update webui.py and README.md
This commit is contained in:
parent
8c289e4974
commit
2ad33e010d
13
README.md
13
README.md
|
|
@ -47,6 +47,15 @@
|
||||||
|
|
||||||
从`0.1.x`升级过来的用户请注意,在完成[“开发部署 3 设置配置项”](docs/INSTALL.md)之后,需要将现有知识库迁移到新格式,具体见[知识库初始化与迁移](docs/INSTALL.md#知识库初始化与迁移)。
|
从`0.1.x`升级过来的用户请注意,在完成[“开发部署 3 设置配置项”](docs/INSTALL.md)之后,需要将现有知识库迁移到新格式,具体见[知识库初始化与迁移](docs/INSTALL.md#知识库初始化与迁移)。
|
||||||
|
|
||||||
|
### `0.2.0` 版本与 `0.1.x` 版本区别
|
||||||
|
|
||||||
|
1. 使用 [FastChat](https://github.com/lm-sys/FastChat) 提供开源 LLM 模型的 API,以 OpenAI API 接口形式接入,提升 LLM 模型加载效果;
|
||||||
|
2. 使用 [langchain](https://github.com/langchain-ai/langchain) 中已有 Chain 的实现,便于后续接入不同类型 Chain,并将对 Agent 接入开展测试;
|
||||||
|
3. 使用 [FastAPI](https://github.com/tiangolo/fastapi) 提供 API 服务,全部接口可在 FastAPI 自动生成的 docs 中开展测试,且所有对话接口支持通过参数设置流式或非流式输出;
|
||||||
|
4. 使用 [Streamlit](https://github.com/streamlit/streamlit) 提供 WebUI 服务,可选是否基于 API 服务启动 WebUI,且后续可支持不同形式输出内容的显示;
|
||||||
|
5. 除 [FAISS](https://github.com/facebookresearch/faiss) 向量库外,还提供 [Milvus](https://github.com/milvus-io/milvus), [PGVector](https://github.com/pgvector/pgvector) 向量库的接入;
|
||||||
|
6. 项目中默认 LLM 模型改为 [THUDM/chatglm2-6b](https://huggingface.co/THUDM/chatglm2-6b),默认 Embedding 模型改为 [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base),文件加载方式与文段划分方式也有调整,后续将重新实现上下文扩充,并增加可选设置。
|
||||||
|
|
||||||
## 模型支持
|
## 模型支持
|
||||||
|
|
||||||
本项目中默认使用的 LLM 模型为 [THUDM/chatglm2-6b](https://huggingface.co/THUDM/chatglm2-6b),默认使用的 Embedding 模型为 [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base) 为例。
|
本项目中默认使用的 LLM 模型为 [THUDM/chatglm2-6b](https://huggingface.co/THUDM/chatglm2-6b),默认使用的 Embedding 模型为 [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base) 为例。
|
||||||
|
|
@ -261,6 +270,10 @@ $ python webui.py
|
||||||
- [ ] 结构化数据接入
|
- [ ] 结构化数据接入
|
||||||
- [X] .csv
|
- [X] .csv
|
||||||
- [ ] .xlsx
|
- [ ] .xlsx
|
||||||
|
- [ ] 分词及召回
|
||||||
|
- [ ] 接入不同类型 TextSplitter
|
||||||
|
- [ ] 优化依据中文标点符号设计的 ChineseTextSplitter
|
||||||
|
- [ ] 重新实现上下文拼接召回
|
||||||
- [ ] 本地网页接入
|
- [ ] 本地网页接入
|
||||||
- [ ] SQL 接入
|
- [ ] SQL 接入
|
||||||
- [ ] 知识图谱/图数据库接入
|
- [ ] 知识图谱/图数据库接入
|
||||||
|
|
|
||||||
|
|
@ -1,272 +0,0 @@
|
||||||
# 基于本地知识库的 ChatGLM 等大语言模型应用实现
|
|
||||||
|
|
||||||
## 目录
|
|
||||||
|
|
||||||
* [介绍](README.md#介绍)
|
|
||||||
* [变更日志](README.md#变更日志)
|
|
||||||
* [模型支持](README.md#模型支持)
|
|
||||||
* [Docker 整合包](README.md#Docker-整合包)
|
|
||||||
* [Docker 部署](README.md#Docker-部署)
|
|
||||||
* [开发部署](README.md#开发部署)
|
|
||||||
* [软件需求](README.md#软件需求)
|
|
||||||
* [1. 开发环境准备](README.md#1.-开发环境准备)
|
|
||||||
* [2. 下载模型至本地](README.md#2.-下载模型至本地)
|
|
||||||
* [3. 设置配置项](README.md#3.-设置配置项)
|
|
||||||
* [4. 启动 API 服务或 Web UI](README.md#4.-启动-API-服务或-Web-UI)
|
|
||||||
* [常见问题](README.md#常见问题)
|
|
||||||
* [路线图](README.md#路线图)
|
|
||||||
* [项目交流群](README.md#项目交流群)
|
|
||||||
|
|
||||||
## 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。
|
|
||||||
|
|
||||||
💡 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。
|
|
||||||
|
|
||||||
⛓️ 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)
|
|
||||||
|
|
||||||

|
|
||||||
|
|
||||||
从文档处理角度来看,实现流程如下:
|
|
||||||
|
|
||||||

|
|
||||||
|
|
||||||
🚩 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。
|
|
||||||
|
|
||||||
🐳 Docker镜像:registry.cn-beijing.aliyuncs.com/isafetech/chatmydata:1.0 (感谢 @InkSong🌲 )
|
|
||||||
|
|
||||||
💻 运行方式:docker run -d -p 80:7860 --gpus all registry.cn-beijing.aliyuncs.com/isafetech/chatmydata:1.0
|
|
||||||
|
|
||||||
## 变更日志
|
|
||||||
|
|
||||||
参见 [版本更新日志](https://github.com/imClumsyPanda/langchain-ChatGLM/releases)。
|
|
||||||
|
|
||||||
从`0.1.x`升级过来的用户请注意,在完成[“开发部署 3 设置配置项”](docs/INSTALL.md)之后,需要将现有知识库迁移到新格式,具体见[知识库初始化与迁移](docs/INSTALL.md#知识库初始化与迁移)。
|
|
||||||
|
|
||||||
## 模型支持
|
|
||||||
|
|
||||||
本项目中默认使用的 LLM 模型为 [THUDM/chatglm2-6b](https://huggingface.co/THUDM/chatglm2-6b),默认使用的 Embedding 模型为 [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base) 为例。
|
|
||||||
|
|
||||||
### LLM 模型支持
|
|
||||||
|
|
||||||
本项目最新版本中基于 [FastChat](https://github.com/lm-sys/FastChat) 进行本地 LLM 模型接入,支持模型如下:
|
|
||||||
|
|
||||||
- [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
|
|
||||||
- Vicuna, Alpaca, LLaMA, Koala
|
|
||||||
- [BlinkDL/RWKV-4-Raven](https://huggingface.co/BlinkDL/rwkv-4-raven)
|
|
||||||
- [camel-ai/CAMEL-13B-Combined-Data](https://huggingface.co/camel-ai/CAMEL-13B-Combined-Data)
|
|
||||||
- [databricks/dolly-v2-12b](https://huggingface.co/databricks/dolly-v2-12b)
|
|
||||||
- [FreedomIntelligence/phoenix-inst-chat-7b](https://huggingface.co/FreedomIntelligence/phoenix-inst-chat-7b)
|
|
||||||
- [h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b](https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b)
|
|
||||||
- [lcw99/polyglot-ko-12.8b-chang-instruct-chat](https://huggingface.co/lcw99/polyglot-ko-12.8b-chang-instruct-chat)
|
|
||||||
- [lmsys/fastchat-t5-3b-v1.0](https://huggingface.co/lmsys/fastchat-t5)
|
|
||||||
- [mosaicml/mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat)
|
|
||||||
- [Neutralzz/BiLLa-7B-SFT](https://huggingface.co/Neutralzz/BiLLa-7B-SFT)
|
|
||||||
- [nomic-ai/gpt4all-13b-snoozy](https://huggingface.co/nomic-ai/gpt4all-13b-snoozy)
|
|
||||||
- [NousResearch/Nous-Hermes-13b](https://huggingface.co/NousResearch/Nous-Hermes-13b)
|
|
||||||
- [openaccess-ai-collective/manticore-13b-chat-pyg](https://huggingface.co/openaccess-ai-collective/manticore-13b-chat-pyg)
|
|
||||||
- [OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5](https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5)
|
|
||||||
- [project-baize/baize-v2-7b](https://huggingface.co/project-baize/baize-v2-7b)
|
|
||||||
- [Salesforce/codet5p-6b](https://huggingface.co/Salesforce/codet5p-6b)
|
|
||||||
- [StabilityAI/stablelm-tuned-alpha-7b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b)
|
|
||||||
- [THUDM/chatglm-6b](https://huggingface.co/THUDM/chatglm-6b)
|
|
||||||
- [THUDM/chatglm2-6b](https://huggingface.co/THUDM/chatglm2-6b)
|
|
||||||
- [tiiuae/falcon-40b](https://huggingface.co/tiiuae/falcon-40b)
|
|
||||||
- [timdettmers/guanaco-33b-merged](https://huggingface.co/timdettmers/guanaco-33b-merged)
|
|
||||||
- [togethercomputer/RedPajama-INCITE-7B-Chat](https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Chat)
|
|
||||||
- [WizardLM/WizardLM-13B-V1.0](https://huggingface.co/WizardLM/WizardLM-13B-V1.0)
|
|
||||||
- [WizardLM/WizardCoder-15B-V1.0](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0)
|
|
||||||
- [baichuan-inc/baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B)
|
|
||||||
- [internlm/internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b)
|
|
||||||
- [Qwen/Qwen-7B-Chat](https://huggingface.co/Qwen/Qwen-7B-Chat)
|
|
||||||
- [HuggingFaceH4/starchat-beta](https://huggingface.co/HuggingFaceH4/starchat-beta)
|
|
||||||
- 任何 [EleutherAI](https://huggingface.co/EleutherAI) 的 pythia 模型,如 [pythia-6.9b](https://huggingface.co/EleutherAI/pythia-6.9b)
|
|
||||||
- 在以上模型基础上训练的任何 [Peft](https://github.com/huggingface/peft) 适配器。为了激活,模型路径中必须有 `peft` 。注意:如果加载多个peft模型,你可以通过在任何模型工作器中设置环境变量 `PEFT_SHARE_BASE_WEIGHTS=true` 来使它们共享基础模型的权重。
|
|
||||||
|
|
||||||
以上模型支持列表可能随 [FastChat](https://github.com/lm-sys/FastChat) 更新而持续更新,可参考 [FastChat 已支持模型列表](https://github.com/lm-sys/FastChat/blob/main/docs/model_support.md)。
|
|
||||||
|
|
||||||
### Embedding 模型支持
|
|
||||||
|
|
||||||
本项目支持调用 [HuggingFace](https://huggingface.co/models?pipeline_tag=sentence-similarity) 中的 Embedding 模型,已支持的 Embedding 模型如下:
|
|
||||||
|
|
||||||
- [moka-ai/m3e-small](https://huggingface.co/moka-ai/m3e-small)
|
|
||||||
- [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base)
|
|
||||||
- [moka-ai/m3e-large](https://huggingface.co/moka-ai/m3e-large)
|
|
||||||
- [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh)
|
|
||||||
- [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh)
|
|
||||||
- [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh)
|
|
||||||
- [text2vec-base-chinese-sentence](https://huggingface.co/shibing624/text2vec-base-chinese-sentence)
|
|
||||||
- [text2vec-base-chinese-paraphrase](https://huggingface.co/shibing624/text2vec-base-chinese-paraphrase)
|
|
||||||
- [text2vec-base-multilingual](https://huggingface.co/shibing624/text2vec-base-multilingual)
|
|
||||||
- [shibing624/text2vec-base-chinese](https://huggingface.co/shibing624/text2vec-base-chinese)
|
|
||||||
- [GanymedeNil/text2vec-large-chinese](https://huggingface.co/GanymedeNil/text2vec-large-chinese)
|
|
||||||
- [nghuyong/ernie-3.0-nano-zh](https://huggingface.co/nghuyong/ernie-3.0-nano-zh)
|
|
||||||
- [nghuyong/ernie-3.0-base-zh](https://huggingface.co/nghuyong/ernie-3.0-base-zh)
|
|
||||||
|
|
||||||
## Docker 整合包
|
|
||||||
|
|
||||||
🐳 Docker镜像地址:`registry.cn-beijing.aliyuncs.com/isafetech/chatmydata:1.0 `🌲
|
|
||||||
|
|
||||||
💻 一行命令运行:
|
|
||||||
|
|
||||||
```shell
|
|
||||||
docker run -d -p 80:7860 --gpus all registry.cn-beijing.aliyuncs.com/isafetech/chatmydata:1.0
|
|
||||||
```
|
|
||||||
|
|
||||||
- 该版本镜像大小 `25.2G`,使用[v0.1.16](https://github.com/imClumsyPanda/langchain-ChatGLM/releases/tag/v0.1.16),以 `nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04`为基础镜像
|
|
||||||
- 该版本内置两个 `embedding`模型:`m3e-base`,`text2vec-large-chinese`,内置 `fastchat+chatglm-6b`
|
|
||||||
- 该版本目标为方便一键部署使用,请确保您已经在Linux发行版上安装了NVIDIA驱动程序
|
|
||||||
- 请注意,您不需要在主机系统上安装CUDA工具包,但需要安装 `NVIDIA Driver`以及 `NVIDIA Container Toolkit`,请参考[安装指南](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
|
|
||||||
- 首次拉取和启动均需要一定时间,首次启动时请参照下图使用 `docker logs -f <container id>`查看日志
|
|
||||||
- 如遇到启动过程卡在 `Waiting..`步骤,建议使用 `docker exec -it <container id> bash`进入 `/logs/`目录查看对应阶段日志
|
|
||||||

|
|
||||||
|
|
||||||
## Docker 部署
|
|
||||||
|
|
||||||
为了能让容器使用主机GPU资源,需要在主机上安装 [NVIDIA Container Toolkit](https://github.com/NVIDIA/nvidia-container-toolkit)。具体安装步骤如下:
|
|
||||||
|
|
||||||
```shell
|
|
||||||
sudo apt-get update
|
|
||||||
sudo apt-get install -y nvidia-container-toolkit-base
|
|
||||||
sudo systemctl daemon-reload
|
|
||||||
sudo systemctl restart docker
|
|
||||||
```
|
|
||||||
|
|
||||||
安装完成后,可以使用以下命令编译镜像和启动容器:
|
|
||||||
|
|
||||||
```
|
|
||||||
docker build -f Dockerfile-cuda -t chatglm-cuda:latest .
|
|
||||||
docker run --gpus all -d --name chatglm -p 7860:7860 chatglm-cuda:latest
|
|
||||||
|
|
||||||
#若要使用离线模型,请配置好模型路径,然后此 repo 挂载到 Container
|
|
||||||
docker run --gpus all -d --name chatglm -p 7860:7860 -v ~/github/langchain-ChatGLM:/chatGLM chatglm-cuda:latest
|
|
||||||
```
|
|
||||||
|
|
||||||
## 开发部署
|
|
||||||
|
|
||||||
### 软件需求
|
|
||||||
|
|
||||||
本项目已在 Python 3.8.1 - 3.10,CUDA 11.7 环境下完成测试。已在 Windows、ARM 架构的 macOS、Linux 系统中完成测试。
|
|
||||||
|
|
||||||
### 1. 开发环境准备
|
|
||||||
|
|
||||||
参见 [开发环境准备](docs/INSTALL.md)。
|
|
||||||
|
|
||||||
### 2. 下载模型至本地
|
|
||||||
|
|
||||||
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/chatglm2-6b](https://huggingface.co/THUDM/chatglm2-6b) 与 Embedding 模型 [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base) 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
|
|
||||||
|
|
||||||
```Shell
|
|
||||||
$ git clone https://huggingface.co/THUDM/chatglm2-6b
|
|
||||||
|
|
||||||
$ git clone https://huggingface.co/moka-ai/m3e-base
|
|
||||||
```
|
|
||||||
|
|
||||||
### 3. 设置配置项
|
|
||||||
|
|
||||||
复制文件 [configs/model_config.py.example](configs/model_config.py.example) 存储至项目路径下 `./configs` 路径下,并重命名为 `model_config.py`。
|
|
||||||
|
|
||||||
在开始执行 Web UI 或命令行交互前,请先检查 `configs/model_config.py` 中的各项模型参数设计是否符合需求:
|
|
||||||
|
|
||||||
- 请确认已下载至本地的 LLM 模型本地存储路径写在 `llm_model_dict` 对应模型的 `local_model_path` 属性中,如:
|
|
||||||
|
|
||||||
```python
|
|
||||||
llm_model_dict={
|
|
||||||
"chatglm2-6b": {
|
|
||||||
"local_model_path": "/Users/xxx/Downloads/chatglm2-6b",
|
|
||||||
"api_base_url": "http://localhost:8888/v1", # "name"修改为fastchat服务中的"api_base_url"
|
|
||||||
"api_key": "EMPTY"
|
|
||||||
},
|
|
||||||
}
|
|
||||||
```
|
|
||||||
|
|
||||||
- 请确认已下载至本地的 Embedding 模型本地存储路径写在 `embedding_model_dict` 对应模型位置,如:
|
|
||||||
|
|
||||||
```python
|
|
||||||
embedding_model_dict = {
|
|
||||||
"m3e-base": "/Users/xxx/Downloads/m3e-base",
|
|
||||||
}
|
|
||||||
```
|
|
||||||
|
|
||||||
### 4. 启动 API 服务或 Web UI
|
|
||||||
|
|
||||||
#### 4.1 启动LLM服务
|
|
||||||
|
|
||||||
在项目根目录下,执行 [server/llm_api.py](server/llm_api.py) 脚本启动 **LLM 模型**服务:
|
|
||||||
|
|
||||||
```shell
|
|
||||||
$ python server/llm_api.py
|
|
||||||
```
|
|
||||||
|
|
||||||
以如上方式启动LLM服务会以nohup命令在后台运行fastchat服务,如需停止服务,可以运行如下命令:
|
|
||||||
|
|
||||||
```shell
|
|
||||||
$python server/llm_api_shutdown.py --serve all
|
|
||||||
```
|
|
||||||
|
|
||||||
亦可单独停止一个fastchat服务模块,可选[all, controller,model_worker,openai_api_server]
|
|
||||||
|
|
||||||
#### 4.2 启动API服务
|
|
||||||
|
|
||||||
启动**LLM服务**后,执行 [server/api.py](server/api.py) 脚本启动 **API** 服务
|
|
||||||
|
|
||||||
```shell
|
|
||||||
$ python server/api.py
|
|
||||||
```
|
|
||||||
|
|
||||||
#### 4.3 启动Web UI服务
|
|
||||||
|
|
||||||
执行 [webui.py](webui.py) 启动 **Web UI** 服务
|
|
||||||
|
|
||||||
```shell
|
|
||||||
$ python webui.py
|
|
||||||
```
|
|
||||||
|
|
||||||
### 常见问题
|
|
||||||
|
|
||||||
参见 [常见问题](docs/FAQ.md)。
|
|
||||||
|
|
||||||
## 路线图
|
|
||||||
|
|
||||||
- [X] Langchain 应用
|
|
||||||
- [X] 本地数据接入
|
|
||||||
- [X] 接入非结构化文档
|
|
||||||
- [X] .md
|
|
||||||
- [X] .txt
|
|
||||||
- [X] .docx
|
|
||||||
- [ ] 结构化数据接入
|
|
||||||
- [X] .csv
|
|
||||||
- [ ] .xlsx
|
|
||||||
- [ ] 本地网页接入
|
|
||||||
- [ ] SQL 接入
|
|
||||||
- [ ] 知识图谱/图数据库接入
|
|
||||||
- [X] 搜索引擎接入
|
|
||||||
- [X] Bing 搜索
|
|
||||||
- [X] DuckDuckGo 搜索
|
|
||||||
- [ ] Agent 实现
|
|
||||||
- [X] LLM 模型接入
|
|
||||||
- [X] 支持通过调用 [fastchat](https://github.com/lm-sys/FastChat) api 调用 llm
|
|
||||||
- [X] 增加更多 Embedding 模型支持
|
|
||||||
- [X] [nghuyong/ernie-3.0-nano-zh](https://huggingface.co/nghuyong/ernie-3.0-nano-zh)
|
|
||||||
- [X] [nghuyong/ernie-3.0-base-zh](https://huggingface.co/nghuyong/ernie-3.0-base-zh)
|
|
||||||
- [X] [shibing624/text2vec-base-chinese](https://huggingface.co/shibing624/text2vec-base-chinese)
|
|
||||||
- [X] [GanymedeNil/text2vec-large-chinese](https://huggingface.co/GanymedeNil/text2vec-large-chinese)
|
|
||||||
- [X] [moka-ai/m3e-small](https://huggingface.co/moka-ai/m3e-small)
|
|
||||||
- [X] [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base)
|
|
||||||
- [X] 基于 FastAPI 的 API 方式调用
|
|
||||||
- [X] Web UI
|
|
||||||
- [X] 基于 Streamlit 的 Web UI
|
|
||||||
|
|
||||||
## 项目交流群
|
|
||||||
|
|
||||||
<img src="img/qr_code_46.jpg" alt="二维码" width="300" height="300" />
|
|
||||||
|
|
||||||
🎉 langchain-ChatGLM 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。
|
|
||||||
Binary file not shown.
Binary file not shown.
46
webui.py
46
webui.py
|
|
@ -21,27 +21,30 @@ if __name__ == "__main__":
|
||||||
)
|
)
|
||||||
|
|
||||||
if "chat_list" not in st.session_state:
|
if "chat_list" not in st.session_state:
|
||||||
st.session_state["chat_list"] = ["对话"]
|
st.session_state["chat_list"] = {"对话1": {"need_rename": True}}
|
||||||
if "cur_chat_name" not in st.session_state:
|
if "cur_chat_name" not in st.session_state:
|
||||||
st.session_state["cur_chat_name"] = "对话"
|
st.session_state["cur_chat_name"] = list(st.session_state["chat_list"].keys())[0]
|
||||||
if "need_chat_name" not in st.session_state:
|
if "need_chat_name" not in st.session_state:
|
||||||
st.session_state["need_chat_name"] = True
|
st.session_state["need_chat_name"] = True
|
||||||
|
|
||||||
pages = {i: {"icon": "chat",
|
pages = {i: {
|
||||||
"func": dialogue_page,
|
"icon": "chat",
|
||||||
} for i in st.session_state.chat_list}
|
"func": dialogue_page,
|
||||||
|
} for i in st.session_state.chat_list.keys()}
|
||||||
|
|
||||||
pages2 = {
|
pages2 = {
|
||||||
"新建对话": {"icon": "plus-circle",
|
"新建对话": {
|
||||||
"func": dialogue_page,
|
"icon": "plus-circle",
|
||||||
},
|
"func": dialogue_page,
|
||||||
"---": {"icon": None,
|
},
|
||||||
"func": None},
|
"---": {
|
||||||
"知识库管理": {"icon": "hdd-stack",
|
"icon": None,
|
||||||
"func": knowledge_base_page,
|
"func": None
|
||||||
},
|
},
|
||||||
# "模型配置": {"icon": "gear",
|
"知识库管理": {
|
||||||
# "func": model_config_page,
|
"icon": "hdd-stack",
|
||||||
# }
|
"func": knowledge_base_page,
|
||||||
|
},
|
||||||
}
|
}
|
||||||
pages.update(pages2)
|
pages.update(pages2)
|
||||||
|
|
||||||
|
|
@ -52,13 +55,12 @@ if __name__ == "__main__":
|
||||||
menu_icon="chat-quote",
|
menu_icon="chat-quote",
|
||||||
default_index=list(pages.keys()).index(st.session_state["cur_chat_name"]))
|
default_index=list(pages.keys()).index(st.session_state["cur_chat_name"]))
|
||||||
if selected_page == "新建对话":
|
if selected_page == "新建对话":
|
||||||
if len(st.session_state.chat_list) > 1 and st.session_state.chat_list[0] == "对话":
|
|
||||||
st.session_state.chat_list[0] = "对话1"
|
|
||||||
st.write(st.session_state.chat_list)
|
|
||||||
new_chat_name = f"对话{len(st.session_state.chat_list) + 1}"
|
new_chat_name = f"对话{len(st.session_state.chat_list) + 1}"
|
||||||
st.session_state.chat_list += [new_chat_name]
|
st.session_state.chat_list[new_chat_name] = {"need_rename": True}
|
||||||
st.session_state["cur_chat_name"] = new_chat_name
|
st.session_state["cur_chat_name"] = new_chat_name
|
||||||
st.session_state["need_chat_name"] = True
|
|
||||||
st.experimental_rerun()
|
st.experimental_rerun()
|
||||||
else:
|
elif selected_page == "知识库管理":
|
||||||
|
pages[selected_page]["func"](api)
|
||||||
|
else:
|
||||||
|
st.session_state["cur_chat_name"] = selected_page
|
||||||
pages[selected_page]["func"](api)
|
pages[selected_page]["func"](api)
|
||||||
|
|
|
||||||
|
|
@ -32,35 +32,10 @@ def get_messages_history(history_len: int) -> List[Dict]:
|
||||||
|
|
||||||
def dialogue_page(api: ApiRequest):
|
def dialogue_page(api: ApiRequest):
|
||||||
chat_box.init_session()
|
chat_box.init_session()
|
||||||
|
chat_box.use_chat_name(st.session_state.cur_chat_name)
|
||||||
|
|
||||||
with st.sidebar:
|
with st.sidebar:
|
||||||
# with st.expander("会话管理", True):
|
# TODO: 对话模型与会话绑定
|
||||||
# col_input, col_btn = st.columns([1.5, 1])
|
|
||||||
# col_input.text_input(
|
|
||||||
# "新会话名称",
|
|
||||||
# placeholder="新会话名称",
|
|
||||||
# label_visibility="collapsed",
|
|
||||||
# key="new_chat_name",
|
|
||||||
# )
|
|
||||||
#
|
|
||||||
# def on_btn_new_chat():
|
|
||||||
# new_chat_name = st.session_state.new_chat_name
|
|
||||||
# if new_chat_name:
|
|
||||||
# chat_box.use_chat_name(new_chat_name)
|
|
||||||
# st.session_state.new_chat_name = ""
|
|
||||||
#
|
|
||||||
# col_btn.button(
|
|
||||||
# "新建会话",
|
|
||||||
# on_click=on_btn_new_chat,
|
|
||||||
# use_container_width=True,
|
|
||||||
# )
|
|
||||||
#
|
|
||||||
# chat_list = chat_box.get_chat_names()
|
|
||||||
# cur_chat_name = sac.buttons(chat_list, 0)
|
|
||||||
# chat_box.use_chat_name(cur_chat_name)
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
def on_mode_change():
|
def on_mode_change():
|
||||||
mode = st.session_state.dialogue_mode
|
mode = st.session_state.dialogue_mode
|
||||||
text = f"已切换到 {mode} 模式。"
|
text = f"已切换到 {mode} 模式。"
|
||||||
|
|
@ -105,18 +80,21 @@ def dialogue_page(api: ApiRequest):
|
||||||
|
|
||||||
# Display chat messages from history on app rerun
|
# Display chat messages from history on app rerun
|
||||||
|
|
||||||
chat_box.use_chat_name(st.session_state.cur_chat_name)
|
|
||||||
chat_box.output_messages()
|
chat_box.output_messages()
|
||||||
chat_input_placeholder = "请输入对话名称" if st.session_state.need_chat_name else "请输入对话内容,换行请使用Ctrl+Enter"
|
if st.session_state.chat_list[st.session_state.cur_chat_name]["need_rename"]:
|
||||||
|
chat_input_placeholder = "请输入对话名称"
|
||||||
|
else:
|
||||||
|
chat_input_placeholder = "请输入对话内容,换行请使用Ctrl+Enter "
|
||||||
if prompt := st.chat_input(chat_input_placeholder):
|
if prompt := st.chat_input(chat_input_placeholder):
|
||||||
if st.session_state.need_chat_name:
|
if st.session_state.chat_list[st.session_state.cur_chat_name]["need_rename"]:
|
||||||
if prompt in st.session_state.chat_list:
|
if prompt in st.session_state.chat_list.keys():
|
||||||
st.toast("已有同名对话,请重新命名")
|
st.toast("已有同名对话,请重新命名")
|
||||||
else:
|
else:
|
||||||
st.session_state.chat_list[st.session_state.chat_list.index(st.session_state.cur_chat_name)] = prompt
|
st.session_state.chat_list[prompt] = {"need_rename": False}
|
||||||
st.session_state.need_chat_name = False
|
st.session_state.chat_list.pop(st.session_state.cur_chat_name)
|
||||||
|
chat_box.del_chat_name(st.session_state.cur_chat_name)
|
||||||
st.session_state.cur_chat_name = prompt
|
st.session_state.cur_chat_name = prompt
|
||||||
chat_box.use_chat_name(prompt)
|
chat_box.use_chat_name(st.session_state.cur_chat_name)
|
||||||
st.experimental_rerun()
|
st.experimental_rerun()
|
||||||
else:
|
else:
|
||||||
history = get_messages_history(history_len)
|
history = get_messages_history(history_len)
|
||||||
|
|
@ -159,20 +137,23 @@ def dialogue_page(api: ApiRequest):
|
||||||
cols = st.columns(3)
|
cols = st.columns(3)
|
||||||
export_btn = cols[0]
|
export_btn = cols[0]
|
||||||
if cols[1].button(
|
if cols[1].button(
|
||||||
"Clear",
|
"清空对话",
|
||||||
use_container_width=True,
|
use_container_width=True,
|
||||||
):
|
):
|
||||||
chat_box.reset_history()
|
chat_box.reset_history()
|
||||||
|
|
||||||
if cols[2].button(
|
if cols[2].button(
|
||||||
"Delete",
|
"删除对话",
|
||||||
disabled=len(st.session_state.chat_list) <= 1,
|
disabled=len(st.session_state.chat_list) <= 1,
|
||||||
use_container_width=True,
|
use_container_width=True,
|
||||||
):
|
):
|
||||||
chat_box.del_chat_name(st.session_state.cur_chat_name)
|
chat_box.del_chat_name(st.session_state.cur_chat_name)
|
||||||
|
st.session_state.chat_list.pop(st.session_state.cur_chat_name)
|
||||||
|
st.session_state.cur_chat_name = list(st.session_state.chat_list.keys())[0]
|
||||||
|
chat_box.use_chat_name(st.session_state.cur_chat_name)
|
||||||
st.experimental_rerun()
|
st.experimental_rerun()
|
||||||
export_btn.download_button(
|
export_btn.download_button(
|
||||||
"Export",
|
"导出记录",
|
||||||
"".join(chat_box.export2md(st.session_state.cur_chat_name)),
|
"".join(chat_box.export2md(st.session_state.cur_chat_name)),
|
||||||
file_name=f"{now:%Y-%m-%d %H.%M}_{st.session_state.cur_chat_name}.md",
|
file_name=f"{now:%Y-%m-%d %H.%M}_{st.session_state.cur_chat_name}.md",
|
||||||
mime="text/markdown",
|
mime="text/markdown",
|
||||||
|
|
|
||||||
|
|
@ -1,3 +1,5 @@
|
||||||
|
import sqlite3
|
||||||
|
|
||||||
import streamlit as st
|
import streamlit as st
|
||||||
from webui_pages.utils import *
|
from webui_pages.utils import *
|
||||||
from st_aggrid import AgGrid, JsCode
|
from st_aggrid import AgGrid, JsCode
|
||||||
|
|
@ -32,7 +34,11 @@ def config_aggrid(
|
||||||
|
|
||||||
|
|
||||||
def knowledge_base_page(api: ApiRequest):
|
def knowledge_base_page(api: ApiRequest):
|
||||||
kb_list = get_kb_details()
|
try:
|
||||||
|
kb_list = 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.stop()
|
||||||
kb_names = [x["kb_name"] for x in kb_list]
|
kb_names = [x["kb_name"] for x in kb_list]
|
||||||
|
|
||||||
if "selected_kb_name" in st.session_state and st.session_state["selected_kb_name"] in kb_names:
|
if "selected_kb_name" in st.session_state and st.session_state["selected_kb_name"] in kb_names:
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue