|
||||||
GROK_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 = ""
|
|
||||||
|
|
||||||
|
|
||||||
# Google Gemini API-Key
|
|
||||||
GEMINI_API_KEY = ''
|
|
||||||
|
|
||||||
|
|
||||||
# HUGGINGFACE的TOKEN，下载LLAMA时起作用 https://huggingface.co/docs/hub/security-tokens
|
|
||||||
HUGGINGFACE_ACCESS_TOKEN = "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"
|
|
||||||
|
|
||||||
|
|
||||||
# GROBID服务器地址（填写多个可以均衡负载），用于高质量地读取PDF文档
|
|
||||||
# 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",
|
|
||||||
]
|
|
||||||
|
|
||||||
|
|
||||||
# Searxng互联网检索服务（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
|
|
||||||
SEARXNG_URLS = [ f"https://kaletianlre-beardvs{i}dd.hf.space/" for i in range(1,5) ]
|
|
||||||
|
|
||||||
|
|
||||||
# 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
|
|
||||||
ALLOW_RESET_CONFIG = False
|
|
||||||
|
|
||||||
|
|
||||||
# 在使用AutoGen插件时，是否使用Docker容器运行代码
|
|
||||||
AUTOGEN_USE_DOCKER = False
|
|
||||||
|
|
||||||
|
|
||||||
# 临时的上传文件夹位置，请尽量不要修改
|
|
||||||
PATH_PRIVATE_UPLOAD = "private_upload"
|
|
||||||
|
|
||||||
|
|
||||||
# 日志文件夹的位置，请尽量不要修改
|
|
||||||
PATH_LOGGING = "gpt_log"
|
|
||||||
|
|
||||||
|
|
||||||
# 存储翻译好的arxiv论文的路径，请尽量不要修改
|
|
||||||
ARXIV_CACHE_DIR = "gpt_log/arxiv_cache"
|
|
||||||
|
|
||||||
|
|
||||||
# 除了连接OpenAI之外，还有哪些场合允许使用代理，请尽量不要修改
|
|
||||||
WHEN_TO_USE_PROXY = ["Connect_OpenAI", "Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
|
|
||||||
"Warmup_Modules", "Nougat_Download", "AutoGen", "Connect_OpenAI_Embedding"]
|
|
||||||
|
|
||||||
|
|
||||||
# 启用插件热加载
|
|
||||||
PLUGIN_HOT_RELOAD = False
|
|
||||||
|
|
||||||
|
|
||||||
# 自定义按钮的最大数量限制
|
|
||||||
NUM_CUSTOM_BASIC_BTN = 4
|
|
||||||
|
|
||||||
|
|
||||||
# 媒体智能体的服务地址（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
|
|
||||||
DAAS_SERVER_URLS = [ f"https://niuziniu-biligpt{i}.hf.space/stream" for i in range(1,5) ]
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
"""
|
|
||||||
--------------- 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
|
|
||||||
│ ├── API_KEY
|
|
||||||
│ ├── CUSTOM_API_KEY_PATTERN（不常用）
|
|
||||||
│ ├── API_ORG（不常用）
|
|
||||||
│ └── API_URL_REDIRECT（不常用）
|
|
||||||
│
|
|
||||||
├── "azure-gpt-3.5" 等azure模型（单个azure模型，不需要动态切换）
|
|
||||||
│ ├── API_KEY
|
|
||||||
│ ├── AZURE_ENDPOINT
|
|
||||||
│ ├── AZURE_API_KEY
|
|
||||||
│ ├── AZURE_ENGINE
|
|
||||||
│ └── API_URL_REDIRECT
|
|
||||||
│
|
|
||||||
├── "azure-gpt-3.5" 等azure模型（多个azure模型，需要动态切换，高优先级）
|
|
||||||
│ └── AZURE_CFG_ARRAY
|
|
||||||
│
|
|
||||||
├── "spark" 星火认知大模型 spark & sparkv2
|
|
||||||
│ ├── XFYUN_APPID
|
|
||||||
│ ├── XFYUN_API_SECRET
|
|
||||||
│ └── XFYUN_API_KEY
|
|
||||||
│
|
|
||||||
├── "claude-3-opus-20240229" 等claude模型
|
|
||||||
│ └── ANTHROPIC_API_KEY
|
|
||||||
│
|
|
||||||
├── "stack-claude"
|
|
||||||
│ ├── SLACK_CLAUDE_BOT_ID
|
|
||||||
│ └── SLACK_CLAUDE_USER_TOKEN
|
|
||||||
│
|
|
||||||
├── "qianfan" 百度千帆大模型库
|
|
||||||
│ ├── BAIDU_CLOUD_QIANFAN_MODEL
|
|
||||||
│ ├── 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
|
|
||||||
│
|
|
||||||
├── "qwen-turbo" 等通义千问大模型
|
|
||||||
│ └── DASHSCOPE_API_KEY
|
|
||||||
│
|
|
||||||
├── "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
|
|
||||||
|
|
||||||
|
|
||||||
本地大模型示意图
|
|
||||||
│
|
|
||||||
├── "chatglm4"
|
|
||||||
├── "chatglm3"
|
|
||||||
├── "chatglm"
|
|
||||||
├── "chatglm_onnx"
|
|
||||||
├── "chatglmft"
|
|
||||||
├── "internlm"
|
|
||||||
├── "moss"
|
|
||||||
├── "jittorllms_pangualpha"
|
|
||||||
├── "jittorllms_llama"
|
|
||||||
├── "deepseekcoder"
|
|
||||||
├── "qwen-local"
|
|
||||||
├── RWKV的支持见Wiki
|
|
||||||
└── "llama2"
|
|
||||||
|
|
||||||
|
|
||||||
用户图形界面布局依赖关系示意图
|
|
||||||
│
|
|
||||||
├── CHATBOT_HEIGHT 对话窗的高度
|
|
||||||
├── CODE_HIGHLIGHT 代码高亮
|
|
||||||
├── LAYOUT 窗口布局
|
|
||||||
├── DARK_MODE 暗色模式 / 亮色模式
|
|
||||||
├── DEFAULT_FN_GROUPS 插件分类默认选项
|
|
||||||
├── THEME 色彩主题
|
|
||||||
├── AUTO_CLEAR_TXT 是否在提交时自动清空输入框
|
|
||||||
├── ADD_WAIFU 加一个live2d装饰
|
|
||||||
└── ALLOW_RESET_CONFIG 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性
|
|
||||||
|
|
||||||
|
|
||||||
插件在线服务配置依赖关系示意图
|
|
||||||
│
|
|
||||||
├── 互联网检索
|
|
||||||
│ └── SEARXNG_URLS
|
|
||||||
│
|
|
||||||
├── 语音功能
|
|
||||||
│ ├── ENABLE_AUDIO
|
|
||||||
│ ├── ALIYUN_TOKEN
|
|
||||||
│ ├── ALIYUN_APPKEY
|
|
||||||
│ ├── ALIYUN_ACCESSKEY
|
|
||||||
│ └── ALIYUN_SECRET
|
|
||||||
│
|
|
||||||
└── PDF文档精准解析
|
|
||||||
├── GROBID_URLS
|
|
||||||
├── MATHPIX_APPID
|
|
||||||
└── MATHPIX_APPKEY
|
|
||||||
|
|
||||||
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
@@ -2,6 +2,7 @@ from toolbox import HotReload # HotReload 的意思是热更新，修改函数
|
|||||||
from toolbox import trimmed_format_exc
|
from toolbox import trimmed_format_exc
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
|
|
||||||
|
|
||||||
def get_crazy_functions():
|
def get_crazy_functions():
|
||||||
from crazy_functions.读文章写摘要 import 读文章写摘要
|
from crazy_functions.读文章写摘要 import 读文章写摘要
|
||||||
from crazy_functions.生成函数注释 import 批量生成函数注释
|
from crazy_functions.生成函数注释 import 批量生成函数注释
|
||||||
@@ -16,7 +17,7 @@ def get_crazy_functions():
|
|||||||
from crazy_functions.SourceCode_Analyse import 解析一个前端项目
|
from crazy_functions.SourceCode_Analyse 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 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.高级功能函数模板 import Demo_Wrap
|
||||||
from crazy_functions.Latex_Project_Polish import Latex英文润色
|
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.询问多个大语言模型 import 同时问询
|
||||||
from crazy_functions.SourceCode_Analyse import 解析一个Lua项目
|
from crazy_functions.SourceCode_Analyse import 解析一个Lua项目
|
||||||
from crazy_functions.SourceCode_Analyse import 解析一个CSharp项目
|
from crazy_functions.SourceCode_Analyse import 解析一个CSharp项目
|
||||||
@@ -27,13 +28,14 @@ def get_crazy_functions():
|
|||||||
from crazy_functions.Conversation_To_File import Conversation_To_File_Wrap
|
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.Conversation_To_File 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.辅助功能 import 清除缓存
|
||||||
|
from crazy_functions.批量文件询问 import 批量文件询问
|
||||||
from crazy_functions.Markdown_Translate import Markdown英译中
|
from crazy_functions.Markdown_Translate 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.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.PDF_Translate 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.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.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_Project_Polish import Latex中文润色
|
from crazy_functions.Latex全文润色 import Latex中文润色
|
||||||
from crazy_functions.Latex_Project_Polish import Latex英文纠错
|
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.Markdown_Translate import Markdown中译英
|
||||||
from crazy_functions.虚空终端 import 虚空终端
|
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.生成多种Mermaid图表 import Mermaid_Gen
|
||||||
@@ -49,16 +51,8 @@ def get_crazy_functions():
|
|||||||
from crazy_functions.Image_Generate_Wrap import ImageGen_Wrap
|
from crazy_functions.Image_Generate_Wrap import ImageGen_Wrap
|
||||||
from crazy_functions.SourceCode_Comment import 注释Python项目
|
from crazy_functions.SourceCode_Comment import 注释Python项目
|
||||||
from crazy_functions.SourceCode_Comment_Wrap import SourceCodeComment_Wrap
|
from crazy_functions.SourceCode_Comment_Wrap import SourceCodeComment_Wrap
|
||||||
from crazy_functions.VideoResource_GPT import 多媒体任务
|
|
||||||
|
|
||||||
function_plugins = {
|
function_plugins = {
|
||||||
"多媒体智能体": {
|
|
||||||
"Group": "智能体",
|
|
||||||
"Color": "stop",
|
|
||||||
"AsButton": False,
|
|
||||||
"Info": "【仅测试】多媒体任务",
|
|
||||||
"Function": HotReload(多媒体任务),
|
|
||||||
},
|
|
||||||
"虚空终端": {
|
"虚空终端": {
|
||||||
"Group": "对话|编程|学术|智能体",
|
"Group": "对话|编程|学术|智能体",
|
||||||
"Color": "stop",
|
"Color": "stop",
|
||||||
@@ -117,12 +111,13 @@ def get_crazy_functions():
|
|||||||
"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
|
"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
|
"Class": Arxiv_Localize, # 新一代插件需要注册Class
|
||||||
},
|
},
|
||||||
"批量总结Word文档": {
|
"批量文件询问": {
|
||||||
"Group": "学术",
|
"Group": "学术",
|
||||||
"Color": "stop",
|
"Color": "stop",
|
||||||
"AsButton": False,
|
"AsButton": False,
|
||||||
"Info": "批量总结word文档 | 输入参数为路径",
|
"AdvancedArgs": True,
|
||||||
"Function": HotReload(总结word文档),
|
"Info": "通过在高级参数区写入prompt，可自定义询问逻辑，默认情况下为总结逻辑 | 输入参数为路径",
|
||||||
|
"Function": HotReload(批量文件询问),
|
||||||
},
|
},
|
||||||
"解析整个Matlab项目": {
|
"解析整个Matlab项目": {
|
||||||
"Group": "编程",
|
"Group": "编程",
|
||||||
@@ -245,7 +240,7 @@ def get_crazy_functions():
|
|||||||
"AsButton": True, # 加入下拉菜单中
|
"AsButton": True, # 加入下拉菜单中
|
||||||
# "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
|
# "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
|
||||||
"Function": HotReload(连接网络回答问题),
|
"Function": HotReload(连接网络回答问题),
|
||||||
"Class": NetworkGPT_Wrap # 新一代插件需要注册Class
|
# "Class": NetworkGPT_Wrap # 新一代插件需要注册Class
|
||||||
},
|
},
|
||||||
"历史上的今天": {
|
"历史上的今天": {
|
||||||
"Group": "对话",
|
"Group": "对话",
|
||||||
@@ -727,6 +722,12 @@ def get_crazy_functions():
|
|||||||
logger.error("Load function plugin failed")
|
logger.error("Load function plugin failed")
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
# try:
|
# try:
|
||||||
# from crazy_functions.高级功能函数模板 import 测试图表渲染
|
# from crazy_functions.高级功能函数模板 import 测试图表渲染
|
||||||
# function_plugins.update({
|
# function_plugins.update({
|
||||||
@@ -741,6 +742,19 @@ def get_crazy_functions():
|
|||||||
# logger.error(trimmed_format_exc())
|
# logger.error(trimmed_format_exc())
|
||||||
# print('Load function plugin failed')
|
# print('Load function plugin failed')
|
||||||
|
|
||||||
|
# try:
|
||||||
|
# from crazy_functions.chatglm微调工具 import 微调数据集生成
|
||||||
|
# function_plugins.update({
|
||||||
|
# "黑盒模型学习: 微调数据集生成 (先上传数据集)": {
|
||||||
|
# "Color": "stop",
|
||||||
|
# "AsButton": False,
|
||||||
|
# "AdvancedArgs": True,
|
||||||
|
# "ArgsReminder": "针对数据集输入（如 绿帽子*深蓝色衬衫*黑色运动裤）给出指令，例如您可以将以下命令复制到下方: --llm_to_learn=azure-gpt-3.5 --prompt_prefix='根据下面的服装类型提示，想象一个穿着者，对这个人外貌、身处的环境、内心世界、过去经历进行描写。要求：100字以内，用第二人称。' --system_prompt=''",
|
||||||
|
# "Function": HotReload(微调数据集生成)
|
||||||
|
# }
|
||||||
|
# })
|
||||||
|
# except:
|
||||||
|
# print('Load function plugin failed')
|
||||||
|
|
||||||
"""
|
"""
|
||||||
设置默认值:
|
设置默认值:
|
||||||
@@ -760,23 +774,3 @@ def get_crazy_functions():
|
|||||||
function_plugins[name]["Color"] = "secondary"
|
function_plugins[name]["Color"] = "secondary"
|
||||||
|
|
||||||
return function_plugins
|
return function_plugins
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
def get_multiplex_button_functions():
|
|
||||||
"""多路复用主提交按钮的功能映射
|
|
||||||
"""
|
|
||||||
return {
|
|
||||||
"常规对话":
|
|
||||||
"",
|
|
||||||
|
|
||||||
"多模型对话":
|
|
||||||
"询问多个GPT模型", # 映射到上面的 `询问多个GPT模型` 插件
|
|
||||||
|
|
||||||
"智能召回 RAG":
|
|
||||||
"Rag智能召回", # 映射到上面的 `Rag智能召回` 插件
|
|
||||||
|
|
||||||
"多媒体查询":
|
|
||||||
"多媒体智能体", # 映射到上面的 `多媒体智能体` 插件
|
|
||||||
}
|
|
||||||
|
|||||||
@@ -7,7 +7,7 @@ from bs4 import BeautifulSoup
|
|||||||
from functools import lru_cache
|
from functools import lru_cache
|
||||||
from itertools import zip_longest
|
from itertools import zip_longest
|
||||||
from check_proxy import check_proxy
|
from check_proxy import check_proxy
|
||||||
from toolbox import CatchException, update_ui, get_conf, update_ui_lastest_msg
|
from toolbox import CatchException, update_ui, get_conf
|
||||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
|
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
|
||||||
from request_llms.bridge_all import model_info
|
from request_llms.bridge_all import model_info
|
||||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||||
@@ -115,8 +115,7 @@ def get_auth_ip():
|
|||||||
|
|
||||||
def searxng_request(query, proxies, categories='general', searxng_url=None, engines=None):
|
def searxng_request(query, proxies, categories='general', searxng_url=None, engines=None):
|
||||||
if searxng_url is None:
|
if searxng_url is None:
|
||||||
urls = get_conf("SEARXNG_URLS")
|
url = get_conf("SEARXNG_URL")
|
||||||
url = random.choice(urls)
|
|
||||||
else:
|
else:
|
||||||
url = searxng_url
|
url = searxng_url
|
||||||
|
|
||||||
@@ -193,38 +192,6 @@ def scrape_text(url, proxies) -> str:
|
|||||||
text = "\n".join(chunk for chunk in chunks if chunk)
|
text = "\n".join(chunk for chunk in chunks if chunk)
|
||||||
return text
|
return text
|
||||||
|
|
||||||
def internet_search_with_analysis_prompt(prompt, analysis_prompt, llm_kwargs, chatbot):
|
|
||||||
from toolbox import get_conf
|
|
||||||
proxies = get_conf('proxies')
|
|
||||||
categories = 'general'
|
|
||||||
searxng_url = None # 使用默认的searxng_url
|
|
||||||
engines = None # 使用默认的搜索引擎
|
|
||||||
yield from update_ui_lastest_msg(lastmsg=f"检索中: {prompt} ...", chatbot=chatbot, history=[], delay=1)
|
|
||||||
urls = searxng_request(prompt, proxies, categories, searxng_url, engines=engines)
|
|
||||||
yield from update_ui_lastest_msg(lastmsg=f"依次访问搜索到的网站 ...", chatbot=chatbot, history=[], delay=1)
|
|
||||||
if len(urls) == 0:
|
|
||||||
return None
|
|
||||||
max_search_result = 5 # 最多收纳多少个网页的结果
|
|
||||||
history = []
|
|
||||||
for index, url in enumerate(urls[:max_search_result]):
|
|
||||||
yield from update_ui_lastest_msg(lastmsg=f"依次访问搜索到的网站: {url['link']} ...", chatbot=chatbot, history=[], delay=1)
|
|
||||||
res = scrape_text(url['link'], proxies)
|
|
||||||
prefix = f"第{index}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
|
|
||||||
history.extend([prefix, res])
|
|
||||||
i_say = f"从以上搜索结果中抽取信息，然后回答问题：{prompt} {analysis_prompt}"
|
|
||||||
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=8192
|
|
||||||
)
|
|
||||||
gpt_say = predict_no_ui_long_connection(
|
|
||||||
inputs=i_say,
|
|
||||||
llm_kwargs=llm_kwargs,
|
|
||||||
history=history,
|
|
||||||
sys_prompt="请从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。",
|
|
||||||
console_slience=False,
|
|
||||||
)
|
|
||||||
return gpt_say
|
|
||||||
|
|
||||||
@CatchException
|
@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, user_request):
|
||||||
|
|||||||
@@ -1,4 +1,4 @@
|
|||||||
import random
|
|
||||||
from toolbox import get_conf
|
from toolbox import get_conf
|
||||||
from crazy_functions.Internet_GPT import 连接网络回答问题
|
from crazy_functions.Internet_GPT import 连接网络回答问题
|
||||||
from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
|
from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
|
||||||
@@ -20,9 +20,6 @@ class NetworkGPT_Wrap(GptAcademicPluginTemplate):
|
|||||||
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；
|
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；
|
||||||
|
|
||||||
"""
|
"""
|
||||||
urls = get_conf("SEARXNG_URLS")
|
|
||||||
url = random.choice(urls)
|
|
||||||
|
|
||||||
gui_definition = {
|
gui_definition = {
|
||||||
"main_input":
|
"main_input":
|
||||||
ArgProperty(title="输入问题", description="待通过互联网检索的问题，会自动读取输入框内容", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
|
ArgProperty(title="输入问题", description="待通过互联网检索的问题，会自动读取输入框内容", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||||
@@ -33,7 +30,7 @@ class NetworkGPT_Wrap(GptAcademicPluginTemplate):
|
|||||||
"optimizer":
|
"optimizer":
|
||||||
ArgProperty(title="搜索优化", options=["关闭", "开启", "开启(增强)"], default_value="关闭", description="是否使用搜索增强。注意这可能会消耗较多token", type="dropdown").model_dump_json(),
|
ArgProperty(title="搜索优化", options=["关闭", "开启", "开启(增强)"], default_value="关闭", description="是否使用搜索增强。注意这可能会消耗较多token", type="dropdown").model_dump_json(),
|
||||||
"searxng_url":
|
"searxng_url":
|
||||||
ArgProperty(title="Searxng服务地址", description="输入Searxng的地址", default_value=url, type="string").model_dump_json(), # 主输入，自动从输入框同步
|
ArgProperty(title="Searxng服务地址", description="输入Searxng的地址", default_value=get_conf("SEARXNG_URL"), type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||||
|
|
||||||
}
|
}
|
||||||
return gui_definition
|
return gui_definition
|
||||||
|
|||||||
@@ -559,7 +559,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
|
|||||||
project_folder = move_project(project_folder)
|
project_folder = move_project(project_folder)
|
||||||
|
|
||||||
# <-------------- set a hash tag for repeat-checking ------------->
|
# <-------------- set a hash tag for repeat-checking ------------->
|
||||||
with open(pj(project_folder, hash_tag + '.tag'), 'w', encoding='utf8') as f:
|
with open(pj(project_folder, hash_tag + '.tag'), 'w') as f:
|
||||||
f.write(hash_tag)
|
f.write(hash_tag)
|
||||||
f.close()
|
f.close()
|
||||||
|
|
||||||
|
|||||||
@@ -47,7 +47,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
|||||||
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)
|
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
|
return
|
||||||
except:
|
except:
|
||||||
chatbot.append([None, f"DOC2X服务不可用，请检查报错详细。{trimmed_format_exc_markdown()}"])
|
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)
|
yield from update_ui(chatbot=chatbot, history=history)
|
||||||
|
|
||||||
if method == "GROBID":
|
if method == "GROBID":
|
||||||
|
|||||||
@@ -1,11 +1,4 @@
|
|||||||
import os,glob
|
|
||||||
from typing import List
|
|
||||||
|
|
||||||
from shared_utils.fastapi_server import validate_path_safety
|
|
||||||
|
|
||||||
from toolbox import report_exception
|
|
||||||
from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_lastest_msg
|
from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_lastest_msg
|
||||||
from shared_utils.fastapi_server import validate_path_safety
|
|
||||||
from crazy_functions.crazy_utils import input_clipping
|
from crazy_functions.crazy_utils import input_clipping
|
||||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||||
|
|
||||||
@@ -14,37 +7,6 @@ MAX_HISTORY_ROUND = 5
|
|||||||
MAX_CONTEXT_TOKEN_LIMIT = 4096
|
MAX_CONTEXT_TOKEN_LIMIT = 4096
|
||||||
REMEMBER_PREVIEW = 1000
|
REMEMBER_PREVIEW = 1000
|
||||||
|
|
||||||
@CatchException
|
|
||||||
def handle_document_upload(files: List[str], llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request, rag_worker):
|
|
||||||
"""
|
|
||||||
Handles document uploads by extracting text and adding it to the vector store.
|
|
||||||
"""
|
|
||||||
from llama_index.core import Document
|
|
||||||
from crazy_functions.rag_fns.rag_file_support import extract_text, supports_format
|
|
||||||
user_name = chatbot.get_user()
|
|
||||||
checkpoint_dir = get_log_folder(user_name, plugin_name='experimental_rag')
|
|
||||||
|
|
||||||
for file_path in files:
|
|
||||||
try:
|
|
||||||
validate_path_safety(file_path, user_name)
|
|
||||||
text = extract_text(file_path)
|
|
||||||
if text is None:
|
|
||||||
chatbot.append(
|
|
||||||
[f"上传文件: {os.path.basename(file_path)}", f"文件解析失败，无法提取文本内容，请更换文件。失败原因可能为：1.文档格式过于复杂；2. 不支持的文件格式，支持的文件格式后缀有:" + ", ".join(supports_format)])
|
|
||||||
else:
|
|
||||||
chatbot.append(
|
|
||||||
[f"上传文件: {os.path.basename(file_path)}", f"上传文件前50个字符为:{text[:50]}。"])
|
|
||||||
document = Document(text=text, metadata={"source": file_path})
|
|
||||||
rag_worker.add_documents_to_vector_store([document])
|
|
||||||
chatbot.append([f"上传文件: {os.path.basename(file_path)}", "文件已成功添加到知识库。"])
|
|
||||||
except Exception as e:
|
|
||||||
report_exception(chatbot, history, a=f"处理文件: {file_path}", b=str(e))
|
|
||||||
|
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
# Main Q&A function with document upload support
|
|
||||||
@CatchException
|
@CatchException
|
||||||
def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||||
|
|
||||||
@@ -61,45 +23,28 @@ def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, u
|
|||||||
# 1. we retrieve rag worker from global context
|
# 1. we retrieve rag worker from global context
|
||||||
user_name = chatbot.get_user()
|
user_name = chatbot.get_user()
|
||||||
checkpoint_dir = get_log_folder(user_name, plugin_name='experimental_rag')
|
checkpoint_dir = get_log_folder(user_name, plugin_name='experimental_rag')
|
||||||
|
|
||||||
if user_name in RAG_WORKER_REGISTER:
|
if user_name in RAG_WORKER_REGISTER:
|
||||||
rag_worker = RAG_WORKER_REGISTER[user_name]
|
rag_worker = RAG_WORKER_REGISTER[user_name]
|
||||||
else:
|
else:
|
||||||
rag_worker = RAG_WORKER_REGISTER[user_name] = LlamaIndexRagWorker(
|
rag_worker = RAG_WORKER_REGISTER[user_name] = LlamaIndexRagWorker(
|
||||||
user_name,
|
user_name,
|
||||||
llm_kwargs,
|
llm_kwargs,
|
||||||
checkpoint_dir=checkpoint_dir,
|
checkpoint_dir=checkpoint_dir,
|
||||||
auto_load_checkpoint=True
|
auto_load_checkpoint=True)
|
||||||
)
|
|
||||||
|
|
||||||
current_context = f"{VECTOR_STORE_TYPE} @ {checkpoint_dir}"
|
current_context = f"{VECTOR_STORE_TYPE} @ {checkpoint_dir}"
|
||||||
tip = "提示：输入“清空向量数据库”可以清空RAG向量数据库"
|
tip = "提示：输入“清空向量数据库”可以清空RAG向量数据库"
|
||||||
|
if txt == "清空向量数据库":
|
||||||
# 2. Handle special commands
|
|
||||||
if os.path.exists(txt) and os.path.isdir(txt):
|
|
||||||
project_folder = txt
|
|
||||||
validate_path_safety(project_folder, chatbot.get_user())
|
|
||||||
# Extract file paths from the user input
|
|
||||||
# Assuming the user inputs file paths separated by commas after the command
|
|
||||||
file_paths = [f for f in glob.glob(f'{project_folder}/**/*', recursive=True)]
|
|
||||||
chatbot.append([txt, f'正在处理上传的文档 ({current_context}) ...'])
|
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
|
||||||
|
|
||||||
yield from handle_document_upload(file_paths, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request, rag_worker)
|
|
||||||
return
|
|
||||||
|
|
||||||
elif txt == "清空向量数据库":
|
|
||||||
chatbot.append([txt, f'正在清空 ({current_context}) ...'])
|
chatbot.append([txt, f'正在清空 ({current_context}) ...'])
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||||
rag_worker.purge_vector_store()
|
rag_worker.purge()
|
||||||
yield from update_ui_lastest_msg('已清空', chatbot, history, delay=0) # 刷新界面
|
yield from update_ui_lastest_msg('已清空', chatbot, history, delay=0) # 刷新界面
|
||||||
return
|
return
|
||||||
|
|
||||||
# 3. Normal Q&A processing
|
|
||||||
chatbot.append([txt, f'正在召回知识 ({current_context}) ...'])
|
chatbot.append([txt, f'正在召回知识 ({current_context}) ...'])
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||||
|
|
||||||
# 4. Clip history to reduce token consumption
|
# 2. clip history to reduce token consumption
|
||||||
|
# 2-1. reduce chat round
|
||||||
txt_origin = txt
|
txt_origin = txt
|
||||||
|
|
||||||
if len(history) > MAX_HISTORY_ROUND * 2:
|
if len(history) > MAX_HISTORY_ROUND * 2:
|
||||||
@@ -107,47 +52,41 @@ def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, u
|
|||||||
txt_clip, history, flags = input_clipping(txt, history, max_token_limit=MAX_CONTEXT_TOKEN_LIMIT, return_clip_flags=True)
|
txt_clip, history, flags = input_clipping(txt, history, max_token_limit=MAX_CONTEXT_TOKEN_LIMIT, return_clip_flags=True)
|
||||||
input_is_clipped_flag = (flags["original_input_len"] != flags["clipped_input_len"])
|
input_is_clipped_flag = (flags["original_input_len"] != flags["clipped_input_len"])
|
||||||
|
|
||||||
# 5. If input is clipped, add input to vector store before retrieve
|
# 2-2. if input is clipped, add input to vector store before retrieve
|
||||||
if input_is_clipped_flag:
|
if input_is_clipped_flag:
|
||||||
yield from update_ui_lastest_msg('检测到长输入, 正在向量化 ...', chatbot, history, delay=0) # 刷新界面
|
yield from update_ui_lastest_msg('检测到长输入, 正在向量化 ...', chatbot, history, delay=0) # 刷新界面
|
||||||
# Save input to vector store
|
# save input to vector store
|
||||||
rag_worker.add_text_to_vector_store(txt_origin)
|
rag_worker.add_text_to_vector_store(txt_origin)
|
||||||
yield from update_ui_lastest_msg('向量化完成 ...', chatbot, history, delay=0) # 刷新界面
|
yield from update_ui_lastest_msg('向量化完成 ...', chatbot, history, delay=0) # 刷新界面
|
||||||
|
|
||||||
if len(txt_origin) > REMEMBER_PREVIEW:
|
if len(txt_origin) > REMEMBER_PREVIEW:
|
||||||
HALF = REMEMBER_PREVIEW // 2
|
HALF = REMEMBER_PREVIEW//2
|
||||||
i_say_to_remember = txt[:HALF] + f" ...\n...(省略{len(txt_origin)-REMEMBER_PREVIEW}字)...\n... " + txt[-HALF:]
|
i_say_to_remember = txt[:HALF] + f" ...\n...(省略{len(txt_origin)-REMEMBER_PREVIEW}字)...\n... " + txt[-HALF:]
|
||||||
if (flags["original_input_len"] - flags["clipped_input_len"]) > HALF:
|
if (flags["original_input_len"] - flags["clipped_input_len"]) > HALF:
|
||||||
txt_clip = txt_clip + f" ...\n...(省略{len(txt_origin)-len(txt_clip)-HALF}字)...\n... " + txt[-HALF:]
|
txt_clip = txt_clip + f" ...\n...(省略{len(txt_origin)-len(txt_clip)-HALF}字)...\n... " + txt[-HALF:]
|
||||||
|
else:
|
||||||
|
pass
|
||||||
|
i_say = txt_clip
|
||||||
else:
|
else:
|
||||||
i_say_to_remember = i_say = txt_clip
|
i_say_to_remember = i_say = txt_clip
|
||||||
else:
|
else:
|
||||||
i_say_to_remember = i_say = txt_clip
|
i_say_to_remember = i_say = txt_clip
|
||||||
|
|
||||||
# 6. Search vector store and build prompts
|
# 3. we search vector store and build prompts
|
||||||
nodes = rag_worker.retrieve_from_store_with_query(i_say)
|
nodes = rag_worker.retrieve_from_store_with_query(i_say)
|
||||||
prompt = rag_worker.build_prompt(query=i_say, nodes=nodes)
|
prompt = rag_worker.build_prompt(query=i_say, nodes=nodes)
|
||||||
# 7. Query language model
|
|
||||||
if len(chatbot) != 0:
|
|
||||||
chatbot.pop(-1) # Pop temp chat, because we are going to add them again inside `request_gpt_model_in_new_thread_with_ui_alive`
|
|
||||||
|
|
||||||
|
# 4. it is time to query llms
|
||||||
|
if len(chatbot) != 0: chatbot.pop(-1) # pop temp chat, because we are going to add them again inside `request_gpt_model_in_new_thread_with_ui_alive`
|
||||||
model_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
model_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||||
inputs=prompt,
|
inputs=prompt, inputs_show_user=i_say,
|
||||||
inputs_show_user=i_say,
|
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||||
llm_kwargs=llm_kwargs,
|
|
||||||
chatbot=chatbot,
|
|
||||||
history=history,
|
|
||||||
sys_prompt=system_prompt,
|
sys_prompt=system_prompt,
|
||||||
retry_times_at_unknown_error=0
|
retry_times_at_unknown_error=0
|
||||||
)
|
)
|
||||||
|
|
||||||
# 8. Remember Q&A
|
# 5. remember what has been asked / answered
|
||||||
yield from update_ui_lastest_msg(
|
yield from update_ui_lastest_msg(model_say + '</br></br>' + f'对话记忆中, 请稍等 ({current_context}) ...', chatbot, history, delay=0.5) # 刷新界面
|
||||||
model_say + '</br></br>' + f'对话记忆中, 请稍等 ({current_context}) ...',
|
|
||||||
chatbot, history, delay=0.5
|
|
||||||
)
|
|
||||||
rag_worker.remember_qa(i_say_to_remember, model_say)
|
rag_worker.remember_qa(i_say_to_remember, model_say)
|
||||||
history.extend([i_say, model_say])
|
history.extend([i_say, model_say])
|
||||||
|
|
||||||
# 9. Final UI Update
|
yield from update_ui_lastest_msg(model_say, chatbot, history, delay=0, msg=tip) # 刷新界面
|
||||||
yield from update_ui_lastest_msg(model_say, chatbot, history, delay=0, msg=tip)
|
|
||||||
|
|||||||
@@ -1,204 +0,0 @@
|
|||||||
import requests
|
|
||||||
import random
|
|
||||||
import time
|
|
||||||
import re
|
|
||||||
import json
|
|
||||||
from bs4 import BeautifulSoup
|
|
||||||
from functools import lru_cache
|
|
||||||
from itertools import zip_longest
|
|
||||||
from check_proxy import check_proxy
|
|
||||||
from toolbox import CatchException, update_ui, get_conf, promote_file_to_downloadzone, update_ui_lastest_msg, generate_file_link
|
|
||||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
|
|
||||||
from request_llms.bridge_all import model_info
|
|
||||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
|
||||||
from crazy_functions.prompts.internet import SearchOptimizerPrompt, SearchAcademicOptimizerPrompt
|
|
||||||
from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
|
|
||||||
from textwrap import dedent
|
|
||||||
from loguru import logger
|
|
||||||
from pydantic import BaseModel, Field
|
|
||||||
|
|
||||||
class Query(BaseModel):
|
|
||||||
search_keyword: str = Field(description="search query for video resource")
|
|
||||||
|
|
||||||
|
|
||||||
class VideoResource(BaseModel):
|
|
||||||
thought: str = Field(description="analysis of the search results based on the user's query")
|
|
||||||
title: str = Field(description="title of the video")
|
|
||||||
author: str = Field(description="author/uploader of the video")
|
|
||||||
bvid: str = Field(description="unique ID of the video")
|
|
||||||
another_failsafe_bvid: str = Field(description="provide another bvid, the other one is not working")
|
|
||||||
|
|
||||||
|
|
||||||
def get_video_resource(search_keyword):
|
|
||||||
from crazy_functions.media_fns.get_media import search_videos
|
|
||||||
|
|
||||||
# Search for videos and return the first result
|
|
||||||
videos = search_videos(
|
|
||||||
search_keyword
|
|
||||||
)
|
|
||||||
|
|
||||||
# Return the first video if results exist, otherwise return None
|
|
||||||
return videos
|
|
||||||
|
|
||||||
def download_video(bvid, user_name, chatbot, history):
|
|
||||||
# from experimental_mods.get_bilibili_resource import download_bilibili
|
|
||||||
from crazy_functions.media_fns.get_media import download_video
|
|
||||||
# pause a while
|
|
||||||
tic_time = 8
|
|
||||||
for i in range(tic_time):
|
|
||||||
yield from update_ui_lastest_msg(
|
|
||||||
lastmsg=f"即将下载音频。等待{tic_time-i}秒后自动继续, 点击“停止”键取消此操作。",
|
|
||||||
chatbot=chatbot, history=[], delay=1)
|
|
||||||
|
|
||||||
# download audio
|
|
||||||
chatbot.append((None, "下载音频, 请稍等...")); yield from update_ui(chatbot=chatbot, history=history)
|
|
||||||
downloaded_files = yield from download_video(bvid, only_audio=True, user_name=user_name, chatbot=chatbot, history=history)
|
|
||||||
|
|
||||||
if len(downloaded_files) == 0:
|
|
||||||
# failed to download audio
|
|
||||||
return []
|
|
||||||
|
|
||||||
# preview
|
|
||||||
preview_list = [promote_file_to_downloadzone(fp) for fp in downloaded_files]
|
|
||||||
file_links = generate_file_link(preview_list)
|
|
||||||
yield from update_ui_lastest_msg(f"已完成的文件: <br/>" + file_links, chatbot=chatbot, history=history, delay=0)
|
|
||||||
chatbot.append((None, f"即将下载视频。"))
|
|
||||||
|
|
||||||
# pause a while
|
|
||||||
tic_time = 16
|
|
||||||
for i in range(tic_time):
|
|
||||||
yield from update_ui_lastest_msg(
|
|
||||||
lastmsg=f"即将下载视频。等待{tic_time-i}秒后自动继续, 点击“停止”键取消此操作。",
|
|
||||||
chatbot=chatbot, history=[], delay=1)
|
|
||||||
|
|
||||||
# download video
|
|
||||||
chatbot.append((None, "下载视频, 请稍等...")); yield from update_ui(chatbot=chatbot, history=history)
|
|
||||||
downloaded_files_part2 = yield from download_video(bvid, only_audio=False, user_name=user_name, chatbot=chatbot, history=history)
|
|
||||||
|
|
||||||
# preview
|
|
||||||
preview_list = [promote_file_to_downloadzone(fp) for fp in downloaded_files_part2]
|
|
||||||
file_links = generate_file_link(preview_list)
|
|
||||||
yield from update_ui_lastest_msg(f"已完成的文件: <br/>" + file_links, chatbot=chatbot, history=history, delay=0)
|
|
||||||
|
|
||||||
# return
|
|
||||||
return downloaded_files + downloaded_files_part2
|
|
||||||
|
|
||||||
|
|
||||||
class Strategy(BaseModel):
|
|
||||||
thought: str = Field(description="analysis of the user's wish, for example, can you recall the name of the resource?")
|
|
||||||
which_methods: str = Field(description="Which method to use to find the necessary information? choose from 'method_1' and 'method_2'.")
|
|
||||||
method_1_search_keywords: str = Field(description="Generate keywords to search the internet if you choose method 1, otherwise empty.")
|
|
||||||
method_2_generate_keywords: str = Field(description="Generate keywords for video download engine if you choose method 2, otherwise empty.")
|
|
||||||
|
|
||||||
|
|
||||||
@CatchException
|
|
||||||
def 多媒体任务(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
|
||||||
user_wish: str = txt
|
|
||||||
# query demos:
|
|
||||||
# - "我想找一首歌，里面有句歌词是“turn your face towards the sun”"
|
|
||||||
# - "一首歌，第一句是红豆生南国"
|
|
||||||
# - "一首音乐，中国航天任务专用的那首"
|
|
||||||
# - "戴森球计划在熔岩星球的音乐"
|
|
||||||
# - "hanser的百变什么精"
|
|
||||||
# - "打大圣残躯时的bgm"
|
|
||||||
# - "渊下宫战斗音乐"
|
|
||||||
|
|
||||||
# 搜索
|
|
||||||
chatbot.append((txt, "检索中, 请稍等..."))
|
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
|
||||||
if "跳过联网搜索" not in user_wish:
|
|
||||||
# 结构化生成
|
|
||||||
internet_search_keyword = user_wish
|
|
||||||
|
|
||||||
yield from update_ui_lastest_msg(lastmsg=f"发起互联网检索: {internet_search_keyword} ...", chatbot=chatbot, history=[], delay=1)
|
|
||||||
from crazy_functions.Internet_GPT import internet_search_with_analysis_prompt
|
|
||||||
result = yield from internet_search_with_analysis_prompt(
|
|
||||||
prompt=internet_search_keyword,
|
|
||||||
analysis_prompt="请根据搜索结果分析，获取用户需要找的资源的名称、作者、出处等信息。",
|
|
||||||
llm_kwargs=llm_kwargs,
|
|
||||||
chatbot=chatbot
|
|
||||||
)
|
|
||||||
|
|
||||||
yield from update_ui_lastest_msg(lastmsg=f"互联网检索结论: {result} \n\n 正在生成进一步检索方案 ...", chatbot=chatbot, history=[], delay=1)
|
|
||||||
rf_req = dedent(f"""
|
|
||||||
The user wish to get the following resource:
|
|
||||||
{user_wish}
|
|
||||||
Meanwhile, you can access another expert's opinion on the user's wish:
|
|
||||||
{result}
|
|
||||||
Generate search keywords (less than 5 keywords) for video download engine accordingly.
|
|
||||||
""")
|
|
||||||
else:
|
|
||||||
user_wish = user_wish.replace("跳过联网搜索", "").strip()
|
|
||||||
rf_req = dedent(f"""
|
|
||||||
The user wish to get the following resource:
|
|
||||||
{user_wish}
|
|
||||||
Generate reseach keywords (less than 5 keywords) accordingly.
|
|
||||||
""")
|
|
||||||
gpt_json_io = GptJsonIO(Query)
|
|
||||||
inputs = rf_req + 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=[])
|
|
||||||
analyze_res = run_gpt_fn(inputs, "")
|
|
||||||
logger.info(analyze_res)
|
|
||||||
query: Query = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
|
|
||||||
video_engine_keywords = query.search_keyword
|
|
||||||
# 关键词展示
|
|
||||||
chatbot.append((None, f"检索关键词已确认: {video_engine_keywords}。筛选中, 请稍等..."))
|
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
|
||||||
|
|
||||||
# 获取候选资源
|
|
||||||
candadate_dictionary: dict = get_video_resource(video_engine_keywords)
|
|
||||||
candadate_dictionary_as_str = json.dumps(candadate_dictionary, ensure_ascii=False, indent=4)
|
|
||||||
|
|
||||||
# 展示候选资源
|
|
||||||
candadate_display = "\n".join([f"{i+1}. {it['title']}" for i, it in enumerate(candadate_dictionary)])
|
|
||||||
chatbot.append((None, f"候选:\n\n{candadate_display}"))
|
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
|
||||||
|
|
||||||
# 结构化生成
|
|
||||||
rf_req_2 = dedent(f"""
|
|
||||||
The user wish to get the following resource:
|
|
||||||
{user_wish}
|
|
||||||
|
|
||||||
Select the most relevant and suitable video resource from the following search results:
|
|
||||||
{candadate_dictionary_as_str}
|
|
||||||
|
|
||||||
Note:
|
|
||||||
1. The first several search video results are more likely to satisfy the user's wish.
|
|
||||||
2. The time duration of the video should be less than 10 minutes.
|
|
||||||
3. You should analyze the search results first, before giving your answer.
|
|
||||||
4. Use Chinese if possible.
|
|
||||||
5. Beside the primary video selection, give a backup video resource `bvid`.
|
|
||||||
""")
|
|
||||||
gpt_json_io = GptJsonIO(VideoResource)
|
|
||||||
inputs = rf_req_2 + 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=[])
|
|
||||||
analyze_res = run_gpt_fn(inputs, "")
|
|
||||||
logger.info(analyze_res)
|
|
||||||
video_resource: VideoResource = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
|
|
||||||
|
|
||||||
# Display
|
|
||||||
chatbot.append(
|
|
||||||
(None,
|
|
||||||
f"分析：{video_resource.thought}" "<br/>"
|
|
||||||
f"选择: `{video_resource.title}`。" "<br/>"
|
|
||||||
f"作者：{video_resource.author}"
|
|
||||||
)
|
|
||||||
)
|
|
||||||
chatbot.append((None, f"下载中, 请稍等..."))
|
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
|
||||||
|
|
||||||
if video_resource and video_resource.bvid:
|
|
||||||
logger.info(video_resource)
|
|
||||||
downloaded = yield from download_video(video_resource.bvid, chatbot.get_user(), chatbot, history)
|
|
||||||
if not downloaded:
|
|
||||||
chatbot.append((None, f"下载失败, 尝试备选 ..."))
|
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
|
||||||
downloaded = yield from download_video(video_resource.another_failsafe_bvid, chatbot.get_user(), chatbot, history)
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
@CatchException
|
|
||||||
def debug(bvid, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
|
||||||
yield from download_video(bvid, chatbot.get_user(), chatbot, history)
|
|
||||||
141
crazy_functions/chatglm微调工具.py
Normal file
141
crazy_functions/chatglm微调工具.py
Normal file
@@ -0,0 +1,141 @@
|
|||||||
|
from toolbox import CatchException, update_ui, promote_file_to_downloadzone
|
||||||
|
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||||
|
import datetime, json
|
||||||
|
|
||||||
|
def fetch_items(list_of_items, batch_size):
|
||||||
|
for i in range(0, len(list_of_items), batch_size):
|
||||||
|
yield list_of_items[i:i + batch_size]
|
||||||
|
|
||||||
|
def string_to_options(arguments):
|
||||||
|
import argparse
|
||||||
|
import shlex
|
||||||
|
|
||||||
|
# Create an argparse.ArgumentParser instance
|
||||||
|
parser = argparse.ArgumentParser()
|
||||||
|
|
||||||
|
# Add command-line arguments
|
||||||
|
parser.add_argument("--llm_to_learn", type=str, help="LLM model to learn", default="gpt-3.5-turbo")
|
||||||
|
parser.add_argument("--prompt_prefix", type=str, help="Prompt prefix", default='')
|
||||||
|
parser.add_argument("--system_prompt", type=str, help="System prompt", default='')
|
||||||
|
parser.add_argument("--batch", type=int, help="System prompt", default=50)
|
||||||
|
parser.add_argument("--pre_seq_len", type=int, help="pre_seq_len", default=50)
|
||||||
|
parser.add_argument("--learning_rate", type=float, help="learning_rate", default=2e-2)
|
||||||
|
parser.add_argument("--num_gpus", type=int, help="num_gpus", default=1)
|
||||||
|
parser.add_argument("--json_dataset", type=str, help="json_dataset", default="")
|
||||||
|
parser.add_argument("--ptuning_directory", type=str, help="ptuning_directory", default="")
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
# Parse the arguments
|
||||||
|
args = parser.parse_args(shlex.split(arguments))
|
||||||
|
|
||||||
|
return args
|
||||||
|
|
||||||
|
@CatchException
|
||||||
|
def 微调数据集生成(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
|
||||||
|
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(("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:
|
||||||
|
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)
|
||||||
|
|
||||||
|
dat = []
|
||||||
|
with open(txt, 'r', encoding='utf8') as f:
|
||||||
|
for line in f.readlines():
|
||||||
|
json_dat = json.loads(line)
|
||||||
|
dat.append(json_dat["content"])
|
||||||
|
|
||||||
|
llm_kwargs['llm_model'] = arguments.llm_to_learn
|
||||||
|
for batch in fetch_items(dat, arguments.batch):
|
||||||
|
res = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||||
|
inputs_array=[f"{arguments.prompt_prefix}\n\n{b}" for b in (batch)],
|
||||||
|
inputs_show_user_array=[f"Show Nothing" for _ in (batch)],
|
||||||
|
llm_kwargs=llm_kwargs,
|
||||||
|
chatbot=chatbot,
|
||||||
|
history_array=[[] for _ in (batch)],
|
||||||
|
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')
|
||||||
|
|
||||||
|
promote_file_to_downloadzone(txt+'.generated.json', rename_file='generated.json', chatbot=chatbot)
|
||||||
|
return
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
@CatchException
|
||||||
|
def 启动微调(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
|
||||||
|
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 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:
|
||||||
|
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
|
||||||
|
learning_rate = arguments.learning_rate # 2e-2
|
||||||
|
num_gpus = arguments.num_gpus # 1
|
||||||
|
json_dataset = arguments.json_dataset # 't_code.json'
|
||||||
|
ptuning_directory = arguments.ptuning_directory # '/home/hmp/ChatGLM2-6B/ptuning'
|
||||||
|
|
||||||
|
command = f"torchrun --standalone --nnodes=1 --nproc-per-node={num_gpus} main.py \
|
||||||
|
--do_train \
|
||||||
|
--train_file AdvertiseGen/{json_dataset} \
|
||||||
|
--validation_file AdvertiseGen/{json_dataset} \
|
||||||
|
--preprocessing_num_workers 20 \
|
||||||
|
--prompt_column content \
|
||||||
|
--response_column summary \
|
||||||
|
--overwrite_cache \
|
||||||
|
--model_name_or_path THUDM/chatglm2-6b \
|
||||||
|
--output_dir output/clothgen-chatglm2-6b-pt-{pre_seq_len}-{learning_rate} \
|
||||||
|
--overwrite_output_dir \
|
||||||
|
--max_source_length 256 \
|
||||||
|
--max_target_length 256 \
|
||||||
|
--per_device_train_batch_size 1 \
|
||||||
|
--per_device_eval_batch_size 1 \
|
||||||
|
--gradient_accumulation_steps 16 \
|
||||||
|
--predict_with_generate \
|
||||||
|
--max_steps 100 \
|
||||||
|
--logging_steps 10 \
|
||||||
|
--save_steps 20 \
|
||||||
|
--learning_rate {learning_rate} \
|
||||||
|
--pre_seq_len {pre_seq_len} \
|
||||||
|
--quantization_bit 4"
|
||||||
|
|
||||||
|
process = subprocess.Popen(command, shell=True, cwd=ptuning_directory)
|
||||||
|
try:
|
||||||
|
process.communicate(timeout=3600*24)
|
||||||
|
except subprocess.TimeoutExpired:
|
||||||
|
process.kill()
|
||||||
|
return
|
||||||
@@ -169,7 +169,6 @@ def can_multi_process(llm) -> bool:
|
|||||||
def default_condition(llm) -> bool:
|
def default_condition(llm) -> bool:
|
||||||
# legacy condition
|
# legacy condition
|
||||||
if llm.startswith('gpt-'): return True
|
if llm.startswith('gpt-'): return True
|
||||||
if llm.startswith('chatgpt-'): return True
|
|
||||||
if llm.startswith('api2d-'): return True
|
if llm.startswith('api2d-'): return True
|
||||||
if llm.startswith('azure-'): return True
|
if llm.startswith('azure-'): return True
|
||||||
if llm.startswith('spark'): return True
|
if llm.startswith('spark'): return True
|
||||||
|
|||||||
450
crazy_functions/doc_fns/batch_file_query_doc.py
Normal file
450
crazy_functions/doc_fns/batch_file_query_doc.py
Normal file
@@ -0,0 +1,450 @@
|
|||||||
|
import os
|
||||||
|
import time
|
||||||
|
from abc import ABC, abstractmethod
|
||||||
|
from datetime import datetime
|
||||||
|
from docx import Document
|
||||||
|
from docx.enum.style import WD_STYLE_TYPE
|
||||||
|
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT, WD_LINE_SPACING
|
||||||
|
from docx.oxml.ns import qn
|
||||||
|
from docx.shared import Inches, Cm
|
||||||
|
from docx.shared import Pt, RGBColor, Inches
|
||||||
|
from typing import Dict, List, Tuple
|
||||||
|
|
||||||
|
|
||||||
|
class DocumentFormatter(ABC):
|
||||||
|
"""文档格式化基类，定义文档格式化的基本接口"""
|
||||||
|
|
||||||
|
def __init__(self, final_summary: str, file_summaries_map: Dict, failed_files: List[Tuple]):
|
||||||
|
self.final_summary = final_summary
|
||||||
|
self.file_summaries_map = file_summaries_map
|
||||||
|
self.failed_files = failed_files
|
||||||
|
|
||||||
|
@abstractmethod
|
||||||
|
def format_failed_files(self) -> str:
|
||||||
|
"""格式化失败文件列表"""
|
||||||
|
pass
|
||||||
|
|
||||||
|
@abstractmethod
|
||||||
|
def format_file_summaries(self) -> str:
|
||||||
|
"""格式化文件总结内容"""
|
||||||
|
pass
|
||||||
|
|
||||||
|
@abstractmethod
|
||||||
|
def create_document(self) -> str:
|
||||||
|
"""创建完整文档"""
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
class WordFormatter(DocumentFormatter):
|
||||||
|
"""Word格式文档生成器 - 符合中国政府公文格式规范(GB/T 9704-2012)，并进行了优化"""
|
||||||
|
|
||||||
|
def __init__(self, *args, **kwargs):
|
||||||
|
super().__init__(*args, **kwargs)
|
||||||
|
self.doc = Document()
|
||||||
|
self._setup_document()
|
||||||
|
self._create_styles()
|
||||||
|
# 初始化三级标题编号系统
|
||||||
|
self.numbers = {
|
||||||
|
1: 0, # 一级标题编号
|
||||||
|
2: 0, # 二级标题编号
|
||||||
|
3: 0 # 三级标题编号
|
||||||
|
}
|
||||||
|
|
||||||
|
def _setup_document(self):
|
||||||
|
"""设置文档基本格式，包括页面设置和页眉"""
|
||||||
|
sections = self.doc.sections
|
||||||
|
for section in sections:
|
||||||
|
# 设置页面大小为A4
|
||||||
|
section.page_width = Cm(21)
|
||||||
|
section.page_height = Cm(29.7)
|
||||||
|
# 设置页边距
|
||||||
|
section.top_margin = Cm(3.7) # 上边距37mm
|
||||||
|
section.bottom_margin = Cm(3.5) # 下边距35mm
|
||||||
|
section.left_margin = Cm(2.8) # 左边距28mm
|
||||||
|
section.right_margin = Cm(2.6) # 右边距26mm
|
||||||
|
# 设置页眉页脚距离
|
||||||
|
section.header_distance = Cm(2.0)
|
||||||
|
section.footer_distance = Cm(2.0)
|
||||||
|
|
||||||
|
# 添加页眉
|
||||||
|
header = section.header
|
||||||
|
header_para = header.paragraphs[0]
|
||||||
|
header_para.alignment = WD_PARAGRAPH_ALIGNMENT.RIGHT
|
||||||
|
header_run = header_para.add_run("该文档由GPT-academic生成")
|
||||||
|
header_run.font.name = '仿宋'
|
||||||
|
header_run._element.rPr.rFonts.set(qn('w:eastAsia'), '仿宋')
|
||||||
|
header_run.font.size = Pt(9)
|
||||||
|
|
||||||
|
def _create_styles(self):
|
||||||
|
"""创建文档样式"""
|
||||||
|
# 创建正文样式
|
||||||
|
style = self.doc.styles.add_style('Normal_Custom', WD_STYLE_TYPE.PARAGRAPH)
|
||||||
|
style.font.name = '仿宋'
|
||||||
|
style._element.rPr.rFonts.set(qn('w:eastAsia'), '仿宋')
|
||||||
|
style.font.size = Pt(14)
|
||||||
|
style.paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
|
||||||
|
style.paragraph_format.space_after = Pt(0)
|
||||||
|
style.paragraph_format.first_line_indent = Pt(28)
|
||||||
|
|
||||||
|
# 创建各级标题样式
|
||||||
|
self._create_heading_style('Title_Custom', '方正小标宋简体', 32, WD_PARAGRAPH_ALIGNMENT.CENTER)
|
||||||
|
self._create_heading_style('Heading1_Custom', '黑体', 22, WD_PARAGRAPH_ALIGNMENT.LEFT)
|
||||||
|
self._create_heading_style('Heading2_Custom', '黑体', 18, WD_PARAGRAPH_ALIGNMENT.LEFT)
|
||||||
|
self._create_heading_style('Heading3_Custom', '黑体', 16, WD_PARAGRAPH_ALIGNMENT.LEFT)
|
||||||
|
|
||||||
|
def _create_heading_style(self, style_name: str, font_name: str, font_size: int, alignment):
|
||||||
|
"""创建标题样式"""
|
||||||
|
style = self.doc.styles.add_style(style_name, WD_STYLE_TYPE.PARAGRAPH)
|
||||||
|
style.font.name = font_name
|
||||||
|
style._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
|
||||||
|
style.font.size = Pt(font_size)
|
||||||
|
style.font.bold = True
|
||||||
|
style.paragraph_format.alignment = alignment
|
||||||
|
style.paragraph_format.space_before = Pt(12)
|
||||||
|
style.paragraph_format.space_after = Pt(12)
|
||||||
|
style.paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
|
||||||
|
return style
|
||||||
|
|
||||||
|
def _get_heading_number(self, level: int) -> str:
|
||||||
|
"""
|
||||||
|
生成标题编号
|
||||||
|
|
||||||
|
Args:
|
||||||
|
level: 标题级别 (0-3)
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
str: 格式化的标题编号
|
||||||
|
"""
|
||||||
|
if level == 0: # 主标题不需要编号
|
||||||
|
return ""
|
||||||
|
|
||||||
|
self.numbers[level] += 1 # 增加当前级别的编号
|
||||||
|
|
||||||
|
# 重置下级标题编号
|
||||||
|
for i in range(level + 1, 4):
|
||||||
|
self.numbers[i] = 0
|
||||||
|
|
||||||
|
# 根据级别返回不同格式的编号
|
||||||
|
if level == 1:
|
||||||
|
return f"{self.numbers[1]}. "
|
||||||
|
elif level == 2:
|
||||||
|
return f"{self.numbers[1]}.{self.numbers[2]} "
|
||||||
|
elif level == 3:
|
||||||
|
return f"{self.numbers[1]}.{self.numbers[2]}.{self.numbers[3]} "
|
||||||
|
return ""
|
||||||
|
|
||||||
|
def _add_heading(self, text: str, level: int):
|
||||||
|
"""
|
||||||
|
添加带编号的标题
|
||||||
|
|
||||||
|
Args:
|
||||||
|
text: 标题文本
|
||||||
|
level: 标题级别 (0-3)
|
||||||
|
"""
|
||||||
|
style_map = {
|
||||||
|
0: 'Title_Custom',
|
||||||
|
1: 'Heading1_Custom',
|
||||||
|
2: 'Heading2_Custom',
|
||||||
|
3: 'Heading3_Custom'
|
||||||
|
}
|
||||||
|
|
||||||
|
number = self._get_heading_number(level)
|
||||||
|
paragraph = self.doc.add_paragraph(style=style_map[level])
|
||||||
|
|
||||||
|
if number:
|
||||||
|
number_run = paragraph.add_run(number)
|
||||||
|
font_size = 22 if level == 1 else (18 if level == 2 else 16)
|
||||||
|
self._get_run_style(number_run, '黑体', font_size, True)
|
||||||
|
|
||||||
|
text_run = paragraph.add_run(text)
|
||||||
|
font_size = 32 if level == 0 else (22 if level == 1 else (18 if level == 2 else 16))
|
||||||
|
self._get_run_style(text_run, '黑体', font_size, True)
|
||||||
|
|
||||||
|
# 主标题添加日期
|
||||||
|
if level == 0:
|
||||||
|
date_paragraph = self.doc.add_paragraph()
|
||||||
|
date_paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
|
||||||
|
date_run = date_paragraph.add_run(datetime.now().strftime('%Y年%m月%d日'))
|
||||||
|
self._get_run_style(date_run, '仿宋', 16, False)
|
||||||
|
|
||||||
|
return paragraph
|
||||||
|
|
||||||
|
def _get_run_style(self, run, font_name: str, font_size: int, bold: bool = False):
|
||||||
|
"""设置文本运行对象的样式"""
|
||||||
|
run.font.name = font_name
|
||||||
|
run._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
|
||||||
|
run.font.size = Pt(font_size)
|
||||||
|
run.font.bold = bold
|
||||||
|
|
||||||
|
def format_failed_files(self) -> str:
|
||||||
|
"""格式化失败文件列表"""
|
||||||
|
result = []
|
||||||
|
if not self.failed_files:
|
||||||
|
return "\n".join(result)
|
||||||
|
|
||||||
|
result.append("处理失败文件:")
|
||||||
|
for fp, reason in self.failed_files:
|
||||||
|
result.append(f"• {os.path.basename(fp)}: {reason}")
|
||||||
|
|
||||||
|
self._add_heading("处理失败文件", 1)
|
||||||
|
for fp, reason in self.failed_files:
|
||||||
|
self._add_content(f"• {os.path.basename(fp)}: {reason}", indent=False)
|
||||||
|
self.doc.add_paragraph()
|
||||||
|
|
||||||
|
return "\n".join(result)
|
||||||
|
|
||||||
|
def _add_content(self, text: str, indent: bool = True):
|
||||||
|
"""添加正文内容"""
|
||||||
|
paragraph = self.doc.add_paragraph(text, style='Normal_Custom')
|
||||||
|
if not indent:
|
||||||
|
paragraph.paragraph_format.first_line_indent = Pt(0)
|
||||||
|
return paragraph
|
||||||
|
|
||||||
|
def format_file_summaries(self) -> str:
|
||||||
|
"""
|
||||||
|
格式化文件总结内容，确保正确的标题层级
|
||||||
|
|
||||||
|
返回:
|
||||||
|
str: 格式化后的文件总结字符串
|
||||||
|
|
||||||
|
标题层级规则:
|
||||||
|
1. 一级标题为"各文件详细总结"
|
||||||
|
2. 如果文件有目录路径:
|
||||||
|
- 目录路径作为二级标题 (2.1, 2.2 等)
|
||||||
|
- 该目录下所有文件作为三级标题 (2.1.1, 2.1.2 等)
|
||||||
|
3. 如果文件没有目录路径:
|
||||||
|
- 文件直接作为二级标题 (2.1, 2.2 等)
|
||||||
|
"""
|
||||||
|
result = []
|
||||||
|
# 首先对文件路径进行分组整理
|
||||||
|
file_groups = {}
|
||||||
|
for path in sorted(self.file_summaries_map.keys()):
|
||||||
|
dir_path = os.path.dirname(path)
|
||||||
|
if dir_path not in file_groups:
|
||||||
|
file_groups[dir_path] = []
|
||||||
|
file_groups[dir_path].append(path)
|
||||||
|
|
||||||
|
# 处理没有目录的文件
|
||||||
|
root_files = file_groups.get("", [])
|
||||||
|
if root_files:
|
||||||
|
for path in sorted(root_files):
|
||||||
|
file_name = os.path.basename(path)
|
||||||
|
result.append(f"\n📄 {file_name}")
|
||||||
|
result.append(self.file_summaries_map[path])
|
||||||
|
# 无目录的文件作为二级标题
|
||||||
|
self._add_heading(f"📄 {file_name}", 2)
|
||||||
|
self._add_content(self.file_summaries_map[path])
|
||||||
|
self.doc.add_paragraph()
|
||||||
|
|
||||||
|
# 处理有目录的文件
|
||||||
|
for dir_path in sorted(file_groups.keys()):
|
||||||
|
if dir_path == "": # 跳过已处理的根目录文件
|
||||||
|
continue
|
||||||
|
|
||||||
|
# 添加目录作为二级标题
|
||||||
|
result.append(f"\n📁 {dir_path}")
|
||||||
|
self._add_heading(f"📁 {dir_path}", 2)
|
||||||
|
|
||||||
|
# 该目录下的所有文件作为三级标题
|
||||||
|
for path in sorted(file_groups[dir_path]):
|
||||||
|
file_name = os.path.basename(path)
|
||||||
|
result.append(f"\n📄 {file_name}")
|
||||||
|
result.append(self.file_summaries_map[path])
|
||||||
|
|
||||||
|
# 添加文件名作为三级标题
|
||||||
|
self._add_heading(f"📄 {file_name}", 3)
|
||||||
|
self._add_content(self.file_summaries_map[path])
|
||||||
|
self.doc.add_paragraph()
|
||||||
|
|
||||||
|
return "\n".join(result)
|
||||||
|
|
||||||
|
|
||||||
|
def create_document(self):
|
||||||
|
"""创建完整Word文档并返回文档对象"""
|
||||||
|
# 重置所有编号
|
||||||
|
for level in self.numbers:
|
||||||
|
self.numbers[level] = 0
|
||||||
|
|
||||||
|
# 添加主标题
|
||||||
|
self._add_heading("文档总结报告", 0)
|
||||||
|
self.doc.add_paragraph()
|
||||||
|
|
||||||
|
# 添加总体摘要
|
||||||
|
self._add_heading("总体摘要", 1)
|
||||||
|
self._add_content(self.final_summary)
|
||||||
|
self.doc.add_paragraph()
|
||||||
|
|
||||||
|
# 添加失败文件列表（如果有）
|
||||||
|
if self.failed_files:
|
||||||
|
self.format_failed_files()
|
||||||
|
|
||||||
|
# 添加文件详细总结
|
||||||
|
self._add_heading("各文件详细总结", 1)
|
||||||
|
self.format_file_summaries()
|
||||||
|
|
||||||
|
return self.doc
|
||||||
|
|
||||||
|
|
||||||
|
class MarkdownFormatter(DocumentFormatter):
|
||||||
|
"""Markdown格式文档生成器"""
|
||||||
|
|
||||||
|
def format_failed_files(self) -> str:
|
||||||
|
if not self.failed_files:
|
||||||
|
return ""
|
||||||
|
|
||||||
|
formatted_text = ["\n## ⚠️ 处理失败的文件"]
|
||||||
|
for fp, reason in self.failed_files:
|
||||||
|
formatted_text.append(f"- {os.path.basename(fp)}: {reason}")
|
||||||
|
formatted_text.append("\n---")
|
||||||
|
return "\n".join(formatted_text)
|
||||||
|
|
||||||
|
def format_file_summaries(self) -> str:
|
||||||
|
formatted_text = []
|
||||||
|
sorted_paths = sorted(self.file_summaries_map.keys())
|
||||||
|
current_dir = ""
|
||||||
|
|
||||||
|
for path in sorted_paths:
|
||||||
|
dir_path = os.path.dirname(path)
|
||||||
|
if dir_path != current_dir:
|
||||||
|
if dir_path:
|
||||||
|
formatted_text.append(f"\n## 📁 {dir_path}")
|
||||||
|
current_dir = dir_path
|
||||||
|
|
||||||
|
file_name = os.path.basename(path)
|
||||||
|
formatted_text.append(f"\n### 📄 {file_name}")
|
||||||
|
formatted_text.append(self.file_summaries_map[path])
|
||||||
|
formatted_text.append("\n---")
|
||||||
|
|
||||||
|
return "\n".join(formatted_text)
|
||||||
|
|
||||||
|
def create_document(self) -> str:
|
||||||
|
document = [
|
||||||
|
"# 📑 文档总结报告",
|
||||||
|
"\n## 总体摘要",
|
||||||
|
self.final_summary
|
||||||
|
]
|
||||||
|
|
||||||
|
if self.failed_files:
|
||||||
|
document.append(self.format_failed_files())
|
||||||
|
|
||||||
|
document.extend([
|
||||||
|
"\n# 📚 各文件详细总结",
|
||||||
|
self.format_file_summaries()
|
||||||
|
])
|
||||||
|
|
||||||
|
return "\n".join(document)
|
||||||
|
|
||||||
|
|
||||||
|
class HtmlFormatter(DocumentFormatter):
|
||||||
|
"""HTML格式文档生成器"""
|
||||||
|
|
||||||
|
def __init__(self, *args, **kwargs):
|
||||||
|
super().__init__(*args, **kwargs)
|
||||||
|
self.css_styles = """
|
||||||
|
body {
|
||||||
|
font-family: "Microsoft YaHei", Arial, sans-serif;
|
||||||
|
line-height: 1.6;
|
||||||
|
max-width: 1000px;
|
||||||
|
margin: 0 auto;
|
||||||
|
padding: 20px;
|
||||||
|
color: #333;
|
||||||
|
}
|
||||||
|
h1 {
|
||||||
|
color: #2c3e50;
|
||||||
|
border-bottom: 2px solid #eee;
|
||||||
|
padding-bottom: 10px;
|
||||||
|
font-size: 24px;
|
||||||
|
text-align: center;
|
||||||
|
}
|
||||||
|
h2 {
|
||||||
|
color: #34495e;
|
||||||
|
margin-top: 30px;
|
||||||
|
font-size: 20px;
|
||||||
|
border-left: 4px solid #3498db;
|
||||||
|
padding-left: 10px;
|
||||||
|
}
|
||||||
|
h3 {
|
||||||
|
color: #2c3e50;
|
||||||
|
font-size: 18px;
|
||||||
|
margin-top: 20px;
|
||||||
|
}
|
||||||
|
.summary {
|
||||||
|
background-color: #f8f9fa;
|
||||||
|
padding: 20px;
|
||||||
|
border-radius: 5px;
|
||||||
|
margin: 20px 0;
|
||||||
|
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
|
||||||
|
}
|
||||||
|
.details {
|
||||||
|
margin-top: 40px;
|
||||||
|
}
|
||||||
|
.failed-files {
|
||||||
|
background-color: #fff3f3;
|
||||||
|
padding: 15px;
|
||||||
|
border-left: 4px solid #e74c3c;
|
||||||
|
margin: 20px 0;
|
||||||
|
}
|
||||||
|
.file-summary {
|
||||||
|
background-color: #fff;
|
||||||
|
padding: 15px;
|
||||||
|
margin: 15px 0;
|
||||||
|
border-radius: 4px;
|
||||||
|
box-shadow: 0 1px 3px rgba(0,0,0,0.1);
|
||||||
|
}
|
||||||
|
"""
|
||||||
|
|
||||||
|
def format_failed_files(self) -> str:
|
||||||
|
if not self.failed_files:
|
||||||
|
return ""
|
||||||
|
|
||||||
|
failed_files_html = ['<div class="failed-files">']
|
||||||
|
failed_files_html.append("<h2>⚠️ 处理失败的文件</h2>")
|
||||||
|
failed_files_html.append("<ul>")
|
||||||
|
for fp, reason in self.failed_files:
|
||||||
|
failed_files_html.append(f"<li><strong>{os.path.basename(fp)}:</strong> {reason}</li>")
|
||||||
|
failed_files_html.append("</ul></div>")
|
||||||
|
return "\n".join(failed_files_html)
|
||||||
|
|
||||||
|
def format_file_summaries(self) -> str:
|
||||||
|
formatted_html = []
|
||||||
|
sorted_paths = sorted(self.file_summaries_map.keys())
|
||||||
|
current_dir = ""
|
||||||
|
|
||||||
|
for path in sorted_paths:
|
||||||
|
dir_path = os.path.dirname(path)
|
||||||
|
if dir_path != current_dir:
|
||||||
|
if dir_path:
|
||||||
|
formatted_html.append(f'<h2>📁 {dir_path}</h2>')
|
||||||
|
current_dir = dir_path
|
||||||
|
|
||||||
|
file_name = os.path.basename(path)
|
||||||
|
formatted_html.append('<div class="file-summary">')
|
||||||
|
formatted_html.append(f'<h3>📄 {file_name}</h3>')
|
||||||
|
formatted_html.append(f'<p>{self.file_summaries_map[path]}</p>')
|
||||||
|
formatted_html.append('</div>')
|
||||||
|
|
||||||
|
return "\n".join(formatted_html)
|
||||||
|
|
||||||
|
def create_document(self) -> str:
|
||||||
|
return f"""
|
||||||
|
<!DOCTYPE html>
|
||||||
|
<html>
|
||||||
|
<head>
|
||||||
|
<meta charset='utf-8'>
|
||||||
|
<title>文档总结报告</title>
|
||||||
|
<style>{self.css_styles}</style>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<h1>📑 文档总结报告</h1>
|
||||||
|
<h2>总体摘要</h2>
|
||||||
|
<div class="summary">{self.final_summary}</div>
|
||||||
|
{self.format_failed_files()}
|
||||||
|
<div class="details">
|
||||||
|
<h2>📚 各文件详细总结</h2>
|
||||||
|
{self.format_file_summaries()}
|
||||||
|
</div>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
|
"""
|
||||||
|
|
||||||
|
|
||||||
@@ -300,8 +300,7 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
|
|||||||
write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
|
write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
|
||||||
|
|
||||||
# <-------- 写出文件 ---------->
|
# <-------- 写出文件 ---------->
|
||||||
model_name = llm_kwargs['llm_model'].replace('_', '\\_') # 替换LLM模型名称中的下划线为转义字符
|
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']}。"
|
||||||
msg = f"当前大语言模型: {model_name}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
|
|
||||||
final_tex = lps.merge_result(pfg.file_result, mode, msg)
|
final_tex = lps.merge_result(pfg.file_result, mode, msg)
|
||||||
objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl'))
|
objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl'))
|
||||||
|
|
||||||
@@ -352,41 +351,6 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
|||||||
chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history)
|
chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history)
|
||||||
chatbot.append([f"正在编译PDF文档", '...']); yield from update_ui(chatbot=chatbot, history=history); time.sleep(1); chatbot[-1] = list(chatbot[-1]) # 刷新界面
|
chatbot.append([f"正在编译PDF文档", '...']); yield from update_ui(chatbot=chatbot, history=history); time.sleep(1); chatbot[-1] = list(chatbot[-1]) # 刷新界面
|
||||||
yield from update_ui_lastest_msg('编译已经开始...', chatbot, history) # 刷新Gradio前端界面
|
yield from update_ui_lastest_msg('编译已经开始...', chatbot, history) # 刷新Gradio前端界面
|
||||||
# 检查是否需要使用xelatex
|
|
||||||
def check_if_need_xelatex(tex_path):
|
|
||||||
try:
|
|
||||||
with open(tex_path, 'r', encoding='utf-8', errors='replace') as f:
|
|
||||||
content = f.read(5000)
|
|
||||||
# 检查是否有使用xelatex的宏包
|
|
||||||
need_xelatex = any(
|
|
||||||
pkg in content
|
|
||||||
for pkg in ['fontspec', 'xeCJK', 'xetex', 'unicode-math', 'xltxtra', 'xunicode']
|
|
||||||
)
|
|
||||||
if need_xelatex:
|
|
||||||
logger.info(f"检测到宏包需要xelatex编译, 切换至xelatex编译")
|
|
||||||
else:
|
|
||||||
logger.info(f"未检测到宏包需要xelatex编译, 使用pdflatex编译")
|
|
||||||
return need_xelatex
|
|
||||||
except Exception:
|
|
||||||
return False
|
|
||||||
|
|
||||||
# 根据编译器类型返回编译命令
|
|
||||||
def get_compile_command(compiler, filename):
|
|
||||||
compile_command = f'{compiler} -interaction=batchmode -file-line-error {filename}.tex'
|
|
||||||
logger.info('Latex 编译指令: ' + compile_command)
|
|
||||||
return compile_command
|
|
||||||
|
|
||||||
# 确定使用的编译器
|
|
||||||
compiler = 'pdflatex'
|
|
||||||
if check_if_need_xelatex(pj(work_folder_modified, f'{main_file_modified}.tex')):
|
|
||||||
logger.info("检测到宏包需要xelatex编译，切换至xelatex编译")
|
|
||||||
# Check if xelatex is installed
|
|
||||||
try:
|
|
||||||
import subprocess
|
|
||||||
subprocess.run(['xelatex', '--version'], capture_output=True, check=True)
|
|
||||||
compiler = 'xelatex'
|
|
||||||
except (subprocess.CalledProcessError, FileNotFoundError):
|
|
||||||
raise RuntimeError("检测到需要使用xelatex编译，但系统中未安装xelatex。请先安装texlive或其他提供xelatex的LaTeX发行版。")
|
|
||||||
|
|
||||||
while True:
|
while True:
|
||||||
import os
|
import os
|
||||||
@@ -397,10 +361,10 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
|||||||
|
|
||||||
# https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
|
# https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
|
||||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history) # 刷新Gradio前端界面
|
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history) # 刷新Gradio前端界面
|
||||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
|
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
|
||||||
|
|
||||||
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
|
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(get_compile_command(compiler, main_file_modified), work_folder_modified)
|
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')):
|
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
|
# 只有第二步成功，才能继续下面的步骤
|
||||||
@@ -411,10 +375,10 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
|||||||
ok = compile_latex_with_timeout(f'bibtex {main_file_modified}.aux', work_folder_modified)
|
ok = compile_latex_with_timeout(f'bibtex {main_file_modified}.aux', work_folder_modified)
|
||||||
|
|
||||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history) # 刷新Gradio前端界面
|
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history) # 刷新Gradio前端界面
|
||||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
|
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
|
||||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
|
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
|
||||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
|
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
|
||||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
|
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
|
||||||
|
|
||||||
if mode!='translate_zh':
|
if mode!='translate_zh':
|
||||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
|
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
|
||||||
@@ -422,10 +386,10 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
|||||||
ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex', os.getcwd())
|
ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex', os.getcwd())
|
||||||
|
|
||||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history) # 刷新Gradio前端界面
|
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history) # 刷新Gradio前端界面
|
||||||
ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
|
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
|
||||||
ok = compile_latex_with_timeout(f'bibtex merge_diff.aux', work_folder)
|
ok = compile_latex_with_timeout(f'bibtex merge_diff.aux', work_folder)
|
||||||
ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
|
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
|
||||||
ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
|
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
|
||||||
|
|
||||||
# <---------- 检查结果 ----------->
|
# <---------- 检查结果 ----------->
|
||||||
results_ = ""
|
results_ = ""
|
||||||
|
|||||||
@@ -6,16 +6,12 @@ class SafeUnpickler(pickle.Unpickler):
|
|||||||
def get_safe_classes(self):
|
def get_safe_classes(self):
|
||||||
from crazy_functions.latex_fns.latex_actions import LatexPaperFileGroup, LatexPaperSplit
|
from crazy_functions.latex_fns.latex_actions import LatexPaperFileGroup, LatexPaperSplit
|
||||||
from crazy_functions.latex_fns.latex_toolbox import LinkedListNode
|
from crazy_functions.latex_fns.latex_toolbox import LinkedListNode
|
||||||
from numpy.core.multiarray import scalar
|
|
||||||
from numpy import dtype
|
|
||||||
# 定义允许的安全类
|
# 定义允许的安全类
|
||||||
safe_classes = {
|
safe_classes = {
|
||||||
# 在这里添加其他安全的类
|
# 在这里添加其他安全的类
|
||||||
'LatexPaperFileGroup': LatexPaperFileGroup,
|
'LatexPaperFileGroup': LatexPaperFileGroup,
|
||||||
'LatexPaperSplit': LatexPaperSplit,
|
'LatexPaperSplit': LatexPaperSplit,
|
||||||
'LinkedListNode': LinkedListNode,
|
'LinkedListNode': LinkedListNode,
|
||||||
'scalar': scalar,
|
|
||||||
'dtype': dtype,
|
|
||||||
}
|
}
|
||||||
return safe_classes
|
return safe_classes
|
||||||
|
|
||||||
@@ -26,6 +22,8 @@ class SafeUnpickler(pickle.Unpickler):
|
|||||||
for class_name in self.safe_classes.keys():
|
for class_name in self.safe_classes.keys():
|
||||||
if (class_name in f'{module}.{name}'):
|
if (class_name in f'{module}.{name}'):
|
||||||
match_class_name = class_name
|
match_class_name = class_name
|
||||||
|
if module == 'numpy' or module.startswith('numpy.'):
|
||||||
|
return super().find_class(module, name)
|
||||||
if match_class_name is not None:
|
if match_class_name is not None:
|
||||||
return self.safe_classes[match_class_name]
|
return self.safe_classes[match_class_name]
|
||||||
# 如果尝试加载未授权的类，则抛出异常
|
# 如果尝试加载未授权的类，则抛出异常
|
||||||
|
|||||||
@@ -1,43 +0,0 @@
|
|||||||
from toolbox import update_ui, get_conf, promote_file_to_downloadzone, update_ui_lastest_msg, generate_file_link
|
|
||||||
from shared_utils.docker_as_service_api import stream_daas
|
|
||||||
from shared_utils.docker_as_service_api import DockerServiceApiComModel
|
|
||||||
import random
|
|
||||||
|
|
||||||
def download_video(video_id, only_audio, user_name, chatbot, history):
|
|
||||||
from toolbox import get_log_folder
|
|
||||||
chatbot.append([None, "Processing..."])
|
|
||||||
yield from update_ui(chatbot, history)
|
|
||||||
client_command = f'{video_id} --audio-only' if only_audio else video_id
|
|
||||||
server_urls = get_conf('DAAS_SERVER_URLS')
|
|
||||||
server_url = random.choice(server_urls)
|
|
||||||
docker_service_api_com_model = DockerServiceApiComModel(client_command=client_command)
|
|
||||||
save_file_dir = get_log_folder(user_name, plugin_name='media_downloader')
|
|
||||||
for output_manifest in stream_daas(docker_service_api_com_model, server_url, save_file_dir):
|
|
||||||
status_buf = ""
|
|
||||||
status_buf += "DaaS message: \n\n"
|
|
||||||
status_buf += output_manifest['server_message'].replace('\n', '<br/>')
|
|
||||||
status_buf += "\n\n"
|
|
||||||
status_buf += "DaaS standard error: \n\n"
|
|
||||||
status_buf += output_manifest['server_std_err'].replace('\n', '<br/>')
|
|
||||||
status_buf += "\n\n"
|
|
||||||
status_buf += "DaaS standard output: \n\n"
|
|
||||||
status_buf += output_manifest['server_std_out'].replace('\n', '<br/>')
|
|
||||||
status_buf += "\n\n"
|
|
||||||
status_buf += "DaaS file attach: \n\n"
|
|
||||||
status_buf += str(output_manifest['server_file_attach'])
|
|
||||||
yield from update_ui_lastest_msg(status_buf, chatbot, history)
|
|
||||||
|
|
||||||
return output_manifest['server_file_attach']
|
|
||||||
|
|
||||||
|
|
||||||
def search_videos(keywords):
|
|
||||||
from toolbox import get_log_folder
|
|
||||||
client_command = keywords
|
|
||||||
server_urls = get_conf('DAAS_SERVER_URLS')
|
|
||||||
server_url = random.choice(server_urls)
|
|
||||||
server_url = server_url.replace('stream', 'search')
|
|
||||||
docker_service_api_com_model = DockerServiceApiComModel(client_command=client_command)
|
|
||||||
save_file_dir = get_log_folder("default_user", plugin_name='media_downloader')
|
|
||||||
for output_manifest in stream_daas(docker_service_api_com_model, server_url, save_file_dir):
|
|
||||||
return output_manifest['server_message']
|
|
||||||
|
|
||||||
@@ -6,128 +6,75 @@ from crazy_functions.crazy_utils import get_files_from_everything
|
|||||||
from shared_utils.colorful import *
|
from shared_utils.colorful import *
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
import os
|
import os
|
||||||
import requests
|
|
||||||
import time
|
import time
|
||||||
|
|
||||||
|
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 retry_request(max_retries=3, delay=3):
|
|
||||||
"""
|
|
||||||
Decorator for retrying HTTP requests
|
|
||||||
Args:
|
|
||||||
max_retries: Maximum number of retry attempts
|
|
||||||
delay: Delay between retries in seconds
|
|
||||||
"""
|
|
||||||
|
|
||||||
def decorator(func):
|
|
||||||
def wrapper(*args, **kwargs):
|
|
||||||
for attempt in range(max_retries):
|
|
||||||
try:
|
|
||||||
return func(*args, **kwargs)
|
|
||||||
except Exception as e:
|
|
||||||
if attempt < max_retries - 1:
|
|
||||||
logger.error(
|
|
||||||
f"Request failed, retrying... ({attempt + 1}/{max_retries}) Error: {e}"
|
|
||||||
)
|
|
||||||
time.sleep(delay)
|
|
||||||
continue
|
|
||||||
raise e
|
|
||||||
return None
|
|
||||||
|
|
||||||
return wrapper
|
|
||||||
|
|
||||||
return decorator
|
|
||||||
|
|
||||||
|
|
||||||
@retry_request()
|
|
||||||
def make_request(method, url, **kwargs):
|
|
||||||
"""
|
|
||||||
Make HTTP request with retry mechanism
|
|
||||||
"""
|
|
||||||
return requests.request(method, url, **kwargs)
|
|
||||||
|
|
||||||
|
|
||||||
def doc2x_api_response_status(response, uid=""):
|
|
||||||
"""
|
|
||||||
Check the status of Doc2x API response
|
|
||||||
Args:
|
|
||||||
response_data: Response object from Doc2x API
|
|
||||||
"""
|
|
||||||
response_json = response.json()
|
|
||||||
response_data = response_json.get("data", {})
|
|
||||||
code = response_json.get("code", "Unknown")
|
|
||||||
meg = response_data.get("message", response_json)
|
|
||||||
trace_id = response.headers.get("trace-id", "Failed to get trace-id")
|
|
||||||
if response.status_code != 200:
|
|
||||||
raise RuntimeError(
|
|
||||||
f"Doc2x return an error:\nTrace ID: {trace_id} {uid}\n{response.status_code} - {response_json}"
|
|
||||||
)
|
|
||||||
if code in ["parse_page_limit_exceeded", "parse_concurrency_limit"]:
|
|
||||||
raise RuntimeError(
|
|
||||||
f"Reached the limit of Doc2x:\nTrace ID: {trace_id} {uid}\n{code} - {meg}"
|
|
||||||
)
|
|
||||||
if code not in ["ok", "success"]:
|
|
||||||
raise RuntimeError(
|
|
||||||
f"Doc2x return an error:\nTrace ID: {trace_id} {uid}\n{code} - {meg}"
|
|
||||||
)
|
|
||||||
return response_data
|
|
||||||
|
|
||||||
|
|
||||||
def 解析PDF_DOC2X_转Latex(pdf_file_path):
|
def 解析PDF_DOC2X_转Latex(pdf_file_path):
|
||||||
zip_file_path, unzipped_folder = 解析PDF_DOC2X(pdf_file_path, format="tex")
|
zip_file_path, unzipped_folder = 解析PDF_DOC2X(pdf_file_path, format='tex')
|
||||||
return unzipped_folder
|
return unzipped_folder
|
||||||
|
|
||||||
|
|
||||||
def 解析PDF_DOC2X(pdf_file_path, format="tex"):
|
def 解析PDF_DOC2X(pdf_file_path, format='tex'):
|
||||||
"""
|
"""
|
||||||
format: 'tex', 'md', 'docx'
|
format: 'tex', 'md', 'docx'
|
||||||
"""
|
"""
|
||||||
|
import requests, json, os
|
||||||
DOC2X_API_KEY = get_conf("DOC2X_API_KEY")
|
DOC2X_API_KEY = get_conf('DOC2X_API_KEY')
|
||||||
latex_dir = get_log_folder(plugin_name="pdf_ocr_latex")
|
latex_dir = get_log_folder(plugin_name="pdf_ocr_latex")
|
||||||
markdown_dir = get_log_folder(plugin_name="pdf_ocr")
|
markdown_dir = get_log_folder(plugin_name="pdf_ocr")
|
||||||
doc2x_api_key = DOC2X_API_KEY
|
doc2x_api_key = DOC2X_API_KEY
|
||||||
|
|
||||||
# < ------ 第1步：预上传获取URL，然后上传文件 ------ >
|
|
||||||
logger.info("Doc2x 上传文件：预上传获取URL")
|
|
||||||
res = make_request(
|
|
||||||
"POST",
|
|
||||||
"https://v2.doc2x.noedgeai.com/api/v2/parse/preupload",
|
|
||||||
headers={"Authorization": "Bearer " + doc2x_api_key},
|
|
||||||
timeout=15,
|
|
||||||
)
|
|
||||||
res_data = doc2x_api_response_status(res)
|
|
||||||
upload_url = res_data["url"]
|
|
||||||
uuid = res_data["uid"]
|
|
||||||
|
|
||||||
logger.info("Doc2x 上传文件：上传文件")
|
# < ------ 第1步：上传 ------ >
|
||||||
with open(pdf_file_path, "rb") as file:
|
logger.info("Doc2x 第1步：上传")
|
||||||
res = make_request("PUT", upload_url, data=file, timeout=60)
|
with open(pdf_file_path, 'rb') as file:
|
||||||
res.raise_for_status()
|
res = requests.post(
|
||||||
|
"https://v2.doc2x.noedgeai.com/api/v2/parse/pdf",
|
||||||
|
headers={"Authorization": "Bearer " + doc2x_api_key},
|
||||||
|
data=file
|
||||||
|
)
|
||||||
|
# res_json = []
|
||||||
|
if res.status_code == 200:
|
||||||
|
res_json = res.json()
|
||||||
|
else:
|
||||||
|
raise RuntimeError(f"Doc2x return an error: {res.json()}")
|
||||||
|
uuid = res_json['data']['uid']
|
||||||
|
|
||||||
# < ------ 第2步：轮询等待 ------ >
|
# < ------ 第2步：轮询等待 ------ >
|
||||||
logger.info("Doc2x 处理文件中：轮询等待")
|
logger.info("Doc2x 第2步：轮询等待")
|
||||||
params = {"uid": uuid}
|
params = {'uid': uuid}
|
||||||
max_attempts = 60
|
while True:
|
||||||
attempt = 0
|
res = requests.get(
|
||||||
while attempt < max_attempts:
|
'https://v2.doc2x.noedgeai.com/api/v2/parse/status',
|
||||||
res = make_request(
|
|
||||||
"GET",
|
|
||||||
"https://v2.doc2x.noedgeai.com/api/v2/parse/status",
|
|
||||||
headers={"Authorization": "Bearer " + doc2x_api_key},
|
headers={"Authorization": "Bearer " + doc2x_api_key},
|
||||||
params=params,
|
params=params
|
||||||
timeout=15,
|
|
||||||
)
|
)
|
||||||
res_data = doc2x_api_response_status(res)
|
res_json = res.json()
|
||||||
if res_data["status"] == "success":
|
if res_json['data']['status'] == "success":
|
||||||
break
|
break
|
||||||
elif res_data["status"] == "processing":
|
elif res_json['data']['status'] == "processing":
|
||||||
time.sleep(5)
|
time.sleep(3)
|
||||||
logger.info(f"Doc2x is processing at {res_data['progress']}%")
|
logger.info(f"Doc2x is processing at {res_json['data']['progress']}%")
|
||||||
attempt += 1
|
elif res_json['data']['status'] == "failed":
|
||||||
else:
|
raise RuntimeError(f"Doc2x return an error: {res_json}")
|
||||||
raise RuntimeError(f"Doc2x return an error: {res_data}")
|
|
||||||
if attempt >= max_attempts:
|
|
||||||
raise RuntimeError("Doc2x processing timeout after maximum attempts")
|
|
||||||
|
|
||||||
# < ------ 第3步：提交转化 ------ >
|
# < ------ 第3步：提交转化 ------ >
|
||||||
logger.info("Doc2x 第3步：提交转化")
|
logger.info("Doc2x 第3步：提交转化")
|
||||||
@@ -137,44 +84,42 @@ def 解析PDF_DOC2X(pdf_file_path, format="tex"):
|
|||||||
"formula_mode": "dollar",
|
"formula_mode": "dollar",
|
||||||
"filename": "output"
|
"filename": "output"
|
||||||
}
|
}
|
||||||
res = make_request(
|
res = requests.post(
|
||||||
"POST",
|
'https://v2.doc2x.noedgeai.com/api/v2/convert/parse',
|
||||||
"https://v2.doc2x.noedgeai.com/api/v2/convert/parse",
|
|
||||||
headers={"Authorization": "Bearer " + doc2x_api_key},
|
headers={"Authorization": "Bearer " + doc2x_api_key},
|
||||||
json=data,
|
json=data
|
||||||
timeout=15,
|
|
||||||
)
|
)
|
||||||
doc2x_api_response_status(res, uid=f"uid: {uuid}")
|
if res.status_code == 200:
|
||||||
|
res_json = res.json()
|
||||||
|
else:
|
||||||
|
raise RuntimeError(f"Doc2x return an error: {res.json()}")
|
||||||
|
|
||||||
|
|
||||||
# < ------ 第4步：等待结果 ------ >
|
# < ------ 第4步：等待结果 ------ >
|
||||||
logger.info("Doc2x 第4步：等待结果")
|
logger.info("Doc2x 第4步：等待结果")
|
||||||
params = {"uid": uuid}
|
params = {'uid': uuid}
|
||||||
max_attempts = 36
|
while True:
|
||||||
attempt = 0
|
res = requests.get(
|
||||||
while attempt < max_attempts:
|
'https://v2.doc2x.noedgeai.com/api/v2/convert/parse/result',
|
||||||
res = make_request(
|
|
||||||
"GET",
|
|
||||||
"https://v2.doc2x.noedgeai.com/api/v2/convert/parse/result",
|
|
||||||
headers={"Authorization": "Bearer " + doc2x_api_key},
|
headers={"Authorization": "Bearer " + doc2x_api_key},
|
||||||
params=params,
|
params=params
|
||||||
timeout=15,
|
|
||||||
)
|
)
|
||||||
res_data = doc2x_api_response_status(res, uid=f"uid: {uuid}")
|
res_json = res.json()
|
||||||
if res_data["status"] == "success":
|
if res_json['data']['status'] == "success":
|
||||||
break
|
break
|
||||||
elif res_data["status"] == "processing":
|
elif res_json['data']['status'] == "processing":
|
||||||
time.sleep(3)
|
time.sleep(3)
|
||||||
logger.info("Doc2x still processing to convert file")
|
logger.info(f"Doc2x still processing")
|
||||||
attempt += 1
|
elif res_json['data']['status'] == "failed":
|
||||||
if attempt >= max_attempts:
|
raise RuntimeError(f"Doc2x return an error: {res_json}")
|
||||||
raise RuntimeError("Doc2x conversion timeout after maximum attempts")
|
|
||||||
|
|
||||||
# < ------ 第5步：最后的处理 ------ >
|
# < ------ 第5步：最后的处理 ------ >
|
||||||
logger.info("Doc2x 第5步：下载转换后的文件")
|
logger.info("Doc2x 第5步：最后的处理")
|
||||||
|
|
||||||
if format == "tex":
|
if format=='tex':
|
||||||
target_path = latex_dir
|
target_path = latex_dir
|
||||||
if format == "md":
|
if format=='md':
|
||||||
target_path = markdown_dir
|
target_path = markdown_dir
|
||||||
os.makedirs(target_path, exist_ok=True)
|
os.makedirs(target_path, exist_ok=True)
|
||||||
|
|
||||||
@@ -182,18 +127,17 @@ def 解析PDF_DOC2X(pdf_file_path, format="tex"):
|
|||||||
# < ------ 下载 ------ >
|
# < ------ 下载 ------ >
|
||||||
for attempt in range(max_attempt):
|
for attempt in range(max_attempt):
|
||||||
try:
|
try:
|
||||||
result_url = res_data["url"]
|
result_url = res_json['data']['url']
|
||||||
res = make_request("GET", result_url, timeout=60)
|
res = requests.get(result_url)
|
||||||
zip_path = os.path.join(target_path, gen_time_str() + ".zip")
|
zip_path = os.path.join(target_path, gen_time_str() + '.zip')
|
||||||
unzip_path = os.path.join(target_path, gen_time_str())
|
unzip_path = os.path.join(target_path, gen_time_str())
|
||||||
if res.status_code == 200:
|
if res.status_code == 200:
|
||||||
with open(zip_path, "wb") as f:
|
with open(zip_path, "wb") as f: f.write(res.content)
|
||||||
f.write(res.content)
|
|
||||||
else:
|
else:
|
||||||
raise RuntimeError(f"Doc2x return an error: {res.json()}")
|
raise RuntimeError(f"Doc2x return an error: {res.json()}")
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
if attempt < max_attempt - 1:
|
if attempt < max_attempt - 1:
|
||||||
logger.error(f"Failed to download uid = {uuid} file, retrying... {e}")
|
logger.error(f"Failed to download latex file, retrying... {e}")
|
||||||
time.sleep(3)
|
time.sleep(3)
|
||||||
continue
|
continue
|
||||||
else:
|
else:
|
||||||
@@ -201,31 +145,22 @@ def 解析PDF_DOC2X(pdf_file_path, format="tex"):
|
|||||||
|
|
||||||
# < ------ 解压 ------ >
|
# < ------ 解压 ------ >
|
||||||
import zipfile
|
import zipfile
|
||||||
with zipfile.ZipFile(zip_path, "r") as zip_ref:
|
with zipfile.ZipFile(zip_path, 'r') as zip_ref:
|
||||||
zip_ref.extractall(unzip_path)
|
zip_ref.extractall(unzip_path)
|
||||||
return zip_path, unzip_path
|
return zip_path, unzip_path
|
||||||
|
|
||||||
|
|
||||||
def 解析PDF_DOC2X_单文件(
|
def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request):
|
||||||
fp,
|
|
||||||
project_folder,
|
|
||||||
llm_kwargs,
|
|
||||||
plugin_kwargs,
|
|
||||||
chatbot,
|
|
||||||
history,
|
|
||||||
system_prompt,
|
|
||||||
DOC2X_API_KEY,
|
|
||||||
user_request,
|
|
||||||
):
|
|
||||||
def pdf2markdown(filepath):
|
def pdf2markdown(filepath):
|
||||||
chatbot.append((None, f"Doc2x 解析中"))
|
chatbot.append((None, f"Doc2x 解析中"))
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||||
|
|
||||||
md_zip_path, unzipped_folder = 解析PDF_DOC2X(filepath, format="md")
|
md_zip_path, unzipped_folder = 解析PDF_DOC2X(filepath, format='md')
|
||||||
|
|
||||||
promote_file_to_downloadzone(md_zip_path, chatbot=chatbot)
|
promote_file_to_downloadzone(md_zip_path, chatbot=chatbot)
|
||||||
chatbot.append((None, f"完成解析 {md_zip_path} ..."))
|
chatbot.append((None, f"完成解析 {md_zip_path} ..."))
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||||
return md_zip_path
|
return md_zip_path
|
||||||
|
|
||||||
def deliver_to_markdown_plugin(md_zip_path, user_request):
|
def deliver_to_markdown_plugin(md_zip_path, user_request):
|
||||||
@@ -239,97 +174,77 @@ def 解析PDF_DOC2X_单文件(
|
|||||||
os.makedirs(target_path_base, exist_ok=True)
|
os.makedirs(target_path_base, exist_ok=True)
|
||||||
shutil.copyfile(md_zip_path, this_file_path)
|
shutil.copyfile(md_zip_path, this_file_path)
|
||||||
ex_folder = this_file_path + ".extract"
|
ex_folder = this_file_path + ".extract"
|
||||||
extract_archive(file_path=this_file_path, dest_dir=ex_folder)
|
extract_archive(
|
||||||
|
file_path=this_file_path, dest_dir=ex_folder
|
||||||
|
)
|
||||||
|
|
||||||
# edit markdown files
|
# edit markdown files
|
||||||
success, file_manifest, project_folder = get_files_from_everything(
|
success, file_manifest, project_folder = get_files_from_everything(ex_folder, type='.md')
|
||||||
ex_folder, type=".md"
|
|
||||||
)
|
|
||||||
for generated_fp in file_manifest:
|
for generated_fp in file_manifest:
|
||||||
# 修正一些公式问题
|
# 修正一些公式问题
|
||||||
with open(generated_fp, "r", encoding="utf8") as f:
|
with open(generated_fp, 'r', encoding='utf8') as f:
|
||||||
content = f.read()
|
content = f.read()
|
||||||
# 将公式中的\[ \]替换成$$
|
# 将公式中的\[ \]替换成$$
|
||||||
content = content.replace(r"\[", r"$$").replace(r"\]", r"$$")
|
content = content.replace(r'\[', r'$$').replace(r'\]', r'$$')
|
||||||
# 将公式中的\( \)替换成$
|
# 将公式中的\( \)替换成$
|
||||||
content = content.replace(r"\(", r"$").replace(r"\)", r"$")
|
content = content.replace(r'\(', r'$').replace(r'\)', r'$')
|
||||||
content = content.replace("```markdown", "\n").replace("```", "\n")
|
content = content.replace('```markdown', '\n').replace('```', '\n')
|
||||||
with open(generated_fp, "w", encoding="utf8") as f:
|
with open(generated_fp, 'w', encoding='utf8') as f:
|
||||||
f.write(content)
|
f.write(content)
|
||||||
promote_file_to_downloadzone(generated_fp, chatbot=chatbot)
|
promote_file_to_downloadzone(generated_fp, chatbot=chatbot)
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||||
|
|
||||||
# 生成在线预览html
|
# 生成在线预览html
|
||||||
file_name = "在线预览翻译（原文）" + gen_time_str() + ".html"
|
file_name = '在线预览翻译（原文）' + gen_time_str() + '.html'
|
||||||
preview_fp = os.path.join(ex_folder, file_name)
|
preview_fp = os.path.join(ex_folder, file_name)
|
||||||
from shared_utils.advanced_markdown_format import (
|
from shared_utils.advanced_markdown_format import markdown_convertion_for_file
|
||||||
markdown_convertion_for_file,
|
|
||||||
)
|
|
||||||
|
|
||||||
with open(generated_fp, "r", encoding="utf-8") as f:
|
with open(generated_fp, "r", encoding="utf-8") as f:
|
||||||
md = f.read()
|
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
|
# # 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)
|
# md = re.sub(r'^<table>', r'.<table>', md, flags=re.MULTILINE)
|
||||||
html = markdown_convertion_for_file(md)
|
html = markdown_convertion_for_file(md)
|
||||||
with open(preview_fp, "w", encoding="utf-8") as f:
|
with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
|
||||||
f.write(html)
|
|
||||||
chatbot.append([None, f"生成在线预览：{generate_file_link([preview_fp])}"])
|
chatbot.append([None, f"生成在线预览：{generate_file_link([preview_fp])}"])
|
||||||
promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
|
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(
|
chatbot.append((None, f"调用Markdown插件 {ex_folder} ..."))
|
||||||
ex_folder, translated_f_name
|
plugin_kwargs['markdown_expected_output_dir'] = ex_folder
|
||||||
)
|
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
translated_f_name = 'translated_markdown.md'
|
||||||
yield from Markdown英译中(
|
generated_fp = plugin_kwargs['markdown_expected_output_path'] = os.path.join(ex_folder, translated_f_name)
|
||||||
ex_folder,
|
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||||
llm_kwargs,
|
yield from Markdown英译中(ex_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||||
plugin_kwargs,
|
|
||||||
chatbot,
|
|
||||||
history,
|
|
||||||
system_prompt,
|
|
||||||
user_request,
|
|
||||||
)
|
|
||||||
if os.path.exists(generated_fp):
|
if os.path.exists(generated_fp):
|
||||||
# 修正一些公式问题
|
# 修正一些公式问题
|
||||||
with open(generated_fp, "r", encoding="utf8") as f:
|
with open(generated_fp, 'r', encoding='utf8') as f: content = f.read()
|
||||||
content = f.read()
|
content = content.replace('```markdown', '\n').replace('```', '\n')
|
||||||
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
|
# 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)
|
# content = re.sub(r'^<table>', r'.<table>', content, flags=re.MULTILINE)
|
||||||
with open(generated_fp, "w", encoding="utf8") as f:
|
with open(generated_fp, 'w', encoding='utf8') as f: f.write(content)
|
||||||
f.write(content)
|
|
||||||
# 生成在线预览html
|
# 生成在线预览html
|
||||||
file_name = "在线预览翻译" + gen_time_str() + ".html"
|
file_name = '在线预览翻译' + gen_time_str() + '.html'
|
||||||
preview_fp = os.path.join(ex_folder, file_name)
|
preview_fp = os.path.join(ex_folder, file_name)
|
||||||
from shared_utils.advanced_markdown_format import (
|
from shared_utils.advanced_markdown_format import markdown_convertion_for_file
|
||||||
markdown_convertion_for_file,
|
|
||||||
)
|
|
||||||
|
|
||||||
with open(generated_fp, "r", encoding="utf-8") as f:
|
with open(generated_fp, "r", encoding="utf-8") as f:
|
||||||
md = f.read()
|
md = f.read()
|
||||||
html = markdown_convertion_for_file(md)
|
html = markdown_convertion_for_file(md)
|
||||||
with open(preview_fp, "w", encoding="utf-8") as f:
|
with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
|
||||||
f.write(html)
|
|
||||||
promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
|
promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
|
||||||
# 生成包含图片的压缩包
|
# 生成包含图片的压缩包
|
||||||
dest_folder = get_log_folder(chatbot.get_user())
|
dest_folder = get_log_folder(chatbot.get_user())
|
||||||
zip_name = "翻译后的带图文档.zip"
|
zip_name = '翻译后的带图文档.zip'
|
||||||
zip_folder(
|
zip_folder(source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name)
|
||||||
source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name
|
|
||||||
)
|
|
||||||
zip_fp = os.path.join(dest_folder, zip_name)
|
zip_fp = os.path.join(dest_folder, zip_name)
|
||||||
promote_file_to_downloadzone(zip_fp, chatbot=chatbot)
|
promote_file_to_downloadzone(zip_fp, chatbot=chatbot)
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||||
|
|
||||||
md_zip_path = yield from pdf2markdown(fp)
|
md_zip_path = yield from pdf2markdown(fp)
|
||||||
yield from deliver_to_markdown_plugin(md_zip_path, user_request)
|
yield from deliver_to_markdown_plugin(md_zip_path, user_request)
|
||||||
|
|
||||||
|
|
||||||
def 解析PDF_基于DOC2X(file_manifest, *args):
|
def 解析PDF_基于DOC2X(file_manifest, *args):
|
||||||
for index, fp in enumerate(file_manifest):
|
for index, fp in enumerate(file_manifest):
|
||||||
yield from 解析PDF_DOC2X_单文件(fp, *args)
|
yield from 解析PDF_DOC2X_单文件(fp, *args)
|
||||||
return
|
return
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -1,22 +1,45 @@
|
|||||||
import os
|
import os
|
||||||
from llama_index.core import SimpleDirectoryReader
|
from llama_index.core import SimpleDirectoryReader
|
||||||
|
|
||||||
supports_format = ['.csv', '.docx', '.epub', '.ipynb', '.mbox', '.md', '.pdf', '.txt', '.ppt',
|
supports_format = ['.csv', '.docx','.doc', '.epub', '.ipynb', '.mbox', '.md', '.pdf', '.txt', '.ppt',
|
||||||
'.pptm', '.pptx']
|
'.pptm', '.pptx','.py', '.xls', '.xlsx', '.html', '.json', '.xml', '.yaml', '.yml' ,'.m']
|
||||||
|
|
||||||
|
def read_docx_doc(file_path):
|
||||||
|
if file_path.split(".")[-1] == "docx":
|
||||||
|
from docx import Document
|
||||||
|
doc = Document(file_path)
|
||||||
|
file_content = "\n".join([para.text for para in doc.paragraphs])
|
||||||
|
else:
|
||||||
|
try:
|
||||||
|
import win32com.client
|
||||||
|
word = win32com.client.Dispatch("Word.Application")
|
||||||
|
word.visible = False
|
||||||
|
# 打开文件
|
||||||
|
doc = word.Documents.Open(os.getcwd() + '/' + file_path)
|
||||||
|
# file_content = doc.Content.Text
|
||||||
|
doc = word.ActiveDocument
|
||||||
|
file_content = doc.Range().Text
|
||||||
|
doc.Close()
|
||||||
|
word.Quit()
|
||||||
|
except:
|
||||||
|
raise RuntimeError('请先将.doc文档转换为.docx文档。')
|
||||||
|
return file_content
|
||||||
|
|
||||||
# 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑
|
# 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑
|
||||||
|
import os
|
||||||
|
|
||||||
def extract_text(file_path):
|
def extract_text(file_path):
|
||||||
_, ext = os.path.splitext(file_path.lower())
|
_, ext = os.path.splitext(file_path.lower())
|
||||||
|
|
||||||
# 使用 SimpleDirectoryReader 处理它支持的文件格式
|
# 使用 SimpleDirectoryReader 处理它支持的文件格式
|
||||||
if ext in supports_format:
|
if ext in ['.docx', '.doc']:
|
||||||
try:
|
return read_docx_doc(file_path)
|
||||||
reader = SimpleDirectoryReader(input_files=[file_path])
|
try:
|
||||||
documents = reader.load_data()
|
reader = SimpleDirectoryReader(input_files=[file_path])
|
||||||
if len(documents) > 0:
|
documents = reader.load_data()
|
||||||
return documents[0].text
|
if len(documents) > 0:
|
||||||
except Exception as e:
|
return documents[0].text
|
||||||
pass
|
except Exception as e:
|
||||||
|
pass
|
||||||
|
|
||||||
return None
|
return None
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
493
crazy_functions/批量文件询问.py
Normal file
493
crazy_functions/批量文件询问.py
Normal file
@@ -0,0 +1,493 @@
|
|||||||
|
import os
|
||||||
|
import threading
|
||||||
|
import time
|
||||||
|
from dataclasses import dataclass
|
||||||
|
from typing import List, Tuple, Dict, Generator
|
||||||
|
|
||||||
|
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||||
|
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
|
||||||
|
from crazy_functions.rag_fns.rag_file_support import extract_text
|
||||||
|
from request_llms.bridge_all import model_info
|
||||||
|
from toolbox import update_ui, CatchException, report_exception
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass
|
||||||
|
class FileFragment:
|
||||||
|
"""文件片段数据类，用于组织处理单元"""
|
||||||
|
file_path: str
|
||||||
|
content: str
|
||||||
|
rel_path: str
|
||||||
|
fragment_index: int
|
||||||
|
total_fragments: int
|
||||||
|
|
||||||
|
|
||||||
|
class BatchDocumentSummarizer:
|
||||||
|
"""优化的文档总结器 - 批处理版本"""
|
||||||
|
|
||||||
|
def __init__(self, llm_kwargs: Dict, plugin_kwargs: Dict, chatbot: List, history: List, system_prompt: str):
|
||||||
|
"""初始化总结器"""
|
||||||
|
self.llm_kwargs = llm_kwargs
|
||||||
|
self.plugin_kwargs = plugin_kwargs
|
||||||
|
self.chatbot = chatbot
|
||||||
|
self.history = history
|
||||||
|
self.system_prompt = system_prompt
|
||||||
|
self.failed_files = []
|
||||||
|
self.file_summaries_map = {}
|
||||||
|
|
||||||
|
def _get_token_limit(self) -> int:
|
||||||
|
"""获取模型token限制"""
|
||||||
|
max_token = model_info[self.llm_kwargs['llm_model']]['max_token']
|
||||||
|
return max_token * 3 // 4
|
||||||
|
|
||||||
|
def _create_batch_inputs(self, fragments: List[FileFragment]) -> Tuple[List, List, List]:
|
||||||
|
"""创建批处理输入"""
|
||||||
|
inputs_array = []
|
||||||
|
inputs_show_user_array = []
|
||||||
|
history_array = []
|
||||||
|
|
||||||
|
for frag in fragments:
|
||||||
|
if self.plugin_kwargs.get("advanced_arg"):
|
||||||
|
i_say = (f'请按照用户要求对文件内容进行处理，文件名为{os.path.basename(frag.file_path)}，'
|
||||||
|
f'用户要求为：{self.plugin_kwargs["advanced_arg"]}：'
|
||||||
|
f'文件内容是 ```{frag.content}```')
|
||||||
|
i_say_show_user = (f'正在处理 {frag.rel_path} (片段 {frag.fragment_index + 1}/{frag.total_fragments})')
|
||||||
|
else:
|
||||||
|
i_say = (f'请对下面的内容用中文做概述，文件名是{os.path.basename(frag.file_path)}，'
|
||||||
|
f'内容是 ```{frag.content}```')
|
||||||
|
i_say_show_user = f'正在处理 {frag.rel_path} (片段 {frag.fragment_index + 1}/{frag.total_fragments})'
|
||||||
|
|
||||||
|
inputs_array.append(i_say)
|
||||||
|
inputs_show_user_array.append(i_say_show_user)
|
||||||
|
history_array.append([])
|
||||||
|
|
||||||
|
return inputs_array, inputs_show_user_array, history_array
|
||||||
|
|
||||||
|
def _process_single_file_with_timeout(self, file_info: Tuple[str, str], mutable_status: List) -> List[FileFragment]:
|
||||||
|
"""包装了超时控制的文件处理函数"""
|
||||||
|
|
||||||
|
def timeout_handler():
|
||||||
|
thread = threading.current_thread()
|
||||||
|
if hasattr(thread, '_timeout_occurred'):
|
||||||
|
thread._timeout_occurred = True
|
||||||
|
|
||||||
|
# 设置超时标记
|
||||||
|
thread = threading.current_thread()
|
||||||
|
thread._timeout_occurred = False
|
||||||
|
|
||||||
|
# 设置超时定时器
|
||||||
|
timer = threading.Timer(self.watch_dog_patience, timeout_handler)
|
||||||
|
timer.start()
|
||||||
|
|
||||||
|
try:
|
||||||
|
fp, project_folder = file_info
|
||||||
|
fragments = []
|
||||||
|
|
||||||
|
# 定期检查是否超时
|
||||||
|
def check_timeout():
|
||||||
|
if hasattr(thread, '_timeout_occurred') and thread._timeout_occurred:
|
||||||
|
raise TimeoutError("处理超时")
|
||||||
|
|
||||||
|
# 更新状态
|
||||||
|
mutable_status[0] = "检查文件大小"
|
||||||
|
mutable_status[1] = time.time()
|
||||||
|
check_timeout()
|
||||||
|
|
||||||
|
# 文件大小检查
|
||||||
|
if os.path.getsize(fp) > self.max_file_size:
|
||||||
|
self.failed_files.append((fp, f"文件过大：超过{self.max_file_size / 1024 / 1024}MB"))
|
||||||
|
mutable_status[2] = "文件过大"
|
||||||
|
return fragments
|
||||||
|
|
||||||
|
check_timeout()
|
||||||
|
|
||||||
|
# 更新状态
|
||||||
|
mutable_status[0] = "提取文件内容"
|
||||||
|
mutable_status[1] = time.time()
|
||||||
|
|
||||||
|
# 提取内容
|
||||||
|
content = extract_text(fp)
|
||||||
|
if content is None:
|
||||||
|
self.failed_files.append((fp, "文件解析失败：不支持的格式或文件损坏"))
|
||||||
|
mutable_status[2] = "格式不支持"
|
||||||
|
return fragments
|
||||||
|
elif not content.strip():
|
||||||
|
self.failed_files.append((fp, "文件内容为空"))
|
||||||
|
mutable_status[2] = "内容为空"
|
||||||
|
return fragments
|
||||||
|
|
||||||
|
check_timeout()
|
||||||
|
|
||||||
|
# 更新状态
|
||||||
|
mutable_status[0] = "分割文本"
|
||||||
|
mutable_status[1] = time.time()
|
||||||
|
|
||||||
|
# 分割文本
|
||||||
|
try:
|
||||||
|
paper_fragments = breakdown_text_to_satisfy_token_limit(
|
||||||
|
txt=content,
|
||||||
|
limit=self._get_token_limit(),
|
||||||
|
llm_model=self.llm_kwargs['llm_model']
|
||||||
|
)
|
||||||
|
except Exception as e:
|
||||||
|
self.failed_files.append((fp, f"文本分割失败：{str(e)}"))
|
||||||
|
mutable_status[2] = "分割失败"
|
||||||
|
return fragments
|
||||||
|
|
||||||
|
check_timeout()
|
||||||
|
|
||||||
|
# 处理片段
|
||||||
|
rel_path = os.path.relpath(fp, project_folder)
|
||||||
|
for i, frag in enumerate(paper_fragments):
|
||||||
|
if frag.strip():
|
||||||
|
fragments.append(FileFragment(
|
||||||
|
file_path=fp,
|
||||||
|
content=frag,
|
||||||
|
rel_path=rel_path,
|
||||||
|
fragment_index=i,
|
||||||
|
total_fragments=len(paper_fragments)
|
||||||
|
))
|
||||||
|
|
||||||
|
mutable_status[2] = "处理完成"
|
||||||
|
return fragments
|
||||||
|
|
||||||
|
except TimeoutError as e:
|
||||||
|
self.failed_files.append((fp, "处理超时"))
|
||||||
|
mutable_status[2] = "处理超时"
|
||||||
|
return []
|
||||||
|
except Exception as e:
|
||||||
|
self.failed_files.append((fp, f"处理失败：{str(e)}"))
|
||||||
|
mutable_status[2] = "处理异常"
|
||||||
|
return []
|
||||||
|
finally:
|
||||||
|
timer.cancel()
|
||||||
|
|
||||||
|
def prepare_fragments(self, project_folder: str, file_paths: List[str]) -> Generator:
|
||||||
|
import concurrent.futures
|
||||||
|
|
||||||
|
|
||||||
|
from concurrent.futures import ThreadPoolExecutor
|
||||||
|
from typing import Generator, List
|
||||||
|
"""并行准备所有文件的处理片段"""
|
||||||
|
all_fragments = []
|
||||||
|
total_files = len(file_paths)
|
||||||
|
|
||||||
|
# 配置参数
|
||||||
|
self.refresh_interval = 0.2 # UI刷新间隔
|
||||||
|
self.watch_dog_patience = 5 # 看门狗超时时间
|
||||||
|
self.max_file_size = 10 * 1024 * 1024 # 10MB限制
|
||||||
|
self.max_workers = min(32, len(file_paths)) # 最多32个线程
|
||||||
|
|
||||||
|
# 创建有超时控制的线程池
|
||||||
|
executor = ThreadPoolExecutor(max_workers=self.max_workers)
|
||||||
|
|
||||||
|
# 用于跨线程状态传递的可变列表 - 增加文件名信息
|
||||||
|
mutable_status_array = [["等待中", time.time(), "pending", file_path] for file_path in file_paths]
|
||||||
|
|
||||||
|
# 创建文件处理任务
|
||||||
|
file_infos = [(fp, project_folder) for fp in file_paths]
|
||||||
|
|
||||||
|
# 提交所有任务，使用带超时控制的处理函数
|
||||||
|
futures = [
|
||||||
|
executor.submit(
|
||||||
|
self._process_single_file_with_timeout,
|
||||||
|
file_info,
|
||||||
|
mutable_status_array[i]
|
||||||
|
) for i, file_info in enumerate(file_infos)
|
||||||
|
]
|
||||||
|
|
||||||
|
# 更新UI的计数器
|
||||||
|
cnt = 0
|
||||||
|
|
||||||
|
try:
|
||||||
|
# 监控任务执行
|
||||||
|
while True:
|
||||||
|
time.sleep(self.refresh_interval)
|
||||||
|
cnt += 1
|
||||||
|
|
||||||
|
# 检查任务完成状态
|
||||||
|
worker_done = [f.done() for f in futures]
|
||||||
|
|
||||||
|
# 更新状态显示
|
||||||
|
status_str = ""
|
||||||
|
for i, (status, timestamp, desc, file_path) in enumerate(mutable_status_array):
|
||||||
|
# 获取文件名（去掉路径）
|
||||||
|
file_name = os.path.basename(file_path)
|
||||||
|
if worker_done[i]:
|
||||||
|
status_str += f"文件 {file_name}: {desc}\n"
|
||||||
|
else:
|
||||||
|
status_str += f"文件 {file_name}: {status} {desc}\n"
|
||||||
|
|
||||||
|
# 更新UI
|
||||||
|
self.chatbot[-1] = [
|
||||||
|
"处理进度",
|
||||||
|
f"正在处理文件...\n\n{status_str}" + "." * (cnt % 10 + 1)
|
||||||
|
]
|
||||||
|
yield from update_ui(chatbot=self.chatbot, history=self.history)
|
||||||
|
|
||||||
|
# 检查是否所有任务完成
|
||||||
|
if all(worker_done):
|
||||||
|
break
|
||||||
|
|
||||||
|
finally:
|
||||||
|
# 确保线程池正确关闭
|
||||||
|
executor.shutdown(wait=False)
|
||||||
|
|
||||||
|
# 收集结果
|
||||||
|
processed_files = 0
|
||||||
|
for future in futures:
|
||||||
|
try:
|
||||||
|
fragments = future.result(timeout=0.1) # 给予一个短暂的超时时间来获取结果
|
||||||
|
all_fragments.extend(fragments)
|
||||||
|
processed_files += 1
|
||||||
|
except concurrent.futures.TimeoutError:
|
||||||
|
# 处理获取结果超时
|
||||||
|
file_index = futures.index(future)
|
||||||
|
self.failed_files.append((file_paths[file_index], "结果获取超时"))
|
||||||
|
continue
|
||||||
|
except Exception as e:
|
||||||
|
# 处理其他异常
|
||||||
|
file_index = futures.index(future)
|
||||||
|
self.failed_files.append((file_paths[file_index], f"未知错误：{str(e)}"))
|
||||||
|
continue
|
||||||
|
|
||||||
|
# 最终进度更新
|
||||||
|
self.chatbot.append([
|
||||||
|
"文件处理完成",
|
||||||
|
f"成功处理 {len(all_fragments)} 个片段，失败 {len(self.failed_files)} 个文件"
|
||||||
|
])
|
||||||
|
yield from update_ui(chatbot=self.chatbot, history=self.history)
|
||||||
|
|
||||||
|
return all_fragments
|
||||||
|
|
||||||
|
def _process_fragments_batch(self, fragments: List[FileFragment]) -> Generator:
|
||||||
|
"""批量处理文件片段"""
|
||||||
|
from collections import defaultdict
|
||||||
|
batch_size = 64 # 每批处理的片段数
|
||||||
|
max_retries = 3 # 最大重试次数
|
||||||
|
retry_delay = 5 # 重试延迟（秒）
|
||||||
|
results = defaultdict(list)
|
||||||
|
|
||||||
|
# 按批次处理
|
||||||
|
for i in range(0, len(fragments), batch_size):
|
||||||
|
batch = fragments[i:i + batch_size]
|
||||||
|
|
||||||
|
inputs_array, inputs_show_user_array, history_array = self._create_batch_inputs(batch)
|
||||||
|
sys_prompt_array = ["请总结以下内容："] * len(batch)
|
||||||
|
|
||||||
|
# 添加重试机制
|
||||||
|
for retry in range(max_retries):
|
||||||
|
try:
|
||||||
|
response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||||
|
inputs_array=inputs_array,
|
||||||
|
inputs_show_user_array=inputs_show_user_array,
|
||||||
|
llm_kwargs=self.llm_kwargs,
|
||||||
|
chatbot=self.chatbot,
|
||||||
|
history_array=history_array,
|
||||||
|
sys_prompt_array=sys_prompt_array,
|
||||||
|
)
|
||||||
|
|
||||||
|
# 处理响应
|
||||||
|
for j, frag in enumerate(batch):
|
||||||
|
summary = response_collection[j * 2 + 1]
|
||||||
|
if summary and summary.strip():
|
||||||
|
results[frag.rel_path].append({
|
||||||
|
'index': frag.fragment_index,
|
||||||
|
'summary': summary,
|
||||||
|
'total': frag.total_fragments
|
||||||
|
})
|
||||||
|
break # 成功处理，跳出重试循环
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
if retry == max_retries - 1: # 最后一次重试失败
|
||||||
|
for frag in batch:
|
||||||
|
self.failed_files.append((frag.file_path, f"处理失败：{str(e)}"))
|
||||||
|
else:
|
||||||
|
yield from update_ui(self.chatbot.append([f"批次处理失败，{retry_delay}秒后重试...", str(e)]))
|
||||||
|
time.sleep(retry_delay)
|
||||||
|
|
||||||
|
return results
|
||||||
|
|
||||||
|
def _generate_final_summary_request(self) -> Tuple[List, List, List]:
|
||||||
|
"""准备最终总结请求"""
|
||||||
|
if not self.file_summaries_map:
|
||||||
|
return (["无可用的文件总结"], ["生成最终总结"], [[]])
|
||||||
|
|
||||||
|
summaries = list(self.file_summaries_map.values())
|
||||||
|
if all(not summary for summary in summaries):
|
||||||
|
return (["所有文件处理均失败"], ["生成最终总结"], [[]])
|
||||||
|
|
||||||
|
if self.plugin_kwargs.get("advanced_arg"):
|
||||||
|
i_say = "根据以上所有文件的处理结果，按要求进行综合处理：" + self.plugin_kwargs['advanced_arg']
|
||||||
|
else:
|
||||||
|
i_say = "请根据以上所有文件的处理结果，生成最终的总结，不超过1000字。"
|
||||||
|
|
||||||
|
return ([i_say], [i_say], [summaries])
|
||||||
|
|
||||||
|
def process_files(self, project_folder: str, file_paths: List[str]) -> Generator:
|
||||||
|
"""处理所有文件"""
|
||||||
|
total_files = len(file_paths)
|
||||||
|
self.chatbot.append([f"开始处理", f"总计 {total_files} 个文件"])
|
||||||
|
yield from update_ui(chatbot=self.chatbot, history=self.history)
|
||||||
|
|
||||||
|
# 1. 准备所有文件片段
|
||||||
|
# 在 process_files 函数中：
|
||||||
|
fragments = yield from self.prepare_fragments(project_folder, file_paths)
|
||||||
|
if not fragments:
|
||||||
|
self.chatbot.append(["处理失败", "没有可处理的文件内容"])
|
||||||
|
return "没有可处理的文件内容"
|
||||||
|
|
||||||
|
# 2. 批量处理所有文件片段
|
||||||
|
self.chatbot.append([f"文件分析", f"共计 {len(fragments)} 个处理单元"])
|
||||||
|
yield from update_ui(chatbot=self.chatbot, history=self.history)
|
||||||
|
|
||||||
|
try:
|
||||||
|
file_summaries = yield from self._process_fragments_batch(fragments)
|
||||||
|
except Exception as e:
|
||||||
|
self.chatbot.append(["处理错误", f"批处理过程失败：{str(e)}"])
|
||||||
|
return "处理过程发生错误"
|
||||||
|
|
||||||
|
# 3. 为每个文件生成整体总结
|
||||||
|
self.chatbot.append(["生成总结", "正在汇总文件内容..."])
|
||||||
|
yield from update_ui(chatbot=self.chatbot, history=self.history)
|
||||||
|
|
||||||
|
# 处理每个文件的总结
|
||||||
|
for rel_path, summaries in file_summaries.items():
|
||||||
|
if len(summaries) > 1: # 多片段文件需要生成整体总结
|
||||||
|
sorted_summaries = sorted(summaries, key=lambda x: x['index'])
|
||||||
|
if self.plugin_kwargs.get("advanced_arg"):
|
||||||
|
i_say = (f"根据以下内容，按要求：{self.plugin_kwargs['advanced_arg']}，"
|
||||||
|
f"总结文件 {os.path.basename(rel_path)} 的主要内容。")
|
||||||
|
else:
|
||||||
|
i_say = f"请总结文件 {os.path.basename(rel_path)} 的主要内容，不超过500字。"
|
||||||
|
|
||||||
|
try:
|
||||||
|
summary_texts = [s['summary'] for s in sorted_summaries]
|
||||||
|
response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||||
|
inputs_array=[i_say],
|
||||||
|
inputs_show_user_array=[f"生成 {rel_path} 的总结"],
|
||||||
|
llm_kwargs=self.llm_kwargs,
|
||||||
|
chatbot=self.chatbot,
|
||||||
|
history_array=[summary_texts],
|
||||||
|
sys_prompt_array=["总结文件内容。"],
|
||||||
|
)
|
||||||
|
self.file_summaries_map[rel_path] = response_collection[1]
|
||||||
|
except Exception as e:
|
||||||
|
self.chatbot.append(["警告", f"文件 {rel_path} 总结生成失败：{str(e)}"])
|
||||||
|
self.file_summaries_map[rel_path] = "总结生成失败"
|
||||||
|
else: # 单片段文件直接使用其唯一的总结
|
||||||
|
self.file_summaries_map[rel_path] = summaries[0]['summary']
|
||||||
|
|
||||||
|
# 4. 生成最终总结
|
||||||
|
try:
|
||||||
|
# 收集所有文件的总结用于生成最终总结
|
||||||
|
file_summaries_for_final = []
|
||||||
|
for rel_path, summary in self.file_summaries_map.items():
|
||||||
|
file_summaries_for_final.append(f"文件 {rel_path} 的总结：\n{summary}")
|
||||||
|
|
||||||
|
if self.plugin_kwargs.get("advanced_arg"):
|
||||||
|
final_summary_prompt = ("根据以下所有文件的总结内容，按要求进行综合处理：" +
|
||||||
|
self.plugin_kwargs['advanced_arg'])
|
||||||
|
else:
|
||||||
|
final_summary_prompt = "请根据以下所有文件的总结内容，生成最终的总结报告。"
|
||||||
|
|
||||||
|
response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||||
|
inputs_array=[final_summary_prompt],
|
||||||
|
inputs_show_user_array=["生成最终总结报告"],
|
||||||
|
llm_kwargs=self.llm_kwargs,
|
||||||
|
chatbot=self.chatbot,
|
||||||
|
history_array=[file_summaries_for_final],
|
||||||
|
sys_prompt_array=["总结所有文件内容。"],
|
||||||
|
max_workers=1
|
||||||
|
)
|
||||||
|
|
||||||
|
return response_collection[1] if len(response_collection) > 1 else "生成总结失败"
|
||||||
|
except Exception as e:
|
||||||
|
self.chatbot.append(["错误", f"最终总结生成失败：{str(e)}"])
|
||||||
|
return "生成总结失败"
|
||||||
|
|
||||||
|
def save_results(self, final_summary: str):
|
||||||
|
"""保存结果到文件"""
|
||||||
|
from toolbox import promote_file_to_downloadzone, write_history_to_file
|
||||||
|
from crazy_functions.doc_fns.batch_file_query_doc import MarkdownFormatter, HtmlFormatter, WordFormatter
|
||||||
|
import os
|
||||||
|
timestamp = time.strftime("%Y%m%d_%H%M%S")
|
||||||
|
|
||||||
|
# 创建各种格式化器
|
||||||
|
md_formatter = MarkdownFormatter(final_summary, self.file_summaries_map, self.failed_files)
|
||||||
|
html_formatter = HtmlFormatter(final_summary, self.file_summaries_map, self.failed_files)
|
||||||
|
word_formatter = WordFormatter(final_summary, self.file_summaries_map, self.failed_files)
|
||||||
|
|
||||||
|
result_files = []
|
||||||
|
|
||||||
|
# 保存 Markdown
|
||||||
|
md_content = md_formatter.create_document()
|
||||||
|
result_file_md = write_history_to_file(
|
||||||
|
history=[md_content], # 直接传入内容列表
|
||||||
|
file_basename=f"文档总结_{timestamp}.md"
|
||||||
|
)
|
||||||
|
result_files.append(result_file_md)
|
||||||
|
|
||||||
|
# 保存 HTML
|
||||||
|
html_content = html_formatter.create_document()
|
||||||
|
result_file_html = write_history_to_file(
|
||||||
|
history=[html_content],
|
||||||
|
file_basename=f"文档总结_{timestamp}.html"
|
||||||
|
)
|
||||||
|
result_files.append(result_file_html)
|
||||||
|
|
||||||
|
# 保存 Word
|
||||||
|
doc = word_formatter.create_document()
|
||||||
|
# 由于 Word 文档需要用 doc.save()，我们使用与 md 文件相同的目录
|
||||||
|
result_file_docx = os.path.join(
|
||||||
|
os.path.dirname(result_file_md),
|
||||||
|
f"文档总结_{timestamp}.docx"
|
||||||
|
)
|
||||||
|
doc.save(result_file_docx)
|
||||||
|
result_files.append(result_file_docx)
|
||||||
|
|
||||||
|
# 添加到下载区
|
||||||
|
for file in result_files:
|
||||||
|
promote_file_to_downloadzone(file, chatbot=self.chatbot)
|
||||||
|
|
||||||
|
self.chatbot.append(["处理完成", f"结果已保存至: {', '.join(result_files)}"])
|
||||||
|
@CatchException
|
||||||
|
def 批量文件询问(txt: str, llm_kwargs: Dict, plugin_kwargs: Dict, chatbot: List,
|
||||||
|
history: List, system_prompt: str, user_request: str):
|
||||||
|
"""主函数 - 优化版本"""
|
||||||
|
# 初始化
|
||||||
|
import glob
|
||||||
|
import re
|
||||||
|
from crazy_functions.rag_fns.rag_file_support import supports_format
|
||||||
|
from toolbox import report_exception
|
||||||
|
|
||||||
|
summarizer = BatchDocumentSummarizer(llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||||
|
chatbot.append(["函数插件功能", f"作者：lbykkkk，批量总结文件。支持格式: {', '.join(supports_format)}等其他文本格式文件，如果长时间卡在文件处理过程，请查看处理进度，然后删除所有处于“pending”状态的文件，然后重新上传处理。"])
|
||||||
|
yield from update_ui(chatbot=chatbot, history=history)
|
||||||
|
|
||||||
|
# 验证输入路径
|
||||||
|
if not os.path.exists(txt):
|
||||||
|
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到项目或无权访问: {txt}")
|
||||||
|
yield from update_ui(chatbot=chatbot, history=history)
|
||||||
|
return
|
||||||
|
|
||||||
|
# 获取文件列表
|
||||||
|
project_folder = txt
|
||||||
|
extract_folder = next((d for d in glob.glob(f'{project_folder}/*')
|
||||||
|
if os.path.isdir(d) and d.endswith('.extract')), project_folder)
|
||||||
|
|
||||||
|
exclude_patterns = r'/[^/]+\.(zip|rar|7z|tar|gz)$'
|
||||||
|
file_manifest = [f for f in glob.glob(f'{extract_folder}/**', recursive=True)
|
||||||
|
if os.path.isfile(f) and not re.search(exclude_patterns, f)]
|
||||||
|
|
||||||
|
if not file_manifest:
|
||||||
|
report_exception(chatbot, history, a=f"解析项目: {txt}", b="未找到支持的文件类型")
|
||||||
|
yield from update_ui(chatbot=chatbot, history=history)
|
||||||
|
return
|
||||||
|
|
||||||
|
# 处理所有文件并生成总结
|
||||||
|
final_summary = yield from summarizer.process_files(project_folder, file_manifest)
|
||||||
|
yield from update_ui(chatbot=chatbot, history=history)
|
||||||
|
|
||||||
|
# 保存结果
|
||||||
|
summarizer.save_results(final_summary)
|
||||||
|
yield from update_ui(chatbot=chatbot, history=history)
|
||||||
@@ -5,10 +5,6 @@ FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest
|
|||||||
|
|
||||||
# edge-tts需要的依赖，某些pip包所需的依赖
|
# edge-tts需要的依赖，某些pip包所需的依赖
|
||||||
RUN apt update && apt install ffmpeg build-essential -y
|
RUN apt update && apt install ffmpeg build-essential -y
|
||||||
RUN apt-get install -y fontconfig
|
|
||||||
RUN ln -s /usr/local/texlive/2023/texmf-dist/fonts/truetype /usr/share/fonts/truetype/texlive
|
|
||||||
RUN fc-cache -fv
|
|
||||||
RUN apt-get clean
|
|
||||||
|
|
||||||
# use python3 as the system default python
|
# use python3 as the system default python
|
||||||
WORKDIR /gpt
|
WORKDIR /gpt
|
||||||
@@ -34,7 +30,7 @@ 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_chatglm.txt
|
||||||
RUN python3 -m pip install -r request_llms/requirements_newbing.txt
|
RUN python3 -m pip install -r request_llms/requirements_newbing.txt
|
||||||
RUN python3 -m pip install nougat-ocr
|
RUN python3 -m pip install nougat-ocr
|
||||||
RUN python3 -m pip cache purge
|
|
||||||
|
|
||||||
# 预热Tiktoken模块
|
# 预热Tiktoken模块
|
||||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||||
|
|||||||
@@ -7,7 +7,6 @@ RUN apt-get install -y git python python3 python-dev python3-dev --fix-missing
|
|||||||
|
|
||||||
# edge-tts需要的依赖，某些pip包所需的依赖
|
# edge-tts需要的依赖，某些pip包所需的依赖
|
||||||
RUN apt update && apt install ffmpeg build-essential -y
|
RUN apt update && apt install ffmpeg build-essential -y
|
||||||
RUN apt-get clean
|
|
||||||
|
|
||||||
# use python3 as the system default python
|
# use python3 as the system default python
|
||||||
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
|
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
|
||||||
@@ -23,7 +22,6 @@ RUN python3 -m pip install -r request_llms/requirements_moss.txt
|
|||||||
RUN python3 -m pip install -r request_llms/requirements_qwen.txt
|
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_chatglm.txt
|
||||||
RUN python3 -m pip install -r request_llms/requirements_newbing.txt
|
RUN python3 -m pip install -r request_llms/requirements_newbing.txt
|
||||||
RUN python3 -m pip cache purge
|
|
||||||
|
|
||||||
|
|
||||||
# 预热Tiktoken模块
|
# 预热Tiktoken模块
|
||||||
|
|||||||
@@ -18,7 +18,5 @@ RUN apt update && apt install ffmpeg -y
|
|||||||
# 可选步骤，用于预热模块
|
# 可选步骤，用于预热模块
|
||||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||||
|
|
||||||
RUN python3 -m pip cache purge && apt-get clean
|
|
||||||
|
|
||||||
# 启动
|
# 启动
|
||||||
CMD ["python3", "-u", "main.py"]
|
CMD ["python3", "-u", "main.py"]
|
||||||
|
|||||||
@@ -30,7 +30,5 @@ COPY --chown=gptuser:gptuser . .
|
|||||||
# 可选步骤，用于预热模块
|
# 可选步骤，用于预热模块
|
||||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||||
|
|
||||||
RUN python3 -m pip cache purge
|
|
||||||
|
|
||||||
# 启动
|
# 启动
|
||||||
CMD ["python3", "-u", "main.py"]
|
CMD ["python3", "-u", "main.py"]
|
||||||
|
|||||||
@@ -24,8 +24,6 @@ RUN apt update && apt install ffmpeg -y
|
|||||||
|
|
||||||
# 可选步骤，用于预热模块
|
# 可选步骤，用于预热模块
|
||||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||||
RUN python3 -m pip cache purge && apt-get clean
|
|
||||||
|
|
||||||
|
|
||||||
# 启动
|
# 启动
|
||||||
CMD ["python3", "-u", "main.py"]
|
CMD ["python3", "-u", "main.py"]
|
||||||
|
|||||||
@@ -1,26 +0,0 @@
|
|||||||
@echo off
|
|
||||||
setlocal
|
|
||||||
|
|
||||||
:: 设置环境变量
|
|
||||||
set ENV_NAME=gpt
|
|
||||||
set ENV_PATH=%~dp0%ENV_NAME%
|
|
||||||
set SCRIPT_PATH=%~dp0main.py
|
|
||||||
|
|
||||||
:: 判断环境是否已解压
|
|
||||||
if not exist "%ENV_PATH%" (
|
|
||||||
echo Extracting environment...
|
|
||||||
mkdir "%ENV_PATH%"
|
|
||||||
tar -xzf gpt.tar.gz -C "%ENV_PATH%"
|
|
||||||
|
|
||||||
:: 运行conda环境激活脚本
|
|
||||||
call "%ENV_PATH%\Scripts\activate.bat"
|
|
||||||
) else (
|
|
||||||
:: 如果环境已存在,直接激活
|
|
||||||
call "%ENV_PATH%\Scripts\activate.bat"
|
|
||||||
)
|
|
||||||
echo Start to run program:
|
|
||||||
:: 运行Python脚本
|
|
||||||
python "%SCRIPT_PATH%"
|
|
||||||
|
|
||||||
endlocal
|
|
||||||
pause
|
|
||||||
45
main.py
45
main.py
@@ -1,7 +1,10 @@
|
|||||||
import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
|
import os, json; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
|
||||||
|
|
||||||
help_menu_description = \
|
help_menu_description = \
|
||||||
"""
|
"""Github源代码开源和更新[地址🚀](https://github.com/binary-husky/gpt_academic),
|
||||||
|
感谢热情的[开发者们❤️](https://github.com/binary-husky/gpt_academic/graphs/contributors).
|
||||||
|
</br></br>常见问题请查阅[项目Wiki](https://github.com/binary-husky/gpt_academic/wiki),
|
||||||
|
如遇到Bug请前往[Bug反馈](https://github.com/binary-husky/gpt_academic/issues).
|
||||||
</br></br>普通对话使用说明: 1. 输入问题; 2. 点击提交
|
</br></br>普通对话使用说明: 1. 输入问题; 2. 点击提交
|
||||||
</br></br>基础功能区使用说明: 1. 输入文本; 2. 点击任意基础功能区按钮
|
</br></br>基础功能区使用说明: 1. 输入文本; 2. 点击任意基础功能区按钮
|
||||||
</br></br>函数插件区使用说明: 1. 输入路径/问题, 或者上传文件; 2. 点击任意函数插件区按钮
|
</br></br>函数插件区使用说明: 1. 输入路径/问题, 或者上传文件; 2. 点击任意函数插件区按钮
|
||||||
@@ -31,9 +34,9 @@ def encode_plugin_info(k, plugin)->str:
|
|||||||
|
|
||||||
def main():
|
def main():
|
||||||
import gradio as gr
|
import gradio as gr
|
||||||
if gr.__version__ not in ['3.32.12']:
|
if gr.__version__ not in ['3.32.9', '3.32.10', '3.32.11']:
|
||||||
raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
|
raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
|
||||||
|
|
||||||
# 一些基础工具
|
# 一些基础工具
|
||||||
from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
|
from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
|
||||||
|
|
||||||
@@ -46,7 +49,7 @@ def main():
|
|||||||
# 读取配置
|
# 读取配置
|
||||||
proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION')
|
proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION')
|
||||||
CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
|
CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
|
||||||
ENABLE_AUDIO, AUTO_CLEAR_TXT, AVAIL_FONTS, AVAIL_THEMES, THEME, ADD_WAIFU = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'AVAIL_FONTS', 'AVAIL_THEMES', 'THEME', 'ADD_WAIFU')
|
ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME, ADD_WAIFU = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME', 'ADD_WAIFU')
|
||||||
NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
|
NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
|
||||||
DARK_MODE, INIT_SYS_PROMPT, ADD_WAIFU, TTS_TYPE = get_conf('DARK_MODE', 'INIT_SYS_PROMPT', 'ADD_WAIFU', 'TTS_TYPE')
|
DARK_MODE, INIT_SYS_PROMPT, ADD_WAIFU, TTS_TYPE = get_conf('DARK_MODE', 'INIT_SYS_PROMPT', 'ADD_WAIFU', 'TTS_TYPE')
|
||||||
if LLM_MODEL not in AVAIL_LLM_MODELS: AVAIL_LLM_MODELS += [LLM_MODEL]
|
if LLM_MODEL not in AVAIL_LLM_MODELS: AVAIL_LLM_MODELS += [LLM_MODEL]
|
||||||
@@ -54,8 +57,8 @@ def main():
|
|||||||
# 如果WEB_PORT是-1, 则随机选取WEB端口
|
# 如果WEB_PORT是-1, 则随机选取WEB端口
|
||||||
PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
|
PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
|
||||||
from check_proxy import get_current_version
|
from check_proxy import get_current_version
|
||||||
from themes.theme import adjust_theme, advanced_css, theme_declaration, js_code_clear, js_code_show_or_hide, js_code_show_or_hide_group2
|
from themes.theme import adjust_theme, advanced_css, theme_declaration, js_code_clear, js_code_reset, js_code_show_or_hide, js_code_show_or_hide_group2
|
||||||
from themes.theme import js_code_for_toggle_darkmode
|
from themes.theme import js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
|
||||||
from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, assign_user_uuid
|
from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, assign_user_uuid
|
||||||
title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
|
title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
|
||||||
|
|
||||||
@@ -65,7 +68,7 @@ def main():
|
|||||||
functional = get_core_functions()
|
functional = get_core_functions()
|
||||||
|
|
||||||
# 高级函数插件
|
# 高级函数插件
|
||||||
from crazy_functional import get_crazy_functions, get_multiplex_button_functions
|
from crazy_functional import get_crazy_functions
|
||||||
DEFAULT_FN_GROUPS = get_conf('DEFAULT_FN_GROUPS')
|
DEFAULT_FN_GROUPS = get_conf('DEFAULT_FN_GROUPS')
|
||||||
plugins = get_crazy_functions()
|
plugins = get_crazy_functions()
|
||||||
all_plugin_groups = list(set([g for _, plugin in plugins.items() for g in plugin['Group'].split('|')]))
|
all_plugin_groups = list(set([g for _, plugin in plugins.items() for g in plugin['Group'].split('|')]))
|
||||||
@@ -103,7 +106,7 @@ def main():
|
|||||||
with gr_L2(scale=2, elem_id="gpt-chat"):
|
with gr_L2(scale=2, elem_id="gpt-chat"):
|
||||||
chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}", elem_id="gpt-chatbot")
|
chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}", elem_id="gpt-chatbot")
|
||||||
if LAYOUT == "TOP-DOWN": chatbot.style(height=CHATBOT_HEIGHT)
|
if LAYOUT == "TOP-DOWN": chatbot.style(height=CHATBOT_HEIGHT)
|
||||||
history, _, _ = make_history_cache() # 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
|
history, history_cache, history_cache_update = make_history_cache() # 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
|
||||||
with gr_L2(scale=1, elem_id="gpt-panel"):
|
with gr_L2(scale=1, elem_id="gpt-panel"):
|
||||||
with gr.Accordion("输入区", open=True, elem_id="input-panel") as area_input_primary:
|
with gr.Accordion("输入区", open=True, elem_id="input-panel") as area_input_primary:
|
||||||
with gr.Row():
|
with gr.Row():
|
||||||
@@ -111,7 +114,12 @@ def main():
|
|||||||
with gr.Row(elem_id="gpt-submit-row"):
|
with gr.Row(elem_id="gpt-submit-row"):
|
||||||
multiplex_submit_btn = gr.Button("提交", elem_id="elem_submit_visible", variant="primary")
|
multiplex_submit_btn = gr.Button("提交", elem_id="elem_submit_visible", variant="primary")
|
||||||
multiplex_sel = gr.Dropdown(
|
multiplex_sel = gr.Dropdown(
|
||||||
choices=get_multiplex_button_functions().keys(), value="常规对话",
|
choices=[
|
||||||
|
"常规对话",
|
||||||
|
"多模型对话",
|
||||||
|
"智能召回 RAG",
|
||||||
|
# "智能上下文",
|
||||||
|
], value="常规对话",
|
||||||
interactive=True, label='', show_label=False,
|
interactive=True, label='', show_label=False,
|
||||||
elem_classes='normal_mut_select', elem_id="gpt-submit-dropdown").style(container=False)
|
elem_classes='normal_mut_select', elem_id="gpt-submit-dropdown").style(container=False)
|
||||||
submit_btn = gr.Button("提交", elem_id="elem_submit", variant="primary", visible=False)
|
submit_btn = gr.Button("提交", elem_id="elem_submit", variant="primary", visible=False)
|
||||||
@@ -171,20 +179,16 @@ def main():
|
|||||||
with gr.Accordion("点击展开“文件下载区”。", open=False) as area_file_up:
|
with gr.Accordion("点击展开“文件下载区”。", open=False) as area_file_up:
|
||||||
file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload")
|
file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload")
|
||||||
|
|
||||||
|
|
||||||
# 左上角工具栏定义
|
# 左上角工具栏定义
|
||||||
from themes.gui_toolbar import define_gui_toolbar
|
from themes.gui_toolbar import define_gui_toolbar
|
||||||
checkboxes, checkboxes_2, max_length_sl, theme_dropdown, system_prompt, file_upload_2, md_dropdown, top_p, temperature = \
|
checkboxes, checkboxes_2, max_length_sl, theme_dropdown, system_prompt, file_upload_2, md_dropdown, top_p, temperature = \
|
||||||
define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAIL_THEMES, AVAIL_FONTS, ADD_WAIFU, help_menu_description, js_code_for_toggle_darkmode)
|
define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAIL_THEMES, ADD_WAIFU, help_menu_description, js_code_for_toggle_darkmode)
|
||||||
|
|
||||||
# 浮动菜单定义
|
# 浮动菜单定义
|
||||||
from themes.gui_floating_menu import define_gui_floating_menu
|
from themes.gui_floating_menu import define_gui_floating_menu
|
||||||
area_input_secondary, txt2, area_customize, _, resetBtn2, clearBtn2, stopBtn2 = \
|
area_input_secondary, txt2, area_customize, _, resetBtn2, clearBtn2, stopBtn2 = \
|
||||||
define_gui_floating_menu(customize_btns, functional, predefined_btns, cookies, web_cookie_cache)
|
define_gui_floating_menu(customize_btns, functional, predefined_btns, cookies, web_cookie_cache)
|
||||||
|
|
||||||
# 浮动时间线定义
|
|
||||||
gr.Spark()
|
|
||||||
|
|
||||||
# 插件二级菜单的实现
|
# 插件二级菜单的实现
|
||||||
from themes.gui_advanced_plugin_class import define_gui_advanced_plugin_class
|
from themes.gui_advanced_plugin_class import define_gui_advanced_plugin_class
|
||||||
new_plugin_callback, route_switchy_bt_with_arg, usr_confirmed_arg = \
|
new_plugin_callback, route_switchy_bt_with_arg, usr_confirmed_arg = \
|
||||||
@@ -214,7 +218,7 @@ def main():
|
|||||||
input_combo_order = ["cookies", "max_length_sl", "md_dropdown", "txt", "txt2", "top_p", "temperature", "chatbot", "history", "system_prompt", "plugin_advanced_arg"]
|
input_combo_order = ["cookies", "max_length_sl", "md_dropdown", "txt", "txt2", "top_p", "temperature", "chatbot", "history", "system_prompt", "plugin_advanced_arg"]
|
||||||
output_combo = [cookies, chatbot, history, status]
|
output_combo = [cookies, chatbot, history, status]
|
||||||
predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True)], outputs=output_combo)
|
predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True)], outputs=output_combo)
|
||||||
|
|
||||||
# 提交按钮、重置按钮
|
# 提交按钮、重置按钮
|
||||||
multiplex_submit_btn.click(
|
multiplex_submit_btn.click(
|
||||||
None, [multiplex_sel], None, _js="""(multiplex_sel)=>multiplex_function_begin(multiplex_sel)""")
|
None, [multiplex_sel], None, _js="""(multiplex_sel)=>multiplex_function_begin(multiplex_sel)""")
|
||||||
@@ -223,8 +227,11 @@ def main():
|
|||||||
multiplex_sel.select(
|
multiplex_sel.select(
|
||||||
None, [multiplex_sel], None, _js=f"""(multiplex_sel)=>run_multiplex_shift(multiplex_sel)""")
|
None, [multiplex_sel], None, _js=f"""(multiplex_sel)=>run_multiplex_shift(multiplex_sel)""")
|
||||||
cancel_handles.append(submit_btn.click(**predict_args))
|
cancel_handles.append(submit_btn.click(**predict_args))
|
||||||
resetBtn.click(None, None, [chatbot, history, status], _js= """clear_conversation""") # 先在前端快速清除chatbot&status
|
resetBtn.click(None, None, [chatbot, history, status], _js=js_code_reset) # 先在前端快速清除chatbot&status
|
||||||
resetBtn2.click(None, None, [chatbot, history, status], _js="""clear_conversation""") # 先在前端快速清除chatbot&status
|
resetBtn2.click(None, None, [chatbot, history, status], _js=js_code_reset) # 先在前端快速清除chatbot&status
|
||||||
|
reset_server_side_args = (lambda history: ([], [], "已重置", json.dumps(history)), [history], [chatbot, history, status, history_cache])
|
||||||
|
resetBtn.click(*reset_server_side_args) # 再在后端清除history，把history转存history_cache备用
|
||||||
|
resetBtn2.click(*reset_server_side_args) # 再在后端清除history，把history转存history_cache备用
|
||||||
clearBtn.click(None, None, [txt, txt2], _js=js_code_clear)
|
clearBtn.click(None, None, [txt, txt2], _js=js_code_clear)
|
||||||
clearBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
|
clearBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
|
||||||
if AUTO_CLEAR_TXT:
|
if AUTO_CLEAR_TXT:
|
||||||
@@ -324,7 +331,7 @@ def main():
|
|||||||
from shared_utils.cookie_manager import load_web_cookie_cache__fn_builder
|
from shared_utils.cookie_manager import load_web_cookie_cache__fn_builder
|
||||||
load_web_cookie_cache = load_web_cookie_cache__fn_builder(customize_btns, cookies, predefined_btns)
|
load_web_cookie_cache = load_web_cookie_cache__fn_builder(customize_btns, cookies, predefined_btns)
|
||||||
app_block.load(load_web_cookie_cache, inputs = [web_cookie_cache, cookies],
|
app_block.load(load_web_cookie_cache, inputs = [web_cookie_cache, cookies],
|
||||||
outputs = [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()], _js="""persistent_cookie_init""")
|
outputs = [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()], _js=js_code_for_persistent_cookie_init)
|
||||||
app_block.load(None, inputs=[], outputs=None, _js=f"""()=>GptAcademicJavaScriptInit("{DARK_MODE}","{INIT_SYS_PROMPT}","{ADD_WAIFU}","{LAYOUT}","{TTS_TYPE}")""") # 配置暗色主题或亮色主题
|
app_block.load(None, inputs=[], outputs=None, _js=f"""()=>GptAcademicJavaScriptInit("{DARK_MODE}","{INIT_SYS_PROMPT}","{ADD_WAIFU}","{LAYOUT}","{TTS_TYPE}")""") # 配置暗色主题或亮色主题
|
||||||
app_block.load(None, inputs=[], outputs=None, _js="""()=>{REP}""".replace("REP", register_advanced_plugin_init_arr))
|
app_block.load(None, inputs=[], outputs=None, _js="""()=>{REP}""".replace("REP", register_advanced_plugin_init_arr))
|
||||||
|
|
||||||
|
|||||||
@@ -26,9 +26,6 @@ from .bridge_chatglm import predict as chatglm_ui
|
|||||||
from .bridge_chatglm3 import predict_no_ui_long_connection as chatglm3_noui
|
from .bridge_chatglm3 import predict_no_ui_long_connection as chatglm3_noui
|
||||||
from .bridge_chatglm3 import predict as chatglm3_ui
|
from .bridge_chatglm3 import predict as chatglm3_ui
|
||||||
|
|
||||||
from .bridge_chatglm4 import predict_no_ui_long_connection as chatglm4_noui
|
|
||||||
from .bridge_chatglm4 import predict as chatglm4_ui
|
|
||||||
|
|
||||||
from .bridge_qianfan import predict_no_ui_long_connection as qianfan_noui
|
from .bridge_qianfan import predict_no_ui_long_connection as qianfan_noui
|
||||||
from .bridge_qianfan import predict as qianfan_ui
|
from .bridge_qianfan import predict as qianfan_ui
|
||||||
|
|
||||||
@@ -79,7 +76,6 @@ cohere_endpoint = "https://api.cohere.ai/v1/chat"
|
|||||||
ollama_endpoint = "http://localhost:11434/api/chat"
|
ollama_endpoint = "http://localhost:11434/api/chat"
|
||||||
yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"
|
yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"
|
||||||
deepseekapi_endpoint = "https://api.deepseek.com/v1/chat/completions"
|
deepseekapi_endpoint = "https://api.deepseek.com/v1/chat/completions"
|
||||||
grok_model_endpoint = "https://api.x.ai/v1/chat/completions"
|
|
||||||
|
|
||||||
if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
|
if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
|
||||||
azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
|
azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
|
||||||
@@ -101,7 +97,6 @@ if cohere_endpoint in API_URL_REDIRECT: cohere_endpoint = API_URL_REDIRECT[coher
|
|||||||
if ollama_endpoint in API_URL_REDIRECT: ollama_endpoint = API_URL_REDIRECT[ollama_endpoint]
|
if ollama_endpoint in API_URL_REDIRECT: ollama_endpoint = API_URL_REDIRECT[ollama_endpoint]
|
||||||
if yimodel_endpoint in API_URL_REDIRECT: yimodel_endpoint = API_URL_REDIRECT[yimodel_endpoint]
|
if yimodel_endpoint in API_URL_REDIRECT: yimodel_endpoint = API_URL_REDIRECT[yimodel_endpoint]
|
||||||
if deepseekapi_endpoint in API_URL_REDIRECT: deepseekapi_endpoint = API_URL_REDIRECT[deepseekapi_endpoint]
|
if deepseekapi_endpoint in API_URL_REDIRECT: deepseekapi_endpoint = API_URL_REDIRECT[deepseekapi_endpoint]
|
||||||
if grok_model_endpoint in API_URL_REDIRECT: grok_model_endpoint = API_URL_REDIRECT[grok_model_endpoint]
|
|
||||||
|
|
||||||
# 获取tokenizer
|
# 获取tokenizer
|
||||||
tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
|
tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
|
||||||
@@ -217,16 +212,6 @@ model_info = {
|
|||||||
"token_cnt": get_token_num_gpt4,
|
"token_cnt": get_token_num_gpt4,
|
||||||
},
|
},
|
||||||
|
|
||||||
"chatgpt-4o-latest": {
|
|
||||||
"fn_with_ui": chatgpt_ui,
|
|
||||||
"fn_without_ui": chatgpt_noui,
|
|
||||||
"endpoint": openai_endpoint,
|
|
||||||
"has_multimodal_capacity": True,
|
|
||||||
"max_token": 128000,
|
|
||||||
"tokenizer": tokenizer_gpt4,
|
|
||||||
"token_cnt": get_token_num_gpt4,
|
|
||||||
},
|
|
||||||
|
|
||||||
"gpt-4o-2024-05-13": {
|
"gpt-4o-2024-05-13": {
|
||||||
"fn_with_ui": chatgpt_ui,
|
"fn_with_ui": chatgpt_ui,
|
||||||
"fn_without_ui": chatgpt_noui,
|
"fn_without_ui": chatgpt_noui,
|
||||||
@@ -273,9 +258,7 @@ model_info = {
|
|||||||
"token_cnt": get_token_num_gpt4,
|
"token_cnt": get_token_num_gpt4,
|
||||||
"openai_disable_system_prompt": True,
|
"openai_disable_system_prompt": True,
|
||||||
"openai_disable_stream": True,
|
"openai_disable_stream": True,
|
||||||
"openai_force_temperature_one": True,
|
|
||||||
},
|
},
|
||||||
|
|
||||||
"o1-mini": {
|
"o1-mini": {
|
||||||
"fn_with_ui": chatgpt_ui,
|
"fn_with_ui": chatgpt_ui,
|
||||||
"fn_without_ui": chatgpt_noui,
|
"fn_without_ui": chatgpt_noui,
|
||||||
@@ -285,31 +268,6 @@ model_info = {
|
|||||||
"token_cnt": get_token_num_gpt4,
|
"token_cnt": get_token_num_gpt4,
|
||||||
"openai_disable_system_prompt": True,
|
"openai_disable_system_prompt": True,
|
||||||
"openai_disable_stream": True,
|
"openai_disable_stream": True,
|
||||||
"openai_force_temperature_one": True,
|
|
||||||
},
|
|
||||||
|
|
||||||
"o1-2024-12-17": {
|
|
||||||
"fn_with_ui": chatgpt_ui,
|
|
||||||
"fn_without_ui": chatgpt_noui,
|
|
||||||
"endpoint": openai_endpoint,
|
|
||||||
"max_token": 200000,
|
|
||||||
"tokenizer": tokenizer_gpt4,
|
|
||||||
"token_cnt": get_token_num_gpt4,
|
|
||||||
"openai_disable_system_prompt": True,
|
|
||||||
"openai_disable_stream": True,
|
|
||||||
"openai_force_temperature_one": True,
|
|
||||||
},
|
|
||||||
|
|
||||||
"o1": {
|
|
||||||
"fn_with_ui": chatgpt_ui,
|
|
||||||
"fn_without_ui": chatgpt_noui,
|
|
||||||
"endpoint": openai_endpoint,
|
|
||||||
"max_token": 200000,
|
|
||||||
"tokenizer": tokenizer_gpt4,
|
|
||||||
"token_cnt": get_token_num_gpt4,
|
|
||||||
"openai_disable_system_prompt": True,
|
|
||||||
"openai_disable_stream": True,
|
|
||||||
"openai_force_temperature_one": True,
|
|
||||||
},
|
},
|
||||||
|
|
||||||
"gpt-4-turbo": {
|
"gpt-4-turbo": {
|
||||||
@@ -427,14 +385,6 @@ model_info = {
|
|||||||
"tokenizer": tokenizer_gpt35,
|
"tokenizer": tokenizer_gpt35,
|
||||||
"token_cnt": get_token_num_gpt35,
|
"token_cnt": get_token_num_gpt35,
|
||||||
},
|
},
|
||||||
"glm-4-plus":{
|
|
||||||
"fn_with_ui": zhipu_ui,
|
|
||||||
"fn_without_ui": zhipu_noui,
|
|
||||||
"endpoint": None,
|
|
||||||
"max_token": 10124 * 8,
|
|
||||||
"tokenizer": tokenizer_gpt35,
|
|
||||||
"token_cnt": get_token_num_gpt35,
|
|
||||||
},
|
|
||||||
|
|
||||||
# api_2d (此后不需要在此处添加api2d的接口了，因为下面的代码会自动添加)
|
# api_2d (此后不需要在此处添加api2d的接口了，因为下面的代码会自动添加)
|
||||||
"api2d-gpt-4": {
|
"api2d-gpt-4": {
|
||||||
@@ -446,7 +396,6 @@ model_info = {
|
|||||||
"token_cnt": get_token_num_gpt4,
|
"token_cnt": get_token_num_gpt4,
|
||||||
},
|
},
|
||||||
|
|
||||||
# ChatGLM本地模型
|
|
||||||
# 将 chatglm 直接对齐到 chatglm2
|
# 将 chatglm 直接对齐到 chatglm2
|
||||||
"chatglm": {
|
"chatglm": {
|
||||||
"fn_with_ui": chatglm_ui,
|
"fn_with_ui": chatglm_ui,
|
||||||
@@ -472,14 +421,6 @@ model_info = {
|
|||||||
"tokenizer": tokenizer_gpt35,
|
"tokenizer": tokenizer_gpt35,
|
||||||
"token_cnt": get_token_num_gpt35,
|
"token_cnt": get_token_num_gpt35,
|
||||||
},
|
},
|
||||||
"chatglm4": {
|
|
||||||
"fn_with_ui": chatglm4_ui,
|
|
||||||
"fn_without_ui": chatglm4_noui,
|
|
||||||
"endpoint": None,
|
|
||||||
"max_token": 8192,
|
|
||||||
"tokenizer": tokenizer_gpt35,
|
|
||||||
"token_cnt": get_token_num_gpt35,
|
|
||||||
},
|
|
||||||
"qianfan": {
|
"qianfan": {
|
||||||
"fn_with_ui": qianfan_ui,
|
"fn_with_ui": qianfan_ui,
|
||||||
"fn_without_ui": qianfan_noui,
|
"fn_without_ui": qianfan_noui,
|
||||||
@@ -812,8 +753,7 @@ if "qwen-local" in AVAIL_LLM_MODELS:
|
|||||||
except:
|
except:
|
||||||
logger.error(trimmed_format_exc())
|
logger.error(trimmed_format_exc())
|
||||||
# -=-=-=-=-=-=- 通义-在线模型 -=-=-=-=-=-=-
|
# -=-=-=-=-=-=- 通义-在线模型 -=-=-=-=-=-=-
|
||||||
qwen_models = ["qwen-max-latest", "qwen-max-2025-01-25","qwen-max","qwen-turbo","qwen-plus"]
|
if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-max" in AVAIL_LLM_MODELS: # zhipuai
|
||||||
if any(item in qwen_models for item in AVAIL_LLM_MODELS):
|
|
||||||
try:
|
try:
|
||||||
from .bridge_qwen import predict_no_ui_long_connection as qwen_noui
|
from .bridge_qwen import predict_no_ui_long_connection as qwen_noui
|
||||||
from .bridge_qwen import predict as qwen_ui
|
from .bridge_qwen import predict as qwen_ui
|
||||||
@@ -823,7 +763,7 @@ if any(item in qwen_models for item in AVAIL_LLM_MODELS):
|
|||||||
"fn_without_ui": qwen_noui,
|
"fn_without_ui": qwen_noui,
|
||||||
"can_multi_thread": True,
|
"can_multi_thread": True,
|
||||||
"endpoint": None,
|
"endpoint": None,
|
||||||
"max_token": 100000,
|
"max_token": 6144,
|
||||||
"tokenizer": tokenizer_gpt35,
|
"tokenizer": tokenizer_gpt35,
|
||||||
"token_cnt": get_token_num_gpt35,
|
"token_cnt": get_token_num_gpt35,
|
||||||
},
|
},
|
||||||
@@ -832,7 +772,7 @@ if any(item in qwen_models for item in AVAIL_LLM_MODELS):
|
|||||||
"fn_without_ui": qwen_noui,
|
"fn_without_ui": qwen_noui,
|
||||||
"can_multi_thread": True,
|
"can_multi_thread": True,
|
||||||
"endpoint": None,
|
"endpoint": None,
|
||||||
"max_token": 129024,
|
"max_token": 30720,
|
||||||
"tokenizer": tokenizer_gpt35,
|
"tokenizer": tokenizer_gpt35,
|
||||||
"token_cnt": get_token_num_gpt35,
|
"token_cnt": get_token_num_gpt35,
|
||||||
},
|
},
|
||||||
@@ -841,25 +781,7 @@ if any(item in qwen_models for item in AVAIL_LLM_MODELS):
|
|||||||
"fn_without_ui": qwen_noui,
|
"fn_without_ui": qwen_noui,
|
||||||
"can_multi_thread": True,
|
"can_multi_thread": True,
|
||||||
"endpoint": None,
|
"endpoint": None,
|
||||||
"max_token": 30720,
|
"max_token": 28672,
|
||||||
"tokenizer": tokenizer_gpt35,
|
|
||||||
"token_cnt": get_token_num_gpt35,
|
|
||||||
},
|
|
||||||
"qwen-max-latest": {
|
|
||||||
"fn_with_ui": qwen_ui,
|
|
||||||
"fn_without_ui": qwen_noui,
|
|
||||||
"can_multi_thread": True,
|
|
||||||
"endpoint": None,
|
|
||||||
"max_token": 30720,
|
|
||||||
"tokenizer": tokenizer_gpt35,
|
|
||||||
"token_cnt": get_token_num_gpt35,
|
|
||||||
},
|
|
||||||
"qwen-max-2025-01-25": {
|
|
||||||
"fn_with_ui": qwen_ui,
|
|
||||||
"fn_without_ui": qwen_noui,
|
|
||||||
"can_multi_thread": True,
|
|
||||||
"endpoint": None,
|
|
||||||
"max_token": 30720,
|
|
||||||
"tokenizer": tokenizer_gpt35,
|
"tokenizer": tokenizer_gpt35,
|
||||||
"token_cnt": get_token_num_gpt35,
|
"token_cnt": get_token_num_gpt35,
|
||||||
}
|
}
|
||||||
@@ -946,31 +868,6 @@ if any(item in yi_models for item in AVAIL_LLM_MODELS):
|
|||||||
})
|
})
|
||||||
except:
|
except:
|
||||||
logger.error(trimmed_format_exc())
|
logger.error(trimmed_format_exc())
|
||||||
|
|
||||||
|
|
||||||
# -=-=-=-=-=-=- Grok model from x.ai -=-=-=-=-=-=-
|
|
||||||
grok_models = ["grok-beta"]
|
|
||||||
if any(item in grok_models for item in AVAIL_LLM_MODELS):
|
|
||||||
try:
|
|
||||||
grok_beta_128k_noui, grok_beta_128k_ui = get_predict_function(
|
|
||||||
api_key_conf_name="GROK_API_KEY", max_output_token=8192, disable_proxy=False
|
|
||||||
)
|
|
||||||
|
|
||||||
model_info.update({
|
|
||||||
"grok-beta": {
|
|
||||||
"fn_with_ui": grok_beta_128k_ui,
|
|
||||||
"fn_without_ui": grok_beta_128k_noui,
|
|
||||||
"can_multi_thread": True,
|
|
||||||
"endpoint": grok_model_endpoint,
|
|
||||||
"max_token": 128000,
|
|
||||||
"tokenizer": tokenizer_gpt35,
|
|
||||||
"token_cnt": get_token_num_gpt35,
|
|
||||||
},
|
|
||||||
|
|
||||||
})
|
|
||||||
except:
|
|
||||||
logger.error(trimmed_format_exc())
|
|
||||||
|
|
||||||
# -=-=-=-=-=-=- 讯飞星火认知大模型 -=-=-=-=-=-=-
|
# -=-=-=-=-=-=- 讯飞星火认知大模型 -=-=-=-=-=-=-
|
||||||
if "spark" in AVAIL_LLM_MODELS:
|
if "spark" in AVAIL_LLM_MODELS:
|
||||||
try:
|
try:
|
||||||
@@ -1090,18 +987,18 @@ if "deepseekcoder" in AVAIL_LLM_MODELS: # deepseekcoder
|
|||||||
except:
|
except:
|
||||||
logger.error(trimmed_format_exc())
|
logger.error(trimmed_format_exc())
|
||||||
# -=-=-=-=-=-=- 幻方-深度求索大模型在线API -=-=-=-=-=-=-
|
# -=-=-=-=-=-=- 幻方-深度求索大模型在线API -=-=-=-=-=-=-
|
||||||
if "deepseek-chat" in AVAIL_LLM_MODELS or "deepseek-coder" in AVAIL_LLM_MODELS or "deepseek-reasoner" in AVAIL_LLM_MODELS:
|
if "deepseek-chat" in AVAIL_LLM_MODELS or "deepseek-coder" in AVAIL_LLM_MODELS:
|
||||||
try:
|
try:
|
||||||
deepseekapi_noui, deepseekapi_ui = get_predict_function(
|
deepseekapi_noui, deepseekapi_ui = get_predict_function(
|
||||||
api_key_conf_name="DEEPSEEK_API_KEY", max_output_token=4096, disable_proxy=False
|
api_key_conf_name="DEEPSEEK_API_KEY", max_output_token=4096, disable_proxy=False
|
||||||
)
|
)
|
||||||
model_info.update({
|
model_info.update({
|
||||||
"deepseek-chat":{
|
"deepseek-chat":{
|
||||||
"fn_with_ui": deepseekapi_ui,
|
"fn_with_ui": deepseekapi_ui,
|
||||||
"fn_without_ui": deepseekapi_noui,
|
"fn_without_ui": deepseekapi_noui,
|
||||||
"endpoint": deepseekapi_endpoint,
|
"endpoint": deepseekapi_endpoint,
|
||||||
"can_multi_thread": True,
|
"can_multi_thread": True,
|
||||||
"max_token": 64000,
|
"max_token": 32000,
|
||||||
"tokenizer": tokenizer_gpt35,
|
"tokenizer": tokenizer_gpt35,
|
||||||
"token_cnt": get_token_num_gpt35,
|
"token_cnt": get_token_num_gpt35,
|
||||||
},
|
},
|
||||||
@@ -1114,16 +1011,6 @@ if "deepseek-chat" in AVAIL_LLM_MODELS or "deepseek-coder" in AVAIL_LLM_MODELS o
|
|||||||
"tokenizer": tokenizer_gpt35,
|
"tokenizer": tokenizer_gpt35,
|
||||||
"token_cnt": get_token_num_gpt35,
|
"token_cnt": get_token_num_gpt35,
|
||||||
},
|
},
|
||||||
"deepseek-reasoner":{
|
|
||||||
"fn_with_ui": deepseekapi_ui,
|
|
||||||
"fn_without_ui": deepseekapi_noui,
|
|
||||||
"endpoint": deepseekapi_endpoint,
|
|
||||||
"can_multi_thread": True,
|
|
||||||
"max_token": 64000,
|
|
||||||
"tokenizer": tokenizer_gpt35,
|
|
||||||
"token_cnt": get_token_num_gpt35,
|
|
||||||
"enable_reasoning": True
|
|
||||||
},
|
|
||||||
})
|
})
|
||||||
except:
|
except:
|
||||||
logger.error(trimmed_format_exc())
|
logger.error(trimmed_format_exc())
|
||||||
@@ -1391,11 +1278,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot,
|
|||||||
|
|
||||||
inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")
|
inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")
|
||||||
|
|
||||||
if llm_kwargs['llm_model'] not in model_info:
|
|
||||||
from toolbox import update_ui
|
|
||||||
chatbot.append([inputs, f"很抱歉，模型 '{llm_kwargs['llm_model']}' 暂不支持<br/>(1) 检查config中的AVAIL_LLM_MODELS选项<br/>(2) 检查request_llms/bridge_all.py中的模型路由"])
|
|
||||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
|
||||||
|
|
||||||
method = model_info[llm_kwargs['llm_model']]["fn_with_ui"] # 如果这里报错，检查config中的AVAIL_LLM_MODELS选项
|
method = model_info[llm_kwargs['llm_model']]["fn_with_ui"] # 如果这里报错，检查config中的AVAIL_LLM_MODELS选项
|
||||||
|
|
||||||
if additional_fn: # 根据基础功能区 ModelOverride 参数调整模型类型
|
if additional_fn: # 根据基础功能区 ModelOverride 参数调整模型类型
|
||||||
|
|||||||
@@ -23,33 +23,39 @@ class GetGLM3Handle(LocalLLMHandle):
|
|||||||
import os
|
import os
|
||||||
import platform
|
import platform
|
||||||
|
|
||||||
LOCAL_MODEL_PATH, LOCAL_MODEL_QUANT, device = get_conf("CHATGLM_LOCAL_MODEL_PATH", "LOCAL_MODEL_QUANT", "LOCAL_MODEL_DEVICE")
|
LOCAL_MODEL_QUANT, device = get_conf("LOCAL_MODEL_QUANT", "LOCAL_MODEL_DEVICE")
|
||||||
model_path = LOCAL_MODEL_PATH
|
_model_name_ = "THUDM/chatglm3-6b"
|
||||||
|
# if LOCAL_MODEL_QUANT == "INT4": # INT4
|
||||||
|
# _model_name_ = "THUDM/chatglm3-6b-int4"
|
||||||
|
# elif LOCAL_MODEL_QUANT == "INT8": # INT8
|
||||||
|
# _model_name_ = "THUDM/chatglm3-6b-int8"
|
||||||
|
# else:
|
||||||
|
# _model_name_ = "THUDM/chatglm3-6b" # FP16
|
||||||
with ProxyNetworkActivate("Download_LLM"):
|
with ProxyNetworkActivate("Download_LLM"):
|
||||||
chatglm_tokenizer = AutoTokenizer.from_pretrained(
|
chatglm_tokenizer = AutoTokenizer.from_pretrained(
|
||||||
model_path, trust_remote_code=True
|
_model_name_, trust_remote_code=True
|
||||||
)
|
)
|
||||||
if device == "cpu":
|
if device == "cpu":
|
||||||
chatglm_model = AutoModel.from_pretrained(
|
chatglm_model = AutoModel.from_pretrained(
|
||||||
model_path,
|
_model_name_,
|
||||||
trust_remote_code=True,
|
trust_remote_code=True,
|
||||||
device="cpu",
|
device="cpu",
|
||||||
).float()
|
).float()
|
||||||
elif LOCAL_MODEL_QUANT == "INT4": # INT4
|
elif LOCAL_MODEL_QUANT == "INT4": # INT4
|
||||||
chatglm_model = AutoModel.from_pretrained(
|
chatglm_model = AutoModel.from_pretrained(
|
||||||
pretrained_model_name_or_path=model_path,
|
pretrained_model_name_or_path=_model_name_,
|
||||||
trust_remote_code=True,
|
trust_remote_code=True,
|
||||||
quantization_config=BitsAndBytesConfig(load_in_4bit=True),
|
quantization_config=BitsAndBytesConfig(load_in_4bit=True),
|
||||||
)
|
)
|
||||||
elif LOCAL_MODEL_QUANT == "INT8": # INT8
|
elif LOCAL_MODEL_QUANT == "INT8": # INT8
|
||||||
chatglm_model = AutoModel.from_pretrained(
|
chatglm_model = AutoModel.from_pretrained(
|
||||||
pretrained_model_name_or_path=model_path,
|
pretrained_model_name_or_path=_model_name_,
|
||||||
trust_remote_code=True,
|
trust_remote_code=True,
|
||||||
quantization_config=BitsAndBytesConfig(load_in_8bit=True),
|
quantization_config=BitsAndBytesConfig(load_in_8bit=True),
|
||||||
)
|
)
|
||||||
else:
|
else:
|
||||||
chatglm_model = AutoModel.from_pretrained(
|
chatglm_model = AutoModel.from_pretrained(
|
||||||
pretrained_model_name_or_path=model_path,
|
pretrained_model_name_or_path=_model_name_,
|
||||||
trust_remote_code=True,
|
trust_remote_code=True,
|
||||||
device="cuda",
|
device="cuda",
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -1,81 +0,0 @@
|
|||||||
model_name = "ChatGLM4"
|
|
||||||
cmd_to_install = """
|
|
||||||
`pip install -r request_llms/requirements_chatglm4.txt`
|
|
||||||
`pip install modelscope`
|
|
||||||
`modelscope download --model ZhipuAI/glm-4-9b-chat --local_dir ./THUDM/glm-4-9b-chat`
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
from toolbox import get_conf, ProxyNetworkActivate
|
|
||||||
from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
|
|
||||||
|
|
||||||
|
|
||||||
# ------------------------------------------------------------------------------------------------------------------------
|
|
||||||
# 🔌💻 Local Model
|
|
||||||
# ------------------------------------------------------------------------------------------------------------------------
|
|
||||||
class GetGLM4Handle(LocalLLMHandle):
|
|
||||||
|
|
||||||
def load_model_info(self):
|
|
||||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
|
||||||
self.model_name = model_name
|
|
||||||
self.cmd_to_install = cmd_to_install
|
|
||||||
|
|
||||||
def load_model_and_tokenizer(self):
|
|
||||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
|
||||||
import torch
|
|
||||||
from transformers import AutoModel, AutoModelForCausalLM, AutoTokenizer
|
|
||||||
import os
|
|
||||||
|
|
||||||
LOCAL_MODEL_PATH, device = get_conf("CHATGLM_LOCAL_MODEL_PATH", "LOCAL_MODEL_DEVICE")
|
|
||||||
model_path = LOCAL_MODEL_PATH
|
|
||||||
chatglm_tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
|
||||||
chatglm_model = AutoModelForCausalLM.from_pretrained(
|
|
||||||
model_path,
|
|
||||||
torch_dtype=torch.bfloat16,
|
|
||||||
low_cpu_mem_usage=True,
|
|
||||||
trust_remote_code=True,
|
|
||||||
device=device
|
|
||||||
).eval().to(device)
|
|
||||||
self._model = chatglm_model
|
|
||||||
self._tokenizer = chatglm_tokenizer
|
|
||||||
return self._model, self._tokenizer
|
|
||||||
|
|
||||||
|
|
||||||
def llm_stream_generator(self, **kwargs):
|
|
||||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
|
||||||
def adaptor(kwargs):
|
|
||||||
query = kwargs["query"]
|
|
||||||
max_length = kwargs["max_length"]
|
|
||||||
top_p = kwargs["top_p"]
|
|
||||||
temperature = kwargs["temperature"]
|
|
||||||
history = kwargs["history"]
|
|
||||||
return query, max_length, top_p, temperature, history
|
|
||||||
|
|
||||||
query, max_length, top_p, temperature, history = adaptor(kwargs)
|
|
||||||
inputs = self._tokenizer.apply_chat_template([{"role": "user", "content": query}],
|
|
||||||
add_generation_prompt=True,
|
|
||||||
tokenize=True,
|
|
||||||
return_tensors="pt",
|
|
||||||
return_dict=True
|
|
||||||
).to(self._model.device)
|
|
||||||
gen_kwargs = {"max_length": max_length, "do_sample": True, "top_k": top_p}
|
|
||||||
|
|
||||||
outputs = self._model.generate(**inputs, **gen_kwargs)
|
|
||||||
outputs = outputs[:, inputs['input_ids'].shape[1]:]
|
|
||||||
response = self._tokenizer.decode(outputs[0], skip_special_tokens=True)
|
|
||||||
yield response
|
|
||||||
|
|
||||||
def try_to_import_special_deps(self, **kwargs):
|
|
||||||
# import something that will raise error if the user does not install requirement_*.txt
|
|
||||||
# 🏃♂️🏃♂️🏃♂️ 主进程执行
|
|
||||||
import importlib
|
|
||||||
|
|
||||||
# importlib.import_module('modelscope')
|
|
||||||
|
|
||||||
|
|
||||||
# ------------------------------------------------------------------------------------------------------------------------
|
|
||||||
# 🔌💻 GPT-Academic Interface
|
|
||||||
# ------------------------------------------------------------------------------------------------------------------------
|
|
||||||
predict_no_ui_long_connection, predict = get_local_llm_predict_fns(
|
|
||||||
GetGLM4Handle, model_name, history_format="chatglm3"
|
|
||||||
)
|
|
||||||
@@ -23,13 +23,8 @@ from loguru import logger
|
|||||||
from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history
|
from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history
|
||||||
from toolbox import trimmed_format_exc, is_the_upload_folder, read_one_api_model_name, log_chat
|
from toolbox import trimmed_format_exc, is_the_upload_folder, read_one_api_model_name, log_chat
|
||||||
from toolbox import ChatBotWithCookies, have_any_recent_upload_image_files, encode_image
|
from toolbox import ChatBotWithCookies, have_any_recent_upload_image_files, encode_image
|
||||||
proxies, WHEN_TO_USE_PROXY, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
|
proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
|
||||||
get_conf('proxies', 'WHEN_TO_USE_PROXY', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
|
get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
|
||||||
|
|
||||||
if "Connect_OpenAI" not in WHEN_TO_USE_PROXY:
|
|
||||||
if proxies is not None:
|
|
||||||
logger.error("虽然您配置了代理设置，但不会在连接OpenAI的过程中起作用，请检查WHEN_TO_USE_PROXY配置。")
|
|
||||||
proxies = None
|
|
||||||
|
|
||||||
timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
|
timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
|
||||||
'网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
|
'网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
|
||||||
@@ -185,20 +180,14 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
|||||||
raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
|
raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
|
||||||
else:
|
else:
|
||||||
raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
|
raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
|
||||||
if ('data: [DONE]' in chunk_decoded): break # api2d & one-api 正常完成
|
if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成
|
||||||
# 提前读取一些信息 （用于判断异常）
|
# 提前读取一些信息 （用于判断异常）
|
||||||
if has_choices and not choice_valid:
|
if has_choices and not choice_valid:
|
||||||
# 一些垃圾第三方接口的出现这样的错误
|
# 一些垃圾第三方接口的出现这样的错误
|
||||||
continue
|
continue
|
||||||
json_data = chunkjson['choices'][0]
|
json_data = chunkjson['choices'][0]
|
||||||
delta = json_data["delta"]
|
delta = json_data["delta"]
|
||||||
|
if len(delta) == 0: break
|
||||||
if len(delta) == 0:
|
|
||||||
is_termination_certain = False
|
|
||||||
if (has_choices) and (chunkjson['choices'][0].get('finish_reason', 'null') == 'stop'): is_termination_certain = True
|
|
||||||
if is_termination_certain: break
|
|
||||||
else: continue # 对于不符合规范的狗屎接口，这里需要继续
|
|
||||||
|
|
||||||
if (not has_content) and has_role: continue
|
if (not has_content) and has_role: continue
|
||||||
if (not has_content) and (not has_role): continue # raise RuntimeError("发现不标准的第三方接口："+delta)
|
if (not has_content) and (not has_role): continue # raise RuntimeError("发现不标准的第三方接口："+delta)
|
||||||
if has_content: # has_role = True/False
|
if has_content: # has_role = True/False
|
||||||
@@ -296,8 +285,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
|||||||
history.extend([inputs, ""])
|
history.extend([inputs, ""])
|
||||||
|
|
||||||
retry = 0
|
retry = 0
|
||||||
previous_ui_reflesh_time = 0
|
|
||||||
ui_reflesh_min_interval = 0.0
|
|
||||||
while True:
|
while True:
|
||||||
try:
|
try:
|
||||||
# make a POST request to the API endpoint, stream=True
|
# make a POST request to the API endpoint, stream=True
|
||||||
@@ -310,13 +297,13 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
|||||||
yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
|
yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
|
||||||
if retry > MAX_RETRY: raise TimeoutError
|
if retry > MAX_RETRY: raise TimeoutError
|
||||||
|
|
||||||
|
|
||||||
if not stream:
|
if not stream:
|
||||||
# 该分支仅适用于不支持stream的o1模型，其他情形一律不适用
|
# 该分支仅适用于不支持stream的o1模型，其他情形一律不适用
|
||||||
yield from handle_o1_model_special(response, inputs, llm_kwargs, chatbot, history)
|
yield from handle_o1_model_special(response, inputs, llm_kwargs, chatbot, history)
|
||||||
return
|
return
|
||||||
|
|
||||||
if stream:
|
if stream:
|
||||||
reach_termination = False # 处理一些 new-api 的奇葩异常
|
|
||||||
gpt_replying_buffer = ""
|
gpt_replying_buffer = ""
|
||||||
is_head_of_the_stream = True
|
is_head_of_the_stream = True
|
||||||
stream_response = response.iter_lines()
|
stream_response = response.iter_lines()
|
||||||
@@ -329,14 +316,11 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
|||||||
error_msg = chunk_decoded
|
error_msg = chunk_decoded
|
||||||
# 首先排除一个one-api没有done数据包的第三方Bug情形
|
# 首先排除一个one-api没有done数据包的第三方Bug情形
|
||||||
if len(gpt_replying_buffer.strip()) > 0 and len(error_msg) == 0:
|
if len(gpt_replying_buffer.strip()) > 0 and len(error_msg) == 0:
|
||||||
yield from update_ui(chatbot=chatbot, history=history, msg="检测到有缺陷的接口，建议选择更稳定的接口。")
|
yield from update_ui(chatbot=chatbot, history=history, msg="检测到有缺陷的非OpenAI官方接口，建议选择更稳定的接口。")
|
||||||
if not reach_termination:
|
|
||||||
reach_termination = True
|
|
||||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
|
|
||||||
break
|
break
|
||||||
# 其他情况，直接返回报错
|
# 其他情况，直接返回报错
|
||||||
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
||||||
yield from update_ui(chatbot=chatbot, history=history, msg="接口返回了错误:" + chunk.decode()) # 刷新界面
|
yield from update_ui(chatbot=chatbot, history=history, msg="非OpenAI官方接口返回了错误:" + chunk.decode()) # 刷新界面
|
||||||
return
|
return
|
||||||
|
|
||||||
# 提前读取一些信息 （用于判断异常）
|
# 提前读取一些信息 （用于判断异常）
|
||||||
@@ -346,8 +330,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
|||||||
# 数据流的第一帧不携带content
|
# 数据流的第一帧不携带content
|
||||||
is_head_of_the_stream = False; continue
|
is_head_of_the_stream = False; continue
|
||||||
|
|
||||||
if "error" in chunk_decoded: logger.error(f"接口返回了未知错误: {chunk_decoded}")
|
|
||||||
|
|
||||||
if chunk:
|
if chunk:
|
||||||
try:
|
try:
|
||||||
if has_choices and not choice_valid:
|
if has_choices and not choice_valid:
|
||||||
@@ -356,25 +338,14 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
|||||||
if ('data: [DONE]' not in chunk_decoded) and len(chunk_decoded) > 0 and (chunkjson is None):
|
if ('data: [DONE]' not in chunk_decoded) and len(chunk_decoded) > 0 and (chunkjson is None):
|
||||||
# 传递进来一些奇怪的东西
|
# 传递进来一些奇怪的东西
|
||||||
raise ValueError(f'无法读取以下数据，请检查配置。\n\n{chunk_decoded}')
|
raise ValueError(f'无法读取以下数据，请检查配置。\n\n{chunk_decoded}')
|
||||||
# 前者是API2D & One-API的结束条件，后者是OPENAI的结束条件
|
# 前者是API2D的结束条件，后者是OPENAI的结束条件
|
||||||
one_api_terminate = ('data: [DONE]' in chunk_decoded)
|
if ('data: [DONE]' in chunk_decoded) or (len(chunkjson['choices'][0]["delta"]) == 0):
|
||||||
openai_terminate = (has_choices) and (len(chunkjson['choices'][0]["delta"]) == 0)
|
# 判定为数据流的结束，gpt_replying_buffer也写完了
|
||||||
if one_api_terminate or openai_terminate:
|
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
|
||||||
is_termination_certain = False
|
break
|
||||||
if one_api_terminate: is_termination_certain = True # 抓取符合规范的结束条件
|
|
||||||
elif (has_choices) and (chunkjson['choices'][0].get('finish_reason', 'null') == 'stop'): is_termination_certain = True # 抓取符合规范的结束条件
|
|
||||||
if is_termination_certain:
|
|
||||||
reach_termination = True
|
|
||||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
|
|
||||||
break # 对于符合规范的接口，这里可以break
|
|
||||||
else:
|
|
||||||
continue # 对于不符合规范的狗屎接口，这里需要继续
|
|
||||||
# 到这里，我们已经可以假定必须包含choice了
|
|
||||||
try:
|
|
||||||
status_text = f"finish_reason: {chunkjson['choices'][0].get('finish_reason', 'null')}"
|
|
||||||
except:
|
|
||||||
logger.error(f"一些垃圾第三方接口出现这样的错误，兼容一下吧: {chunk_decoded}")
|
|
||||||
# 处理数据流的主体
|
# 处理数据流的主体
|
||||||
|
status_text = f"finish_reason: {chunkjson['choices'][0].get('finish_reason', 'null')}"
|
||||||
|
# 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
|
||||||
if has_content:
|
if has_content:
|
||||||
# 正常情况
|
# 正常情况
|
||||||
gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]
|
gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]
|
||||||
@@ -383,26 +354,21 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
|||||||
continue
|
continue
|
||||||
else:
|
else:
|
||||||
# 至此已经超出了正常接口应该进入的范围，一些垃圾第三方接口会出现这样的错误
|
# 至此已经超出了正常接口应该进入的范围，一些垃圾第三方接口会出现这样的错误
|
||||||
if chunkjson['choices'][0]["delta"].get("content", None) is None:
|
if chunkjson['choices'][0]["delta"]["content"] is None: continue # 一些垃圾第三方接口出现这样的错误，兼容一下吧
|
||||||
logger.error(f"一些垃圾第三方接口出现这样的错误，兼容一下吧: {chunk_decoded}")
|
|
||||||
continue
|
|
||||||
gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]
|
gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]
|
||||||
|
|
||||||
history[-1] = gpt_replying_buffer
|
history[-1] = gpt_replying_buffer
|
||||||
chatbot[-1] = (history[-2], history[-1])
|
chatbot[-1] = (history[-2], history[-1])
|
||||||
if time.time() - previous_ui_reflesh_time > ui_reflesh_min_interval:
|
yield from update_ui(chatbot=chatbot, history=history, msg=status_text) # 刷新界面
|
||||||
yield from update_ui(chatbot=chatbot, history=history, msg=status_text) # 刷新界面
|
|
||||||
previous_ui_reflesh_time = time.time()
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
|
yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
|
||||||
chunk = get_full_error(chunk, stream_response)
|
chunk = get_full_error(chunk, stream_response)
|
||||||
chunk_decoded = chunk.decode()
|
chunk_decoded = chunk.decode()
|
||||||
error_msg = chunk_decoded
|
error_msg = chunk_decoded
|
||||||
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
||||||
logger.error(error_msg)
|
|
||||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json解析异常" + error_msg) # 刷新界面
|
yield from update_ui(chatbot=chatbot, history=history, msg="Json解析异常" + error_msg) # 刷新界面
|
||||||
|
logger.error(error_msg)
|
||||||
return
|
return
|
||||||
yield from update_ui(chatbot=chatbot, history=history, msg="完成") # 刷新界面
|
|
||||||
return # return from stream-branch
|
return # return from stream-branch
|
||||||
|
|
||||||
def handle_o1_model_special(response, inputs, llm_kwargs, chatbot, history):
|
def handle_o1_model_special(response, inputs, llm_kwargs, chatbot, history):
|
||||||
@@ -570,8 +536,6 @@ def generate_payload(inputs:str, llm_kwargs:dict, history:list, system_prompt:st
|
|||||||
"n": 1,
|
"n": 1,
|
||||||
"stream": stream,
|
"stream": stream,
|
||||||
}
|
}
|
||||||
openai_force_temperature_one = model_info[llm_kwargs['llm_model']].get('openai_force_temperature_one', False)
|
|
||||||
if openai_force_temperature_one:
|
|
||||||
payload.pop('temperature')
|
|
||||||
return headers,payload
|
return headers,payload
|
||||||
|
|
||||||
|
|||||||
@@ -26,7 +26,7 @@ class GetLlamaHandle(LocalLLMHandle):
|
|||||||
import platform
|
import platform
|
||||||
huggingface_token, device = get_conf('HUGGINGFACE_ACCESS_TOKEN', 'LOCAL_MODEL_DEVICE')
|
huggingface_token, device = get_conf('HUGGINGFACE_ACCESS_TOKEN', 'LOCAL_MODEL_DEVICE')
|
||||||
assert len(huggingface_token) != 0, "没有填写 HUGGINGFACE_ACCESS_TOKEN"
|
assert len(huggingface_token) != 0, "没有填写 HUGGINGFACE_ACCESS_TOKEN"
|
||||||
with open(os.path.expanduser('~/.cache/huggingface/token'), 'w', encoding='utf8') as f:
|
with open(os.path.expanduser('~/.cache/huggingface/token'), 'w') as f:
|
||||||
f.write(huggingface_token)
|
f.write(huggingface_token)
|
||||||
model_id = 'meta-llama/Llama-2-7b-chat-hf'
|
model_id = 'meta-llama/Llama-2-7b-chat-hf'
|
||||||
with ProxyNetworkActivate('Download_LLM'):
|
with ProxyNetworkActivate('Download_LLM'):
|
||||||
|
|||||||
@@ -31,7 +31,7 @@ class MoonShotInit:
|
|||||||
files.append(f)
|
files.append(f)
|
||||||
for file in files:
|
for file in files:
|
||||||
if file.split('.')[-1] in ['pdf']:
|
if file.split('.')[-1] in ['pdf']:
|
||||||
with open(file, 'r', encoding='utf8') as fp:
|
with open(file, 'r') as fp:
|
||||||
from crazy_functions.crazy_utils import read_and_clean_pdf_text
|
from crazy_functions.crazy_utils import read_and_clean_pdf_text
|
||||||
file_content, _ = read_and_clean_pdf_text(fp)
|
file_content, _ = read_and_clean_pdf_text(fp)
|
||||||
what_ask.append({"role": "system", "content": file_content})
|
what_ask.append({"role": "system", "content": file_content})
|
||||||
|
|||||||
@@ -75,7 +75,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
|
|||||||
# make a POST request to the API endpoint, stream=False
|
# make a POST request to the API endpoint, stream=False
|
||||||
from .bridge_all import model_info
|
from .bridge_all import model_info
|
||||||
endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
||||||
response = requests.post(endpoint, headers=headers, proxies=None,
|
response = requests.post(endpoint, headers=headers, proxies=proxies,
|
||||||
json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
|
json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
|
||||||
except requests.exceptions.ReadTimeout as e:
|
except requests.exceptions.ReadTimeout as e:
|
||||||
retry += 1
|
retry += 1
|
||||||
@@ -152,12 +152,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
|||||||
history.append(inputs); history.append("")
|
history.append(inputs); history.append("")
|
||||||
|
|
||||||
retry = 0
|
retry = 0
|
||||||
if proxies is not None:
|
|
||||||
logger.error("Ollama不会使用代理服务器, 忽略了proxies的设置。")
|
|
||||||
while True:
|
while True:
|
||||||
try:
|
try:
|
||||||
# make a POST request to the API endpoint, stream=True
|
# make a POST request to the API endpoint, stream=True
|
||||||
response = requests.post(endpoint, headers=headers, proxies=None,
|
response = requests.post(endpoint, headers=headers, proxies=proxies,
|
||||||
json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
|
json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
|
||||||
except:
|
except:
|
||||||
retry += 1
|
retry += 1
|
||||||
|
|||||||
@@ -170,7 +170,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
|||||||
except requests.exceptions.ConnectionError:
|
except requests.exceptions.ConnectionError:
|
||||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||||
chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
|
chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
|
||||||
if len(chunk_decoded)==0 or chunk_decoded.startswith(':'): continue
|
if len(chunk_decoded)==0: continue
|
||||||
if not chunk_decoded.startswith('data:'):
|
if not chunk_decoded.startswith('data:'):
|
||||||
error_msg = get_full_error(chunk, stream_response).decode()
|
error_msg = get_full_error(chunk, stream_response).decode()
|
||||||
if "reduce the length" in error_msg:
|
if "reduce the length" in error_msg:
|
||||||
@@ -181,6 +181,9 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
|||||||
raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
|
raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
|
||||||
if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成
|
if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成
|
||||||
# 提前读取一些信息 （用于判断异常）
|
# 提前读取一些信息 （用于判断异常）
|
||||||
|
if (has_choices and not choice_valid) or ('OPENROUTER PROCESSING' in chunk_decoded):
|
||||||
|
# 一些垃圾第三方接口的出现这样的错误，openrouter的特殊处理
|
||||||
|
continue
|
||||||
json_data = chunkjson['choices'][0]
|
json_data = chunkjson['choices'][0]
|
||||||
delta = json_data["delta"]
|
delta = json_data["delta"]
|
||||||
if len(delta) == 0: break
|
if len(delta) == 0: break
|
||||||
@@ -325,7 +328,8 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
|||||||
|
|
||||||
if chunk:
|
if chunk:
|
||||||
try:
|
try:
|
||||||
if (has_choices and not choice_valid) or chunk_decoded.startswith(':'):
|
if (has_choices and not choice_valid) or ('OPENROUTER PROCESSING' in chunk_decoded):
|
||||||
|
# 一些垃圾第三方接口的出现这样的错误, 或者OPENROUTER的特殊处理,因为OPENROUTER的数据流未连接到模型时会出现OPENROUTER PROCESSING
|
||||||
continue
|
continue
|
||||||
if ('data: [DONE]' not in chunk_decoded) and len(chunk_decoded) > 0 and (chunkjson is None):
|
if ('data: [DONE]' not in chunk_decoded) and len(chunk_decoded) > 0 and (chunkjson is None):
|
||||||
# 传递进来一些奇怪的东西
|
# 传递进来一些奇怪的东西
|
||||||
|
|||||||
@@ -202,29 +202,16 @@ class GoogleChatInit:
|
|||||||
) # 处理 history
|
) # 处理 history
|
||||||
|
|
||||||
messages.append(self.__conversation_user(inputs, llm_kwargs, enable_multimodal_capacity)) # 处理用户对话
|
messages.append(self.__conversation_user(inputs, llm_kwargs, enable_multimodal_capacity)) # 处理用户对话
|
||||||
stop_sequences = str(llm_kwargs.get("stop", "")).split(" ")
|
payload = {
|
||||||
# 过滤空字符串并确保至少有一个停止序列
|
"contents": messages,
|
||||||
stop_sequences = [s for s in stop_sequences if s]
|
"generationConfig": {
|
||||||
if not stop_sequences:
|
# "maxOutputTokens": llm_kwargs.get("max_token", 1024),
|
||||||
payload = {
|
"stopSequences": str(llm_kwargs.get("stop", "")).split(" "),
|
||||||
"contents": messages,
|
"temperature": llm_kwargs.get("temperature", 1),
|
||||||
"generationConfig": {
|
"topP": llm_kwargs.get("top_p", 0.8),
|
||||||
"temperature": llm_kwargs.get("temperature", 1),
|
"topK": 10,
|
||||||
"topP": llm_kwargs.get("top_p", 0.8),
|
},
|
||||||
"topK": 10,
|
}
|
||||||
},
|
|
||||||
}
|
|
||||||
else:
|
|
||||||
payload = {
|
|
||||||
"contents": messages,
|
|
||||||
"generationConfig": {
|
|
||||||
# "maxOutputTokens": llm_kwargs.get("max_token", 1024),
|
|
||||||
"stopSequences": stop_sequences,
|
|
||||||
"temperature": llm_kwargs.get("temperature", 1),
|
|
||||||
"topP": llm_kwargs.get("top_p", 0.8),
|
|
||||||
"topK": 10,
|
|
||||||
},
|
|
||||||
}
|
|
||||||
|
|
||||||
return header, payload
|
return header, payload
|
||||||
|
|
||||||
|
|||||||
@@ -24,13 +24,18 @@ class QwenRequestInstance():
|
|||||||
def generate(self, inputs, llm_kwargs, history, system_prompt):
|
def generate(self, inputs, llm_kwargs, history, system_prompt):
|
||||||
# import _thread as thread
|
# import _thread as thread
|
||||||
from dashscope import Generation
|
from dashscope import Generation
|
||||||
|
QWEN_MODEL = {
|
||||||
|
'qwen-turbo': Generation.Models.qwen_turbo,
|
||||||
|
'qwen-plus': Generation.Models.qwen_plus,
|
||||||
|
'qwen-max': Generation.Models.qwen_max,
|
||||||
|
}[llm_kwargs['llm_model']]
|
||||||
top_p = llm_kwargs.get('top_p', 0.8)
|
top_p = llm_kwargs.get('top_p', 0.8)
|
||||||
if top_p == 0: top_p += 1e-5
|
if top_p == 0: top_p += 1e-5
|
||||||
if top_p == 1: top_p -= 1e-5
|
if top_p == 1: top_p -= 1e-5
|
||||||
|
|
||||||
self.result_buf = ""
|
self.result_buf = ""
|
||||||
responses = Generation.call(
|
responses = Generation.call(
|
||||||
model=llm_kwargs['llm_model'],
|
model=QWEN_MODEL,
|
||||||
messages=generate_message_payload(inputs, llm_kwargs, history, system_prompt),
|
messages=generate_message_payload(inputs, llm_kwargs, history, system_prompt),
|
||||||
top_p=top_p,
|
top_p=top_p,
|
||||||
temperature=llm_kwargs.get('temperature', 1.0),
|
temperature=llm_kwargs.get('temperature', 1.0),
|
||||||
|
|||||||
@@ -36,11 +36,10 @@ def get_full_error(chunk, stream_response):
|
|||||||
|
|
||||||
def decode_chunk(chunk):
|
def decode_chunk(chunk):
|
||||||
"""
|
"""
|
||||||
用于解读"content"和"finish_reason"的内容（如果支持思维链也会返回"reasoning_content"内容）
|
用于解读"content"和"finish_reason"的内容
|
||||||
"""
|
"""
|
||||||
chunk = chunk.decode()
|
chunk = chunk.decode()
|
||||||
respose = ""
|
respose = ""
|
||||||
reasoning_content = ""
|
|
||||||
finish_reason = "False"
|
finish_reason = "False"
|
||||||
try:
|
try:
|
||||||
chunk = json.loads(chunk[6:])
|
chunk = json.loads(chunk[6:])
|
||||||
@@ -58,20 +57,14 @@ def decode_chunk(chunk):
|
|||||||
return respose, finish_reason
|
return respose, finish_reason
|
||||||
|
|
||||||
try:
|
try:
|
||||||
if chunk["choices"][0]["delta"]["content"] is not None:
|
respose = chunk["choices"][0]["delta"]["content"]
|
||||||
respose = chunk["choices"][0]["delta"]["content"]
|
|
||||||
except:
|
|
||||||
pass
|
|
||||||
try:
|
|
||||||
if chunk["choices"][0]["delta"]["reasoning_content"] is not None:
|
|
||||||
reasoning_content = chunk["choices"][0]["delta"]["reasoning_content"]
|
|
||||||
except:
|
except:
|
||||||
pass
|
pass
|
||||||
try:
|
try:
|
||||||
finish_reason = chunk["choices"][0]["finish_reason"]
|
finish_reason = chunk["choices"][0]["finish_reason"]
|
||||||
except:
|
except:
|
||||||
pass
|
pass
|
||||||
return respose, reasoning_content, finish_reason
|
return respose, finish_reason
|
||||||
|
|
||||||
|
|
||||||
def generate_message(input, model, key, history, max_output_token, system_prompt, temperature):
|
def generate_message(input, model, key, history, max_output_token, system_prompt, temperature):
|
||||||
@@ -156,7 +149,6 @@ def get_predict_function(
|
|||||||
observe_window = None：
|
observe_window = None：
|
||||||
用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
|
用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
|
||||||
"""
|
"""
|
||||||
from .bridge_all import model_info
|
|
||||||
watch_dog_patience = 5 # 看门狗的耐心，设置5秒不准咬人(咬的也不是人
|
watch_dog_patience = 5 # 看门狗的耐心，设置5秒不准咬人(咬的也不是人
|
||||||
if len(APIKEY) == 0:
|
if len(APIKEY) == 0:
|
||||||
raise RuntimeError(f"APIKEY为空,请检查配置文件的{APIKEY}")
|
raise RuntimeError(f"APIKEY为空,请检查配置文件的{APIKEY}")
|
||||||
@@ -171,21 +163,29 @@ def get_predict_function(
|
|||||||
system_prompt=sys_prompt,
|
system_prompt=sys_prompt,
|
||||||
temperature=llm_kwargs["temperature"],
|
temperature=llm_kwargs["temperature"],
|
||||||
)
|
)
|
||||||
|
|
||||||
reasoning = model_info[llm_kwargs['llm_model']].get('enable_reasoning', False)
|
|
||||||
|
|
||||||
retry = 0
|
retry = 0
|
||||||
while True:
|
while True:
|
||||||
try:
|
try:
|
||||||
|
from .bridge_all import model_info
|
||||||
|
|
||||||
endpoint = model_info[llm_kwargs["llm_model"]]["endpoint"]
|
endpoint = model_info[llm_kwargs["llm_model"]]["endpoint"]
|
||||||
response = requests.post(
|
if not disable_proxy:
|
||||||
endpoint,
|
response = requests.post(
|
||||||
headers=headers,
|
endpoint,
|
||||||
proxies=None if disable_proxy else proxies,
|
headers=headers,
|
||||||
json=playload,
|
proxies=proxies,
|
||||||
stream=True,
|
json=playload,
|
||||||
timeout=TIMEOUT_SECONDS,
|
stream=True,
|
||||||
)
|
timeout=TIMEOUT_SECONDS,
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
response = requests.post(
|
||||||
|
endpoint,
|
||||||
|
headers=headers,
|
||||||
|
json=playload,
|
||||||
|
stream=True,
|
||||||
|
timeout=TIMEOUT_SECONDS,
|
||||||
|
)
|
||||||
break
|
break
|
||||||
except:
|
except:
|
||||||
retry += 1
|
retry += 1
|
||||||
@@ -194,13 +194,10 @@ def get_predict_function(
|
|||||||
raise TimeoutError
|
raise TimeoutError
|
||||||
if MAX_RETRY != 0:
|
if MAX_RETRY != 0:
|
||||||
logger.error(f"请求超时，正在重试 ({retry}/{MAX_RETRY}) ……")
|
logger.error(f"请求超时，正在重试 ({retry}/{MAX_RETRY}) ……")
|
||||||
|
|
||||||
|
stream_response = response.iter_lines()
|
||||||
result = ""
|
result = ""
|
||||||
finish_reason = ""
|
finish_reason = ""
|
||||||
if reasoning:
|
|
||||||
resoning_buffer = ""
|
|
||||||
|
|
||||||
stream_response = response.iter_lines()
|
|
||||||
while True:
|
while True:
|
||||||
try:
|
try:
|
||||||
chunk = next(stream_response)
|
chunk = next(stream_response)
|
||||||
@@ -210,9 +207,9 @@ def get_predict_function(
|
|||||||
break
|
break
|
||||||
except requests.exceptions.ConnectionError:
|
except requests.exceptions.ConnectionError:
|
||||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||||
response_text, reasoning_content, finish_reason = decode_chunk(chunk)
|
response_text, finish_reason = decode_chunk(chunk)
|
||||||
# 返回的数据流第一次为空，继续等待
|
# 返回的数据流第一次为空，继续等待
|
||||||
if response_text == "" and (reasoning == False or reasoning_content == "") and finish_reason != "False":
|
if response_text == "" and finish_reason != "False":
|
||||||
continue
|
continue
|
||||||
if response_text == "API_ERROR" and (
|
if response_text == "API_ERROR" and (
|
||||||
finish_reason != "False" or finish_reason != "stop"
|
finish_reason != "False" or finish_reason != "stop"
|
||||||
@@ -230,8 +227,6 @@ def get_predict_function(
|
|||||||
print(f"[response] {result}")
|
print(f"[response] {result}")
|
||||||
break
|
break
|
||||||
result += response_text
|
result += response_text
|
||||||
if reasoning:
|
|
||||||
resoning_buffer += reasoning_content
|
|
||||||
if observe_window is not None:
|
if observe_window is not None:
|
||||||
# 观测窗，把已经获取的数据显示出去
|
# 观测窗，把已经获取的数据显示出去
|
||||||
if len(observe_window) >= 1:
|
if len(observe_window) >= 1:
|
||||||
@@ -246,10 +241,6 @@ def get_predict_function(
|
|||||||
error_msg = chunk_decoded
|
error_msg = chunk_decoded
|
||||||
logger.error(error_msg)
|
logger.error(error_msg)
|
||||||
raise RuntimeError("Json解析不合常规")
|
raise RuntimeError("Json解析不合常规")
|
||||||
if reasoning:
|
|
||||||
# reasoning 的部分加上框 (>)
|
|
||||||
return '\n'.join(map(lambda x: '> ' + x, resoning_buffer.split('\n'))) + \
|
|
||||||
'\n\n' + result
|
|
||||||
return result
|
return result
|
||||||
|
|
||||||
def predict(
|
def predict(
|
||||||
@@ -271,7 +262,6 @@ def get_predict_function(
|
|||||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||||
"""
|
"""
|
||||||
from .bridge_all import model_info
|
|
||||||
if len(APIKEY) == 0:
|
if len(APIKEY) == 0:
|
||||||
raise RuntimeError(f"APIKEY为空,请检查配置文件的{APIKEY}")
|
raise RuntimeError(f"APIKEY为空,请检查配置文件的{APIKEY}")
|
||||||
if inputs == "":
|
if inputs == "":
|
||||||
@@ -308,23 +298,32 @@ def get_predict_function(
|
|||||||
system_prompt=system_prompt,
|
system_prompt=system_prompt,
|
||||||
temperature=llm_kwargs["temperature"],
|
temperature=llm_kwargs["temperature"],
|
||||||
)
|
)
|
||||||
|
|
||||||
reasoning = model_info[llm_kwargs['llm_model']].get('enable_reasoning', False)
|
|
||||||
|
|
||||||
history.append(inputs)
|
history.append(inputs)
|
||||||
history.append("")
|
history.append("")
|
||||||
retry = 0
|
retry = 0
|
||||||
while True:
|
while True:
|
||||||
try:
|
try:
|
||||||
|
from .bridge_all import model_info
|
||||||
|
|
||||||
endpoint = model_info[llm_kwargs["llm_model"]]["endpoint"]
|
endpoint = model_info[llm_kwargs["llm_model"]]["endpoint"]
|
||||||
response = requests.post(
|
if not disable_proxy:
|
||||||
endpoint,
|
response = requests.post(
|
||||||
headers=headers,
|
endpoint,
|
||||||
proxies=None if disable_proxy else proxies,
|
headers=headers,
|
||||||
json=playload,
|
proxies=proxies,
|
||||||
stream=True,
|
json=playload,
|
||||||
timeout=TIMEOUT_SECONDS,
|
stream=True,
|
||||||
)
|
timeout=TIMEOUT_SECONDS,
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
response = requests.post(
|
||||||
|
endpoint,
|
||||||
|
headers=headers,
|
||||||
|
json=playload,
|
||||||
|
stream=True,
|
||||||
|
timeout=TIMEOUT_SECONDS,
|
||||||
|
)
|
||||||
break
|
break
|
||||||
except:
|
except:
|
||||||
retry += 1
|
retry += 1
|
||||||
@@ -339,8 +338,6 @@ def get_predict_function(
|
|||||||
raise TimeoutError
|
raise TimeoutError
|
||||||
|
|
||||||
gpt_replying_buffer = ""
|
gpt_replying_buffer = ""
|
||||||
if reasoning:
|
|
||||||
gpt_reasoning_buffer = ""
|
|
||||||
|
|
||||||
stream_response = response.iter_lines()
|
stream_response = response.iter_lines()
|
||||||
while True:
|
while True:
|
||||||
@@ -350,9 +347,9 @@ def get_predict_function(
|
|||||||
break
|
break
|
||||||
except requests.exceptions.ConnectionError:
|
except requests.exceptions.ConnectionError:
|
||||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||||
response_text, reasoning_content, finish_reason = decode_chunk(chunk)
|
response_text, finish_reason = decode_chunk(chunk)
|
||||||
# 返回的数据流第一次为空，继续等待
|
# 返回的数据流第一次为空，继续等待
|
||||||
if response_text == "" and (reasoning == False or reasoning_content == "") and finish_reason != "False":
|
if response_text == "" and finish_reason != "False":
|
||||||
status_text = f"finish_reason: {finish_reason}"
|
status_text = f"finish_reason: {finish_reason}"
|
||||||
yield from update_ui(
|
yield from update_ui(
|
||||||
chatbot=chatbot, history=history, msg=status_text
|
chatbot=chatbot, history=history, msg=status_text
|
||||||
@@ -382,14 +379,9 @@ def get_predict_function(
|
|||||||
logger.info(f"[response] {gpt_replying_buffer}")
|
logger.info(f"[response] {gpt_replying_buffer}")
|
||||||
break
|
break
|
||||||
status_text = f"finish_reason: {finish_reason}"
|
status_text = f"finish_reason: {finish_reason}"
|
||||||
if reasoning:
|
gpt_replying_buffer += response_text
|
||||||
gpt_replying_buffer += response_text
|
# 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
|
||||||
gpt_reasoning_buffer += reasoning_content
|
history[-1] = gpt_replying_buffer
|
||||||
history[-1] = '\n'.join(map(lambda x: '> ' + x, gpt_reasoning_buffer.split('\n'))) + '\n\n' + gpt_replying_buffer
|
|
||||||
else:
|
|
||||||
gpt_replying_buffer += response_text
|
|
||||||
# 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
|
|
||||||
history[-1] = gpt_replying_buffer
|
|
||||||
chatbot[-1] = (history[-2], history[-1])
|
chatbot[-1] = (history[-2], history[-1])
|
||||||
yield from update_ui(
|
yield from update_ui(
|
||||||
chatbot=chatbot, history=history, msg=status_text
|
chatbot=chatbot, history=history, msg=status_text
|
||||||
|
|||||||
@@ -1,7 +0,0 @@
|
|||||||
protobuf
|
|
||||||
cpm_kernels
|
|
||||||
torch>=1.10
|
|
||||||
transformers>=4.44
|
|
||||||
mdtex2html
|
|
||||||
sentencepiece
|
|
||||||
accelerate
|
|
||||||
@@ -1,4 +1,4 @@
|
|||||||
https://public.agent-matrix.com/publish/gradio-3.32.12-py3-none-any.whl
|
https://public.agent-matrix.com/publish/gradio-3.32.10-py3-none-any.whl
|
||||||
fastapi==0.110
|
fastapi==0.110
|
||||||
gradio-client==0.8
|
gradio-client==0.8
|
||||||
pypdf2==2.12.1
|
pypdf2==2.12.1
|
||||||
@@ -13,7 +13,7 @@ scipdf_parser>=0.52
|
|||||||
spacy==3.7.4
|
spacy==3.7.4
|
||||||
anthropic>=0.18.1
|
anthropic>=0.18.1
|
||||||
python-markdown-math
|
python-markdown-math
|
||||||
pymdown-extensions>=10.14
|
pymdown-extensions
|
||||||
websocket-client
|
websocket-client
|
||||||
beautifulsoup4
|
beautifulsoup4
|
||||||
prompt_toolkit
|
prompt_toolkit
|
||||||
@@ -25,7 +25,7 @@ pyautogen
|
|||||||
colorama
|
colorama
|
||||||
Markdown
|
Markdown
|
||||||
pygments
|
pygments
|
||||||
edge-tts>=7.0.0
|
edge-tts
|
||||||
pymupdf
|
pymupdf
|
||||||
openai
|
openai
|
||||||
rjsmin
|
rjsmin
|
||||||
|
|||||||
@@ -2,7 +2,6 @@ import markdown
|
|||||||
import re
|
import re
|
||||||
import os
|
import os
|
||||||
import math
|
import math
|
||||||
import html
|
|
||||||
|
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
from textwrap import dedent
|
from textwrap import dedent
|
||||||
@@ -385,24 +384,6 @@ def markdown_convertion(txt):
|
|||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
def code_block_title_replace_format(match):
|
|
||||||
lang = match.group(1)
|
|
||||||
filename = match.group(2)
|
|
||||||
return f"```{lang} {{title=\"{filename}\"}}\n"
|
|
||||||
|
|
||||||
|
|
||||||
def get_last_backticks_indent(text):
|
|
||||||
# 从后向前查找最后一个 ```
|
|
||||||
lines = text.splitlines()
|
|
||||||
for line in reversed(lines):
|
|
||||||
if '```' in line:
|
|
||||||
# 计算前面的空格数量
|
|
||||||
indent = len(line) - len(line.lstrip())
|
|
||||||
return indent
|
|
||||||
return 0 # 如果没找到返回0
|
|
||||||
|
|
||||||
|
|
||||||
@lru_cache(maxsize=16) # 使用lru缓存
|
|
||||||
def close_up_code_segment_during_stream(gpt_reply):
|
def close_up_code_segment_during_stream(gpt_reply):
|
||||||
"""
|
"""
|
||||||
在gpt输出代码的中途（输出了前面的```，但还没输出完后面的```），补上后面的```
|
在gpt输出代码的中途（输出了前面的```，但还没输出完后面的```），补上后面的```
|
||||||
@@ -416,12 +397,6 @@ def close_up_code_segment_during_stream(gpt_reply):
|
|||||||
"""
|
"""
|
||||||
if "```" not in gpt_reply:
|
if "```" not in gpt_reply:
|
||||||
return gpt_reply
|
return gpt_reply
|
||||||
|
|
||||||
# replace [```python:warp.py] to [```python {title="warp.py"}]
|
|
||||||
pattern = re.compile(r"```([a-z]{1,12}):([^:\n]{1,35}\.([a-zA-Z^:\n]{1,3}))\n")
|
|
||||||
if pattern.search(gpt_reply):
|
|
||||||
gpt_reply = pattern.sub(code_block_title_replace_format, gpt_reply)
|
|
||||||
|
|
||||||
if gpt_reply.endswith("```"):
|
if gpt_reply.endswith("```"):
|
||||||
return gpt_reply
|
return gpt_reply
|
||||||
|
|
||||||
@@ -429,11 +404,7 @@ def close_up_code_segment_during_stream(gpt_reply):
|
|||||||
segments = gpt_reply.split("```")
|
segments = gpt_reply.split("```")
|
||||||
n_mark = len(segments) - 1
|
n_mark = len(segments) - 1
|
||||||
if n_mark % 2 == 1:
|
if n_mark % 2 == 1:
|
||||||
try:
|
return gpt_reply + "\n```" # 输出代码片段中！
|
||||||
num_padding = get_last_backticks_indent(gpt_reply)
|
|
||||||
except:
|
|
||||||
num_padding = 0
|
|
||||||
return gpt_reply + "\n" + " "*num_padding + "```" # 输出代码片段中！
|
|
||||||
else:
|
else:
|
||||||
return gpt_reply
|
return gpt_reply
|
||||||
|
|
||||||
@@ -450,19 +421,6 @@ def special_render_issues_for_mermaid(text):
|
|||||||
return text
|
return text
|
||||||
|
|
||||||
|
|
||||||
def contain_html_tag(text):
|
|
||||||
"""
|
|
||||||
判断文本中是否包含HTML标签。
|
|
||||||
"""
|
|
||||||
pattern = r'</?([a-zA-Z0-9_]{3,16})>|<script\s+[^>]*src=["\']([^"\']+)["\'][^>]*>'
|
|
||||||
return re.search(pattern, text) is not None
|
|
||||||
|
|
||||||
|
|
||||||
def contain_image(text):
|
|
||||||
pattern = r'<br/><br/><div align="center"><img src="file=(.*?)" base64="(.*?)"></div>'
|
|
||||||
return re.search(pattern, text) is not None
|
|
||||||
|
|
||||||
|
|
||||||
def compat_non_markdown_input(text):
|
def compat_non_markdown_input(text):
|
||||||
"""
|
"""
|
||||||
改善非markdown输入的显示效果，例如将空格转换为 ，将换行符转换为</br>等。
|
改善非markdown输入的显示效果，例如将空格转换为 ，将换行符转换为</br>等。
|
||||||
@@ -471,13 +429,9 @@ def compat_non_markdown_input(text):
|
|||||||
# careful input：markdown输入
|
# careful input：markdown输入
|
||||||
text = special_render_issues_for_mermaid(text) # 处理特殊的渲染问题
|
text = special_render_issues_for_mermaid(text) # 处理特殊的渲染问题
|
||||||
return text
|
return text
|
||||||
elif ("<" in text) and (">" in text) and contain_html_tag(text):
|
elif "</div>" in text:
|
||||||
# careful input：html输入
|
# careful input：html输入
|
||||||
if contain_image(text):
|
return text
|
||||||
return text
|
|
||||||
else:
|
|
||||||
escaped_text = html.escape(text)
|
|
||||||
return escaped_text
|
|
||||||
else:
|
else:
|
||||||
# whatever input：非markdown输入
|
# whatever input：非markdown输入
|
||||||
lines = text.split("\n")
|
lines = text.split("\n")
|
||||||
|
|||||||
@@ -77,28 +77,16 @@ def make_history_cache():
|
|||||||
# 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
|
# 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
|
||||||
import gradio as gr
|
import gradio as gr
|
||||||
# 定义history的后端state
|
# 定义history的后端state
|
||||||
# history = gr.State([])
|
history = gr.State([])
|
||||||
history = gr.Textbox(visible=False, elem_id="history-ng")
|
# 定义history的一个孪生的前端存储区（隐藏）
|
||||||
# # 定义history的一个孪生的前端存储区（隐藏）
|
history_cache = gr.Textbox(visible=False, elem_id="history_cache")
|
||||||
# history_cache = gr.Textbox(visible=False, elem_id="history_cache")
|
# 定义history_cache->history的更新方法（隐藏）。在触发这个按钮时，会先执行js代码更新history_cache，然后再执行python代码更新history
|
||||||
# # 定义history_cache->history的更新方法（隐藏）。在触发这个按钮时，会先执行js代码更新history_cache，然后再执行python代码更新history
|
def process_history_cache(history_cache):
|
||||||
# def process_history_cache(history_cache):
|
return json.loads(history_cache)
|
||||||
# return json.loads(history_cache)
|
# 另一种更简单的setter方法
|
||||||
# # 另一种更简单的setter方法
|
history_cache_update = gr.Button("", elem_id="elem_update_history", visible=False).click(
|
||||||
# history_cache_update = gr.Button("", elem_id="elem_update_history", visible=False).click(
|
process_history_cache, inputs=[history_cache], outputs=[history])
|
||||||
# process_history_cache, inputs=[history_cache], outputs=[history])
|
return history, history_cache, history_cache_update
|
||||||
# # save history to history_cache
|
|
||||||
# def process_history_cache(history_cache):
|
|
||||||
# return json.dumps(history_cache)
|
|
||||||
# # 定义history->history_cache的更新方法（隐藏）
|
|
||||||
# def sync_history_cache(history):
|
|
||||||
# print("sync_history_cache", history)
|
|
||||||
# return json.dumps(history)
|
|
||||||
# # history.change(sync_history_cache, inputs=[history], outputs=[history_cache])
|
|
||||||
|
|
||||||
# # history_cache_sync = gr.Button("", elem_id="elem_sync_history", visible=False).click(
|
|
||||||
# # lambda history: (json.dumps(history)), inputs=[history_cache], outputs=[history])
|
|
||||||
return history, None, None
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -1,83 +0,0 @@
|
|||||||
import requests
|
|
||||||
import pickle
|
|
||||||
import io
|
|
||||||
import os
|
|
||||||
from pydantic import BaseModel, Field
|
|
||||||
from typing import Optional, Dict, Any
|
|
||||||
from loguru import logger
|
|
||||||
|
|
||||||
class DockerServiceApiComModel(BaseModel):
|
|
||||||
client_command: Optional[str] = Field(default=None, title="Client command", description="The command to be executed on the client side")
|
|
||||||
client_file_attach: Optional[dict] = Field(default=None, title="Client file attach", description="The file to be attached to the client side")
|
|
||||||
server_message: Optional[Any] = Field(default=None, title="Server standard error", description="The standard error from the server side")
|
|
||||||
server_std_err: Optional[str] = Field(default=None, title="Server standard error", description="The standard error from the server side")
|
|
||||||
server_std_out: Optional[str] = Field(default=None, title="Server standard output", description="The standard output from the server side")
|
|
||||||
server_file_attach: Optional[dict] = Field(default=None, title="Server file attach", description="The file to be attached to the server side")
|
|
||||||
|
|
||||||
def process_received(received: DockerServiceApiComModel, save_file_dir="./daas_output", output_manifest=None):
|
|
||||||
# Process the received data
|
|
||||||
if received.server_message:
|
|
||||||
try:
|
|
||||||
output_manifest['server_message'] += received.server_message
|
|
||||||
except:
|
|
||||||
output_manifest['server_message'] = received.server_message
|
|
||||||
if received.server_std_err:
|
|
||||||
output_manifest['server_std_err'] += received.server_std_err
|
|
||||||
if received.server_std_out:
|
|
||||||
output_manifest['server_std_out'] += received.server_std_out
|
|
||||||
if received.server_file_attach:
|
|
||||||
# print(f"Recv file attach: {received.server_file_attach}")
|
|
||||||
for file_name, file_content in received.server_file_attach.items():
|
|
||||||
new_fp = os.path.join(save_file_dir, file_name)
|
|
||||||
new_fp_dir = os.path.dirname(new_fp)
|
|
||||||
if not os.path.exists(new_fp_dir):
|
|
||||||
os.makedirs(new_fp_dir, exist_ok=True)
|
|
||||||
with open(new_fp, 'wb') as f:
|
|
||||||
f.write(file_content)
|
|
||||||
output_manifest['server_file_attach'].append(new_fp)
|
|
||||||
return output_manifest
|
|
||||||
|
|
||||||
def stream_daas(docker_service_api_com_model, server_url, save_file_dir):
|
|
||||||
# Prepare the file
|
|
||||||
# Pickle the object
|
|
||||||
pickled_data = pickle.dumps(docker_service_api_com_model)
|
|
||||||
|
|
||||||
# Create a file-like object from the pickled data
|
|
||||||
file_obj = io.BytesIO(pickled_data)
|
|
||||||
|
|
||||||
# Prepare the file for sending
|
|
||||||
files = {'file': ('docker_service_api_com_model.pkl', file_obj, 'application/octet-stream')}
|
|
||||||
|
|
||||||
# Send the POST request
|
|
||||||
response = requests.post(server_url, files=files, stream=True)
|
|
||||||
|
|
||||||
max_full_package_size = 1024 * 1024 * 1024 * 1 # 1 GB
|
|
||||||
|
|
||||||
received_output_manifest = {}
|
|
||||||
received_output_manifest['server_message'] = ""
|
|
||||||
received_output_manifest['server_std_err'] = ""
|
|
||||||
received_output_manifest['server_std_out'] = ""
|
|
||||||
received_output_manifest['server_file_attach'] = []
|
|
||||||
|
|
||||||
# Check if the request was successful
|
|
||||||
if response.status_code == 200:
|
|
||||||
# Process the streaming response
|
|
||||||
chunk_buf = None
|
|
||||||
for chunk in response.iter_content(max_full_package_size):
|
|
||||||
if chunk:
|
|
||||||
if chunk_buf is None: chunk_buf = chunk
|
|
||||||
else: chunk_buf += chunk
|
|
||||||
|
|
||||||
try:
|
|
||||||
received = pickle.loads(chunk_buf)
|
|
||||||
chunk_buf = None
|
|
||||||
received_output_manifest = process_received(received, save_file_dir, output_manifest = received_output_manifest)
|
|
||||||
yield received_output_manifest
|
|
||||||
except Exception as e:
|
|
||||||
# logger.error(f"pickle data was truncated, but don't worry, we will continue to receive the rest of the data.")
|
|
||||||
continue
|
|
||||||
|
|
||||||
else:
|
|
||||||
logger.error(f"Error: Received status code {response.status_code}, response.text: {response.text}")
|
|
||||||
|
|
||||||
return received_output_manifest
|
|
||||||
@@ -138,9 +138,7 @@ def start_app(app_block, CONCURRENT_COUNT, AUTHENTICATION, PORT, SSL_KEYFILE, SS
|
|||||||
app_block.is_sagemaker = False
|
app_block.is_sagemaker = False
|
||||||
|
|
||||||
gradio_app = App.create_app(app_block)
|
gradio_app = App.create_app(app_block)
|
||||||
for route in list(gradio_app.router.routes):
|
|
||||||
if route.path == "/proxy={url_path:path}":
|
|
||||||
gradio_app.router.routes.remove(route)
|
|
||||||
# --- --- replace gradio endpoint to forbid access to sensitive files --- ---
|
# --- --- replace gradio endpoint to forbid access to sensitive files --- ---
|
||||||
if len(AUTHENTICATION) > 0:
|
if len(AUTHENTICATION) > 0:
|
||||||
dependencies = []
|
dependencies = []
|
||||||
@@ -156,13 +154,9 @@ def start_app(app_block, CONCURRENT_COUNT, AUTHENTICATION, PORT, SSL_KEYFILE, SS
|
|||||||
@gradio_app.head("/file={path_or_url:path}", dependencies=dependencies)
|
@gradio_app.head("/file={path_or_url:path}", dependencies=dependencies)
|
||||||
@gradio_app.get("/file={path_or_url:path}", dependencies=dependencies)
|
@gradio_app.get("/file={path_or_url:path}", dependencies=dependencies)
|
||||||
async def file(path_or_url: str, request: fastapi.Request):
|
async def file(path_or_url: str, request: fastapi.Request):
|
||||||
if not _authorize_user(path_or_url, request, gradio_app):
|
if len(AUTHENTICATION) > 0:
|
||||||
return "越权访问!"
|
if not _authorize_user(path_or_url, request, gradio_app):
|
||||||
stripped = path_or_url.lstrip().lower()
|
return "越权访问!"
|
||||||
if stripped.startswith("https://") or stripped.startswith("http://"):
|
|
||||||
return "账户密码授权模式下, 禁止链接!"
|
|
||||||
if '../' in stripped:
|
|
||||||
return "非法路径!"
|
|
||||||
return await endpoint(path_or_url, request)
|
return await endpoint(path_or_url, request)
|
||||||
|
|
||||||
from fastapi import Request, status
|
from fastapi import Request, status
|
||||||
@@ -173,26 +167,6 @@ def start_app(app_block, CONCURRENT_COUNT, AUTHENTICATION, PORT, SSL_KEYFILE, SS
|
|||||||
response.delete_cookie('access-token')
|
response.delete_cookie('access-token')
|
||||||
response.delete_cookie('access-token-unsecure')
|
response.delete_cookie('access-token-unsecure')
|
||||||
return response
|
return response
|
||||||
else:
|
|
||||||
dependencies = []
|
|
||||||
endpoint = None
|
|
||||||
for route in list(gradio_app.router.routes):
|
|
||||||
if route.path == "/file/{path:path}":
|
|
||||||
gradio_app.router.routes.remove(route)
|
|
||||||
if route.path == "/file={path_or_url:path}":
|
|
||||||
dependencies = route.dependencies
|
|
||||||
endpoint = route.endpoint
|
|
||||||
gradio_app.router.routes.remove(route)
|
|
||||||
@gradio_app.get("/file/{path:path}", dependencies=dependencies)
|
|
||||||
@gradio_app.head("/file={path_or_url:path}", dependencies=dependencies)
|
|
||||||
@gradio_app.get("/file={path_or_url:path}", dependencies=dependencies)
|
|
||||||
async def file(path_or_url: str, request: fastapi.Request):
|
|
||||||
stripped = path_or_url.lstrip().lower()
|
|
||||||
if stripped.startswith("https://") or stripped.startswith("http://"):
|
|
||||||
return "账户密码授权模式下, 禁止链接!"
|
|
||||||
if '../' in stripped:
|
|
||||||
return "非法路径!"
|
|
||||||
return await endpoint(path_or_url, request)
|
|
||||||
|
|
||||||
# --- --- enable TTS (text-to-speech) functionality --- ---
|
# --- --- enable TTS (text-to-speech) functionality --- ---
|
||||||
TTS_TYPE = get_conf("TTS_TYPE")
|
TTS_TYPE = get_conf("TTS_TYPE")
|
||||||
|
|||||||
@@ -104,27 +104,17 @@ def extract_archive(file_path, dest_dir):
|
|||||||
logger.info("Successfully extracted zip archive to {}".format(dest_dir))
|
logger.info("Successfully extracted zip archive to {}".format(dest_dir))
|
||||||
|
|
||||||
elif file_extension in [".tar", ".gz", ".bz2"]:
|
elif file_extension in [".tar", ".gz", ".bz2"]:
|
||||||
try:
|
with tarfile.open(file_path, "r:*") as tarobj:
|
||||||
with tarfile.open(file_path, "r:*") as tarobj:
|
# 清理提取路径，移除任何不安全的元素
|
||||||
# 清理提取路径，移除任何不安全的元素
|
for member in tarobj.getmembers():
|
||||||
for member in tarobj.getmembers():
|
member_path = os.path.normpath(member.name)
|
||||||
member_path = os.path.normpath(member.name)
|
full_path = os.path.join(dest_dir, member_path)
|
||||||
full_path = os.path.join(dest_dir, member_path)
|
full_path = os.path.abspath(full_path)
|
||||||
full_path = os.path.abspath(full_path)
|
if not full_path.startswith(os.path.abspath(dest_dir) + os.sep):
|
||||||
if not full_path.startswith(os.path.abspath(dest_dir) + os.sep):
|
raise Exception(f"Attempted Path Traversal in {member.name}")
|
||||||
raise Exception(f"Attempted Path Traversal in {member.name}")
|
|
||||||
|
|
||||||
tarobj.extractall(path=dest_dir)
|
tarobj.extractall(path=dest_dir)
|
||||||
logger.info("Successfully extracted tar archive to {}".format(dest_dir))
|
logger.info("Successfully extracted tar archive to {}".format(dest_dir))
|
||||||
except tarfile.ReadError as e:
|
|
||||||
if file_extension == ".gz":
|
|
||||||
# 一些特别奇葩的项目，是一个gz文件，里面不是tar，只有一个tex文件
|
|
||||||
import gzip
|
|
||||||
with gzip.open(file_path, 'rb') as f_in:
|
|
||||||
with open(os.path.join(dest_dir, 'main.tex'), 'wb') as f_out:
|
|
||||||
f_out.write(f_in.read())
|
|
||||||
else:
|
|
||||||
raise e
|
|
||||||
|
|
||||||
# 第三方库，需要预先pip install rarfile
|
# 第三方库，需要预先pip install rarfile
|
||||||
# 此外，Windows上还需要安装winrar软件，配置其Path环境变量，如"C:\Program Files\WinRAR"才可以
|
# 此外，Windows上还需要安装winrar软件，配置其Path环境变量，如"C:\Program Files\WinRAR"才可以
|
||||||
|
|||||||
@@ -14,7 +14,6 @@ openai_regex = re.compile(
|
|||||||
r"sk-[a-zA-Z0-9_-]{92}$|" +
|
r"sk-[a-zA-Z0-9_-]{92}$|" +
|
||||||
r"sk-proj-[a-zA-Z0-9_-]{48}$|"+
|
r"sk-proj-[a-zA-Z0-9_-]{48}$|"+
|
||||||
r"sk-proj-[a-zA-Z0-9_-]{124}$|"+
|
r"sk-proj-[a-zA-Z0-9_-]{124}$|"+
|
||||||
r"sk-proj-[a-zA-Z0-9_-]{156}$|"+ #新版apikey位数不匹配故修改此正则表达式
|
|
||||||
r"sess-[a-zA-Z0-9]{40}$"
|
r"sess-[a-zA-Z0-9]{40}$"
|
||||||
)
|
)
|
||||||
def is_openai_api_key(key):
|
def is_openai_api_key(key):
|
||||||
@@ -45,13 +44,6 @@ def is_cohere_api_key(key):
|
|||||||
|
|
||||||
|
|
||||||
def is_any_api_key(key):
|
def is_any_api_key(key):
|
||||||
# key 一般只包含字母、数字、下划线、逗号、中划线
|
|
||||||
if not re.match(r"^[a-zA-Z0-9_\-,]+$", key):
|
|
||||||
# 如果配置了 CUSTOM_API_KEY_PATTERN，再检查以下以免误杀
|
|
||||||
if CUSTOM_API_KEY_PATTERN := get_conf('CUSTOM_API_KEY_PATTERN'):
|
|
||||||
return bool(re.match(CUSTOM_API_KEY_PATTERN, key))
|
|
||||||
return False
|
|
||||||
|
|
||||||
if ',' in key:
|
if ',' in key:
|
||||||
keys = key.split(',')
|
keys = key.split(',')
|
||||||
for k in keys:
|
for k in keys:
|
||||||
@@ -85,8 +77,7 @@ def select_api_key(keys, llm_model):
|
|||||||
avail_key_list = []
|
avail_key_list = []
|
||||||
key_list = keys.split(',')
|
key_list = keys.split(',')
|
||||||
|
|
||||||
if llm_model.startswith('gpt-') or llm_model.startswith('chatgpt-') or \
|
if llm_model.startswith('gpt-') or llm_model.startswith('one-api-') or llm_model.startswith('o1-'):
|
||||||
llm_model.startswith('one-api-') or llm_model == 'o1' or llm_model.startswith('o1-'):
|
|
||||||
for k in key_list:
|
for k in key_list:
|
||||||
if is_openai_api_key(k): avail_key_list.append(k)
|
if is_openai_api_key(k): avail_key_list.append(k)
|
||||||
|
|
||||||
|
|||||||
11
start.sh
11
start.sh
@@ -1,11 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
GPT_COMMAND="/home/van/.env/python3.12-venv/bin/python main.py"
|
|
||||||
LOG_FILE="/home/van/project/gpt/gpt.log"
|
|
||||||
GPT_PROCESS=$(ps aux | grep "$/home/van/.env/python3.12-venv/bin/python main.py" | grep -v grep)
|
|
||||||
if [ -n "$GPT_PROCESS" ]; then
|
|
||||||
echo "gpt is running..."
|
|
||||||
else
|
|
||||||
cd /home/van/project/gpt/
|
|
||||||
$GPT_COMMAND > "$LOG_FILE" 2>&1 &
|
|
||||||
echo "gpt start successfully. Log file: $LOG_FILE"
|
|
||||||
fi
|
|
||||||
@@ -1,15 +0,0 @@
|
|||||||
"""
|
|
||||||
对项目中的各个插件进行测试。运行方法：直接运行 python tests/test_plugins.py
|
|
||||||
"""
|
|
||||||
|
|
||||||
import init_test
|
|
||||||
import os, sys
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
from experimental_mods.get_bilibili_resource import download_bilibili
|
|
||||||
download_bilibili("BV1LSSHYXEtv", only_audio=True, user_name="test")
|
|
||||||
|
|
||||||
# if __name__ == "__main__":
|
|
||||||
# from test_utils import plugin_test
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.VideoResource_GPT->视频任务', main_input="帮我找到《天文馆的猫》，歌手泠鸢")
|
|
||||||
@@ -19,8 +19,4 @@ if __name__ == "__main__":
|
|||||||
plugin_test = importlib.import_module('test_utils').plugin_test
|
plugin_test = importlib.import_module('test_utils').plugin_test
|
||||||
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="2203.01927")
|
plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="2203.01927")
|
||||||
# plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="gpt_log/arxiv_cache/2203.01927/workfolder")
|
|
||||||
# plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="2410.05779")
|
|
||||||
plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="gpt_log/default_user/workfolder")
|
|
||||||
|
|
||||||
|
|||||||
@@ -20,7 +20,7 @@ Replace 'Tex/' with the actual directory path where your files are located befor
|
|||||||
md = """
|
md = """
|
||||||
Following code including wrapper
|
Following code including wrapper
|
||||||
|
|
||||||
```python:wrapper.py
|
```mermaid
|
||||||
graph TD
|
graph TD
|
||||||
A[Enter Chart Definition] --> B(Preview)
|
A[Enter Chart Definition] --> B(Preview)
|
||||||
B --> C{decide}
|
B --> C{decide}
|
||||||
@@ -29,45 +29,8 @@ graph TD
|
|||||||
E --> B
|
E --> B
|
||||||
D --> F[Save Image and Code]
|
D --> F[Save Image and Code]
|
||||||
F --> B
|
F --> B
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
```
|
```
|
||||||
|
|
||||||
<details>
|
|
||||||
<summary><b>My section header in bold</b></summary>
|
|
||||||
|
|
||||||
Any folded content here. It requires an empty line just above it.
|
|
||||||
|
|
||||||
</details>
|
|
||||||
|
|
||||||
"""
|
|
||||||
|
|
||||||
md ="""
|
|
||||||
|
|
||||||
在这种场景中，您希望机器 B 能够通过轮询机制来间接地“请求”机器 A，而实际上机器 A 只能主动向机器 B 发出请求。这是一种典型的客户端-服务器轮询模式。下面是如何实现这种机制的详细步骤：
|
|
||||||
|
|
||||||
### 机器 B 的实现
|
|
||||||
|
|
||||||
1. **安装 FastAPI 和必要的依赖库**：
|
|
||||||
```bash
|
|
||||||
pip install fastapi uvicorn
|
|
||||||
```
|
|
||||||
|
|
||||||
2. **创建 FastAPI 服务**：
|
|
||||||
```python
|
|
||||||
from fastapi import FastAPI
|
|
||||||
from fastapi.responses import JSONResponse
|
|
||||||
from uuid import uuid4
|
|
||||||
from threading import Lock
|
|
||||||
import time
|
|
||||||
|
|
||||||
app = FastAPI()
|
|
||||||
|
|
||||||
# 字典用于存储请求和状态
|
|
||||||
requests = {}
|
|
||||||
process_lock = Lock()
|
|
||||||
|
|
||||||
"""
|
"""
|
||||||
def validate_path():
|
def validate_path():
|
||||||
import os, sys
|
import os, sys
|
||||||
@@ -80,12 +43,10 @@ def validate_path():
|
|||||||
|
|
||||||
validate_path() # validate path so you can run from base directory
|
validate_path() # validate path so you can run from base directory
|
||||||
from toolbox import markdown_convertion
|
from toolbox import markdown_convertion
|
||||||
# from shared_utils.advanced_markdown_format import markdown_convertion_for_file
|
from shared_utils.advanced_markdown_format import markdown_convertion_for_file
|
||||||
from shared_utils.advanced_markdown_format import close_up_code_segment_during_stream
|
with open("gpt_log/default_user/shared/2024-04-22-01-27-43.zip.extract/translated_markdown.md", "r", encoding="utf-8") as f:
|
||||||
# with open("gpt_log/default_user/shared/2024-04-22-01-27-43.zip.extract/translated_markdown.md", "r", encoding="utf-8") as f:
|
md = f.read()
|
||||||
# md = f.read()
|
html = markdown_convertion_for_file(md)
|
||||||
md = close_up_code_segment_during_stream(md)
|
|
||||||
html = markdown_convertion(md)
|
|
||||||
# print(html)
|
# print(html)
|
||||||
with open("test.html", "w", encoding="utf-8") as f:
|
with open("test.html", "w", encoding="utf-8") as f:
|
||||||
f.write(html)
|
f.write(html)
|
||||||
|
|||||||
@@ -1,67 +0,0 @@
|
|||||||
"""
|
|
||||||
对项目中的各个插件进行测试。运行方法：直接运行 python tests/test_plugins.py
|
|
||||||
"""
|
|
||||||
|
|
||||||
import init_test
|
|
||||||
import os, sys
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
from test_utils import plugin_test
|
|
||||||
|
|
||||||
plugin_test(plugin='crazy_functions.VideoResource_GPT->多媒体任务', main_input="我想找一首歌，里面有句歌词是“turn your face towards the sun”")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.Internet_GPT->连接网络回答问题', main_input="谁是应急食品？")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.函数动态生成->函数动态生成', main_input='交换图像的蓝色通道和红色通道', advanced_arg={"file_path_arg": "./build/ants.jpg"})
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="2307.07522")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.PDF_Translate->批量翻译PDF文档', main_input='build/pdf/t1.pdf')
|
|
||||||
|
|
||||||
# plugin_test(
|
|
||||||
# plugin="crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF",
|
|
||||||
# main_input="G:/SEAFILE_LOCAL/50503047/我的资料库/学位/paperlatex/aaai/Fu_8368_with_appendix",
|
|
||||||
# )
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.虚空终端->虚空终端', main_input='修改api-key为sk-jhoejriotherjep')
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.批量翻译PDF文档_NOUGAT->批量翻译PDF文档', main_input='crazy_functions/test_project/pdf_and_word/aaai.pdf')
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.虚空终端->虚空终端', main_input='调用插件，对C:/Users/fuqingxu/Desktop/旧文件/gpt/chatgpt_academic/crazy_functions/latex_fns中的python文件进行解析')
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.命令行助手->命令行助手', main_input='查看当前的docker容器列表')
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.SourceCode_Analyse->解析一个Python项目', main_input="crazy_functions/test_project/python/dqn")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.SourceCode_Analyse->解析一个C项目', main_input="crazy_functions/test_project/cpp/cppipc")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.Latex_Project_Polish->Latex英文润色', main_input="crazy_functions/test_project/latex/attention")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.Markdown_Translate->Markdown中译英', main_input="README.md")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.PDF_Translate->批量翻译PDF文档', main_input='crazy_functions/test_project/pdf_and_word/aaai.pdf')
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.谷歌检索小助手->谷歌检索小助手', main_input="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=auto+reinforcement+learning&btnG=")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.总结word文档->总结word文档', main_input="crazy_functions/test_project/pdf_and_word")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.下载arxiv论文翻译摘要->下载arxiv论文并翻译摘要', main_input="1812.10695")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.联网的ChatGPT->连接网络回答问题', main_input="谁是应急食品？")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.解析JupyterNotebook->解析ipynb文件', main_input="crazy_functions/test_samples")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.数学动画生成manim->动画生成', main_input="A ball split into 2, and then split into 4, and finally split into 8.")
|
|
||||||
|
|
||||||
# for lang in ["English", "French", "Japanese", "Korean", "Russian", "Italian", "German", "Portuguese", "Arabic"]:
|
|
||||||
# plugin_test(plugin='crazy_functions.Markdown_Translate->Markdown翻译指定语言', main_input="README.md", advanced_arg={"advanced_arg": lang})
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.知识库文件注入->知识库文件注入', main_input="./")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.知识库文件注入->读取知识库作答', main_input="What is the installation method？")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.知识库文件注入->读取知识库作答', main_input="远程云服务器部署？")
|
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="2210.03629")
|
|
||||||
|
|
||||||
@@ -36,7 +36,7 @@ if __name__ == "__main__":
|
|||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.SourceCode_Analyse->解析一个C项目', main_input="crazy_functions/test_project/cpp/cppipc")
|
# plugin_test(plugin='crazy_functions.SourceCode_Analyse->解析一个C项目', main_input="crazy_functions/test_project/cpp/cppipc")
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.Latex_Project_Polish->Latex英文润色', main_input="crazy_functions/test_project/latex/attention")
|
# plugin_test(plugin='crazy_functions.Latex全文润色->Latex英文润色', main_input="crazy_functions/test_project/latex/attention")
|
||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.Markdown_Translate->Markdown中译英', main_input="README.md")
|
# plugin_test(plugin='crazy_functions.Markdown_Translate->Markdown中译英', main_input="README.md")
|
||||||
|
|
||||||
@@ -65,3 +65,8 @@ if __name__ == "__main__":
|
|||||||
|
|
||||||
# plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="2210.03629")
|
# plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="2210.03629")
|
||||||
|
|
||||||
|
# advanced_arg = {"advanced_arg":"--llm_to_learn=gpt-3.5-turbo --prompt_prefix='根据下面的服装类型提示，想象一个穿着者，对这个人外貌、身处的环境、内心世界、人设进行描写。要求：100字以内，用第二人称。' --system_prompt=''" }
|
||||||
|
# plugin_test(plugin='crazy_functions.chatglm微调工具->微调数据集生成', main_input='build/dev.json', advanced_arg=advanced_arg)
|
||||||
|
|
||||||
|
# advanced_arg = {"advanced_arg":"--pre_seq_len=128 --learning_rate=2e-2 --num_gpus=1 --json_dataset='t_code.json' --ptuning_directory='/home/hmp/ChatGLM2-6B/ptuning' " }
|
||||||
|
# plugin_test(plugin='crazy_functions.chatglm微调工具->启动微调', main_input='build/dev.json', advanced_arg=advanced_arg)
|
||||||
|
|||||||
@@ -1,33 +0,0 @@
|
|||||||
import edge_tts
|
|
||||||
import os
|
|
||||||
import httpx
|
|
||||||
from toolbox import get_conf
|
|
||||||
|
|
||||||
|
|
||||||
async def test_tts():
|
|
||||||
async with httpx.AsyncClient() as client:
|
|
||||||
try:
|
|
||||||
# Forward the request to the target service
|
|
||||||
import tempfile
|
|
||||||
import edge_tts
|
|
||||||
import wave
|
|
||||||
import uuid
|
|
||||||
from pydub import AudioSegment
|
|
||||||
voice = get_conf("EDGE_TTS_VOICE")
|
|
||||||
tts = edge_tts.Communicate(text="测试", voice=voice)
|
|
||||||
temp_folder = tempfile.gettempdir()
|
|
||||||
temp_file_name = str(uuid.uuid4().hex)
|
|
||||||
temp_file = os.path.join(temp_folder, f'{temp_file_name}.mp3')
|
|
||||||
await tts.save(temp_file)
|
|
||||||
try:
|
|
||||||
mp3_audio = AudioSegment.from_file(temp_file, format="mp3")
|
|
||||||
mp3_audio.export(temp_file, format="wav")
|
|
||||||
with open(temp_file, 'rb') as wav_file: t = wav_file.read()
|
|
||||||
except:
|
|
||||||
raise RuntimeError("ffmpeg未安装，无法处理EdgeTTS音频。安装方法见`https://github.com/jiaaro/pydub#getting-ffmpeg-set-up`")
|
|
||||||
except httpx.RequestError as e:
|
|
||||||
raise RuntimeError(f"请求失败: {e}")
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
import asyncio
|
|
||||||
asyncio.run(test_tts())
|
|
||||||
@@ -1,16 +1,9 @@
|
|||||||
:root {
|
|
||||||
--gpt-academic-message-font-size: 15px;
|
|
||||||
}
|
|
||||||
|
|
||||||
.message {
|
|
||||||
font-size: var(--gpt-academic-message-font-size) !important;
|
|
||||||
}
|
|
||||||
|
|
||||||
#plugin_arg_menu {
|
#plugin_arg_menu {
|
||||||
transform: translate(-50%, -50%);
|
transform: translate(-50%, -50%);
|
||||||
border: dashed;
|
border: dashed;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
/* hide remove all button */
|
/* hide remove all button */
|
||||||
.remove-all.svelte-aqlk7e.svelte-aqlk7e.svelte-aqlk7e {
|
.remove-all.svelte-aqlk7e.svelte-aqlk7e.svelte-aqlk7e {
|
||||||
visibility: hidden;
|
visibility: hidden;
|
||||||
@@ -32,6 +25,7 @@
|
|||||||
visibility: hidden;
|
visibility: hidden;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
/* height of the upload box */
|
/* height of the upload box */
|
||||||
.wrap.svelte-xwlu1w {
|
.wrap.svelte-xwlu1w {
|
||||||
min-height: var(--size-32);
|
min-height: var(--size-32);
|
||||||
@@ -103,9 +97,13 @@
|
|||||||
min-width: min(80px, 100%);
|
min-width: min(80px, 100%);
|
||||||
}
|
}
|
||||||
|
|
||||||
#cbs,
|
|
||||||
|
#cbs {
|
||||||
|
background-color: var(--block-background-fill) !important;
|
||||||
|
}
|
||||||
|
|
||||||
#cbsc {
|
#cbsc {
|
||||||
background-color: rgba(var(--block-background-fill), 0.5) !important;
|
background-color: var(--block-background-fill) !important;
|
||||||
}
|
}
|
||||||
|
|
||||||
#interact-panel .form {
|
#interact-panel .form {
|
||||||
@@ -157,7 +155,7 @@
|
|||||||
transform: translate(-50%, -50%);
|
transform: translate(-50%, -50%);
|
||||||
flex-wrap: wrap;
|
flex-wrap: wrap;
|
||||||
justify-content: center;
|
justify-content: center;
|
||||||
transition: opacity 0.6s ease-in-out;
|
transition: opacity 1s ease-in-out;
|
||||||
opacity: 0;
|
opacity: 0;
|
||||||
}
|
}
|
||||||
.welcome-card-container.show {
|
.welcome-card-container.show {
|
||||||
@@ -209,7 +207,6 @@
|
|||||||
.welcome-content {
|
.welcome-content {
|
||||||
text-wrap: balance;
|
text-wrap: balance;
|
||||||
height: 55px;
|
height: 55px;
|
||||||
font-size: 13px;
|
|
||||||
display: flex;
|
display: flex;
|
||||||
align-items: center;
|
align-items: center;
|
||||||
}
|
}
|
||||||
@@ -273,41 +270,4 @@
|
|||||||
}
|
}
|
||||||
#gpt-submit-row #gpt-submit-dropdown > *:hover {
|
#gpt-submit-row #gpt-submit-dropdown > *:hover {
|
||||||
cursor: context-menu;
|
cursor: context-menu;
|
||||||
}
|
}
|
||||||
|
|
||||||
.tooltip.svelte-p2nen8.svelte-p2nen8 {
|
|
||||||
box-shadow: 10px 10px 15px rgba(0, 0, 0, 0.5);
|
|
||||||
left: 10px;
|
|
||||||
}
|
|
||||||
|
|
||||||
#tooltip .hidden {
|
|
||||||
/* display: none; */
|
|
||||||
opacity: 0;
|
|
||||||
transition: opacity 0.5s ease;
|
|
||||||
}
|
|
||||||
|
|
||||||
#tooltip .visible {
|
|
||||||
/* display: block; */
|
|
||||||
opacity: 1;
|
|
||||||
transition: opacity 0.5s ease;
|
|
||||||
}
|
|
||||||
|
|
||||||
#elem_fontsize,
|
|
||||||
#elem_top_p,
|
|
||||||
#elem_temperature,
|
|
||||||
#elem_max_length_sl,
|
|
||||||
#elem_prompt {
|
|
||||||
/* 左右为0；顶部为0，底部为2px */
|
|
||||||
padding: 0 0 4px 0;
|
|
||||||
backdrop-filter: blur(10px);
|
|
||||||
background-color: rgba(var(--block-background-fill), 0.5);
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
#tooltip #cbs,
|
|
||||||
#tooltip #cbsc,
|
|
||||||
#tooltip .svelte-b6y5bg,
|
|
||||||
#tooltip .tabitem {
|
|
||||||
backdrop-filter: blur(10px);
|
|
||||||
background-color: rgba(var(--block-background-fill), 0.5);
|
|
||||||
}
|
|
||||||
378
themes/common.js
378
themes/common.js
@@ -318,7 +318,7 @@ function addCopyButton(botElement, index, is_last_in_arr) {
|
|||||||
}
|
}
|
||||||
});
|
});
|
||||||
|
|
||||||
if (enable_tts) {
|
if (enable_tts){
|
||||||
var audioButton = document.createElement('button');
|
var audioButton = document.createElement('button');
|
||||||
audioButton.classList.add('audio-toggle-btn');
|
audioButton.classList.add('audio-toggle-btn');
|
||||||
audioButton.innerHTML = audioIcon;
|
audioButton.innerHTML = audioIcon;
|
||||||
@@ -346,7 +346,7 @@ function addCopyButton(botElement, index, is_last_in_arr) {
|
|||||||
var messageBtnColumn = document.createElement('div');
|
var messageBtnColumn = document.createElement('div');
|
||||||
messageBtnColumn.classList.add('message-btn-row');
|
messageBtnColumn.classList.add('message-btn-row');
|
||||||
messageBtnColumn.appendChild(copyButton);
|
messageBtnColumn.appendChild(copyButton);
|
||||||
if (enable_tts) {
|
if (enable_tts){
|
||||||
messageBtnColumn.appendChild(audioButton);
|
messageBtnColumn.appendChild(audioButton);
|
||||||
}
|
}
|
||||||
botElement.appendChild(messageBtnColumn);
|
botElement.appendChild(messageBtnColumn);
|
||||||
@@ -391,9 +391,6 @@ function chatbotContentChanged(attempt = 1, force = false) {
|
|||||||
|
|
||||||
// Now pass both the message element and the is_last_in_arr boolean to addCopyButton
|
// Now pass both the message element and the is_last_in_arr boolean to addCopyButton
|
||||||
addCopyButton(message, index, is_last_in_arr);
|
addCopyButton(message, index, is_last_in_arr);
|
||||||
|
|
||||||
// save_conversation_history
|
|
||||||
save_conversation_history_slow_down();
|
|
||||||
});
|
});
|
||||||
// gradioApp().querySelectorAll('#gpt-chatbot .message-wrap .message.bot').forEach(addCopyButton);
|
// gradioApp().querySelectorAll('#gpt-chatbot .message-wrap .message.bot').forEach(addCopyButton);
|
||||||
}, i === 0 ? 0 : 200);
|
}, i === 0 ? 0 : 200);
|
||||||
@@ -750,24 +747,10 @@ function minor_ui_adjustment() {
|
|||||||
var bar_btn_width = [];
|
var bar_btn_width = [];
|
||||||
// 自动隐藏超出范围的toolbar按钮
|
// 自动隐藏超出范围的toolbar按钮
|
||||||
function auto_hide_toolbar() {
|
function auto_hide_toolbar() {
|
||||||
// if chatbot hit upper page boarder, hide all
|
var qq = document.getElementById('tooltip');
|
||||||
const elem_chatbot = document.getElementById('gpt-chatbot');
|
var tab_nav = qq.getElementsByClassName('tab-nav');
|
||||||
const chatbot_top = elem_chatbot.getBoundingClientRect().top;
|
|
||||||
var tooltip = document.getElementById('tooltip');
|
|
||||||
var tab_nav = tooltip.getElementsByClassName('tab-nav')[0];
|
|
||||||
|
|
||||||
// 20 px 大概是一个字的高度
|
|
||||||
if (chatbot_top < 20) {
|
|
||||||
// tab_nav.style.display = 'none';
|
|
||||||
if (tab_nav.classList.contains('visible')) {tab_nav.classList.remove('visible');}
|
|
||||||
if (!tab_nav.classList.contains('hidden')) {tab_nav.classList.add('hidden');}
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
if (tab_nav.classList.contains('hidden')) {tab_nav.classList.remove('hidden');}
|
|
||||||
if (!tab_nav.classList.contains('visible')) {tab_nav.classList.add('visible');}
|
|
||||||
// tab_nav.style.display = '';
|
|
||||||
if (tab_nav.length == 0) { return; }
|
if (tab_nav.length == 0) { return; }
|
||||||
var btn_list = tab_nav.getElementsByTagName('button')
|
var btn_list = tab_nav[0].getElementsByTagName('button')
|
||||||
if (btn_list.length == 0) { return; }
|
if (btn_list.length == 0) { return; }
|
||||||
// 获取页面宽度
|
// 获取页面宽度
|
||||||
var page_width = document.documentElement.clientWidth;
|
var page_width = document.documentElement.clientWidth;
|
||||||
@@ -871,7 +854,8 @@ function limit_scroll_position() {
|
|||||||
// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||||
|
|
||||||
function loadLive2D() {
|
function loadLive2D() {
|
||||||
if (document.querySelector(".waifu")) {
|
if (document.querySelector(".waifu") )
|
||||||
|
{
|
||||||
$('.waifu').show();
|
$('.waifu').show();
|
||||||
} else {
|
} else {
|
||||||
try {
|
try {
|
||||||
@@ -938,12 +922,12 @@ function gpt_academic_gradio_saveload(
|
|||||||
if (save_or_load === "load") {
|
if (save_or_load === "load") {
|
||||||
let value = getCookie(cookie_key);
|
let value = getCookie(cookie_key);
|
||||||
if (value) {
|
if (value) {
|
||||||
// console.log('加载cookie', elem_id, value)
|
console.log('加载cookie', elem_id, value)
|
||||||
push_data_to_gradio_component(value, elem_id, load_type);
|
push_data_to_gradio_component(value, elem_id, load_type);
|
||||||
}
|
}
|
||||||
else {
|
else {
|
||||||
if (load_default) {
|
if (load_default) {
|
||||||
// console.log('加载cookie的默认值', elem_id, load_default_value)
|
console.log('加载cookie的默认值', elem_id, load_default_value)
|
||||||
push_data_to_gradio_component(load_default_value, elem_id, load_type);
|
push_data_to_gradio_component(load_default_value, elem_id, load_type);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -953,153 +937,113 @@ function gpt_academic_gradio_saveload(
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
function generateUUID() {
|
|
||||||
// Generate a random number and convert it to a hexadecimal string
|
|
||||||
function randomHexDigit() {
|
|
||||||
return Math.floor((1 + Math.random()) * 0x10000).toString(16).slice(1);
|
|
||||||
}
|
|
||||||
|
|
||||||
// Construct the UUID using the randomHexDigit function
|
|
||||||
return (
|
|
||||||
randomHexDigit() + randomHexDigit() + '-' +
|
|
||||||
randomHexDigit() + '-' +
|
|
||||||
'4' + randomHexDigit().slice(0, 3) + '-' + // Version 4 UUID
|
|
||||||
((Math.floor(Math.random() * 4) + 8).toString(16)) + randomHexDigit().slice(0, 3) + '-' +
|
|
||||||
randomHexDigit() + randomHexDigit() + randomHexDigit()
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
function update_conversation_metadata() {
|
|
||||||
// Create a conversation UUID and timestamp
|
|
||||||
try {
|
|
||||||
const conversationId = generateUUID();
|
|
||||||
console.log('Create conversation ID:', conversationId);
|
|
||||||
const timestamp = new Date().toISOString();
|
|
||||||
const conversationMetaData = {
|
|
||||||
id: conversationId,
|
|
||||||
timestamp: timestamp
|
|
||||||
};
|
|
||||||
localStorage.setItem("conversation_metadata", JSON.stringify(conversationMetaData));
|
|
||||||
} catch (e) {
|
|
||||||
console.error('Error in updating conversation metadata:', e);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
// Helper function to generate conversation preview
|
|
||||||
function generatePreview(conversation, timestamp, maxLength = 100) {
|
|
||||||
if (!conversation || conversation.length === 0) return "";
|
|
||||||
// Join all messages with dash separator
|
|
||||||
let preview = conversation.join("\n");
|
|
||||||
const readableDate = new Date(timestamp).toLocaleString();
|
|
||||||
preview = readableDate + "\n" + preview;
|
|
||||||
if (preview.length <= maxLength) return preview;
|
|
||||||
return preview.substring(0, maxLength) + "...";
|
|
||||||
}
|
|
||||||
|
|
||||||
async function save_conversation_history() {
|
|
||||||
|
|
||||||
let chatbot = await get_data_from_gradio_component('gpt-chatbot');
|
|
||||||
let history = await get_data_from_gradio_component('history-ng');
|
|
||||||
let conversation = {};
|
|
||||||
let conversation_metadata = localStorage.getItem("conversation_metadata");
|
|
||||||
try {
|
|
||||||
conversation_metadata = JSON.parse(conversation_metadata);
|
|
||||||
conversation = {
|
|
||||||
timestamp: conversation_metadata.timestamp,
|
|
||||||
id: conversation_metadata.id,
|
|
||||||
metadata: conversation_metadata,
|
|
||||||
conversation: chatbot,
|
|
||||||
history: history,
|
|
||||||
preview: generatePreview(JSON.parse(history), conversation_metadata.timestamp)
|
|
||||||
};
|
|
||||||
} catch (e) {
|
|
||||||
// console.error('Conversation metadata parse error, recreate conversation metadata');
|
|
||||||
update_conversation_metadata();
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
||||||
// Get existing conversation history from local storage
|
|
||||||
let conversation_history = [];
|
|
||||||
try {
|
|
||||||
const stored = localStorage.getItem('conversation_history');
|
|
||||||
if (stored) {
|
|
||||||
conversation_history = JSON.parse(stored);
|
|
||||||
}
|
|
||||||
} catch (e) {
|
|
||||||
// console.error('Error reading conversation history from localStorage:', e);
|
|
||||||
}
|
|
||||||
|
|
||||||
// Find existing conversation with same ID
|
|
||||||
const existingIndex = conversation_history.findIndex(c => c.id === conversation.id);
|
|
||||||
|
|
||||||
if (existingIndex >= 0) {
|
|
||||||
// Update existing conversation
|
|
||||||
conversation_history[existingIndex] = conversation;
|
|
||||||
} else {
|
|
||||||
// Add new conversation
|
|
||||||
conversation_history.push(conversation);
|
|
||||||
}
|
|
||||||
|
|
||||||
// Sort conversations by timestamp, newest first
|
|
||||||
conversation_history.sort((a, b) => {
|
|
||||||
const timeA = new Date(a.timestamp).getTime();
|
|
||||||
const timeB = new Date(b.timestamp).getTime();
|
|
||||||
return timeB - timeA;
|
|
||||||
});
|
|
||||||
|
|
||||||
const max_chat_preserve = 10;
|
|
||||||
|
|
||||||
if (conversation_history.length >= max_chat_preserve + 1) {
|
|
||||||
toast_push('对话时间线记录已满，正在移除最早的对话记录。您也可以点击左侧的记录点进行手动清理。', 3000);
|
|
||||||
conversation_history = conversation_history.slice(0, max_chat_preserve);
|
|
||||||
}
|
|
||||||
|
|
||||||
// Save back to local storage
|
|
||||||
try {
|
|
||||||
localStorage.setItem('conversation_history', JSON.stringify(conversation_history));
|
|
||||||
const LOCAL_STORAGE_UPDATED = "gptac_conversation_history_updated";
|
|
||||||
window.dispatchEvent(
|
|
||||||
new CustomEvent(LOCAL_STORAGE_UPDATED, {
|
|
||||||
detail: conversation_history
|
|
||||||
})
|
|
||||||
);
|
|
||||||
} catch (e) {
|
|
||||||
console.error('Error saving conversation history to localStorage:', e);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
save_conversation_history_slow_down = do_something_but_not_too_frequently(300, save_conversation_history);
|
|
||||||
|
|
||||||
function restore_chat_from_local_storage(event) {
|
|
||||||
let conversation = event.detail;
|
|
||||||
push_data_to_gradio_component(conversation.conversation, "gpt-chatbot", "obj");
|
|
||||||
push_data_to_gradio_component(conversation.history, "history-ng", "obj");
|
|
||||||
const conversationId = conversation.id;
|
|
||||||
const timestamp = conversation.timestamp;
|
|
||||||
const conversationData = {
|
|
||||||
id: conversationId,
|
|
||||||
timestamp: timestamp
|
|
||||||
};
|
|
||||||
localStorage.setItem("conversation_metadata", JSON.stringify(conversationData));
|
|
||||||
}
|
|
||||||
|
|
||||||
async function clear_conversation(a, b, c) {
|
|
||||||
await save_conversation_history();
|
|
||||||
update_conversation_metadata();
|
|
||||||
let stopButton = document.getElementById("elem_stop");
|
|
||||||
stopButton.click();
|
|
||||||
return reset_conversation(a, b);
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
function reset_conversation(a, b) {
|
function reset_conversation(a, b) {
|
||||||
|
// console.log("js_code_reset");
|
||||||
|
a = btoa(unescape(encodeURIComponent(JSON.stringify(a))));
|
||||||
|
setCookie("js_previous_chat_cookie", a, 1);
|
||||||
|
gen_restore_btn();
|
||||||
return [[], [], "已重置"];
|
return [[], [], "已重置"];
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// clear -> 将 history 缓存至 history_cache -> 点击复原 -> restore_previous_chat() -> 触发elem_update_history -> 读取 history_cache
|
||||||
|
function restore_previous_chat() {
|
||||||
|
console.log("restore_previous_chat");
|
||||||
|
let chat = getCookie("js_previous_chat_cookie");
|
||||||
|
chat = JSON.parse(decodeURIComponent(escape(atob(chat))));
|
||||||
|
push_data_to_gradio_component(chat, "gpt-chatbot", "obj");
|
||||||
|
document.querySelector("#elem_update_history").click(); // in order to call set_history_gr_state, and send history state to server
|
||||||
|
}
|
||||||
|
|
||||||
|
function gen_restore_btn() {
|
||||||
|
|
||||||
|
|
||||||
|
// 创建按钮元素
|
||||||
|
const button = document.createElement('div');
|
||||||
|
// const recvIcon = '<span><svg stroke="currentColor" fill="none" stroke-width="2" viewBox="0 0 24 24" stroke-linecap="round" stroke-linejoin="round" height=".8em" width=".8em" xmlns="http://www.w3.org/2000/svg"><polyline points="20 6 9 17 4 12"></polyline></svg></span>';
|
||||||
|
const rec_svg = '<svg t="1714361184567" style="transform:translate(1px, 2.5px)" class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="4389" width="35" height="35"><path d="M320 512h384v64H320zM320 384h384v64H320zM320 640h192v64H320z" p-id="4390" fill="#ffffff"></path><path d="M863.7 544c-1.9 44-11.4 86.8-28.5 127.2-18.5 43.8-45.1 83.2-78.9 117-33.8 33.8-73.2 60.4-117 78.9C593.9 886.3 545.7 896 496 896s-97.9-9.7-143.2-28.9c-43.8-18.5-83.2-45.1-117-78.9-33.8-33.8-60.4-73.2-78.9-117C137.7 625.9 128 577.7 128 528s9.7-97.9 28.9-143.2c18.5-43.8 45.1-83.2 78.9-117s73.2-60.4 117-78.9C398.1 169.7 446.3 160 496 160s97.9 9.7 143.2 28.9c23.5 9.9 45.8 22.2 66.5 36.7l-119.7 20 9.9 59.4 161.6-27 59.4-9.9-9.9-59.4-27-161.5-59.4 9.9 19 114.2C670.3 123.8 586.4 96 496 96 257.4 96 64 289.4 64 528s193.4 432 432 432c233.2 0 423.3-184.8 431.7-416h-64z" p-id="4391" fill="#ffffff"></path></svg>'
|
||||||
|
const recvIcon = '<span>' + rec_svg + '</span>';
|
||||||
|
|
||||||
|
// 设置按钮的样式和属性
|
||||||
|
button.id = 'floatingButton';
|
||||||
|
button.className = 'glow';
|
||||||
|
button.style.textAlign = 'center';
|
||||||
|
button.style.position = 'fixed';
|
||||||
|
button.style.bottom = '10px';
|
||||||
|
button.style.left = '10px';
|
||||||
|
button.style.width = '50px';
|
||||||
|
button.style.height = '50px';
|
||||||
|
button.style.borderRadius = '50%';
|
||||||
|
button.style.backgroundColor = '#007bff';
|
||||||
|
button.style.color = 'white';
|
||||||
|
button.style.display = 'flex';
|
||||||
|
button.style.alignItems = 'center';
|
||||||
|
button.style.justifyContent = 'center';
|
||||||
|
button.style.cursor = 'pointer';
|
||||||
|
button.style.transition = 'all 0.3s ease';
|
||||||
|
button.style.boxShadow = '0 0 10px rgba(0,0,0,0.2)';
|
||||||
|
|
||||||
|
button.innerHTML = recvIcon;
|
||||||
|
|
||||||
|
// 添加发光动画的关键帧
|
||||||
|
const styleSheet = document.createElement('style');
|
||||||
|
styleSheet.id = 'floatingButtonStyle';
|
||||||
|
styleSheet.innerText = `
|
||||||
|
@keyframes glow {
|
||||||
|
from {
|
||||||
|
box-shadow: 0 0 10px rgba(0,0,0,0.2);
|
||||||
|
}
|
||||||
|
to {
|
||||||
|
box-shadow: 0 0 13px rgba(0,0,0,0.5);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
#floatingButton.glow {
|
||||||
|
animation: glow 1s infinite alternate;
|
||||||
|
}
|
||||||
|
#floatingButton:hover {
|
||||||
|
transform: scale(1.2);
|
||||||
|
box-shadow: 0 0 20px rgba(0,0,0,0.4);
|
||||||
|
}
|
||||||
|
#floatingButton.disappearing {
|
||||||
|
animation: shrinkAndDisappear 0.5s forwards;
|
||||||
|
}
|
||||||
|
`;
|
||||||
|
|
||||||
|
// only add when not exist
|
||||||
|
if (!document.getElementById('recvButtonStyle'))
|
||||||
|
{
|
||||||
|
document.head.appendChild(styleSheet);
|
||||||
|
}
|
||||||
|
|
||||||
|
// 鼠标悬停和移开的事件监听器
|
||||||
|
button.addEventListener('mouseover', function () {
|
||||||
|
this.textContent = "还原\n对话";
|
||||||
|
});
|
||||||
|
|
||||||
|
button.addEventListener('mouseout', function () {
|
||||||
|
this.innerHTML = recvIcon;
|
||||||
|
});
|
||||||
|
|
||||||
|
// 点击事件监听器
|
||||||
|
button.addEventListener('click', function () {
|
||||||
|
// 添加一个类来触发缩小和消失的动画
|
||||||
|
restore_previous_chat();
|
||||||
|
this.classList.add('disappearing');
|
||||||
|
// 在动画结束后移除按钮
|
||||||
|
document.body.removeChild(this);
|
||||||
|
});
|
||||||
|
// only add when not exist
|
||||||
|
if (!document.getElementById('recvButton'))
|
||||||
|
{
|
||||||
|
document.body.appendChild(button);
|
||||||
|
}
|
||||||
|
|
||||||
|
// 将按钮添加到页面中
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
async function on_plugin_exe_complete(fn_name) {
|
async function on_plugin_exe_complete(fn_name) {
|
||||||
// console.log(fn_name);
|
console.log(fn_name);
|
||||||
if (fn_name === "保存当前的对话") {
|
if (fn_name === "保存当前的对话") {
|
||||||
// get chat profile path
|
// get chat profile path
|
||||||
let chatbot = await get_data_from_gradio_component('gpt-chatbot');
|
let chatbot = await get_data_from_gradio_component('gpt-chatbot');
|
||||||
@@ -1118,15 +1062,15 @@ async function on_plugin_exe_complete(fn_name) {
|
|||||||
}
|
}
|
||||||
let href = get_href(may_have_chat_profile_info);
|
let href = get_href(may_have_chat_profile_info);
|
||||||
if (href) {
|
if (href) {
|
||||||
const cleanedHref = href.replace('file=', ''); // gpt_log/default_user/chat_history/GPT-Academic对话存档2024-04-12-00-35-06.html
|
const cleanedHref = href.replace('file=', ''); // /home/fuqingxu/chatgpt_academic/gpt_log/default_user/chat_history/GPT-Academic对话存档2024-04-12-00-35-06.html
|
||||||
// console.log(cleanedHref);
|
console.log(cleanedHref);
|
||||||
}
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
async function generate_menu(guiBase64String, btnName) {
|
async function generate_menu(guiBase64String, btnName){
|
||||||
// assign the button and menu data
|
// assign the button and menu data
|
||||||
push_data_to_gradio_component(guiBase64String, "invisible_current_pop_up_plugin_arg", "string");
|
push_data_to_gradio_component(guiBase64String, "invisible_current_pop_up_plugin_arg", "string");
|
||||||
push_data_to_gradio_component(btnName, "invisible_callback_btn_for_plugin_exe", "string");
|
push_data_to_gradio_component(btnName, "invisible_callback_btn_for_plugin_exe", "string");
|
||||||
@@ -1160,22 +1104,22 @@ async function generate_menu(guiBase64String, btnName) {
|
|||||||
///////////////////////////////////////////////////////////////////////////////////////////
|
///////////////////////////////////////////////////////////////////////////////////////////
|
||||||
//////////////////////////////////// Textbox ////////////////////////////////////
|
//////////////////////////////////// Textbox ////////////////////////////////////
|
||||||
///////////////////////////////////////////////////////////////////////////////////////////
|
///////////////////////////////////////////////////////////////////////////////////////////
|
||||||
if (gui_args[key].type == 'string') { // PLUGIN_ARG_MENU
|
if (gui_args[key].type=='string'){ // PLUGIN_ARG_MENU
|
||||||
const component_name = "plugin_arg_txt_" + text_cnt;
|
const component_name = "plugin_arg_txt_" + text_cnt;
|
||||||
push_data_to_gradio_component({
|
push_data_to_gradio_component({
|
||||||
visible: true,
|
visible: true,
|
||||||
label: gui_args[key].title + "(" + gui_args[key].description + ")",
|
label: gui_args[key].title + "(" + gui_args[key].description + ")",
|
||||||
// label: gui_args[key].title,
|
// label: gui_args[key].title,
|
||||||
placeholder: gui_args[key].description,
|
placeholder: gui_args[key].description,
|
||||||
__type__: 'update'
|
__type__: 'update'
|
||||||
}, component_name, "obj");
|
}, component_name, "obj");
|
||||||
if (key === "main_input") {
|
if (key === "main_input"){
|
||||||
// 为了与旧插件兼容，生成菜单时，自动加载输入栏的值
|
// 为了与旧插件兼容，生成菜单时，自动加载输入栏的值
|
||||||
let current_main_input = await get_data_from_gradio_component('user_input_main');
|
let current_main_input = await get_data_from_gradio_component('user_input_main');
|
||||||
let current_main_input_2 = await get_data_from_gradio_component('user_input_float');
|
let current_main_input_2 = await get_data_from_gradio_component('user_input_float');
|
||||||
push_data_to_gradio_component(current_main_input + current_main_input_2, component_name, "obj");
|
push_data_to_gradio_component(current_main_input + current_main_input_2, component_name, "obj");
|
||||||
}
|
}
|
||||||
else if (key === "advanced_arg") {
|
else if (key === "advanced_arg"){
|
||||||
// 为了与旧插件兼容，生成菜单时，自动加载旧高级参数输入区的值
|
// 为了与旧插件兼容，生成菜单时，自动加载旧高级参数输入区的值
|
||||||
let advance_arg_input_legacy = await get_data_from_gradio_component('advance_arg_input_legacy');
|
let advance_arg_input_legacy = await get_data_from_gradio_component('advance_arg_input_legacy');
|
||||||
push_data_to_gradio_component(advance_arg_input_legacy, component_name, "obj");
|
push_data_to_gradio_component(advance_arg_input_legacy, component_name, "obj");
|
||||||
@@ -1190,12 +1134,12 @@ async function generate_menu(guiBase64String, btnName) {
|
|||||||
///////////////////////////////////////////////////////////////////////////////////////////
|
///////////////////////////////////////////////////////////////////////////////////////////
|
||||||
//////////////////////////////////// Dropdown ////////////////////////////////////
|
//////////////////////////////////// Dropdown ////////////////////////////////////
|
||||||
///////////////////////////////////////////////////////////////////////////////////////////
|
///////////////////////////////////////////////////////////////////////////////////////////
|
||||||
if (gui_args[key].type == 'dropdown') { // PLUGIN_ARG_MENU
|
if (gui_args[key].type=='dropdown'){ // PLUGIN_ARG_MENU
|
||||||
const component_name = "plugin_arg_drop_" + dropdown_cnt;
|
const component_name = "plugin_arg_drop_" + dropdown_cnt;
|
||||||
push_data_to_gradio_component({
|
push_data_to_gradio_component({
|
||||||
visible: true,
|
visible: true,
|
||||||
choices: gui_args[key].options,
|
choices: gui_args[key].options,
|
||||||
label: gui_args[key].title + "(" + gui_args[key].description + ")",
|
label: gui_args[key].title + "(" + gui_args[key].description + ")",
|
||||||
// label: gui_args[key].title,
|
// label: gui_args[key].title,
|
||||||
placeholder: gui_args[key].description,
|
placeholder: gui_args[key].description,
|
||||||
__type__: 'update'
|
__type__: 'update'
|
||||||
@@ -1210,7 +1154,7 @@ async function generate_menu(guiBase64String, btnName) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
async function execute_current_pop_up_plugin() {
|
async function execute_current_pop_up_plugin(){
|
||||||
let guiBase64String = await get_data_from_gradio_component('invisible_current_pop_up_plugin_arg');
|
let guiBase64String = await get_data_from_gradio_component('invisible_current_pop_up_plugin_arg');
|
||||||
const stringData = atob(guiBase64String);
|
const stringData = atob(guiBase64String);
|
||||||
let guiJsonData = JSON.parse(stringData);
|
let guiJsonData = JSON.parse(stringData);
|
||||||
@@ -1226,8 +1170,8 @@ async function execute_current_pop_up_plugin() {
|
|||||||
let text_cnt = 0;
|
let text_cnt = 0;
|
||||||
for (const key in gui_args) {
|
for (const key in gui_args) {
|
||||||
if (gui_args.hasOwnProperty(key)) {
|
if (gui_args.hasOwnProperty(key)) {
|
||||||
if (gui_args[key].type == 'string') { // PLUGIN_ARG_MENU
|
if (gui_args[key].type=='string'){ // PLUGIN_ARG_MENU
|
||||||
corrisponding_elem_id = "plugin_arg_txt_" + text_cnt
|
corrisponding_elem_id = "plugin_arg_txt_"+text_cnt
|
||||||
gui_args[key].user_confirmed_value = await get_data_from_gradio_component(corrisponding_elem_id);
|
gui_args[key].user_confirmed_value = await get_data_from_gradio_component(corrisponding_elem_id);
|
||||||
text_cnt += 1;
|
text_cnt += 1;
|
||||||
}
|
}
|
||||||
@@ -1236,8 +1180,8 @@ async function execute_current_pop_up_plugin() {
|
|||||||
let dropdown_cnt = 0;
|
let dropdown_cnt = 0;
|
||||||
for (const key in gui_args) {
|
for (const key in gui_args) {
|
||||||
if (gui_args.hasOwnProperty(key)) {
|
if (gui_args.hasOwnProperty(key)) {
|
||||||
if (gui_args[key].type == 'dropdown') { // PLUGIN_ARG_MENU
|
if (gui_args[key].type=='dropdown'){ // PLUGIN_ARG_MENU
|
||||||
corrisponding_elem_id = "plugin_arg_drop_" + dropdown_cnt
|
corrisponding_elem_id = "plugin_arg_drop_"+dropdown_cnt
|
||||||
gui_args[key].user_confirmed_value = await get_data_from_gradio_component(corrisponding_elem_id);
|
gui_args[key].user_confirmed_value = await get_data_from_gradio_component(corrisponding_elem_id);
|
||||||
dropdown_cnt += 1;
|
dropdown_cnt += 1;
|
||||||
}
|
}
|
||||||
@@ -1256,29 +1200,29 @@ async function execute_current_pop_up_plugin() {
|
|||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
function hide_all_elem() {
|
function hide_all_elem(){
|
||||||
// PLUGIN_ARG_MENU
|
// PLUGIN_ARG_MENU
|
||||||
for (text_cnt = 0; text_cnt < 8; text_cnt++) {
|
for (text_cnt = 0; text_cnt < 8; text_cnt++){
|
||||||
push_data_to_gradio_component({
|
push_data_to_gradio_component({
|
||||||
visible: false,
|
visible: false,
|
||||||
label: "",
|
label: "",
|
||||||
__type__: 'update'
|
__type__: 'update'
|
||||||
}, "plugin_arg_txt_" + text_cnt, "obj");
|
}, "plugin_arg_txt_"+text_cnt, "obj");
|
||||||
document.getElementById("plugin_arg_txt_" + text_cnt).parentNode.parentNode.style.display = 'none';
|
document.getElementById("plugin_arg_txt_"+text_cnt).parentNode.parentNode.style.display = 'none';
|
||||||
}
|
}
|
||||||
for (dropdown_cnt = 0; dropdown_cnt < 8; dropdown_cnt++) {
|
for (dropdown_cnt = 0; dropdown_cnt < 8; dropdown_cnt++){
|
||||||
push_data_to_gradio_component({
|
push_data_to_gradio_component({
|
||||||
visible: false,
|
visible: false,
|
||||||
choices: [],
|
choices: [],
|
||||||
label: "",
|
label: "",
|
||||||
__type__: 'update'
|
__type__: 'update'
|
||||||
}, "plugin_arg_drop_" + dropdown_cnt, "obj");
|
}, "plugin_arg_drop_"+dropdown_cnt, "obj");
|
||||||
document.getElementById("plugin_arg_drop_" + dropdown_cnt).parentNode.style.display = 'none';
|
document.getElementById("plugin_arg_drop_"+dropdown_cnt).parentNode.style.display = 'none';
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
function close_current_pop_up_plugin() {
|
function close_current_pop_up_plugin(){
|
||||||
// PLUGIN_ARG_MENU
|
// PLUGIN_ARG_MENU
|
||||||
push_data_to_gradio_component({
|
push_data_to_gradio_component({
|
||||||
visible: false,
|
visible: false,
|
||||||
__type__: 'update'
|
__type__: 'update'
|
||||||
@@ -1289,13 +1233,15 @@ function close_current_pop_up_plugin() {
|
|||||||
|
|
||||||
// 生成高级插件的选择菜单
|
// 生成高级插件的选择菜单
|
||||||
plugin_init_info_lib = {}
|
plugin_init_info_lib = {}
|
||||||
function register_plugin_init(key, base64String) {
|
function register_plugin_init(key, base64String){
|
||||||
// console.log('x')
|
// console.log('x')
|
||||||
const stringData = atob(base64String);
|
const stringData = atob(base64String);
|
||||||
let guiJsonData = JSON.parse(stringData);
|
let guiJsonData = JSON.parse(stringData);
|
||||||
if (key in plugin_init_info_lib) {
|
if (key in plugin_init_info_lib)
|
||||||
|
{
|
||||||
}
|
}
|
||||||
else {
|
else
|
||||||
|
{
|
||||||
plugin_init_info_lib[key] = {};
|
plugin_init_info_lib[key] = {};
|
||||||
}
|
}
|
||||||
plugin_init_info_lib[key].info = guiJsonData.Info;
|
plugin_init_info_lib[key].info = guiJsonData.Info;
|
||||||
@@ -1305,26 +1251,28 @@ function register_plugin_init(key, base64String) {
|
|||||||
plugin_init_info_lib[key].enable_advanced_arg = guiJsonData.AdvancedArgs;
|
plugin_init_info_lib[key].enable_advanced_arg = guiJsonData.AdvancedArgs;
|
||||||
plugin_init_info_lib[key].arg_reminder = guiJsonData.ArgsReminder;
|
plugin_init_info_lib[key].arg_reminder = guiJsonData.ArgsReminder;
|
||||||
}
|
}
|
||||||
function register_advanced_plugin_init_code(key, code) {
|
function register_advanced_plugin_init_code(key, code){
|
||||||
if (key in plugin_init_info_lib) {
|
if (key in plugin_init_info_lib)
|
||||||
|
{
|
||||||
}
|
}
|
||||||
else {
|
else
|
||||||
|
{
|
||||||
plugin_init_info_lib[key] = {};
|
plugin_init_info_lib[key] = {};
|
||||||
}
|
}
|
||||||
plugin_init_info_lib[key].secondary_menu_code = code;
|
plugin_init_info_lib[key].secondary_menu_code = code;
|
||||||
}
|
}
|
||||||
function run_advanced_plugin_launch_code(key) {
|
function run_advanced_plugin_launch_code(key){
|
||||||
// convert js code string to function
|
// convert js code string to function
|
||||||
generate_menu(plugin_init_info_lib[key].secondary_menu_code, key);
|
generate_menu(plugin_init_info_lib[key].secondary_menu_code, key);
|
||||||
}
|
}
|
||||||
function on_flex_button_click(key) {
|
function on_flex_button_click(key){
|
||||||
if (plugin_init_info_lib.hasOwnProperty(key) && plugin_init_info_lib[key].hasOwnProperty('secondary_menu_code')) {
|
if (plugin_init_info_lib.hasOwnProperty(key) && plugin_init_info_lib[key].hasOwnProperty('secondary_menu_code')){
|
||||||
run_advanced_plugin_launch_code(key);
|
run_advanced_plugin_launch_code(key);
|
||||||
} else {
|
}else{
|
||||||
document.getElementById("old_callback_btn_for_plugin_exe").click();
|
document.getElementById("old_callback_btn_for_plugin_exe").click();
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
async function run_dropdown_shift(dropdown) {
|
async function run_dropdown_shift(dropdown){
|
||||||
let key = dropdown;
|
let key = dropdown;
|
||||||
push_data_to_gradio_component({
|
push_data_to_gradio_component({
|
||||||
value: key,
|
value: key,
|
||||||
@@ -1333,7 +1281,7 @@ async function run_dropdown_shift(dropdown) {
|
|||||||
__type__: 'update'
|
__type__: 'update'
|
||||||
}, "elem_switchy_bt", "obj");
|
}, "elem_switchy_bt", "obj");
|
||||||
|
|
||||||
if (plugin_init_info_lib[key].enable_advanced_arg) {
|
if (plugin_init_info_lib[key].enable_advanced_arg){
|
||||||
push_data_to_gradio_component({
|
push_data_to_gradio_component({
|
||||||
visible: true,
|
visible: true,
|
||||||
label: plugin_init_info_lib[key].label,
|
label: plugin_init_info_lib[key].label,
|
||||||
@@ -1355,9 +1303,9 @@ async function duplicate_in_new_window() {
|
|||||||
window.open(url, '_blank');
|
window.open(url, '_blank');
|
||||||
}
|
}
|
||||||
|
|
||||||
async function run_classic_plugin_via_id(plugin_elem_id) {
|
async function run_classic_plugin_via_id(plugin_elem_id){
|
||||||
for (key in plugin_init_info_lib) {
|
for (key in plugin_init_info_lib){
|
||||||
if (plugin_init_info_lib[key].elem_id == plugin_elem_id) {
|
if (plugin_init_info_lib[key].elem_id == plugin_elem_id){
|
||||||
// 获取按钮名称
|
// 获取按钮名称
|
||||||
let current_btn_name = await get_data_from_gradio_component(plugin_elem_id);
|
let current_btn_name = await get_data_from_gradio_component(plugin_elem_id);
|
||||||
// 执行
|
// 执行
|
||||||
@@ -1378,7 +1326,7 @@ async function call_plugin_via_name(current_btn_name) {
|
|||||||
hide_all_elem();
|
hide_all_elem();
|
||||||
// 为了与旧插件兼容，生成菜单时，自动加载旧高级参数输入区的值
|
// 为了与旧插件兼容，生成菜单时，自动加载旧高级参数输入区的值
|
||||||
let advance_arg_input_legacy = await get_data_from_gradio_component('advance_arg_input_legacy');
|
let advance_arg_input_legacy = await get_data_from_gradio_component('advance_arg_input_legacy');
|
||||||
if (advance_arg_input_legacy.length != 0) {
|
if (advance_arg_input_legacy.length != 0){
|
||||||
gui_args["advanced_arg"] = {};
|
gui_args["advanced_arg"] = {};
|
||||||
gui_args["advanced_arg"].user_confirmed_value = advance_arg_input_legacy;
|
gui_args["advanced_arg"].user_confirmed_value = advance_arg_input_legacy;
|
||||||
}
|
}
|
||||||
@@ -1401,11 +1349,18 @@ async function multiplex_function_begin(multiplex_sel) {
|
|||||||
click_real_submit_btn();
|
click_real_submit_btn();
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
|
if (multiplex_sel === "多模型对话") {
|
||||||
// do not delete `REPLACE_EXTENDED_MULTIPLEX_FUNCTIONS_HERE`! It will be read and replaced by Python code.
|
let _align_name_in_crazy_function_py = "询问多个GPT模型";
|
||||||
// REPLACE_EXTENDED_MULTIPLEX_FUNCTIONS_HERE
|
call_plugin_via_name(_align_name_in_crazy_function_py);
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
if (multiplex_sel === "智能召回 RAG") {
|
||||||
|
let _align_name_in_crazy_function_py = "Rag智能召回";
|
||||||
|
call_plugin_via_name(_align_name_in_crazy_function_py);
|
||||||
|
return;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
async function run_multiplex_shift(multiplex_sel) {
|
async function run_multiplex_shift(multiplex_sel){
|
||||||
let key = multiplex_sel;
|
let key = multiplex_sel;
|
||||||
if (multiplex_sel === "常规对话") {
|
if (multiplex_sel === "常规对话") {
|
||||||
key = "提交";
|
key = "提交";
|
||||||
@@ -1417,8 +1372,3 @@ async function run_multiplex_shift(multiplex_sel) {
|
|||||||
__type__: 'update'
|
__type__: 'update'
|
||||||
}, "elem_submit_visible", "obj");
|
}, "elem_submit_visible", "obj");
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
async function persistent_cookie_init(web_cookie_cache, cookie) {
|
|
||||||
return [localStorage.getItem('web_cookie_cache'), cookie];
|
|
||||||
}
|
|
||||||
@@ -2,25 +2,6 @@ from functools import lru_cache
|
|||||||
from toolbox import get_conf
|
from toolbox import get_conf
|
||||||
CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf("CODE_HIGHLIGHT", "ADD_WAIFU", "LAYOUT")
|
CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf("CODE_HIGHLIGHT", "ADD_WAIFU", "LAYOUT")
|
||||||
|
|
||||||
def inject_mutex_button_code(js_content):
|
|
||||||
from crazy_functional import get_multiplex_button_functions
|
|
||||||
fns = get_multiplex_button_functions()
|
|
||||||
|
|
||||||
template = """
|
|
||||||
if (multiplex_sel === "{x}") {
|
|
||||||
let _align_name_in_crazy_function_py = "{y}";
|
|
||||||
call_plugin_via_name(_align_name_in_crazy_function_py);
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
"""
|
|
||||||
|
|
||||||
replacement = ""
|
|
||||||
for fn in fns.keys():
|
|
||||||
if fn == "常规对话": continue
|
|
||||||
replacement += template.replace("{x}", fn).replace("{y}", fns[fn])
|
|
||||||
js_content = js_content.replace("// REPLACE_EXTENDED_MULTIPLEX_FUNCTIONS_HERE", replacement)
|
|
||||||
return js_content
|
|
||||||
|
|
||||||
def minimize_js(common_js_path):
|
def minimize_js(common_js_path):
|
||||||
try:
|
try:
|
||||||
import rjsmin, hashlib, glob, os
|
import rjsmin, hashlib, glob, os
|
||||||
@@ -29,16 +10,14 @@ def minimize_js(common_js_path):
|
|||||||
os.remove(old_min_js)
|
os.remove(old_min_js)
|
||||||
# use rjsmin to minimize `common_js_path`
|
# use rjsmin to minimize `common_js_path`
|
||||||
c_jsmin = rjsmin.jsmin
|
c_jsmin = rjsmin.jsmin
|
||||||
with open(common_js_path, "r", encoding='utf-8') as f:
|
with open(common_js_path, "r") as f:
|
||||||
js_content = f.read()
|
js_content = f.read()
|
||||||
if common_js_path == "themes/common.js":
|
|
||||||
js_content = inject_mutex_button_code(js_content)
|
|
||||||
minimized_js_content = c_jsmin(js_content)
|
minimized_js_content = c_jsmin(js_content)
|
||||||
# compute sha256 hash of minimized js content
|
# compute sha256 hash of minimized js content
|
||||||
sha_hash = hashlib.sha256(minimized_js_content.encode()).hexdigest()[:8]
|
sha_hash = hashlib.sha256(minimized_js_content.encode()).hexdigest()[:8]
|
||||||
minimized_js_path = common_js_path + '.min.' + sha_hash + '.js'
|
minimized_js_path = common_js_path + '.min.' + sha_hash + '.js'
|
||||||
# save to minimized js file
|
# save to minimized js file
|
||||||
with open(minimized_js_path, "w", encoding='utf-8') as f:
|
with open(minimized_js_path, "w") as f:
|
||||||
f.write(minimized_js_content)
|
f.write(minimized_js_content)
|
||||||
# return minimized js file path
|
# return minimized js file path
|
||||||
return minimized_js_path
|
return minimized_js_path
|
||||||
|
|||||||
1180
themes/green.css
1180
themes/green.css
File diff suppressed because it is too large
Load Diff
@@ -10,14 +10,6 @@ theme_dir = os.path.dirname(__file__)
|
|||||||
def adjust_theme():
|
def adjust_theme():
|
||||||
try:
|
try:
|
||||||
set_theme = gr.themes.Soft(
|
set_theme = gr.themes.Soft(
|
||||||
font=[
|
|
||||||
"Helvetica",
|
|
||||||
"Microsoft YaHei",
|
|
||||||
"ui-sans-serif",
|
|
||||||
"sans-serif",
|
|
||||||
"system-ui",
|
|
||||||
],
|
|
||||||
font_mono=["ui-monospace", "Consolas", "monospace"],
|
|
||||||
primary_hue=gr.themes.Color(
|
primary_hue=gr.themes.Color(
|
||||||
c50="#EBFAF2",
|
c50="#EBFAF2",
|
||||||
c100="#CFF3E1",
|
c100="#CFF3E1",
|
||||||
|
|||||||
@@ -1,7 +1,7 @@
|
|||||||
import gradio as gr
|
import gradio as gr
|
||||||
|
|
||||||
def define_gui_floating_menu(customize_btns, functional, predefined_btns, cookies, web_cookie_cache):
|
def define_gui_floating_menu(customize_btns, functional, predefined_btns, cookies, web_cookie_cache):
|
||||||
with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top", elem_id="f_area_input_secondary") as area_input_secondary:
|
with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_input_secondary:
|
||||||
with gr.Accordion("浮动输入区", open=True, elem_id="input-panel2"):
|
with gr.Accordion("浮动输入区", open=True, elem_id="input-panel2"):
|
||||||
with gr.Row() as row:
|
with gr.Row() as row:
|
||||||
row.style(equal_height=True)
|
row.style(equal_height=True)
|
||||||
@@ -17,7 +17,7 @@ def define_gui_floating_menu(customize_btns, functional, predefined_btns, cookie
|
|||||||
clearBtn2 = gr.Button("清除", elem_id="elem_clear2", variant="secondary", visible=False); clearBtn2.style(size="sm")
|
clearBtn2 = gr.Button("清除", elem_id="elem_clear2", variant="secondary", visible=False); clearBtn2.style(size="sm")
|
||||||
|
|
||||||
|
|
||||||
with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top", elem_id="f_area_customize") as area_customize:
|
with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_customize:
|
||||||
with gr.Accordion("自定义菜单", open=True, elem_id="edit-panel"):
|
with gr.Accordion("自定义菜单", open=True, elem_id="edit-panel"):
|
||||||
with gr.Row() as row:
|
with gr.Row() as row:
|
||||||
with gr.Column(scale=10):
|
with gr.Column(scale=10):
|
||||||
@@ -35,9 +35,9 @@ def define_gui_floating_menu(customize_btns, functional, predefined_btns, cookie
|
|||||||
# update btn
|
# update btn
|
||||||
h = basic_fn_confirm.click(assign_btn, [web_cookie_cache, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
|
h = basic_fn_confirm.click(assign_btn, [web_cookie_cache, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
|
||||||
[web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()])
|
[web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()])
|
||||||
h.then(None, [web_cookie_cache], None, _js="""(web_cookie_cache)=>{localStorage.setItem("web_cookie_cache", web_cookie_cache);}""")
|
h.then(None, [web_cookie_cache], None, _js="""(web_cookie_cache)=>{setCookie("web_cookie_cache", web_cookie_cache, 365);}""")
|
||||||
# clean up btn
|
# clean up btn
|
||||||
h2 = basic_fn_clean.click(assign_btn, [web_cookie_cache, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix, gr.State(True)],
|
h2 = basic_fn_clean.click(assign_btn, [web_cookie_cache, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix, gr.State(True)],
|
||||||
[web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()])
|
[web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()])
|
||||||
h2.then(None, [web_cookie_cache], None, _js="""(web_cookie_cache)=>{localStorage.setItem("web_cookie_cache", web_cookie_cache);}""")
|
h2.then(None, [web_cookie_cache], None, _js="""(web_cookie_cache)=>{setCookie("web_cookie_cache", web_cookie_cache, 365);}""")
|
||||||
return area_input_secondary, txt2, area_customize, submitBtn2, resetBtn2, clearBtn2, stopBtn2
|
return area_input_secondary, txt2, area_customize, submitBtn2, resetBtn2, clearBtn2, stopBtn2
|
||||||
@@ -1,7 +1,6 @@
|
|||||||
import gradio as gr
|
import gradio as gr
|
||||||
from toolbox import get_conf
|
|
||||||
|
|
||||||
def define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAIL_THEMES, AVAIL_FONTS, ADD_WAIFU, help_menu_description, js_code_for_toggle_darkmode):
|
def define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAIL_THEMES, ADD_WAIFU, help_menu_description, js_code_for_toggle_darkmode):
|
||||||
with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden", elem_id="tooltip"):
|
with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden", elem_id="tooltip"):
|
||||||
with gr.Row():
|
with gr.Row():
|
||||||
with gr.Tab("上传文件", elem_id="interact-panel"):
|
with gr.Tab("上传文件", elem_id="interact-panel"):
|
||||||
@@ -10,12 +9,12 @@ def define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAI
|
|||||||
|
|
||||||
with gr.Tab("更换模型", elem_id="interact-panel"):
|
with gr.Tab("更换模型", elem_id="interact-panel"):
|
||||||
md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, elem_id="elem_model_sel", label="更换LLM模型/请求源").style(container=False)
|
md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, elem_id="elem_model_sel", label="更换LLM模型/请求源").style(container=False)
|
||||||
top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)", elem_id="elem_top_p")
|
top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
|
||||||
temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature", elem_id="elem_temperature")
|
temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature", elem_id="elem_temperature")
|
||||||
max_length_sl = gr.Slider(minimum=256, maximum=1024*32, value=4096, step=128, interactive=True, label="Local LLM MaxLength", elem_id="elem_max_length_sl")
|
max_length_sl = gr.Slider(minimum=256, maximum=1024*32, value=4096, step=128, interactive=True, label="Local LLM MaxLength",)
|
||||||
system_prompt = gr.Textbox(show_label=True, lines=2, placeholder=f"System Prompt", label="System prompt", value=INIT_SYS_PROMPT, elem_id="elem_prompt")
|
system_prompt = gr.Textbox(show_label=True, lines=2, placeholder=f"System Prompt", label="System prompt", value=INIT_SYS_PROMPT, elem_id="elem_prompt")
|
||||||
temperature.change(None, inputs=[temperature], outputs=None,
|
temperature.change(None, inputs=[temperature], outputs=None,
|
||||||
_js="""(temperature)=>gpt_academic_gradio_saveload("save", "elem_temperature", "js_temperature_cookie", temperature)""")
|
_js="""(temperature)=>gpt_academic_gradio_saveload("save", "elem_prompt", "js_temperature_cookie", temperature)""")
|
||||||
system_prompt.change(None, inputs=[system_prompt], outputs=None,
|
system_prompt.change(None, inputs=[system_prompt], outputs=None,
|
||||||
_js="""(system_prompt)=>gpt_academic_gradio_saveload("save", "elem_prompt", "js_system_prompt_cookie", system_prompt)""")
|
_js="""(system_prompt)=>gpt_academic_gradio_saveload("save", "elem_prompt", "js_system_prompt_cookie", system_prompt)""")
|
||||||
md_dropdown.change(None, inputs=[md_dropdown], outputs=None,
|
md_dropdown.change(None, inputs=[md_dropdown], outputs=None,
|
||||||
@@ -23,8 +22,6 @@ def define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAI
|
|||||||
|
|
||||||
with gr.Tab("界面外观", elem_id="interact-panel"):
|
with gr.Tab("界面外观", elem_id="interact-panel"):
|
||||||
theme_dropdown = gr.Dropdown(AVAIL_THEMES, value=THEME, label="更换UI主题").style(container=False)
|
theme_dropdown = gr.Dropdown(AVAIL_THEMES, value=THEME, label="更换UI主题").style(container=False)
|
||||||
fontfamily_dropdown = gr.Dropdown(AVAIL_FONTS, value=get_conf("FONT"), elem_id="elem_fontfamily", label="更换字体类型").style(container=False)
|
|
||||||
fontsize_slider = gr.Slider(minimum=5, maximum=25, value=15, step=1, interactive=True, label="字体大小(默认15)", elem_id="elem_fontsize")
|
|
||||||
checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "浮动输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区", elem_id='cbs').style(container=False)
|
checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "浮动输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区", elem_id='cbs').style(container=False)
|
||||||
opt = ["自定义菜单"]
|
opt = ["自定义菜单"]
|
||||||
value=[]
|
value=[]
|
||||||
@@ -34,10 +31,7 @@ def define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAI
|
|||||||
dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode)
|
dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode)
|
||||||
open_new_tab = gr.Button("打开新对话", variant="secondary").style(size="sm")
|
open_new_tab = gr.Button("打开新对话", variant="secondary").style(size="sm")
|
||||||
open_new_tab.click(None, None, None, _js=f"""()=>duplicate_in_new_window()""")
|
open_new_tab.click(None, None, None, _js=f"""()=>duplicate_in_new_window()""")
|
||||||
fontfamily_dropdown.select(None, inputs=[fontfamily_dropdown], outputs=None,
|
|
||||||
_js="""(fontfamily)=>{gpt_academic_gradio_saveload("save", "elem_fontfamily", "js_fontfamily", fontfamily); gpt_academic_change_chatbot_font(fontfamily, null, null);}""")
|
|
||||||
fontsize_slider.change(None, inputs=[fontsize_slider], outputs=None,
|
|
||||||
_js="""(fontsize)=>{gpt_academic_gradio_saveload("save", "elem_fontsize", "js_fontsize", fontsize); gpt_academic_change_chatbot_font(null, fontsize, null);}""")
|
|
||||||
|
|
||||||
with gr.Tab("帮助", elem_id="interact-panel"):
|
with gr.Tab("帮助", elem_id="interact-panel"):
|
||||||
gr.Markdown(help_menu_description)
|
gr.Markdown(help_menu_description)
|
||||||
|
|||||||
147
themes/init.js
147
themes/init.js
@@ -1,142 +1,9 @@
|
|||||||
function remove_legacy_cookie() {
|
|
||||||
setCookie("web_cookie_cache", "", -1);
|
|
||||||
setCookie("js_previous_chat_cookie", "", -1);
|
|
||||||
setCookie("js_previous_history_cookie", "", -1);
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
function processFontFamily(fontfamily) {
|
|
||||||
// 检查是否包含括号
|
|
||||||
if (fontfamily.includes('(')) {
|
|
||||||
// 分割字符串
|
|
||||||
const parts = fontfamily.split('(');
|
|
||||||
const fontNamePart = parts[1].split(')')[0].trim(); // 获取括号内的部分
|
|
||||||
|
|
||||||
// 检查是否包含 @
|
|
||||||
if (fontNamePart.includes('@')) {
|
|
||||||
const [fontName, fontUrl] = fontNamePart.split('@').map(part => part.trim());
|
|
||||||
return { fontName, fontUrl };
|
|
||||||
} else {
|
|
||||||
return { fontName: fontNamePart, fontUrl: null };
|
|
||||||
}
|
|
||||||
} else {
|
|
||||||
return { fontName: fontfamily, fontUrl: null };
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// 检查字体是否存在
|
|
||||||
function checkFontAvailability(fontfamily) {
|
|
||||||
return new Promise((resolve) => {
|
|
||||||
const canvas = document.createElement('canvas');
|
|
||||||
const context = canvas.getContext('2d');
|
|
||||||
|
|
||||||
// 设置两个不同的字体进行比较
|
|
||||||
const testText = 'abcdefghijklmnopqrstuvwxyz0123456789';
|
|
||||||
context.font = `16px ${fontfamily}, sans-serif`;
|
|
||||||
const widthWithFont = context.measureText(testText).width;
|
|
||||||
|
|
||||||
context.font = '16px sans-serif';
|
|
||||||
const widthWithFallback = context.measureText(testText).width;
|
|
||||||
|
|
||||||
// 如果宽度相同，说明字体不存在
|
|
||||||
resolve(widthWithFont !== widthWithFallback);
|
|
||||||
});
|
|
||||||
}
|
|
||||||
async function checkFontAvailabilityV2(fontfamily) {
|
|
||||||
fontName = fontfamily;
|
|
||||||
console.log('Checking font availability:', fontName);
|
|
||||||
if ('queryLocalFonts' in window) {
|
|
||||||
try {
|
|
||||||
const fonts = await window.queryLocalFonts();
|
|
||||||
const fontExists = fonts.some(font => font.family === fontName);
|
|
||||||
console.log(`Local Font "${fontName}" exists:`, fontExists);
|
|
||||||
return fontExists;
|
|
||||||
} catch (error) {
|
|
||||||
console.error('Error querying local fonts:', error);
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
} else {
|
|
||||||
console.error('queryLocalFonts is not supported in this browser.');
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
// 动态加载字体
|
|
||||||
function loadFont(fontfamily, fontUrl) {
|
|
||||||
return new Promise((resolve, reject) => {
|
|
||||||
// 使用 Google Fonts 或其他字体来源
|
|
||||||
const link = document.createElement('link');
|
|
||||||
link.rel = 'stylesheet';
|
|
||||||
link.href = fontUrl;
|
|
||||||
link.onload = () => {
|
|
||||||
toast_push(`字体 "${fontfamily}" 已成功加载`, 3000);
|
|
||||||
resolve();
|
|
||||||
};
|
|
||||||
link.onerror = (error) => {
|
|
||||||
reject(error);
|
|
||||||
};
|
|
||||||
document.head.appendChild(link);
|
|
||||||
});
|
|
||||||
}
|
|
||||||
function gpt_academic_change_chatbot_font(fontfamily, fontsize, fontcolor) {
|
|
||||||
const chatbot = document.querySelector('#gpt-chatbot');
|
|
||||||
// 检查元素是否存在
|
|
||||||
if (chatbot) {
|
|
||||||
if (fontfamily != null) {
|
|
||||||
// 更改字体
|
|
||||||
const result = processFontFamily(fontfamily);
|
|
||||||
if (result.fontName == "Theme-Default-Font") {
|
|
||||||
chatbot.style.fontFamily = result.fontName;
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
// 检查字体是否存在
|
|
||||||
checkFontAvailability(result.fontName).then((isAvailable) => {
|
|
||||||
if (isAvailable) {
|
|
||||||
// 如果字体存在，直接应用
|
|
||||||
chatbot.style.fontFamily = result.fontName;
|
|
||||||
} else {
|
|
||||||
if (result.fontUrl == null) {
|
|
||||||
// toast_push('无法加载字体，本地字体不存在，且URL未提供', 3000);
|
|
||||||
// 直接把失效的字体放上去，让系统自动fallback
|
|
||||||
chatbot.style.fontFamily = result.fontName;
|
|
||||||
return;
|
|
||||||
} else {
|
|
||||||
toast_push('正在下载字体', 3000);
|
|
||||||
// 如果字体不存在，尝试加载字体
|
|
||||||
loadFont(result.fontName, result.fontUrl).then(() => {
|
|
||||||
chatbot.style.fontFamily = result.fontName;
|
|
||||||
}).catch((error) => {
|
|
||||||
console.error(`无法加载字体 "${result.fontName}":`, error);
|
|
||||||
});
|
|
||||||
}
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
}
|
|
||||||
if (fontsize != null) {
|
|
||||||
// 修改字体大小
|
|
||||||
document.documentElement.style.setProperty(
|
|
||||||
'--gpt-academic-message-font-size',
|
|
||||||
`${fontsize}px`
|
|
||||||
);
|
|
||||||
}
|
|
||||||
if (fontcolor != null) {
|
|
||||||
// 更改字体颜色
|
|
||||||
chatbot.style.color = fontcolor;
|
|
||||||
}
|
|
||||||
} else {
|
|
||||||
console.error('#gpt-chatbot is missing');
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
async function GptAcademicJavaScriptInit(dark, prompt, live2d, layout, tts) {
|
async function GptAcademicJavaScriptInit(dark, prompt, live2d, layout, tts) {
|
||||||
// 第一部分，布局初始化
|
// 第一部分，布局初始化
|
||||||
remove_legacy_cookie();
|
|
||||||
audio_fn_init();
|
audio_fn_init();
|
||||||
minor_ui_adjustment();
|
minor_ui_adjustment();
|
||||||
ButtonWithDropdown_init();
|
ButtonWithDropdown_init();
|
||||||
update_conversation_metadata();
|
|
||||||
window.addEventListener("gptac_restore_chat_from_local_storage", restore_chat_from_local_storage);
|
|
||||||
|
|
||||||
// 加载欢迎页面
|
// 加载欢迎页面
|
||||||
const welcomeMessage = new WelcomeMessage();
|
const welcomeMessage = new WelcomeMessage();
|
||||||
welcomeMessage.begin_render();
|
welcomeMessage.begin_render();
|
||||||
@@ -146,7 +13,7 @@ async function GptAcademicJavaScriptInit(dark, prompt, live2d, layout, tts) {
|
|||||||
welcomeMessage.update();
|
welcomeMessage.update();
|
||||||
});
|
});
|
||||||
chatbotObserver.observe(chatbotIndicator, { attributes: true, childList: true, subtree: true });
|
chatbotObserver.observe(chatbotIndicator, { attributes: true, childList: true, subtree: true });
|
||||||
|
|
||||||
if (layout === "LEFT-RIGHT") { chatbotAutoHeight(); }
|
if (layout === "LEFT-RIGHT") { chatbotAutoHeight(); }
|
||||||
if (layout === "LEFT-RIGHT") { limit_scroll_position(); }
|
if (layout === "LEFT-RIGHT") { limit_scroll_position(); }
|
||||||
|
|
||||||
@@ -169,7 +36,7 @@ async function GptAcademicJavaScriptInit(dark, prompt, live2d, layout, tts) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
// 自动朗读
|
// 自动朗读
|
||||||
if (tts != "DISABLE") {
|
if (tts != "DISABLE"){
|
||||||
enable_tts = true;
|
enable_tts = true;
|
||||||
if (getCookie("js_auto_read_cookie")) {
|
if (getCookie("js_auto_read_cookie")) {
|
||||||
auto_read_tts = getCookie("js_auto_read_cookie")
|
auto_read_tts = getCookie("js_auto_read_cookie")
|
||||||
@@ -179,11 +46,7 @@ async function GptAcademicJavaScriptInit(dark, prompt, live2d, layout, tts) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
// 字体
|
|
||||||
gpt_academic_gradio_saveload("load", "elem_fontfamily", "js_fontfamily", null, "str");
|
|
||||||
gpt_academic_change_chatbot_font(getCookie("js_fontfamily"), null, null);
|
|
||||||
gpt_academic_gradio_saveload("load", "elem_fontsize", "js_fontsize", null, "str");
|
|
||||||
gpt_academic_change_chatbot_font(null, getCookie("js_fontsize"), null);
|
|
||||||
// SysPrompt 系统静默提示词
|
// SysPrompt 系统静默提示词
|
||||||
gpt_academic_gradio_saveload("load", "elem_prompt", "js_system_prompt_cookie", null, "str");
|
gpt_academic_gradio_saveload("load", "elem_prompt", "js_system_prompt_cookie", null, "str");
|
||||||
// Temperature 大模型温度参数
|
// Temperature 大模型温度参数
|
||||||
@@ -193,7 +56,7 @@ async function GptAcademicJavaScriptInit(dark, prompt, live2d, layout, tts) {
|
|||||||
const cached_model = getCookie("js_md_dropdown_cookie");
|
const cached_model = getCookie("js_md_dropdown_cookie");
|
||||||
var model_sel = await get_gradio_component("elem_model_sel");
|
var model_sel = await get_gradio_component("elem_model_sel");
|
||||||
// determine whether the cached model is in the choices
|
// determine whether the cached model is in the choices
|
||||||
if (model_sel.props.choices.includes(cached_model)) {
|
if (model_sel.props.choices.includes(cached_model)){
|
||||||
// change dropdown
|
// change dropdown
|
||||||
gpt_academic_gradio_saveload("load", "elem_model_sel", "js_md_dropdown_cookie", null, "str");
|
gpt_academic_gradio_saveload("load", "elem_model_sel", "js_md_dropdown_cookie", null, "str");
|
||||||
// 连锁修改chatbot的label
|
// 连锁修改chatbot的label
|
||||||
|
|||||||
@@ -87,6 +87,21 @@ js_code_for_toggle_darkmode = """() => {
|
|||||||
}"""
|
}"""
|
||||||
|
|
||||||
|
|
||||||
|
js_code_for_persistent_cookie_init = """(web_cookie_cache, cookie) => {
|
||||||
|
return [getCookie("web_cookie_cache"), cookie];
|
||||||
|
}
|
||||||
|
"""
|
||||||
|
|
||||||
|
# 详见 themes/common.js
|
||||||
|
js_code_reset = """
|
||||||
|
(a,b,c)=>{
|
||||||
|
let stopButton = document.getElementById("elem_stop");
|
||||||
|
stopButton.click();
|
||||||
|
return reset_conversation(a,b);
|
||||||
|
}
|
||||||
|
"""
|
||||||
|
|
||||||
|
|
||||||
js_code_clear = """
|
js_code_clear = """
|
||||||
(a,b)=>{
|
(a,b)=>{
|
||||||
return ["", ""];
|
return ["", ""];
|
||||||
|
|||||||
@@ -84,9 +84,8 @@ class WelcomeMessage {
|
|||||||
this.max_welcome_card_num = 6;
|
this.max_welcome_card_num = 6;
|
||||||
this.card_array = [];
|
this.card_array = [];
|
||||||
this.static_welcome_message_previous = [];
|
this.static_welcome_message_previous = [];
|
||||||
this.reflesh_time_interval = 15 * 1000;
|
this.reflesh_time_interval = 15*1000;
|
||||||
this.update_time_interval = 2 * 1000;
|
|
||||||
this.major_title = "欢迎使用GPT-Academic";
|
|
||||||
|
|
||||||
const reflesh_render_status = () => {
|
const reflesh_render_status = () => {
|
||||||
for (let index = 0; index < this.card_array.length; index++) {
|
for (let index = 0; index < this.card_array.length; index++) {
|
||||||
@@ -97,31 +96,16 @@ class WelcomeMessage {
|
|||||||
};
|
};
|
||||||
const pageFocusHandler = new PageFocusHandler();
|
const pageFocusHandler = new PageFocusHandler();
|
||||||
pageFocusHandler.addFocusCallback(reflesh_render_status);
|
pageFocusHandler.addFocusCallback(reflesh_render_status);
|
||||||
|
|
||||||
// call update when page size change, call this.update when page size change
|
|
||||||
window.addEventListener('resize', this.update.bind(this));
|
|
||||||
// add a loop to reflesh cards
|
|
||||||
this.startRefleshCards();
|
|
||||||
this.startAutoUpdate();
|
|
||||||
}
|
}
|
||||||
|
|
||||||
begin_render() {
|
begin_render() {
|
||||||
this.update();
|
this.update();
|
||||||
}
|
}
|
||||||
|
|
||||||
async startAutoUpdate() {
|
|
||||||
// sleep certain time
|
|
||||||
await new Promise(r => setTimeout(r, this.update_time_interval));
|
|
||||||
this.update();
|
|
||||||
}
|
|
||||||
|
|
||||||
async startRefleshCards() {
|
async startRefleshCards() {
|
||||||
// sleep certain time
|
|
||||||
await new Promise(r => setTimeout(r, this.reflesh_time_interval));
|
await new Promise(r => setTimeout(r, this.reflesh_time_interval));
|
||||||
// checkout visible status
|
await this.reflesh_cards();
|
||||||
if (this.visible) {
|
if (this.visible){
|
||||||
// if visible, then reflesh cards
|
|
||||||
await this.reflesh_cards();
|
|
||||||
setTimeout(() => {
|
setTimeout(() => {
|
||||||
this.startRefleshCards.call(this);
|
this.startRefleshCards.call(this);
|
||||||
}, 1);
|
}, 1);
|
||||||
@@ -129,7 +113,7 @@ class WelcomeMessage {
|
|||||||
}
|
}
|
||||||
|
|
||||||
async reflesh_cards() {
|
async reflesh_cards() {
|
||||||
if (!this.visible) {
|
if (!this.visible){
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -142,7 +126,6 @@ class WelcomeMessage {
|
|||||||
|
|
||||||
// combine two lists
|
// combine two lists
|
||||||
this.static_welcome_message_previous = not_shown_previously.concat(already_shown_previously);
|
this.static_welcome_message_previous = not_shown_previously.concat(already_shown_previously);
|
||||||
this.static_welcome_message_previous = this.static_welcome_message_previous.slice(0, this.max_welcome_card_num);
|
|
||||||
|
|
||||||
(async () => {
|
(async () => {
|
||||||
// 使用 for...of 循环来处理异步操作
|
// 使用 for...of 循环来处理异步操作
|
||||||
@@ -159,10 +142,8 @@ class WelcomeMessage {
|
|||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// 等待动画结束
|
||||||
card.classList.add('hide');
|
card.addEventListener('transitionend', () => {
|
||||||
const timeout = 100; // 与CSS中transition的时间保持一致(0.1s)
|
|
||||||
setTimeout(() => {
|
|
||||||
// 更新卡片信息
|
// 更新卡片信息
|
||||||
const message = this.static_welcome_message_previous[index];
|
const message = this.static_welcome_message_previous[index];
|
||||||
const title = card.getElementsByClassName('welcome-card-title')[0];
|
const title = card.getElementsByClassName('welcome-card-title')[0];
|
||||||
@@ -174,14 +155,16 @@ class WelcomeMessage {
|
|||||||
text.href = message.url;
|
text.href = message.url;
|
||||||
content.textContent = message.content;
|
content.textContent = message.content;
|
||||||
card.classList.remove('hide');
|
card.classList.remove('hide');
|
||||||
// 等待动画结束
|
|
||||||
card.classList.add('show');
|
|
||||||
const timeout = 100; // 与CSS中transition的时间保持一致(0.1s)
|
|
||||||
setTimeout(() => {
|
|
||||||
card.classList.remove('show');
|
|
||||||
}, timeout);
|
|
||||||
}, timeout);
|
|
||||||
|
|
||||||
|
// 等待动画结束
|
||||||
|
card.addEventListener('transitionend', () => {
|
||||||
|
card.classList.remove('show');
|
||||||
|
}, { once: true });
|
||||||
|
card.classList.add('show');
|
||||||
|
|
||||||
|
}, { once: true });
|
||||||
|
|
||||||
|
card.classList.add('hide');
|
||||||
|
|
||||||
// 等待 250 毫秒
|
// 等待 250 毫秒
|
||||||
await new Promise(r => setTimeout(r, 200));
|
await new Promise(r => setTimeout(r, 200));
|
||||||
@@ -190,55 +173,43 @@ class WelcomeMessage {
|
|||||||
}
|
}
|
||||||
|
|
||||||
shuffle(array) {
|
shuffle(array) {
|
||||||
var currentIndex = array.length, randomIndex;
|
var currentIndex = array.length, randomIndex;
|
||||||
|
|
||||||
// While there remain elements to shuffle...
|
// While there remain elements to shuffle...
|
||||||
while (currentIndex != 0) {
|
while (currentIndex != 0) {
|
||||||
|
|
||||||
// Pick a remaining element...
|
// Pick a remaining element...
|
||||||
randomIndex = Math.floor(Math.random() * currentIndex);
|
randomIndex = Math.floor(Math.random() * currentIndex);
|
||||||
currentIndex--;
|
currentIndex--;
|
||||||
|
|
||||||
// And swap it with the current element.
|
// And swap it with the current element.
|
||||||
[array[currentIndex], array[randomIndex]] = [
|
[array[currentIndex], array[randomIndex]] = [
|
||||||
array[randomIndex], array[currentIndex]];
|
array[randomIndex], array[currentIndex]];
|
||||||
}
|
}
|
||||||
|
|
||||||
return array;
|
return array;
|
||||||
}
|
}
|
||||||
|
|
||||||
async can_display() {
|
async update() {
|
||||||
// update the card visibility
|
// console.log('update')
|
||||||
const elem_chatbot = document.getElementById('gpt-chatbot');
|
|
||||||
const chatbot_top = elem_chatbot.getBoundingClientRect().top;
|
|
||||||
const welcome_card_container = document.getElementsByClassName('welcome-card-container')[0];
|
|
||||||
// detect if welcome card overflow
|
|
||||||
let welcome_card_overflow = false;
|
|
||||||
if (welcome_card_container) {
|
|
||||||
const welcome_card_top = welcome_card_container.getBoundingClientRect().top;
|
|
||||||
if (welcome_card_top < chatbot_top) {
|
|
||||||
welcome_card_overflow = true;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
var page_width = document.documentElement.clientWidth;
|
var page_width = document.documentElement.clientWidth;
|
||||||
const width_to_hide_welcome = 1200;
|
const width_to_hide_welcome = 1200;
|
||||||
if (!await this.isChatbotEmpty() || page_width < width_to_hide_welcome || welcome_card_overflow) {
|
if (!await this.isChatbotEmpty() || page_width < width_to_hide_welcome) {
|
||||||
// cannot display
|
if (this.visible) {
|
||||||
return false;
|
this.removeWelcome();
|
||||||
}
|
this.visible = false;
|
||||||
return true;
|
this.card_array = [];
|
||||||
}
|
this.static_welcome_message_previous = [];
|
||||||
|
}
|
||||||
async update() {
|
|
||||||
const can_display = await this.can_display();
|
|
||||||
if (can_display && !this.visible) {
|
|
||||||
this.showWelcome();
|
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
if (!can_display && this.visible) {
|
if (this.visible){
|
||||||
this.removeWelcome();
|
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
|
// console.log("welcome");
|
||||||
|
this.showWelcome();
|
||||||
|
this.visible = true;
|
||||||
|
this.startRefleshCards();
|
||||||
}
|
}
|
||||||
|
|
||||||
showCard(message) {
|
showCard(message) {
|
||||||
@@ -249,28 +220,28 @@ class WelcomeMessage {
|
|||||||
const title = document.createElement('div');
|
const title = document.createElement('div');
|
||||||
title.classList.add('welcome-card-title');
|
title.classList.add('welcome-card-title');
|
||||||
|
|
||||||
// 创建图标
|
// 创建图标
|
||||||
const svg = document.createElement('img');
|
const svg = document.createElement('img');
|
||||||
svg.classList.add('welcome-svg');
|
svg.classList.add('welcome-svg');
|
||||||
svg.src = message.svg;
|
svg.src = message.svg;
|
||||||
svg.style.height = '30px';
|
svg.style.height = '30px';
|
||||||
title.appendChild(svg);
|
title.appendChild(svg);
|
||||||
|
|
||||||
// 创建标题
|
// 创建标题
|
||||||
const text = document.createElement('a');
|
const text = document.createElement('a');
|
||||||
text.textContent = message.title;
|
text.textContent = message.title;
|
||||||
text.classList.add('welcome-title-text');
|
text.classList.add('welcome-title-text');
|
||||||
text.href = message.url;
|
text.href = message.url;
|
||||||
text.target = "_blank";
|
text.target = "_blank";
|
||||||
title.appendChild(text)
|
title.appendChild(text)
|
||||||
|
|
||||||
// 创建内容
|
// 创建内容
|
||||||
const content = document.createElement('div');
|
const content = document.createElement('div');
|
||||||
content.classList.add('welcome-content');
|
content.classList.add('welcome-content');
|
||||||
const content_c = document.createElement('div');
|
const content_c = document.createElement('div');
|
||||||
content_c.classList.add('welcome-content-c');
|
content_c.classList.add('welcome-content-c');
|
||||||
content_c.textContent = message.content;
|
content_c.textContent = message.content;
|
||||||
content.appendChild(content_c);
|
content.appendChild(content_c);
|
||||||
|
|
||||||
// 将标题和内容添加到卡片 div 中
|
// 将标题和内容添加到卡片 div 中
|
||||||
card.appendChild(title);
|
card.appendChild(title);
|
||||||
@@ -279,7 +250,7 @@ class WelcomeMessage {
|
|||||||
}
|
}
|
||||||
|
|
||||||
async showWelcome() {
|
async showWelcome() {
|
||||||
this.visible = true;
|
|
||||||
// 首先，找到想要添加子元素的父元素
|
// 首先，找到想要添加子元素的父元素
|
||||||
const elem_chatbot = document.getElementById('gpt-chatbot');
|
const elem_chatbot = document.getElementById('gpt-chatbot');
|
||||||
|
|
||||||
@@ -290,7 +261,7 @@ class WelcomeMessage {
|
|||||||
// 创建主标题
|
// 创建主标题
|
||||||
const major_title = document.createElement('div');
|
const major_title = document.createElement('div');
|
||||||
major_title.classList.add('welcome-title');
|
major_title.classList.add('welcome-title');
|
||||||
major_title.textContent = this.major_title;
|
major_title.textContent = "欢迎使用GPT-Academic";
|
||||||
welcome_card_container.appendChild(major_title)
|
welcome_card_container.appendChild(major_title)
|
||||||
|
|
||||||
// 创建卡片
|
// 创建卡片
|
||||||
@@ -305,16 +276,6 @@ class WelcomeMessage {
|
|||||||
});
|
});
|
||||||
|
|
||||||
elem_chatbot.appendChild(welcome_card_container);
|
elem_chatbot.appendChild(welcome_card_container);
|
||||||
const can_display = await this.can_display();
|
|
||||||
if (!can_display) {
|
|
||||||
// undo
|
|
||||||
this.visible = false;
|
|
||||||
this.card_array = [];
|
|
||||||
this.static_welcome_message_previous = [];
|
|
||||||
elem_chatbot.removeChild(welcome_card_container);
|
|
||||||
await new Promise(r => setTimeout(r, this.update_time_interval / 2));
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
||||||
// 添加显示动画
|
// 添加显示动画
|
||||||
requestAnimationFrame(() => {
|
requestAnimationFrame(() => {
|
||||||
@@ -323,24 +284,15 @@ class WelcomeMessage {
|
|||||||
}
|
}
|
||||||
|
|
||||||
async removeWelcome() {
|
async removeWelcome() {
|
||||||
this.visible = false;
|
|
||||||
// remove welcome-card-container
|
// remove welcome-card-container
|
||||||
const elem_chatbot = document.getElementById('gpt-chatbot');
|
const elem_chatbot = document.getElementById('gpt-chatbot');
|
||||||
const welcome_card_container = document.getElementsByClassName('welcome-card-container')[0];
|
const welcome_card_container = document.getElementsByClassName('welcome-card-container')[0];
|
||||||
// begin hide animation
|
// 添加隐藏动画
|
||||||
welcome_card_container.classList.add('hide');
|
welcome_card_container.classList.add('hide');
|
||||||
|
// 等待动画结束后再移除元素
|
||||||
welcome_card_container.addEventListener('transitionend', () => {
|
welcome_card_container.addEventListener('transitionend', () => {
|
||||||
elem_chatbot.removeChild(welcome_card_container);
|
elem_chatbot.removeChild(welcome_card_container);
|
||||||
this.card_array = [];
|
|
||||||
this.static_welcome_message_previous = [];
|
|
||||||
}, { once: true });
|
}, { once: true });
|
||||||
// add a fail safe timeout
|
|
||||||
const timeout = 600; // 与 CSS 中 transition 的时间保持一致(1s)
|
|
||||||
setTimeout(() => {
|
|
||||||
if (welcome_card_container.parentNode) {
|
|
||||||
elem_chatbot.removeChild(welcome_card_container);
|
|
||||||
}
|
|
||||||
}, timeout);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
async isChatbotEmpty() {
|
async isChatbotEmpty() {
|
||||||
@@ -355,28 +307,28 @@ class WelcomeMessage {
|
|||||||
|
|
||||||
class PageFocusHandler {
|
class PageFocusHandler {
|
||||||
constructor() {
|
constructor() {
|
||||||
this.hasReturned = false;
|
this.hasReturned = false;
|
||||||
this.focusCallbacks = [];
|
this.focusCallbacks = [];
|
||||||
|
|
||||||
// Bind the focus and blur event handlers
|
// Bind the focus and blur event handlers
|
||||||
window.addEventListener('visibilitychange', this.handleFocus.bind(this));
|
window.addEventListener('visibilitychange', this.handleFocus.bind(this));
|
||||||
}
|
}
|
||||||
|
|
||||||
// Method to handle the focus event
|
// Method to handle the focus event
|
||||||
handleFocus() {
|
handleFocus() {
|
||||||
if (this.hasReturned) {
|
if (this.hasReturned) {
|
||||||
this.focusCallbacks.forEach(callback => callback());
|
this.focusCallbacks.forEach(callback => callback());
|
||||||
}
|
}
|
||||||
this.hasReturned = true;
|
this.hasReturned = true;
|
||||||
}
|
}
|
||||||
|
|
||||||
// Method to add a custom callback function
|
// Method to add a custom callback function
|
||||||
addFocusCallback(callback) {
|
addFocusCallback(callback) {
|
||||||
if (typeof callback === 'function') {
|
if (typeof callback === 'function') {
|
||||||
this.focusCallbacks.push(callback);
|
this.focusCallbacks.push(callback);
|
||||||
} else {
|
} else {
|
||||||
throw new Error('Callback must be a function');
|
throw new Error('Callback must be a function');
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
13
toolbox.py
13
toolbox.py
@@ -8,7 +8,6 @@ import base64
|
|||||||
import gradio
|
import gradio
|
||||||
import shutil
|
import shutil
|
||||||
import glob
|
import glob
|
||||||
import json
|
|
||||||
import uuid
|
import uuid
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
from functools import wraps
|
from functools import wraps
|
||||||
@@ -93,9 +92,8 @@ def ArgsGeneralWrapper(f):
|
|||||||
"""
|
"""
|
||||||
def decorated(request: gradio.Request, cookies:dict, max_length:int, llm_model:str,
|
def decorated(request: gradio.Request, cookies:dict, max_length:int, llm_model:str,
|
||||||
txt:str, txt2:str, top_p:float, temperature:float, chatbot:list,
|
txt:str, txt2:str, top_p:float, temperature:float, chatbot:list,
|
||||||
json_history:str, system_prompt:str, plugin_advanced_arg:dict, *args):
|
history:list, system_prompt:str, plugin_advanced_arg:dict, *args):
|
||||||
txt_passon = txt
|
txt_passon = txt
|
||||||
history = json.loads(json_history) if json_history else []
|
|
||||||
if txt == "" and txt2 != "": txt_passon = txt2
|
if txt == "" and txt2 != "": txt_passon = txt2
|
||||||
# 引入一个有cookie的chatbot
|
# 引入一个有cookie的chatbot
|
||||||
if request.username is not None:
|
if request.username is not None:
|
||||||
@@ -150,11 +148,10 @@ def ArgsGeneralWrapper(f):
|
|||||||
return decorated
|
return decorated
|
||||||
|
|
||||||
|
|
||||||
def update_ui(chatbot:ChatBotWithCookies, history:list, msg:str="正常", **kwargs): # 刷新界面
|
def update_ui(chatbot:ChatBotWithCookies, history, msg="正常", **kwargs): # 刷新界面
|
||||||
"""
|
"""
|
||||||
刷新用户界面
|
刷新用户界面
|
||||||
"""
|
"""
|
||||||
assert isinstance(history, list), "history必须是一个list"
|
|
||||||
assert isinstance(
|
assert isinstance(
|
||||||
chatbot, ChatBotWithCookies
|
chatbot, ChatBotWithCookies
|
||||||
), "在传递chatbot的过程中不要将其丢弃。必要时, 可用clear将其清空, 然后用for+append循环重新赋值。"
|
), "在传递chatbot的过程中不要将其丢弃。必要时, 可用clear将其清空, 然后用for+append循环重新赋值。"
|
||||||
@@ -178,12 +175,10 @@ def update_ui(chatbot:ChatBotWithCookies, history:list, msg:str="正常", **kwar
|
|||||||
else:
|
else:
|
||||||
chatbot_gr = chatbot
|
chatbot_gr = chatbot
|
||||||
|
|
||||||
history = [str(history_item) for history_item in history] # ensure all items are string
|
yield cookies, chatbot_gr, history, msg
|
||||||
json_history = json.dumps(history, ensure_ascii=False)
|
|
||||||
yield cookies, chatbot_gr, json_history, msg
|
|
||||||
|
|
||||||
|
|
||||||
def update_ui_lastest_msg(lastmsg:str, chatbot:ChatBotWithCookies, history:list, delay:float=1, msg:str="正常"): # 刷新界面
|
def update_ui_lastest_msg(lastmsg:str, chatbot:ChatBotWithCookies, history:list, delay=1, msg="正常"): # 刷新界面
|
||||||
"""
|
"""
|
||||||
刷新用户界面
|
刷新用户界面
|
||||||
"""
|
"""
|
||||||
|
|||||||
Reference in New Issue
Block a user