diff --git a/README.md b/README.md
index ad09490e..20e67a9d 100644
--- a/README.md
+++ b/README.md
@@ -1,12 +1,13 @@
-
🌍 [READ THIS IN ENGLISH](README_en.md)
📃 **LangChain-Chatchat** (原 Langchain-ChatGLM)
基于 ChatGLM 等大语言模型与 Langchain 等应用框架实现，开源、可离线部署的检索增强生成(RAG)大模型知识库项目。
+⚠️`0.2.10`将会是`0.2.x`系列的最后一个版本，`0.2.x`系列版本将会停止更新和技术支持，全力研发具有更强应用性的 `Langchain-Chatchat 0.3.x`。
+
---
## 目录
@@ -14,23 +15,31 @@
* [介绍](README.md#介绍)
* [解决的痛点](README.md#解决的痛点)
* [快速上手](README.md#快速上手)
- * [1. 环境配置](README.md#1-环境配置)
- * [2. 模型下载](README.md#2-模型下载)
- * [3. 初始化知识库和配置文件](README.md#3-初始化知识库和配置文件)
- * [4. 一键启动](README.md#4-一键启动)
- * [5. 启动界面示例](README.md#5-启动界面示例)
+ * [1. 环境配置](README.md#1-环境配置)
+ * [2. 模型下载](README.md#2-模型下载)
+ * [3. 初始化知识库和配置文件](README.md#3-初始化知识库和配置文件)
+ * [4. 一键启动](README.md#4-一键启动)
+ * [5. 启动界面示例](README.md#5-启动界面示例)
* [联系我们](README.md#联系我们)
-
## 介绍
-🤖️ 一种利用 [langchain](https://github.com/hwchase17/langchain) 思想实现的基于本地知识库的问答应用，目标期望建立一套对中文场景与开源模型支持友好、可离线运行的知识库问答解决方案。
+🤖️ 一种利用 [langchain](https://github.com/langchain-ai/langchain)
+思想实现的基于本地知识库的问答应用，目标期望建立一套对中文场景与开源模型支持友好、可离线运行的知识库问答解决方案。
-💡 受 [GanymedeNil](https://github.com/GanymedeNil) 的项目 [document.ai](https://github.com/GanymedeNil/document.ai) 和 [AlexZhangji](https://github.com/AlexZhangji) 创建的 [ChatGLM-6B Pull Request](https://github.com/THUDM/ChatGLM-6B/pull/216) 启发，建立了全流程可使用开源模型实现的本地知识库问答应用。本项目的最新版本中通过使用 [FastChat](https://github.com/lm-sys/FastChat) 接入 Vicuna, Alpaca, LLaMA, Koala, RWKV 等模型，依托于 [langchain](https://github.com/langchain-ai/langchain) 框架支持通过基于 [FastAPI](https://github.com/tiangolo/fastapi) 提供的 API 调用服务，或使用基于 [Streamlit](https://github.com/streamlit/streamlit) 的 WebUI 进行操作。
+💡 受 [GanymedeNil](https://github.com/GanymedeNil) 的项目 [document.ai](https://github.com/GanymedeNil/document.ai)
+和 [AlexZhangji](https://github.com/AlexZhangji)
+创建的 [ChatGLM-6B Pull Request](https://github.com/THUDM/ChatGLM-6B/pull/216)
+启发，建立了全流程可使用开源模型实现的本地知识库问答应用。本项目的最新版本中通过使用 [FastChat](https://github.com/lm-sys/FastChat)
+接入 Vicuna, Alpaca, LLaMA, Koala, RWKV 等模型，依托于 [langchain](https://github.com/langchain-ai/langchain)
+框架支持通过基于 [FastAPI](https://github.com/tiangolo/fastapi) 提供的 API
+调用服务，或使用基于 [Streamlit](https://github.com/streamlit/streamlit) 的 WebUI 进行操作。
-✅ 依托于本项目支持的开源 LLM 与 Embedding 模型，本项目可实现全部使用**开源**模型**离线私有部署**。与此同时，本项目也支持 OpenAI GPT API 的调用，并将在后续持续扩充对各类模型及模型 API 的接入。
+✅ 依托于本项目支持的开源 LLM 与 Embedding 模型，本项目可实现全部使用**开源**模型**离线私有部署**。与此同时，本项目也支持
+OpenAI GPT API 的调用，并将在后续持续扩充对各类模型及模型 API 的接入。
-⛓️ 本项目实现原理如下图所示，过程包括加载文件 -> 读取文本 -> 文本分割 -> 文本向量化 -> 问句向量化 -> 在文本向量中匹配出与问句向量最相似的 `top k`个 -> 匹配出的文本作为上下文和问题一起添加到 `prompt`中 -> 提交给 `LLM`生成回答。
+⛓️ 本项目实现原理如下图所示，过程包括加载文件 -> 读取文本 -> 文本分割 -> 文本向量化 -> 问句向量化 ->
+在文本向量中匹配出与问句向量最相似的 `top k`个 -> 匹配出的文本作为上下文和问题一起添加到 `prompt`中 -> 提交给 `LLM`生成回答。
📺 [原理介绍视频](https://www.bilibili.com/video/BV13M4y1e7cN/?share_source=copy_web&vd_source=e6c5aafe684f30fbe41925d61ca6d514)
@@ -42,7 +51,8 @@
🚩 本项目未涉及微调、训练过程，但可利用微调或训练对本项目效果进行优化。
-🌐 [AutoDL 镜像](https://www.codewithgpu.com/i/chatchat-space/Langchain-Chatchat/Langchain-Chatchat) 中 `v13` 版本所使用代码已更新至本项目 `v0.2.9` 版本。
+🌐 [AutoDL 镜像](https://www.codewithgpu.com/i/chatchat-space/Langchain-Chatchat/Langchain-Chatchat) 中 `v13`
+版本所使用代码已更新至本项目 `v0.2.9` 版本。
🐳 [Docker 镜像](registry.cn-beijing.aliyuncs.com/chatchat/chatchat:0.2.6) 已经更新到 ```0.2.7``` 版本。
@@ -52,7 +62,10 @@
docker run -d --gpus all -p 80:8501 registry.cn-beijing.aliyuncs.com/chatchat/chatchat:0.2.7
```
-🧩 本项目有一个非常完整的[Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/) ， README只是一个简单的介绍，__仅仅是入门教程，能够基础运行__。 如果你想要更深入的了解本项目，或者想对本项目做出贡献。请移步 [Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/) 界面
+🧩 本项目有一个非常完整的[Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/) ， README只是一个简单的介绍，_
+_仅仅是入门教程，能够基础运行__。
+如果你想要更深入的了解本项目，或者想对本项目做出贡献。请移步 [Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/)
+界面
## 解决的痛点
@@ -62,17 +75,19 @@ docker run -d --gpus all -p 80:8501 registry.cn-beijing.aliyuncs.com/chatchat/ch
我们支持市面上主流的本地大语言模型和Embedding模型，支持开源的本地向量数据库。
支持列表详见[Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/)
-
## 快速上手
### 1. 环境配置
-+ 首先，确保你的机器安装了 Python 3.8 - 3.11
++ 首先，确保你的机器安装了 Python 3.8 - 3.11 (我们强烈推荐使用 Python3.11)。
+
```
$ python --version
Python 3.11.7
```
+
接着，创建一个虚拟环境，并在虚拟环境内安装项目的依赖
+
```shell
# 拉取仓库
@@ -88,33 +103,44 @@ $ pip install -r requirements_webui.txt
# 默认依赖包括基本运行环境（FAISS向量库）。如果要使用 milvus/pg_vector 等向量库，请将 requirements.txt 中相应依赖取消注释再安装。
```
-请注意，LangChain-Chatchat `0.2.x` 系列是针对 Langchain `0.0.x` 系列版本的，如果你使用的是 Langchain `0.1.x` 系列版本，需要降级。
+
+请注意，LangChain-Chatchat `0.2.x` 系列是针对 Langchain `0.0.x` 系列版本的，如果你使用的是 Langchain `0.1.x`
+系列版本，需要降级您的`Langchain`版本。
+
### 2， 模型下载
-如需在本地或离线环境下运行本项目，需要首先将项目所需的模型下载至本地，通常开源 LLM 与 Embedding 模型可以从 [HuggingFace](https://huggingface.co/models) 下载。
+如需在本地或离线环境下运行本项目，需要首先将项目所需的模型下载至本地，通常开源 LLM 与 Embedding
+模型可以从 [HuggingFace](https://huggingface.co/models) 下载。
-以本项目中默认使用的 LLM 模型 [THUDM/ChatGLM3-6B](https://huggingface.co/THUDM/chatglm3-6b) 与 Embedding 模型 [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) 为例：
+以本项目中默认使用的 LLM 模型 [THUDM/ChatGLM3-6B](https://huggingface.co/THUDM/chatglm3-6b) 与 Embedding
+模型 [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) 为例：
-下载模型需要先[安装 Git LFS](https://docs.github.com/zh/repositories/working-with-files/managing-large-files/installing-git-large-file-storage)，然后运行
+下载模型需要先[安装 Git LFS](https://docs.github.com/zh/repositories/working-with-files/managing-large-files/installing-git-large-file-storage)
+，然后运行
```Shell
$ git lfs install
$ git clone https://huggingface.co/THUDM/chatglm3-6b
$ git clone https://huggingface.co/BAAI/bge-large-zh
```
+
### 3. 初始化知识库和配置文件
按照下列方式初始化自己的知识库和简单的复制配置文件
+
```shell
$ python copy_config_example.py
$ python init_database.py --recreate-vs
```
+
### 4. 一键启动
按照以下命令启动项目
+
```shell
$ python startup.py -a
```
+
### 5. 启动界面示例
如果正常启动，你将能看到以下界面
@@ -133,29 +159,37 @@ $ python startup.py -a
-
### 注意
-以上方式只是为了快速上手，如果需要更多的功能和自定义启动方式 ，请参考[Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/)
+以上方式只是为了快速上手，如果需要更多的功能和自定义启动方式
+，请参考[Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/)
---
+
## 项目里程碑
+ `2023年4月`: `Langchain-ChatGLM 0.1.0` 发布，支持基于 ChatGLM-6B 模型的本地知识库问答。
+ `2023年8月`: `Langchain-ChatGLM` 改名为 `Langchain-Chatchat`，`0.2.0` 发布，使用 `fastchat` 作为模型加载方案，支持更多的模型和数据库。
-+ `2023年10月`: `Langchain-Chatchat 0.2.5` 发布，推出 Agent 内容，开源项目在`Founder Park & Zhipu AI & Zilliz` 举办的黑客马拉松获得三等奖。
++ `2023年10月`: `Langchain-Chatchat 0.2.5` 发布，推出 Agent 内容，开源项目在`Founder Park & Zhipu AI & Zilliz`
+ 举办的黑客马拉松获得三等奖。
+ `2023年12月`: `Langchain-Chatchat` 开源项目获得超过 **20K** stars.
-+ `2024年1月`: `LangChain 0.1.x` 推出，`Langchain-Chatchat 0.2.x` 停止更新和技术支持，全力研发具有更强应用性的 `Langchain-Chatchat 0.3.x`。
++ `2024年1月`: `LangChain 0.1.x` 推出，`Langchain-Chatchat 0.2.x` 发布稳定版本`0.2.10`
+ 后将停止更新和技术支持，全力研发具有更强应用性的 `Langchain-Chatchat 0.3.x`。
+ 🔥 让我们一起期待未来 Chatchat 的故事 ···
+
---
+
## 联系我们
+
### Telegram
+
[](https://t.me/+RjliQ3jnJ1YyN2E9)
### 项目交流群
-
+
+
🎉 Langchain-Chatchat 项目微信交流群，如果你也对本项目感兴趣，欢迎加入群聊参与讨论交流。
diff --git a/README_en.md b/README_en.md
index cd18304e..dba6d3b7 100644
--- a/README_en.md
+++ b/README_en.md
@@ -7,6 +7,10 @@
A LLM application aims to implement knowledge and search engine based QA based on Langchain and open-source or remote
LLM API.
+⚠️`0.2.10` will be the last version of the `0.2.x` series. The `0.2.x` series will stop updating and technical support,
+and strive to develop `Langchain-Chachat 0.3.x with stronger applicability. `.
+
+
---
## Table of Contents
@@ -24,7 +28,8 @@ LLM API.
## Introduction
🤖️ A Q&A application based on local knowledge base implemented using the idea
-of [langchain](https://github.com/hwchase17/langchain). The goal is to build a KBQA(Knowledge based Q&A) solution that
+of [langchain](https://github.com/langchain-ai/langchain). The goal is to build a KBQA(Knowledge based Q&A) solution
+that
is friendly to Chinese scenarios and open source models and can run both offline and online.
💡 Inspired by [document.ai](https://github.com/GanymedeNil/document.ai)
@@ -55,10 +60,9 @@ The main process analysis from the aspect of document process:
🚩 The training or fine-tuning are not involved in the project, but still, one always can improve performance by do
these.
-🌐 [AutoDL image](registry.cn-beijing.aliyuncs.com/chatchat/chatchat:0.2.5) is supported, and in v13 the codes are update
-to v0.2.9.
+🌐 [AutoDL image](https://www.codewithgpu.com/i/chatchat-space/Langchain-Chatchat/Langchain-Chatchat) is supported, and in v13 the codes are update to v0.2.9.
-🐳 [Docker image](registry.cn-beijing.aliyuncs.com/chatchat/chatchat:0.2.7)
+🐳 [Docker image](registry.cn-beijing.aliyuncs.com/chatchat/chatchat:0.2.7) is supported to 0.2.7
## Pain Points Addressed
@@ -98,7 +102,9 @@ $ pip install -r requirements_webui.txt
# 默认依赖包括基本运行环境（FAISS向量库）。如果要使用 milvus/pg_vector 等向量库，请将 requirements.txt 中相应依赖取消注释再安装。
```
-Please note that the LangChain-Chachat `0.2.x` series is for the Langchain `0.0.x` series version. If you are using the Langchain `0.1.x` series version, you need to downgrade.
+
+Please note that the LangChain-Chachat `0.2.x` series is for the Langchain `0.0.x` series version. If you are using the
+Langchain `0.1.x` series version, you need to downgrade.
### Model Download
@@ -157,15 +163,23 @@ The above instructions are provided for a quick start. If you need more features
please refer to the [Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/).
---
+
## Project Milestones
-+ `April 2023`: `Langchain-ChatGLM 0.1.0` released, supporting local knowledge base question and answer based on the ChatGLM-6B model.
-+ `August 2023`: `Langchain-ChatGLM` was renamed to `Langchain-Chatchat`, `0.2.0` was released, using `fastchat` as the model loading solution, supporting more models and databases.
-+ `October 2023`: `Langchain-Chachat 0.2.5` was released, Agent content was launched, and the open source project won the third prize in the hackathon held by `Founder Park & Zhipu AI & Zilliz`.
++ `April 2023`: `Langchain-ChatGLM 0.1.0` released, supporting local knowledge base question and answer based on the
+ ChatGLM-6B model.
++ `August 2023`: `Langchain-ChatGLM` was renamed to `Langchain-Chatchat`, `0.2.0` was released, using `fastchat` as the
+ model loading solution, supporting more models and databases.
++ `October 2023`: `Langchain-Chachat 0.2.5` was released, Agent content was launched, and the open source project won
+ the third prize in the hackathon held by `Founder Park & Zhipu AI & Zilliz`.
+ `December 2023`: `Langchain-Chachat` open source project received more than **20K** stars.
-+ `January 2024`: `LangChain 0.1.x` is launched, `Langchain-Chatchat 0.2.x` will stop updating and technical support, and all efforts will be made to develop `Langchain-Chatchat 0.3.x` with stronger applicability.
++ `January 2024`: `LangChain 0.1.x` is launched, `Langchain-Chachat 0.2.x` is released. After the stable
+ version `0.2.10` is released, updates and technical support will be stopped, and all efforts will be made to
+ develop `Langchain with stronger applicability -Chat 0.3.x`.
+
+ 🔥 Let’s look forward to the future Chatchat stories together···
+
---
## Contact Us
@@ -176,7 +190,7 @@ please refer to the [Wiki](https://github.com/chatchat-space/Langchain-Chatchat/
### WeChat Group
-
+
### WeChat Official Account
diff --git a/configs/model_config.py.example b/configs/model_config.py.example
index be1f4d18..d7053564 100644
--- a/configs/model_config.py.example
+++ b/configs/model_config.py.example
@@ -120,7 +120,7 @@ ONLINE_LLM_MODEL = {
"secret_key": "",
"provider": "TianGongWorker",
},
- # Gemini API (开发组未测试，由社群提供，只支持pro）
+ # Gemini API https://makersuite.google.com/app/apikey
"gemini-api": {
"api_key": "",
"provider": "GeminiWorker",
diff --git a/configs/server_config.py.example b/configs/server_config.py.example
index 2f51c3ad..09b1546b 100644
--- a/configs/server_config.py.example
+++ b/configs/server_config.py.example
@@ -92,11 +92,10 @@ FSCHAT_MODEL_WORKERS = {
# 'disable_log_requests': False
},
- # 可以如下示例方式更改默认配置
- # "Qwen-1_8B-Chat": { # 使用default中的IP和端口
- # "device": "cpu",
- # },
- "chatglm3-6b": { # 使用default中的IP和端口
+ "Qwen-1_8B-Chat": {
+ "device": "cpu",
+ },
+ "chatglm3-6b": {
"device": "cuda",
},
@@ -129,16 +128,10 @@ FSCHAT_MODEL_WORKERS = {
"port": 21009,
},
"gemini-api": {
- "port": 21012,
+ "port": 21010,
},
}
-# fastchat multi model worker server
-FSCHAT_MULTI_MODEL_WORKERS = {
- # TODO:
-}
-
-# fastchat controller server
FSCHAT_CONTROLLER = {
"host": DEFAULT_BIND_HOST,
"port": 20001,
diff --git a/document_loaders/mypdfloader.py b/document_loaders/mypdfloader.py
index 5c480cff..faaf63dd 100644
--- a/document_loaders/mypdfloader.py
+++ b/document_loaders/mypdfloader.py
@@ -16,11 +16,8 @@ class RapidOCRPDFLoader(UnstructuredFileLoader):
b_unit = tqdm.tqdm(total=doc.page_count, desc="RapidOCRPDFLoader context page index: 0")
for i, page in enumerate(doc):
- # 更新描述
b_unit.set_description("RapidOCRPDFLoader context page index: {}".format(i))
- # 立即显示进度条更新结果
b_unit.refresh()
- # TODO: 依据文本与图片顺序调整处理方式
text = page.get_text("")
resp += text + "\n"
diff --git a/img/qr_code_85.jpg b/img/qr_code_85.jpg
deleted file mode 100644
index d294f22f..00000000
Binary files a/img/qr_code_85.jpg and /dev/null differ
diff --git a/img/qr_code_87.jpg b/img/qr_code_87.jpg
new file mode 100644
index 00000000..ce8fc77a
Binary files /dev/null and b/img/qr_code_87.jpg differ
diff --git a/requirements.txt b/requirements.txt
index 3484ba4e..4307ab9d 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,79 +1,61 @@
-# API requirements
-
torch~=2.1.2
torchvision~=0.16.2
torchaudio~=2.1.2
-xformers==0.0.23.post1
-transformers==4.36.2
-sentence_transformers==2.2.2
-
+xformers~=0.0.23.post1
+transformers~=4.36.2
+sentence_transformers~=2.2.2
langchain==0.0.354
langchain-experimental==0.0.47
pydantic==1.10.13
-fschat==0.2.35
-openai~=1.7.1
-fastapi~=0.108.0
-sse_starlette==1.8.2
-nltk>=3.8.1
-uvicorn>=0.24.0.post1
+fschat~=0.2.35
+openai~=1.9.0
+fastapi~=0.109.0
+sse_starlette~=1.8.2
+nltk~=3.8.1
+uvicorn~=0.24.0.post1
starlette~=0.32.0
-unstructured[all-docs]==0.11.0
-python-magic-bin; sys_platform == 'win32'
-SQLAlchemy==2.0.19
-faiss-cpu~=1.7.4 # `conda install faiss-gpu -c conda-forge` if you want to accelerate with gpus
+unstructured[all-docs]~=0.12.0
+python-magic-bin; sys_platform ~= 'win32'
+SQLAlchemy~=2.0.25
+faiss-cpu~=1.7.4
accelerate~=0.24.1
spacy~=3.7.2
-PyMuPDF~=1.23.8
-rapidocr_onnxruntime==1.3.8
+PyMuPDF~=1.23.16
+rapidocr_onnxruntime~=1.3.8
requests~=2.31.0
pathlib~=1.0.1
pytest~=7.4.3
-numexpr~=2.8.6 # max version for py38
+numexpr~=2.8.6
strsimpy~=0.2.1
markdownify~=0.11.6
tiktoken~=0.5.2
-tqdm>=4.66.1
-websockets>=12.0
+tqdm~=4.66.1
+websockets~=12.0
numpy~=1.24.4
pandas~=2.0.3
-einops>=0.7.0
-transformers_stream_generator==0.0.4
-vllm==0.2.7; sys_platform == "linux"
-
-# flash-attn>=2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat
-
-
-# optional document loaders
-
-#rapidocr_paddle[gpu]>=1.3.0.post5 # gpu accelleration for ocr of pdf and image files
-jq==1.6.0 # for .json and .jsonl files. suggest `conda install jq` on windows
-beautifulsoup4~=4.12.2 # for .mhtml files
+einops~=0.7.0
+transformers_stream_generator~=0.0.4
+vllm~=0.2.7; sys_platform ~= "linux"
+jq~=1.6.0
+beautifulsoup4~=4.12.2
pysrt~=1.1.2
-
-# Online api libs dependencies
-# zhipuAI sdk is not supported on our platform, so use http instead
-dashscope==1.13.6 # qwen
-# volcengine>=1.0.119 # fangzhou
-
+dashscope~=1.13.6 # qwen
+# volcengine~=1.0.119 # fangzhou
# uncomment libs if you want to use corresponding vector store
-# pymilvus>=2.3.4
-# psycopg2==2.9.9
-# pgvector>=0.2.4
-
-# Agent and Search Tools
-
+# pymilvus~=2.3.4
+# psycopg2~=2.9.9
+# pgvector~=0.2.4
+# flash-attn~=2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat
+#rapidocr_paddle[gpu]~=1.3.0.post5 # gpu accelleration for ocr of pdf and image files
arxiv~=2.1.0
youtube-search~=2.1.2
duckduckgo-search~=3.9.9
metaphor-python~=0.1.23
-
-# WebUI requirements
-
-streamlit==1.30.0
-streamlit-option-menu==0.3.6
-streamlit-antd-components==0.3.1
-streamlit-chatbox==1.1.11
-streamlit-modal==0.1.0
-streamlit-aggrid==0.3.4.post3
-httpx==0.26.0
-watchdog==3.0.0
\ No newline at end of file
+streamlit~=1.30.0
+streamlit-option-menu~=0.3.12
+streamlit-antd-components~=0.3.1
+streamlit-chatbox~=1.1.11
+streamlit-modal~=0.1.0
+streamlit-aggrid~=0.3.4.post3
+httpx~=0.26.0
+watchdog~=3.0.0
\ No newline at end of file
diff --git a/requirements_api.txt b/requirements_api.txt
index e126c8c5..81660dae 100644
--- a/requirements_api.txt
+++ b/requirements_api.txt
@@ -1,15 +1,14 @@
torch~=2.1.2
torchvision~=0.16.2
torchaudio~=2.1.2
-xformers==0.0.23.post1
+xformers>=0.0.23.post1
transformers==4.36.2
sentence_transformers==2.2.2
-
langchain==0.0.354
langchain-experimental==0.0.47
pydantic==1.10.13
fschat==0.2.35
-openai~=1.7.1
+openai~=1.9.0
fastapi~=0.108.0
sse_starlette==1.8.2
nltk>=3.8.1
@@ -18,7 +17,7 @@ starlette~=0.32.0
unstructured[all-docs]==0.11.0
python-magic-bin; sys_platform == 'win32'
SQLAlchemy==2.0.19
-faiss-cpu~=1.7.4 # `conda install faiss-gpu -c conda-forge` if you want to accelerate with gpus
+faiss-cpu~=1.7.4
accelerate~=0.24.1
spacy~=3.7.2
PyMuPDF~=1.23.8
@@ -26,7 +25,7 @@ rapidocr_onnxruntime==1.3.8
requests~=2.31.0
pathlib~=1.0.1
pytest~=7.4.3
-numexpr~=2.8.6 # max version for py38
+numexpr~=2.8.6
strsimpy~=0.2.1
markdownify~=0.11.6
tiktoken~=0.5.2
@@ -39,29 +38,18 @@ transformers_stream_generator==0.0.4
vllm==0.2.7; sys_platform == "linux"
httpx==0.26.0
llama-index
-# flash-attn>=2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat
-
-# optional document loaders
-
-# rapidocr_paddle[gpu]>=1.3.0.post5 # gpu accelleration for ocr of pdf and image files
-jq==1.6.0 # for .json and .jsonl files. suggest `conda install jq` on windows
-beautifulsoup4~=4.12.2 # for .mhtml files
+jq==1.6.0
+beautifulsoup4~=4.12.2
pysrt~=1.1.2
-
-# Online api libs dependencies
-
-# zhipuAI sdk is not supported on our platform, so use http instead
-dashscope==1.13.6 # qwen
-# volcengine>=1.0.119 # fangzhou
-
-# uncomment libs if you want to use corresponding vector store
-# pymilvus>=2.3.4
-# psycopg2==2.9.9
-# pgvector>=0.2.4
-
-# Agent and Search Tools
-
+dashscope==1.13.6
arxiv~=2.1.0
youtube-search~=2.1.2
duckduckgo-search~=3.9.9
-metaphor-python~=0.1.23
\ No newline at end of file
+metaphor-python~=0.1.23
+
+# volcengine>=1.0.119
+# pymilvus>=2.3.4
+# psycopg2==2.9.9
+# pgvector>=0.2.4
+# flash-attn>=2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat
+# rapidocr_paddle[gpu]>=1.3.0.post5
\ No newline at end of file
diff --git a/requirements_lite.txt b/requirements_lite.txt
index 4274b649..5a0ace76 100644
--- a/requirements_lite.txt
+++ b/requirements_lite.txt
@@ -1,64 +1,32 @@
-# API requirements
-
langchain==0.0.354
langchain-experimental==0.0.47
pydantic==1.10.13
-fschat==0.2.35
-openai~=1.7.1
-fastapi~=0.108.0
-sse_starlette==1.8.2
-nltk>=3.8.1
-uvicorn>=0.24.0.post1
+fschat~=0.2.35
+openai~=1.9.0
+fastapi~=0.109.0
+sse_starlette~=1.8.2
+nltk~=3.8.1
+uvicorn~=0.24.0.post1
starlette~=0.32.0
-unstructured[all-docs]==0.11.0
-python-magic-bin; sys_platform == 'win32'
-SQLAlchemy==2.0.19
+unstructured[all-docs]~=0.12.0
+python-magic-bin; sys_platform ~= 'win32'
+SQLAlchemy~=2.0.25
faiss-cpu~=1.7.4
+accelerate~=0.24.1
+spacy~=3.7.2
+PyMuPDF~=1.23.16
+rapidocr_onnxruntime~=1.3.8
requests~=2.31.0
pathlib~=1.0.1
pytest~=7.4.3
-numexpr~=2.8.6 # max version for py38
-strsimpy~=0.2.1
-markdownify~=0.11.6
-tiktoken~=0.5.2
-tqdm>=4.66.1
-websockets>=12.0
-numpy~=1.24.4
-pandas~=2.0.3
-einops>=0.7.0
-transformers_stream_generator==0.0.4
-vllm==0.2.7; sys_platform == "linux"
-httpx[brotli,http2,socks]==0.25.2
-requests
-pathlib
-pytest
-
-
-# Online api libs dependencies
-
-# zhipuAI sdk is not supported on our platform, so use http instead
dashscope==1.13.6
-# volcengine>=1.0.119
-
-# uncomment libs if you want to use corresponding vector store
-# pymilvus>=2.3.4
-# psycopg2==2.9.9
-# pgvector>=0.2.4
-
-# Agent and Search Tools
-
arxiv~=2.1.0
youtube-search~=2.1.2
duckduckgo-search~=3.9.9
metaphor-python~=0.1.23
-
-# WebUI requirements
-
-streamlit==1.30.0
-streamlit-option-menu==0.3.6
-streamlit-antd-components==0.3.1
-streamlit-chatbox==1.1.11
-streamlit-modal==0.1.0
-streamlit-aggrid==0.3.4.post3
-httpx==0.26.0
-watchdog==3.0.0
\ No newline at end of file
+watchdog~=3.0.0
+# volcengine>=1.0.119
+# pymilvus>=2.3.4
+# psycopg2==2.9.9
+# pgvector>=0.2.4
+# flash-attn>=2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat
\ No newline at end of file
diff --git a/requirements_webui.txt b/requirements_webui.txt
index 111dedaa..9dae4620 100644
--- a/requirements_webui.txt
+++ b/requirements_webui.txt
@@ -1,10 +1,8 @@
-# WebUI requirements
-
-streamlit==1.30.0
-streamlit-option-menu==0.3.6
-streamlit-antd-components==0.3.1
-streamlit-chatbox==1.1.11
-streamlit-modal==0.1.0
-streamlit-aggrid==0.3.4.post3
-httpx==0.26.0
-watchdog==3.0.0
\ No newline at end of file
+streamlit~=1.30.0
+streamlit-option-menu~=0.3.12
+streamlit-antd-components~=0.3.1
+streamlit-chatbox~=1.1.11
+streamlit-modal~=0.1.0
+streamlit-aggrid~=0.3.4.post3
+httpx~=0.26.0
+watchdog~=3.0.0
\ No newline at end of file
diff --git a/server/embeddings_api.py b/server/embeddings_api.py
index 440bb774..e907de07 100644
--- a/server/embeddings_api.py
+++ b/server/embeddings_api.py
@@ -16,7 +16,6 @@ def embed_texts(
) -> BaseResponse:
'''
对文本进行向量化。返回数据格式：BaseResponse(data=List[List[float]])
- TODO: 也许需要加入缓存机制，减少 token 消耗
'''
try:
if embed_model in list_embed_models(): # 使用本地Embeddings模型
diff --git a/server/knowledge_base/kb_api.py b/server/knowledge_base/kb_api.py
index f50d8a73..0d2fbce9 100644
--- a/server/knowledge_base/kb_api.py
+++ b/server/knowledge_base/kb_api.py
@@ -13,9 +13,9 @@ def list_kbs():
def create_kb(knowledge_base_name: str = Body(..., examples=["samples"]),
- vector_store_type: str = Body("faiss"),
- embed_model: str = Body(EMBEDDING_MODEL),
- ) -> BaseResponse:
+ vector_store_type: str = Body("faiss"),
+ embed_model: str = Body(EMBEDDING_MODEL),
+ ) -> BaseResponse:
# Create selected knowledge base
if not validate_kb_name(knowledge_base_name):
return BaseResponse(code=403, msg="Don't attack me")
@@ -39,8 +39,8 @@ def create_kb(knowledge_base_name: str = Body(..., examples=["samples"]),
def delete_kb(
- knowledge_base_name: str = Body(..., examples=["samples"])
- ) -> BaseResponse:
+ knowledge_base_name: str = Body(..., examples=["samples"])
+) -> BaseResponse:
# Delete selected knowledge base
if not validate_kb_name(knowledge_base_name):
return BaseResponse(code=403, msg="Don't attack me")
diff --git a/server/knowledge_base/kb_cache/faiss_cache.py b/server/knowledge_base/kb_cache/faiss_cache.py
index ed48b5dd..60c550ee 100644
--- a/server/knowledge_base/kb_cache/faiss_cache.py
+++ b/server/knowledge_base/kb_cache/faiss_cache.py
@@ -55,8 +55,6 @@ class _FaissPool(CachePool):
embed_model: str = EMBEDDING_MODEL,
embed_device: str = embedding_device(),
) -> FAISS:
- # TODO: 整个Embeddings加载逻辑有些混乱，待清理
- # create an empty vector store
embeddings = EmbeddingsFunAdapter(embed_model)
doc = Document(page_content="init", metadata={})
vector_store = FAISS.from_documents([doc], embeddings, normalize_L2=True,distance_strategy="METRIC_INNER_PRODUCT")
diff --git a/server/knowledge_base/kb_doc_api.py b/server/knowledge_base/kb_doc_api.py
index 09a264f9..e58ea41f 100644
--- a/server/knowledge_base/kb_doc_api.py
+++ b/server/knowledge_base/kb_doc_api.py
@@ -95,7 +95,6 @@ def _save_files_in_thread(files: List[UploadFile],
and not override
and os.path.getsize(file_path) == len(file_content)
):
- # TODO: filesize 不同后的处理
file_status = f"文件 {filename} 已存在。"
logger.warn(file_status)
return dict(code=404, msg=file_status, data=data)
@@ -116,7 +115,6 @@ def _save_files_in_thread(files: List[UploadFile],
yield result
-# TODO: 等langchain.document_loaders支持内存文件的时候再开通
# def files2docs(files: List[UploadFile] = File(..., description="上传文件，支持多文件"),
# knowledge_base_name: str = Form(..., description="知识库名称", examples=["samples"]),
# override: bool = Form(False, description="覆盖已有文件"),
diff --git a/server/knowledge_base/kb_service/base.py b/server/knowledge_base/kb_service/base.py
index 44c0d64e..bd5a54eb 100644
--- a/server/knowledge_base/kb_service/base.py
+++ b/server/knowledge_base/kb_service/base.py
@@ -191,7 +191,6 @@ class KBService(ABC):
'''
传入参数为： {doc_id: Document, ...}
如果对应 doc_id 的值为 None，或其 page_content 为空，则删除该文档
- TODO：是否要支持新增 docs ？
'''
self.del_doc_by_ids(list(docs.keys()))
docs = []
diff --git a/server/knowledge_base/kb_service/milvus_kb_service.py b/server/knowledge_base/kb_service/milvus_kb_service.py
index 32382929..43b616e2 100644
--- a/server/knowledge_base/kb_service/milvus_kb_service.py
+++ b/server/knowledge_base/kb_service/milvus_kb_service.py
@@ -70,7 +70,6 @@ class MilvusKBService(KBService):
return score_threshold_process(score_threshold, top_k, docs)
def do_add_doc(self, docs: List[Document], **kwargs) -> List[Dict]:
- # TODO: workaround for bug #10492 in langchain
for doc in docs:
for k, v in doc.metadata.items():
doc.metadata[k] = str(v)
diff --git a/server/knowledge_base/kb_service/pg_kb_service.py b/server/knowledge_base/kb_service/pg_kb_service.py
index ec0e147b..46efe7d8 100644
--- a/server/knowledge_base/kb_service/pg_kb_service.py
+++ b/server/knowledge_base/kb_service/pg_kb_service.py
@@ -32,8 +32,6 @@ class PGKBService(KBService):
results = [Document(page_content=row[0], metadata=row[1]) for row in
session.execute(stmt, {'ids': ids}).fetchall()]
return results
-
- # TODO:
def del_doc_by_ids(self, ids: List[str]) -> bool:
return super().del_doc_by_ids(ids)
diff --git a/server/knowledge_base/kb_summary/base.py b/server/knowledge_base/kb_summary/base.py
index 00dcea6f..6d095fee 100644
--- a/server/knowledge_base/kb_summary/base.py
+++ b/server/knowledge_base/kb_summary/base.py
@@ -13,7 +13,6 @@ from server.db.repository.knowledge_metadata_repository import add_summary_to_db
from langchain.docstore.document import Document
-# TODO 暂不考虑文件更新，需要重新删除相关文档，再重新添加
class KBSummaryService(ABC):
kb_name: str
embed_model: str
diff --git a/server/knowledge_base/kb_summary/summary_chunk.py b/server/knowledge_base/kb_summary/summary_chunk.py
index 0b88f233..7c2aaf47 100644
--- a/server/knowledge_base/kb_summary/summary_chunk.py
+++ b/server/knowledge_base/kb_summary/summary_chunk.py
@@ -112,12 +112,6 @@ class SummaryAdapter:
docs: List[DocumentWithVSId] = []) -> List[Document]:
logger.info("start summary")
- # TODO 暂不处理文档中涉及语义重复、上下文缺失、document was longer than the context length 的问题
- # merge_docs = self._drop_overlap(docs)
- # # 将merge_docs中的句子合并成一个文档
- # text = self._join_docs(merge_docs)
- # 根据段落于句子的分隔符，将文档分成chunk，每个chunk长度小于token_max长度
-
"""
这个过程分成两个部分：
1. 对每个文档进行处理，得到每个文档的摘要
diff --git a/server/knowledge_base/utils.py b/server/knowledge_base/utils.py
index 6064477a..3a8c701b 100644
--- a/server/knowledge_base/utils.py
+++ b/server/knowledge_base/utils.py
@@ -174,7 +174,6 @@ def get_loader(loader_name: str, file_path: str, loader_kwargs: Dict = None):
if encode_detect is None:
encode_detect = {"encoding": "utf-8"}
loader_kwargs["encoding"] = encode_detect["encoding"]
- ## TODO：支持更多的自定义CSV读取逻辑
elif loader_name == "JSONLoader":
loader_kwargs.setdefault("jq_schema", ".")
diff --git a/server/model_workers/azure.py b/server/model_workers/azure.py
index 70959325..f0835ae1 100644
--- a/server/model_workers/azure.py
+++ b/server/model_workers/azure.py
@@ -67,12 +67,10 @@ class AzureWorker(ApiModelWorker):
self.logger.error(f"请求 Azure API 时发生错误：{resp}")
def get_embeddings(self, params):
- # TODO: 支持embeddings
print("embedding")
print(params)
def make_conv_template(self, conv_template: str = None, model_path: str = None) -> Conversation:
- # TODO: 确认模板是否需要修改
return conv.Conversation(
name=self.model_names[0],
system_message="You are a helpful, respectful and honest assistant.",
diff --git a/server/model_workers/baichuan.py b/server/model_workers/baichuan.py
index 5e9cbbb0..75cfad4e 100644
--- a/server/model_workers/baichuan.py
+++ b/server/model_workers/baichuan.py
@@ -88,12 +88,10 @@ class BaiChuanWorker(ApiModelWorker):
yield data
def get_embeddings(self, params):
- # TODO: 支持embeddings
print("embedding")
print(params)
def make_conv_template(self, conv_template: str = None, model_path: str = None) -> Conversation:
- # TODO: 确认模板是否需要修改
return conv.Conversation(
name=self.model_names[0],
system_message="",
diff --git a/server/model_workers/base.py b/server/model_workers/base.py
index 88affb43..234ab47a 100644
--- a/server/model_workers/base.py
+++ b/server/model_workers/base.py
@@ -125,8 +125,6 @@ class ApiModelWorker(BaseModelWorker):
def count_token(self, params):
- # TODO：需要完善
- # print("count token")
prompt = params["prompt"]
return {"count": len(str(prompt)), "error_code": 0}
diff --git a/server/model_workers/fangzhou.py b/server/model_workers/fangzhou.py
index ddbad4ab..fdb50a1c 100644
--- a/server/model_workers/fangzhou.py
+++ b/server/model_workers/fangzhou.py
@@ -12,16 +12,16 @@ class FangZhouWorker(ApiModelWorker):
"""
def __init__(
- self,
- *,
- model_names: List[str] = ["fangzhou-api"],
- controller_addr: str = None,
- worker_addr: str = None,
- version: Literal["chatglm-6b-model"] = "chatglm-6b-model",
- **kwargs,
+ self,
+ *,
+ model_names: List[str] = ["fangzhou-api"],
+ controller_addr: str = None,
+ worker_addr: str = None,
+ version: Literal["chatglm-6b-model"] = "chatglm-6b-model",
+ **kwargs,
):
kwargs.update(model_names=model_names, controller_addr=controller_addr, worker_addr=worker_addr)
- kwargs.setdefault("context_len", 16384) # TODO: 不同的模型有不同的大小
+ kwargs.setdefault("context_len", 16384)
super().__init__(**kwargs)
self.version = version
@@ -53,15 +53,15 @@ class FangZhouWorker(ApiModelWorker):
if error := resp.error:
if error.code_n > 0:
data = {
- "error_code": error.code_n,
- "text": error.message,
- "error": {
- "message": error.message,
- "type": "invalid_request_error",
- "param": None,
- "code": None,
- }
+ "error_code": error.code_n,
+ "text": error.message,
+ "error": {
+ "message": error.message,
+ "type": "invalid_request_error",
+ "param": None,
+ "code": None,
}
+ }
self.logger.error(f"请求方舟 API 时发生错误：{data}")
yield data
elif chunk := resp.choice.message.content:
@@ -77,7 +77,6 @@ class FangZhouWorker(ApiModelWorker):
break
def get_embeddings(self, params):
- # TODO: 支持embeddings
print("embedding")
print(params)
diff --git a/server/model_workers/gemini.py b/server/model_workers/gemini.py
index 0cd8e159..e9175b6e 100644
--- a/server/model_workers/gemini.py
+++ b/server/model_workers/gemini.py
@@ -3,7 +3,7 @@ from fastchat.conversation import Conversation
from server.model_workers.base import *
from server.utils import get_httpx_client
from fastchat import conversation as conv
-import json,httpx
+import json, httpx
from typing import List, Dict
from configs import logger, log_verbose
@@ -14,14 +14,14 @@ class GeminiWorker(ApiModelWorker):
*,
controller_addr: str = None,
worker_addr: str = None,
- model_names: List[str] = ["Gemini-api"],
+ model_names: List[str] = ["gemini-api"],
**kwargs,
):
kwargs.update(model_names=model_names, controller_addr=controller_addr, worker_addr=worker_addr)
kwargs.setdefault("context_len", 4096)
super().__init__(**kwargs)
- def create_gemini_messages(self,messages) -> json:
+ def create_gemini_messages(self, messages) -> json:
has_history = any(msg['role'] == 'assistant' for msg in messages)
gemini_msg = []
@@ -42,11 +42,11 @@ class GeminiWorker(ApiModelWorker):
msg = dict(contents=gemini_msg)
return msg
-
+
def do_chat(self, params: ApiChatParams) -> Dict:
params.load_config(self.model_names[0])
data = self.create_gemini_messages(messages=params.messages)
- generationConfig=dict(
+ generationConfig = dict(
temperature=params.temperature,
topK=1,
topP=1,
@@ -54,8 +54,8 @@ class GeminiWorker(ApiModelWorker):
stopSequences=[]
)
- data['generationConfig'] = generationConfig
- url = "https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateContent"+ '?key=' + params.api_key
+ data['generationConfig'] = generationConfig
+ url = "https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateContent" + '?key=' + params.api_key
headers = {
'Content-Type': 'application/json',
}
@@ -67,7 +67,7 @@ class GeminiWorker(ApiModelWorker):
text = ""
json_string = ""
timeout = httpx.Timeout(60.0)
- client=get_httpx_client(timeout=timeout)
+ client = get_httpx_client(timeout=timeout)
with client.stream("POST", url, headers=headers, json=data) as response:
for line in response.iter_lines():
line = line.strip()
@@ -89,13 +89,12 @@ class GeminiWorker(ApiModelWorker):
"error_code": 0,
"text": text
}
- print(text)
+ print(text)
except json.JSONDecodeError as e:
print("Failed to decode JSON:", e)
print("Invalid JSON string:", json_string)
def get_embeddings(self, params):
- # TODO: 支持embeddings
print("embedding")
print(params)
diff --git a/server/model_workers/minimax.py b/server/model_workers/minimax.py
index ba610d52..79d24514 100644
--- a/server/model_workers/minimax.py
+++ b/server/model_workers/minimax.py
@@ -37,7 +37,6 @@ class MiniMaxWorker(ApiModelWorker):
def do_chat(self, params: ApiChatParams) -> Dict:
# 按照官网推荐，直接调用abab 5.5模型
- # TODO: 支持指定回复要求，支持指定用户名称、AI名称
params.load_config(self.model_names[0])
url = 'https://api.minimax.chat/v1/text/chatcompletion{pro}?GroupId={group_id}'
@@ -55,7 +54,7 @@ class MiniMaxWorker(ApiModelWorker):
"temperature": params.temperature,
"top_p": params.top_p,
"tokens_to_generate": params.max_tokens or 1024,
- # TODO: 以下参数为minimax特有，传入空值会出错。
+ # 以下参数为minimax特有，传入空值会出错。
# "prompt": params.system_message or self.conv.system_message,
# "bot_setting": [],
# "role_meta": params.role_meta,
@@ -143,12 +142,10 @@ class MiniMaxWorker(ApiModelWorker):
return {"code": 200, "data": result}
def get_embeddings(self, params):
- # TODO: 支持embeddings
print("embedding")
print(params)
def make_conv_template(self, conv_template: str = None, model_path: str = None) -> Conversation:
- # TODO: 确认模板是否需要修改
return conv.Conversation(
name=self.model_names[0],
system_message="你是MiniMax自主研发的大型语言模型，回答问题简洁有条理。",
diff --git a/server/model_workers/qianfan.py b/server/model_workers/qianfan.py
index 7dd3a355..da362ec6 100644
--- a/server/model_workers/qianfan.py
+++ b/server/model_workers/qianfan.py
@@ -187,14 +187,11 @@ class QianFanWorker(ApiModelWorker):
i += batch_size
return {"code": 200, "data": result}
- # TODO: qianfan支持续写模型
def get_embeddings(self, params):
- # TODO: 支持embeddings
print("embedding")
print(params)
def make_conv_template(self, conv_template: str = None, model_path: str = None) -> Conversation:
- # TODO: 确认模板是否需要修改
return conv.Conversation(
name=self.model_names[0],
system_message="你是一个聪明的助手，请根据用户的提示来完成任务",
diff --git a/server/model_workers/qwen.py b/server/model_workers/qwen.py
index 58d1bcd1..2741b74d 100644
--- a/server/model_workers/qwen.py
+++ b/server/model_workers/qwen.py
@@ -100,12 +100,10 @@ class QwenWorker(ApiModelWorker):
return {"code": 200, "data": result}
def get_embeddings(self, params):
- # TODO: 支持embeddings
print("embedding")
print(params)
def make_conv_template(self, conv_template: str = None, model_path: str = None) -> Conversation:
- # TODO: 确认模板是否需要修改
return conv.Conversation(
name=self.model_names[0],
system_message="你是一个聪明、对人类有帮助的人工智能，你可以对人类提出的问题给出有用、详细、礼貌的回答。",
diff --git a/server/model_workers/tiangong.py b/server/model_workers/tiangong.py
index e127ea55..88010a15 100644
--- a/server/model_workers/tiangong.py
+++ b/server/model_workers/tiangong.py
@@ -70,12 +70,10 @@ class TianGongWorker(ApiModelWorker):
yield data
def get_embeddings(self, params):
- # TODO: 支持embeddings
print("embedding")
print(params)
def make_conv_template(self, conv_template: str = None, model_path: str = None) -> Conversation:
- # TODO: 确认模板是否需要修改
return conv.Conversation(
name=self.model_names[0],
system_message="",
diff --git a/server/model_workers/xinghuo.py b/server/model_workers/xinghuo.py
index 1e772a33..de38308b 100644
--- a/server/model_workers/xinghuo.py
+++ b/server/model_workers/xinghuo.py
@@ -42,7 +42,6 @@ class XingHuoWorker(ApiModelWorker):
self.version = version
def do_chat(self, params: ApiChatParams) -> Dict:
- # TODO: 当前每次对话都要重新连接websocket，确认是否可以保持连接
params.load_config(self.model_names[0])
version_mapping = {
@@ -73,12 +72,10 @@ class XingHuoWorker(ApiModelWorker):
yield {"error_code": 0, "text": text}
def get_embeddings(self, params):
- # TODO: 支持embeddings
print("embedding")
print(params)
def make_conv_template(self, conv_template: str = None, model_path: str = None) -> Conversation:
- # TODO: 确认模板是否需要修改
return conv.Conversation(
name=self.model_names[0],
system_message="你是一个聪明的助手，请根据用户的提示来完成任务",
diff --git a/server/utils.py b/server/utils.py
index 26ef967e..7fed5f8c 100644
--- a/server/utils.py
+++ b/server/utils.py
@@ -36,7 +36,6 @@ async def wrap_done(fn: Awaitable, event: asyncio.Event):
await fn
except Exception as e:
logging.exception(e)
- # TODO: handle exception
msg = f"Caught exception: {e}"
logger.error(f'{e.__class__.__name__}: {msg}',
exc_info=e if log_verbose else None)
@@ -404,7 +403,7 @@ def fschat_controller_address() -> str:
def fschat_model_worker_address(model_name: str = LLM_MODELS[0]) -> str:
- if model := get_model_worker_config(model_name): # TODO: depends fastchat
+ if model := get_model_worker_config(model_name):
host = model["host"]
if host == "0.0.0.0":
host = "127.0.0.1"
@@ -449,7 +448,7 @@ def get_prompt_template(type: str, name: str) -> Optional[str]:
from configs import prompt_config
import importlib
- importlib.reload(prompt_config) # TODO: 检查configs/prompt_config.py文件有修改再重新加载
+ importlib.reload(prompt_config)
return prompt_config.PROMPT_TEMPLATES[type].get(name)
@@ -550,7 +549,7 @@ def run_in_thread_pool(
thread = pool.submit(func, **kwargs)
tasks.append(thread)
- for obj in as_completed(tasks): # TODO: Ctrl+c无法停止
+ for obj in as_completed(tasks):
yield obj.result()
diff --git a/startup.py b/startup.py
index 0681dcda..359fb709 100644
--- a/startup.py
+++ b/startup.py
@@ -418,7 +418,7 @@ def run_openai_api(log_level: str = "INFO", started_event: mp.Event = None):
set_httpx_config()
controller_addr = fschat_controller_address()
- app = create_openai_api_app(controller_addr, log_level=log_level) # TODO: not support keys yet.
+ app = create_openai_api_app(controller_addr, log_level=log_level)
_set_app_event(app, started_event)
host = FSCHAT_OPENAI_API["host"]
diff --git a/webui_pages/dialogue/dialogue.py b/webui_pages/dialogue/dialogue.py
index 325cd5d1..b9d2f7fd 100644
--- a/webui_pages/dialogue/dialogue.py
+++ b/webui_pages/dialogue/dialogue.py
@@ -12,7 +12,6 @@ from server.knowledge_base.utils import LOADER_DICT
import uuid
from typing import List, Dict
-
chat_box = ChatBox(
assistant_avatar=os.path.join(
"img",
@@ -127,7 +126,6 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
chat_box.use_chat_name(conversation_name)
conversation_id = st.session_state["conversation_ids"][conversation_name]
- # TODO: 对话模型与会话绑定
def on_mode_change():
mode = st.session_state.dialogue_mode
text = f"已切换到 {mode} 模式。"
@@ -138,11 +136,11 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
st.toast(text)
dialogue_modes = ["LLM 对话",
- "知识库问答",
- "文件对话",
- "搜索引擎问答",
- "自定义Agent问答",
- ]
+ "知识库问答",
+ "文件对话",
+ "搜索引擎问答",
+ "自定义Agent问答",
+ ]
dialogue_mode = st.selectbox("请选择对话模式：",
dialogue_modes,
index=0,
@@ -166,9 +164,9 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
available_models = []
config_models = api.list_config_models()
if not is_lite:
- for k, v in config_models.get("local", {}).items(): # 列出配置了有效本地路径的模型
+ for k, v in config_models.get("local", {}).items(): # 列出配置了有效本地路径的模型
if (v.get("model_path_exists")
- and k not in running_models):
+ and k not in running_models):
available_models.append(k)
for k, v in config_models.get("online", {}).items(): # 列出ONLINE_MODELS中直接访问的模型
if not v.get("provider") and k not in running_models:
@@ -250,14 +248,14 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
elif dialogue_mode == "文件对话":
with st.expander("文件对话配置", True):
files = st.file_uploader("上传知识文件：",
- [i for ls in LOADER_DICT.values() for i in ls],
- accept_multiple_files=True,
- )
+ [i for ls in LOADER_DICT.values() for i in ls],
+ accept_multiple_files=True,
+ )
kb_top_k = st.number_input("匹配知识条数：", 1, 20, VECTOR_SEARCH_TOP_K)
## Bge 模型会超过1
score_threshold = st.slider("知识匹配分数阈值：", 0.0, 2.0, float(SCORE_THRESHOLD), 0.01)
- if st.button("开始上传", disabled=len(files)==0):
+ if st.button("开始上传", disabled=len(files) == 0):
st.session_state["file_chat_id"] = upload_temp_docs(files, api)
elif dialogue_mode == "搜索引擎问答":
search_engine_list = api.list_search_engines()
@@ -279,9 +277,9 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
chat_input_placeholder = "请输入对话内容，换行请使用Shift+Enter。输入/help查看自定义命令 "
def on_feedback(
- feedback,
- message_id: str = "",
- history_index: int = -1,
+ feedback,
+ message_id: str = "",
+ history_index: int = -1,
):
reason = feedback["text"]
score_int = chat_box.set_feedback(feedback=feedback, history_index=history_index)
@@ -296,7 +294,7 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
}
if prompt := st.chat_input(chat_input_placeholder, key="prompt"):
- if parse_command(text=prompt, modal=modal): # 用户输入自定义命令
+ if parse_command(text=prompt, modal=modal): # 用户输入自定义命令
st.rerun()
else:
history = get_messages_history(history_len)
@@ -306,11 +304,11 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
text = ""
message_id = ""
r = api.chat_chat(prompt,
- history=history,
- conversation_id=conversation_id,
- model=llm_model,
- prompt_name=prompt_template_name,
- temperature=temperature)
+ history=history,
+ conversation_id=conversation_id,
+ model=llm_model,
+ prompt_name=prompt_template_name,
+ temperature=temperature)
for t in r:
if error_msg := check_error_msg(t): # check whether error occured
st.error(error_msg)
@@ -321,12 +319,12 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
metadata = {
"message_id": message_id,
- }
+ }
chat_box.update_msg(text, streaming=False, metadata=metadata) # 更新最终的字符串，去除光标
chat_box.show_feedback(**feedback_kwargs,
- key=message_id,
- on_submit=on_feedback,
- kwargs={"message_id": message_id, "history_index": len(chat_box.history) - 1})
+ key=message_id,
+ on_submit=on_feedback,
+ kwargs={"message_id": message_id, "history_index": len(chat_box.history) - 1})
elif dialogue_mode == "自定义Agent问答":
if not any(agent in llm_model for agent in SUPPORT_AGENT_MODEL):
@@ -373,13 +371,13 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
])
text = ""
for d in api.knowledge_base_chat(prompt,
- knowledge_base_name=selected_kb,
- top_k=kb_top_k,
- score_threshold=score_threshold,
- history=history,
- model=llm_model,
- prompt_name=prompt_template_name,
- temperature=temperature):
+ knowledge_base_name=selected_kb,
+ top_k=kb_top_k,
+ score_threshold=score_threshold,
+ history=history,
+ model=llm_model,
+ prompt_name=prompt_template_name,
+ temperature=temperature):
if error_msg := check_error_msg(d): # check whether error occured
st.error(error_msg)
elif chunk := d.get("answer"):
@@ -397,13 +395,13 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
])
text = ""
for d in api.file_chat(prompt,
- knowledge_id=st.session_state["file_chat_id"],
- top_k=kb_top_k,
- score_threshold=score_threshold,
- history=history,
- model=llm_model,
- prompt_name=prompt_template_name,
- temperature=temperature):
+ knowledge_id=st.session_state["file_chat_id"],
+ top_k=kb_top_k,
+ score_threshold=score_threshold,
+ history=history,
+ model=llm_model,
+ prompt_name=prompt_template_name,
+ temperature=temperature):
if error_msg := check_error_msg(d): # check whether error occured
st.error(error_msg)
elif chunk := d.get("answer"):
@@ -455,4 +453,4 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
file_name=f"{now:%Y-%m-%d %H.%M}_对话记录.md",
mime="text/markdown",
use_container_width=True,
- )
\ No newline at end of file
+ )
diff --git a/webui_pages/knowledge_base/knowledge_base.py b/webui_pages/knowledge_base/knowledge_base.py
index 31fc1512..76a97377 100644
--- a/webui_pages/knowledge_base/knowledge_base.py
+++ b/webui_pages/knowledge_base/knowledge_base.py
@@ -7,15 +7,12 @@ from server.knowledge_base.utils import get_file_path, LOADER_DICT
from server.knowledge_base.kb_service.base import get_kb_details, get_kb_file_details
from typing import Literal, Dict, Tuple
from configs import (kbs_config,
- EMBEDDING_MODEL, DEFAULT_VS_TYPE,
- CHUNK_SIZE, OVERLAP_SIZE, ZH_TITLE_ENHANCE)
+ EMBEDDING_MODEL, DEFAULT_VS_TYPE,
+ CHUNK_SIZE, OVERLAP_SIZE, ZH_TITLE_ENHANCE)
from server.utils import list_embed_models, list_online_embed_models
import os
import time
-
-# SENTENCE_SIZE = 100
-
cell_renderer = JsCode("""function(params) {if(params.value==true){return '✓'}else{return '×'}}""")
@@ -32,7 +29,7 @@ def config_aggrid(
gb.configure_selection(
selection_mode=selection_mode,
use_checkbox=use_checkbox,
- # pre_selected_rows=st.session_state.get("selected_rows", [0]),
+ pre_selected_rows=st.session_state.get("selected_rows", [0]),
)
gb.configure_pagination(
enabled=True,
@@ -59,7 +56,8 @@ def knowledge_base_page(api: ApiRequest, is_lite: bool = None):
try:
kb_list = {x["kb_name"]: x for x in get_kb_details()}
except Exception as e:
- st.error("获取知识库信息错误，请检查是否已按照 `README.md` 中 `4 知识库初始化与迁移` 步骤完成初始化或迁移，或是否为数据库连接错误。")
+ st.error(
+ "获取知识库信息错误，请检查是否已按照 `README.md` 中 `4 知识库初始化与迁移` 步骤完成初始化或迁移，或是否为数据库连接错误。")
st.stop()
kb_names = list(kb_list.keys())
@@ -150,7 +148,8 @@ def knowledge_base_page(api: ApiRequest, is_lite: bool = None):
[i for ls in LOADER_DICT.values() for i in ls],
accept_multiple_files=True,
)
- kb_info = st.text_area("请输入知识库介绍:", value=st.session_state["selected_kb_info"], max_chars=None, key=None,
+ kb_info = st.text_area("请输入知识库介绍:", value=st.session_state["selected_kb_info"], max_chars=None,
+ key=None,
help=None, on_change=None, args=None, kwargs=None)
if kb_info != st.session_state["selected_kb_info"]:
@@ -200,8 +199,8 @@ def knowledge_base_page(api: ApiRequest, is_lite: bool = None):
doc_details = doc_details[[
"No", "file_name", "document_loader", "text_splitter", "docs_count", "in_folder", "in_db",
]]
- # doc_details["in_folder"] = doc_details["in_folder"].replace(True, "✓").replace(False, "×")
- # doc_details["in_db"] = doc_details["in_db"].replace(True, "✓").replace(False, "×")
+ doc_details["in_folder"] = doc_details["in_folder"].replace(True, "✓").replace(False, "×")
+ doc_details["in_db"] = doc_details["in_db"].replace(True, "✓").replace(False, "×")
gb = config_aggrid(
doc_details,
{
@@ -252,7 +251,8 @@ def knowledge_base_page(api: ApiRequest, is_lite: bool = None):
st.write()
# 将文件分词并加载到向量库中
if cols[1].button(
- "重新添加至向量库" if selected_rows and (pd.DataFrame(selected_rows)["in_db"]).any() else "添加至向量库",
+ "重新添加至向量库" if selected_rows and (
+ pd.DataFrame(selected_rows)["in_db"]).any() else "添加至向量库",
disabled=not file_exists(kb, selected_rows)[0],
use_container_width=True,
):
@@ -285,39 +285,39 @@ def knowledge_base_page(api: ApiRequest, is_lite: bool = None):
st.divider()
- # cols = st.columns(3)
+ cols = st.columns(3)
- # if cols[0].button(
- # "依据源文件重建向量库",
- # # help="无需上传文件，通过其它方式将文档拷贝到对应知识库content目录下，点击本按钮即可重建知识库。",
- # use_container_width=True,
- # type="primary",
- # ):
- # with st.spinner("向量库重构中，请耐心等待，勿刷新或关闭页面。"):
- # empty = st.empty()
- # empty.progress(0.0, "")
- # for d in api.recreate_vector_store(kb,
- # chunk_size=chunk_size,
- # chunk_overlap=chunk_overlap,
- # zh_title_enhance=zh_title_enhance):
- # if msg := check_error_msg(d):
- # st.toast(msg)
- # else:
- # empty.progress(d["finished"] / d["total"], d["msg"])
- # st.rerun()
+ if cols[0].button(
+ "依据源文件重建向量库",
+ help="无需上传文件，通过其它方式将文档拷贝到对应知识库content目录下，点击本按钮即可重建知识库。",
+ use_container_width=True,
+ type="primary",
+ ):
+ with st.spinner("向量库重构中，请耐心等待，勿刷新或关闭页面。"):
+ empty = st.empty()
+ empty.progress(0.0, "")
+ for d in api.recreate_vector_store(kb,
+ chunk_size=chunk_size,
+ chunk_overlap=chunk_overlap,
+ zh_title_enhance=zh_title_enhance):
+ if msg := check_error_msg(d):
+ st.toast(msg)
+ else:
+ empty.progress(d["finished"] / d["total"], d["msg"])
+ st.rerun()
- # if cols[2].button(
- # "删除知识库",
- # use_container_width=True,
- # ):
- # ret = api.delete_knowledge_base(kb)
- # st.toast(ret.get("msg", " "))
- # time.sleep(1)
- # st.rerun()
+ if cols[2].button(
+ "删除知识库",
+ use_container_width=True,
+ ):
+ ret = api.delete_knowledge_base(kb)
+ st.toast(ret.get("msg", " "))
+ time.sleep(1)
+ st.rerun()
- # with st.sidebar:
- # keyword = st.text_input("查询关键字")
- # top_k = st.slider("匹配条数", 1, 100, 3)
+ with st.sidebar:
+ keyword = st.text_input("查询关键字")
+ top_k = st.slider("匹配条数", 1, 100, 3)
st.write("文件内文档列表。双击进行修改，在删除列填入 Y 可删除对应行。")
docs = []
@@ -325,11 +325,12 @@ def knowledge_base_page(api: ApiRequest, is_lite: bool = None):
if selected_rows:
file_name = selected_rows[0]["file_name"]
docs = api.search_kb_docs(knowledge_base_name=selected_kb, file_name=file_name)
- data = [{"seq": i+1, "id": x["id"], "page_content": x["page_content"], "source": x["metadata"].get("source"),
- "type": x["type"],
- "metadata": json.dumps(x["metadata"], ensure_ascii=False),
- "to_del": "",
- } for i, x in enumerate(docs)]
+ data = [
+ {"seq": i + 1, "id": x["id"], "page_content": x["page_content"], "source": x["metadata"].get("source"),
+ "type": x["type"],
+ "metadata": json.dumps(x["metadata"], ensure_ascii=False),
+ "to_del": "",
+ } for i, x in enumerate(docs)]
df = pd.DataFrame(data)
gb = GridOptionsBuilder.from_dataframe(df)
@@ -343,22 +344,24 @@ def knowledge_base_page(api: ApiRequest, is_lite: bool = None):
edit_docs = AgGrid(df, gb.build())
if st.button("保存更改"):
- # origin_docs = {x["id"]: {"page_content": x["page_content"], "type": x["type"], "metadata": x["metadata"]} for x in docs}
+ origin_docs = {
+ x["id"]: {"page_content": x["page_content"], "type": x["type"], "metadata": x["metadata"]} for x in
+ docs}
changed_docs = []
for index, row in edit_docs.data.iterrows():
- # origin_doc = origin_docs[row["id"]]
- # if row["page_content"] != origin_doc["page_content"]:
- if row["to_del"] not in ["Y", "y", 1]:
- changed_docs.append({
- "page_content": row["page_content"],
- "type": row["type"],
- "metadata": json.loads(row["metadata"]),
- })
+ origin_doc = origin_docs[row["id"]]
+ if row["page_content"] != origin_doc["page_content"]:
+ if row["to_del"] not in ["Y", "y", 1]:
+ changed_docs.append({
+ "page_content": row["page_content"],
+ "type": row["type"],
+ "metadata": json.loads(row["metadata"]),
+ })
if changed_docs:
if api.update_kb_docs(knowledge_base_name=selected_kb,
- file_names=[file_name],
- docs={file_name: changed_docs}):
+ file_names=[file_name],
+ docs={file_name: changed_docs}):
st.toast("更新文档成功")
else:
st.toast("更新文档失败")