Upload 16 files

.gitignore

@@ -0,0 +1,176 @@
+*.log
+*.log.*
+*.bak
+logs
+/knowledge_base/*
+!/knowledge_base/samples
+/knowledge_base/samples/vector_store
+
+/configs/*.py
+.vscode/
+
+# below are standard python ignore files
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+.pytest_cache
+.DS_Store
+
+

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "knowledge_base/samples/content/wiki"]
+	path = knowledge_base/samples/content/wiki
+	url = https://github.com/chatchat-space/Langchain-Chatchat.wiki.git

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,12 +1,200 @@
+![](img/logo-long-chatchat-trans-v2.png)
+
+🌍 [READ THIS IN ENGLISH](README_en.md)
+🌍 [日本語で読む](README_ja.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
+
+* [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)
+* [联系我们](README.md#联系我们)
+
+## 介绍
+
+🤖️ 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。
+
+✅ 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)
+
+![实现原理图](img/langchain+chatglm.png)
+
+从文档处理角度来看，实现流程如下：
+
+![实现原理图2](img/langchain+chatglm2.png)
+
+🚩 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 `v0.2.10`
+版本所使用代码已更新至本项目 `v0.2.10` 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。
+
+🌲 一行命令运行 Docker ：
+
+```shell
+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
+
+## 解决的痛点
+
+该项目是一个可以实现 __完全本地化__推理的知识库增强方案, 重点解决数据安全保护，私域化部署的企业痛点。
+本开源方案采用```Apache License```，可以免费商用，无需付费。
+
+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 (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
+$ git clone https://github.com/chatchat-space/Langchain-Chatchat.git
+
+# 进入目录
+$ cd Langchain-Chatchat
+
+# 安装全部依赖
+$ pip install -r requirements.txt 
+$ pip install -r requirements_api.txt
+$ 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。
+
+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
+
+```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
+
+1. FastAPI Docs 界面
+
+![](img/fastapi_docs_026.png)
+
+2. Web UI 启动界面示例：
+
+- Web UI 对话界面：
+
+![img](img/LLM_success.png)
+
+- Web UI 知识库管理页面：
+
+![](img/init_knowledge_base.jpg)
+
+### 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/)
+
+
 ---
-title: Langchain Chatchat
-emoji: 👁
-colorFrom: gray
-colorTo: red
-sdk: streamlit
-sdk_version: 1.30.0
-app_file: app.py
-pinned: false
+
+## 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` 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 ···
+
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## 联系我们
+
+### Telegram
+
+[![Telegram](https://img.shields.io/badge/Telegram-2CA5E0?style=for-the-badge&logo=telegram&logoColor=white "langchain-chatglm")](https://t.me/+RjliQ3jnJ1YyN2E9)
+
+### 项目交流群
+<img src="img/qr_code_88.jpg" alt="二维码" width="300" />
+
+🎉 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。
+
+### 公众号
+
+<img src="img/official_wechat_mp_account.png" alt="二维码" width="300" />
+
+🎉 Langchain-Chatchat 项目官方公众号，欢迎扫码关注。

README_en.md

@@ -0,0 +1,198 @@
+![](img/logo-long-chatchat-trans-v2.png)
+
+🌍 [中文文档](README.md)
+🌍 [日本語で読む](README_ja.md)
+
+📃 **LangChain-Chatchat** (formerly Langchain-ChatGLM):
+
+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
+
+- [Introduction](README.md#Introduction)
+- [Pain Points Addressed](README.md#Pain-Points-Addressed)
+- [Quick Start](README.md#Quick-Start)
+    - [1. Environment Setup](README.md#1-Environment-Setup)
+    - [2. Model Download](README.md#2-Model-Download)
+    - [3. Initialize Knowledge Base and Configuration Files](README.md#3-Initialize-Knowledge-Base-and-Configuration-Files)
+    - [4. One-Click Startup](README.md#4-One-Click-Startup)
+    - [5. Startup Interface Examples](README.md#5-Startup-Interface-Examples)
+- [Contact Us](README.md#Contact-Us)
+
+## Introduction
+
+🤖️ A Q&A application based on local knowledge base implemented using the idea
+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)
+and [ChatGLM-6B Pull Request](https://github.com/THUDM/ChatGLM-6B/pull/216) , we build a local knowledge base question
+answering application that can be implemented using an open source model or remote LLM api throughout the process. In
+the latest version of this project, [FastChat](https://github.com/lm-sys/FastChat) is used to access Vicuna, Alpaca,
+LLaMA, Koala, RWKV and many other models. Relying on [langchain](https://github.com/langchain-ai/langchain) , this
+project supports calling services through the API provided based on [FastAPI](https://github.com/tiangolo/fastapi), or
+using the WebUI based on [Streamlit](https://github.com/streamlit/streamlit).
+
+✅ Relying on the open source LLM and Embedding models, this project can realize full-process **offline private
+deployment**. At the same time, this project also supports the call of OpenAI GPT API- and Zhipu API, and will continue
+to expand the access to various models and remote APIs in the future.
+
+⛓️ The implementation principle of this project is shown in the graph below. The main process includes: loading files ->
+reading text -> text segmentation -> text vectorization -> question vectorization -> matching the `top-k` most similar
+to the question vector in the text vector -> The matched text is added to `prompt `as context and question -> submitte
+to `LLM` to generate an answer.
+
+📺[video introduction](https://www.bilibili.com/video/BV13M4y1e7cN/?share_source=copy_web&vd_source=e6c5aafe684f30fbe41925d61ca6d514)
+
+![实现原理图](img/langchain+chatglm.png)
+
+The main process analysis from the aspect of document process:
+
+![实现原理图2](img/langchain+chatglm2.png)
+
+🚩 The training or fine-tuning are not involved in the project, but still, one always can improve performance by do
+these.
+
+🌐 [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) is supported to 0.2.7
+
+## Pain Points Addressed
+
+This project is a solution for enhancing knowledge bases with fully localized inference, specifically addressing the
+pain points of data security and private deployments for businesses.
+This open-source solution is under the Apache License and can be used for commercial purposes for free, with no fees
+required.
+We support mainstream local large prophecy models and Embedding models available in the market, as well as open-source
+local vector databases. For a detailed list of supported models and databases, please refer to
+our [Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/)
+
+## Quick Start
+
+### Environment Setup
+
+First, make sure your machine has Python 3.10 installed.
+
+```
+$ python --version
+Python 3.10.12
+```
+
+Then, create a virtual environment and install the project's dependencies within the virtual environment.
+
+```shell
+
+# 拉取仓库
+$ git clone https://github.com/chatchat-space/Langchain-Chatchat.git
+
+# 进入目录
+$ cd Langchain-Chatchat
+
+# 安装全部依赖
+$ pip install -r requirements.txt 
+$ pip install -r requirements_api.txt
+$ 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.
+
+### Model Download
+
+If you need to run this project locally or in an offline environment, you must first download the required models for
+the project. Typically, open-source LLM and Embedding models can be downloaded from HuggingFace.
+
+Taking the default LLM model used in this project, [THUDM/chatglm2-6b](https://huggingface.co/THUDM/chatglm2-6b), and
+the Embedding model [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base) as examples:
+
+To download the models, you need to first
+install [Git LFS](https://docs.github.com/zh/repositories/working-with-files/managing-large-files/installing-git-large-file-storage)
+and then run:
+
+```Shell
+$ git lfs install
+$ git clone https://huggingface.co/THUDM/chatglm2-6b
+$ git clone https://huggingface.co/moka-ai/m3e-base
+```
+
+### Initializing the Knowledge Base and Config File
+
+Follow the steps below to initialize your own knowledge base and config file:
+
+```shell
+$ python copy_config_example.py
+$ python init_database.py --recreate-vs
+ ```
+
+### One-Click Launch
+
+To start the project, run the following command:
+
+```shell
+$ python startup.py -a
+```
+
+### Example of Launch Interface
+
+1. FastAPI docs interface
+
+![](img/fastapi_docs_026.png)
+
+2. webui page
+
+- Web UI dialog page:
+
+![img](img/LLM_success.png)
+
+- Web UI knowledge base management page:
+
+![](img/init_knowledge_base.jpg)
+
+### Note
+
+The above instructions are provided for a quick start. If you need more features or want to customize the launch method,
+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`.
++ `December 2023`: `Langchain-Chachat` open source project received more than **20K** stars.
++ `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
+
+### Telegram
+
+[![Telegram](https://img.shields.io/badge/Telegram-2CA5E0?style=for-the-badge&logo=telegram&logoColor=white "langchain-chatglm")](https://t.me/+RjliQ3jnJ1YyN2E9)
+
+### WeChat Group
+
+<img src="img/qr_code_87.jpg" alt="二维码" width="300" height="300" />
+
+### WeChat Official Account
+
+<img src="img/official_wechat_mp_account.png" alt="图片" width="900" height="300" />

README_ja.md

@@ -0,0 +1,158 @@
+![](img/logo-long-chatchat-trans-v2.png)
+
+🌍 [中文文档](README.md)
+🌍 [READ THIS IN ENGLISH](README_en.md)
+
+📃 **LangChain-Chatchat** (旧名 Langchain-ChatGLM):
+
+LLM アプリケーションは、Langchain とオープンソースまたはリモートの LLM API に基づいて、知識と検索エンジンベースの QA を実装することを目的としています。
+
+---
+
+## 目次
+
+- [イントロ](README_ja.md#イントロ)
+- [ペインポイントへの対応](README_ja.md#ペインポイントへの対応)
+- [クイックスタート](README_ja.md#クイックスタート)
+    - [1. 環境セットアップ](README_ja.md#環境セットアップ)
+    - [2. モデルをダウンロード](README_ja.md#モデルをダウンロード)
+    - [3. ナレッジベースと設定ファイルの初期化](README_ja.md#ナレッジベースと設定ファイルの初期化)
+    - [4. ワンクリック起動](README_ja.md#ワンクリック起動)
+    - [5. 起動インターフェースの例](README_ja.md#起動インターフェースの例)
+- [お問い合わせ](README_ja.md#お問い合わせ)
+
+## イントロ
+
+🤖️ [langchain](https://github.com/hwchase17/langchain) のアイデアを用いて実装された、ローカルナレッジベースに基づく Q&A アプリケーション。
+目標は、中国のシナリオとオープンソースモデルに親和性があり、オフラインとオンラインの両方で実行可能な KBQA（ナレッジベースの Q&A）ソリューションを構築することです。
+
+💡 [document.ai](https://github.com/GanymedeNil/document.ai) と [ChatGLM-6B Pull Request](https://github.com/THUDM/ChatGLM-6B/pull/216) に触発され、
+プロセス全体を通してオープンソースモデルまたはリモート LLM api を使用して実装することができるローカルナレッジベースの質問応答アプリケーションを構築します。
+このプロジェクトの最新バージョンでは、[FastChat](https://github.com/lm-sys/FastChat) を使用して、Vicuna、Alpaca、LLaMA、Koala、RWKV、その他多くのモデルにアクセスしています。
+このプロジェクトは [langchain](https://github.com/langchain-ai/langchain) に依存し、[FastAPI](https://github.com/tiangolo/fastapi) に基づいて提供されるAPIを通してサービスを呼び出したり、
+[Streamlit](https://github.com/streamlit/streamlit) に基づいて WebUI を使ったりすることをサポートしています。
+
+✅ オープンソースの LLM と Embedding モデルに依存して、このプロジェクトはフルプロセスの **オフラインプライベートデプロイメント** を実現することができます。
+同時に、本プロジェクトは OpenAI GPT API や Zhipu API の呼び出しにも対応しており、今後も様々な機種やリモート API へのアクセスを拡大していきます。
+
+⛓️ このプロジェクトの実施原則を下のグラフに示します。主なプロセスは以下の通りです:
+ファイルの読み込み -> テキストの読み込み -> テキストのセグメンテーション -> テキストのベクトル化 -> 質問のベクトル化 -> 質問ベクトルと最も似ている `top-k` をテキストベクトルでマッチング -> マッチしたテキストをコンテキストと質問として `prompt` に追加 -> 回答を生成するために `LLM` に送信。
+
+📺[video introduction](https://www.bilibili.com/video/BV13M4y1e7cN/?share_source=copy_web&vd_source=e6c5aafe684f30fbe41925d61ca6d514)
+
+![实现原理图](img/langchain+chatglm.png)
+
+文書プロセスの側面からの主なプロセス分析:
+
+![实现原理图2](img/langchain+chatglm2.png)
+
+🚩 トレーニングやファインチューニングはプロジェクトには含まれないが、これらを行うことで必ずパフォーマンスを向上させることができます。
+
+🌐 [AutoDL イメージ](registry.cn-beijing.aliyuncs.com/chatchat/chatchat:0.2.5)がサポートされ、v13 では v0.2.9 にアップデートされました。
+
+🐳 [Docker イメージ](registry.cn-beijing.aliyuncs.com/chatchat/chatchat:0.2.7)
+
+## ペインポイントへの対応
+
+このプロジェクトは、完全にローカライズされた推論によってナレッジベースを強化するソリューションであり、特にデータセキュリティと企業向けのプライベートな展開の問題に取り組んでいます。
+このオープンソースソリューションは Apache ライセンスに基づき、無償で商用利用できます。
+私たちは、市場で入手可能な主流のローカル大予言モデルや Embedding モデル、オープンソースのローカルベクターデータベースをサポートしています。
+対応機種とデータベースの詳細については、[Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/) をご参照くださ���。
+
+## クイックスタート
+
+### 環境セットアップ
+
+まず、マシンにPython 3.10がインストールされていることを確認してください。
+
+```
+$ python --version
+Python 3.10.12
+```
+
+次に、仮想環境を作成し、プロジェクトの依存関係を仮想環境内にインストールする。
+
+```shell
+
+# リポジトリをクローン
+$ git clone https://github.com/chatchat-space/Langchain-Chatchat.git
+
+# ディレクトリに移動
+$ cd Langchain-Chatchat
+
+# すべての依存関係をインストール
+$ pip install -r requirements.txt
+$ pip install -r requirements_api.txt
+$ pip install -r requirements_webui.txt
+
+# デフォルトの依存関係には、基本的な実行環境(FAISS ベクターライブラリ)が含まれます。milvus/pg_vector などのベクターライブラリを使用する場合は、requirements.txt 内の対応する依存関係のコメントを解除してからインストールしてください。
+```
+LangChain-Chachat `0.2.x` シリーズは Langchain `0.0.x` シリーズ用です。Langchain `0.1.x` シリーズをお使いの場合は、ダウングレードする必要があります。
+
+### モデルをダウンロード
+
+このプロジェクトをローカルまたはオフライン環境で実行する必要がある場合は、まずプロジェクトに必要なモデルをダウンロードする必要があります。
+通常、オープンソースの LLM と Embedding モデルは Hugging Face からダウンロードできる。
+
+このプロジェクトで使用されているデフォルトの LLM モデルである [THUDM/chatglm2-6b](https://huggingface.co/THUDM/chatglm2-6b)と、Embedding モデル [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base) を例にとると、次のようになります:
+
+モデルをダウンロードするには、まず [Git LFS](https://docs.github.com/zh/repositories/working-with-files/managing-large-files/installing-git-large-file-storage) をインストールし、次のように実行する必要があります:
+
+```Shell
+$ git lfs install
+$ git clone https://huggingface.co/THUDM/chatglm2-6b
+$ git clone https://huggingface.co/moka-ai/m3e-base
+```
+
+### ナレッジベースと設定ファイルの初期化
+
+以下の手順に従って、ナレッジベースと設定ファイルを初期化してください:
+
+```shell
+$ python copy_config_example.py
+$ python init_database.py --recreate-vs
+ ```
+
+### ワンクリック起動
+
+プロジェクトを開始するには、次のコマンドを実行します:
+
+```shell
+$ python startup.py -a
+```
+
+### 起動インターフェースの例
+
+1. FastAPI docs インターフェース
+
+![](img/fastapi_docs_026.png)
+
+2. webui ページ
+
+- Web UI ダイアログページ:
+
+![img](img/LLM_success.png)
+
+- Web UI ナレッジベースマネジメントページ:
+
+![](img/init_knowledge_base.jpg)
+
+### 注
+
+上記の手順はクイックスタートのために提供されています。より多くの機能が必要な場合や、起動方法をカスタマイズしたい場合は、[Wiki](https://github.com/chatchat-space/Langchain-Chatchat/wiki/) を参照してください。
+
+---
+
+## お問い合わせ
+
+### Telegram
+
+[![Telegram](https://img.shields.io/badge/Telegram-2CA5E0?style=for-the-badge&logo=telegram&logoColor=white "langchain-chatglm")](https://t.me/+RjliQ3jnJ1YyN2E9)
+
+### WeChat グループ
+
+<img src="img/qr_code_67.jpg" alt="二维码" width="300" height="300" />
+
+### WeChat 公式アカウント
+
+<img src="img/official_wechat_mp_account.png" alt="图片" width="900" height="300" />

copy_config_example.py

@@ -0,0 +1,12 @@
+# 用于批量将configs下的.example文件复制并命名为.py文件
+import os
+import shutil
+
+if __name__ == "__main__":
+    files = os.listdir("configs")
+
+    src_files = [os.path.join("configs", file) for file in files if ".example" in file]
+
+    for src_file in src_files:
+        tar_file = src_file.replace(".example", "")
+        shutil.copy(src_file, tar_file)

init_database.py

@@ -0,0 +1,120 @@
+import sys
+sys.path.append(".")
+from server.knowledge_base.migrate import (create_tables, reset_tables, import_from_db,
+                                           folder2db, prune_db_docs, prune_folder_files)
+from configs.model_config import NLTK_DATA_PATH, EMBEDDING_MODEL
+import nltk
+nltk.data.path = [NLTK_DATA_PATH] + nltk.data.path
+from datetime import datetime
+
+
+if __name__ == "__main__":
+    import argparse
+    
+    parser = argparse.ArgumentParser(description="please specify only one operate method once time.")
+
+    parser.add_argument(
+        "-r",
+        "--recreate-vs",
+        action="store_true",
+        help=('''
+            recreate vector store.
+            use this option if you have copied document files to the content folder, but vector store has not been populated or DEFAUL_VS_TYPE/EMBEDDING_MODEL changed.
+            '''
+        )
+    )
+    parser.add_argument(
+        "--create-tables",
+        action="store_true",
+        help=("create empty tables if not existed")
+    )
+    parser.add_argument(
+        "--clear-tables",
+        action="store_true",
+        help=("create empty tables, or drop the database tables before recreate vector stores")
+    )
+    parser.add_argument(
+        "--import-db",
+        help="import tables from specified sqlite database"
+    )
+    parser.add_argument(
+        "-u",
+        "--update-in-db",
+        action="store_true",
+        help=('''
+            update vector store for files exist in database.
+            use this option if you want to recreate vectors for files exist in db and skip files exist in local folder only.
+            '''
+        )
+    )
+    parser.add_argument(
+        "-i",
+        "--increment",
+        action="store_true",
+        help=('''
+            update vector store for files exist in local folder and not exist in database.
+            use this option if you want to create vectors incrementally.
+            '''
+        )
+    )
+    parser.add_argument(
+        "--prune-db",
+        action="store_true",
+        help=('''
+            delete docs in database that not existed in local folder.
+            it is used to delete database docs after user deleted some doc files in file browser
+            '''
+        )
+    )
+    parser.add_argument(
+        "--prune-folder",
+        action="store_true",
+        help=('''
+            delete doc files in local folder that not existed in database.
+            is is used to free local disk space by delete unused doc files.
+            '''
+        )
+    )
+    parser.add_argument(
+        "-n",
+        "--kb-name",
+        type=str,
+        nargs="+",
+        default=[],
+        help=("specify knowledge base names to operate on. default is all folders exist in KB_ROOT_PATH.")
+    )
+    parser.add_argument(
+        "-e",
+        "--embed-model",
+        type=str,
+        default=EMBEDDING_MODEL,
+        help=("specify embeddings model.")
+    )
+
+    args = parser.parse_args()
+    start_time = datetime.now()
+
+    if args.create_tables:
+        create_tables() # confirm tables exist
+
+    if args.clear_tables:
+        reset_tables()
+        print("database tables reset")
+
+    if args.recreate_vs:
+        create_tables()
+        print("recreating all vector stores")
+        folder2db(kb_names=args.kb_name, mode="recreate_vs", embed_model=args.embed_model)
+    elif args.import_db:
+        import_from_db(args.import_db)
+    elif args.update_in_db:
+        folder2db(kb_names=args.kb_name, mode="update_in_db", embed_model=args.embed_model)
+    elif args.increment:
+        folder2db(kb_names=args.kb_name, mode="increment", embed_model=args.embed_model)
+    elif args.prune_db:
+        prune_db_docs(args.kb_name)
+    elif args.prune_folder:
+        prune_folder_files(args.kb_name)
+
+    end_time = datetime.now()
+    print(f"总计用时： {end_time-start_time}")

release.py

@@ -0,0 +1,50 @@
+import os
+import subprocess
+import re
+
+def get_latest_tag():
+    output = subprocess.check_output(['git', 'tag'])
+    tags = output.decode('utf-8').split('\n')[:-1]
+    latest_tag = sorted(tags, key=lambda t: tuple(map(int, re.match(r'v(\d+)\.(\d+)\.(\d+)', t).groups())))[-1]
+    return latest_tag
+
+def update_version_number(latest_tag, increment):
+    major, minor, patch = map(int, re.match(r'v(\d+)\.(\d+)\.(\d+)', latest_tag).groups())
+    if increment == 'X':
+        major += 1
+        minor, patch = 0, 0
+    elif increment == 'Y':
+        minor += 1
+        patch = 0
+    elif increment == 'Z':
+        patch += 1
+    new_version = f"v{major}.{minor}.{patch}"
+    return new_version
+
+def main():
+    print("当前最近的Git标签：")
+    latest_tag = get_latest_tag()
+    print(latest_tag)
+
+    print("请选择要递增的版本号部分（X, Y, Z）：")
+    increment = input().upper()
+
+    while increment not in ['X', 'Y', 'Z']:
+        print("输入错误，请输入X, Y或Z：")
+        increment = input().upper()
+
+    new_version = update_version_number(latest_tag, increment)
+    print(f"新的版本号为：{new_version}")
+
+    print("确认更新版本号并推送到远程仓库？（y/n）")
+    confirmation = input().lower()
+
+    if confirmation == 'y':
+        subprocess.run(['git', 'tag', new_version])
+        subprocess.run(['git', 'push', 'origin', new_version])
+        print("新版本号已创建并推送到远程仓库。")
+    else:
+        print("操作已取消。")
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,66 @@
+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
+langchain==0.0.354
+langchain-experimental==0.0.47
+pydantic==1.10.13
+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==0.35.0
+unstructured[all-docs] # ==0.11.8
+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
+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"
+llama-index==0.9.35
+
+#jq==1.6.0
+# beautifulsoup4==4.12.2
+# pysrt==1.1.2
+# 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
+#flash-attn==2.4.2 # For Orion-14B-Chat and Qwen-14B-Chat
+#autoawq==0.1.8 # For Int4
+#rapidocr_paddle[gpu]==1.3.11 # 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
+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
+jwt==1.3.1

requirements_api.txt

@@ -0,0 +1,57 @@
+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
+langchain==0.0.354
+langchain-experimental==0.0.47
+pydantic==1.10.13
+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~=0.35.0
+unstructured[all-docs]==0.11.0
+python-magic-bin; sys_platform == 'win32'
+SQLAlchemy==2.0.19
+faiss-cpu~=1.7.4
+accelerate~=0.24.1
+spacy~=3.7.2
+PyMuPDF~=1.23.8
+rapidocr_onnxruntime==1.3.8
+requests~=2.31.0
+pathlib~=1.0.1
+pytest~=7.4.3
+numexpr~=2.8.6
+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==0.26.0
+llama-index==0.9.35
+
+# jq==1.6.0
+# beautifulsoup4~=4.12.2
+# pysrt~=1.1.2
+# dashscope==1.13.6
+# arxiv~=2.1.0
+# youtube-search~=2.1.2
+# duckduckgo-search~=3.9.9
+# metaphor-python~=0.1.23
+
+# volcengine>=1.0.119
+# pymilvus>=2.3.4
+# psycopg2==2.9.9
+# pgvector>=0.2.4
+#flash-attn==2.4.2 # For Orion-14B-Chat and Qwen-14B-Chat
+#autoawq==0.1.8 # For Int4
+#rapidocr_paddle[gpu]==1.3.11 # gpu accelleration for ocr of pdf and image files

requirements_lite.txt

@@ -0,0 +1,33 @@
+langchain==0.0.354
+langchain-experimental==0.0.47
+pydantic==1.10.13
+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~=0.35.0
+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
+llama-index==0.9.35
+
+dashscope==1.13.6
+arxiv~=2.1.0
+youtube-search~=2.1.2
+duckduckgo-search~=3.9.9
+metaphor-python~=0.1.23
+watchdog~=3.0.0
+# volcengine>=1.0.119
+# pymilvus>=2.3.4
+# psycopg2==2.9.9
+# pgvector>=0.2.4

requirements_webui.txt

@@ -0,0 +1,8 @@
+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

shutdown_all.sh

@@ -0,0 +1,2 @@
+# mac设备上的grep命令可能不支持grep -P选项，请使用Homebrew安装;或使用ggrep命令
+ps -eo pid,user,cmd|grep -P 'server/api.py|webui.py|fastchat.serve|multiprocessing'|grep -v grep|awk '{print $1}'|xargs kill -9

startup.py

@@ -0,0 +1,900 @@
+import asyncio
+import multiprocessing as mp
+import os
+import subprocess
+import sys
+from multiprocessing import Process
+from datetime import datetime
+from pprint import pprint
+from langchain_core._api import deprecated
+
+try:
+    import numexpr
+
+    n_cores = numexpr.utils.detect_number_of_cores()
+    os.environ["NUMEXPR_MAX_THREADS"] = str(n_cores)
+except:
+    pass
+
+sys.path.append(os.path.dirname(os.path.dirname(__file__)))
+from configs import (
+    LOG_PATH,
+    log_verbose,
+    logger,
+    LLM_MODELS,
+    EMBEDDING_MODEL,
+    TEXT_SPLITTER_NAME,
+    FSCHAT_CONTROLLER,
+    FSCHAT_OPENAI_API,
+    FSCHAT_MODEL_WORKERS,
+    API_SERVER,
+    WEBUI_SERVER,
+    HTTPX_DEFAULT_TIMEOUT,
+)
+from server.utils import (fschat_controller_address, fschat_model_worker_address,
+                          fschat_openai_api_address, get_httpx_client, get_model_worker_config,
+                          MakeFastAPIOffline, FastAPI, llm_device, embedding_device)
+from server.knowledge_base.migrate import create_tables
+import argparse
+from typing import List, Dict
+from configs import VERSION
+
+
+@deprecated(
+    since="0.3.0",
+    message="模型启动功能将于 Langchain-Chatchat 0.3.x重写,支持更多模式和加速启动，0.2.x中相关功能将废弃",
+    removal="0.3.0")
+def create_controller_app(
+        dispatch_method: str,
+        log_level: str = "INFO",
+) -> FastAPI:
+    import fastchat.constants
+    fastchat.constants.LOGDIR = LOG_PATH
+    from fastchat.serve.controller import app, Controller, logger
+    logger.setLevel(log_level)
+
+    controller = Controller(dispatch_method)
+    sys.modules["fastchat.serve.controller"].controller = controller
+
+    MakeFastAPIOffline(app)
+    app.title = "FastChat Controller"
+    app._controller = controller
+    return app
+
+
+def create_model_worker_app(log_level: str = "INFO", **kwargs) -> FastAPI:
+    """
+    kwargs包含的字段如下：
+    host:
+    port:
+    model_names:[`model_name`]
+    controller_address:
+    worker_address:
+
+    对于Langchain支持的模型：
+        langchain_model:True
+        不会使用fschat
+    对于online_api:
+        online_api:True
+        worker_class: `provider`
+    对于离线模型：
+        model_path: `model_name_or_path`,huggingface的repo-id或本地路径
+        device:`LLM_DEVICE`
+    """
+    import fastchat.constants
+    fastchat.constants.LOGDIR = LOG_PATH
+    import argparse
+
+    parser = argparse.ArgumentParser()
+    args = parser.parse_args([])
+
+    for k, v in kwargs.items():
+        setattr(args, k, v)
+    if worker_class := kwargs.get("langchain_model"):  # Langchian支持的模型不用做操作
+        from fastchat.serve.base_model_worker import app
+        worker = ""
+    # 在线模型API
+    elif worker_class := kwargs.get("worker_class"):
+        from fastchat.serve.base_model_worker import app
+
+        worker = worker_class(model_names=args.model_names,
+                              controller_addr=args.controller_address,
+                              worker_addr=args.worker_address)
+        # sys.modules["fastchat.serve.base_model_worker"].worker = worker
+        sys.modules["fastchat.serve.base_model_worker"].logger.setLevel(log_level)
+    # 本地模型
+    else:
+        from configs.model_config import VLLM_MODEL_DICT
+        if kwargs["model_names"][0] in VLLM_MODEL_DICT and args.infer_turbo == "vllm":
+            import fastchat.serve.vllm_worker
+            from fastchat.serve.vllm_worker import VLLMWorker, app, worker_id
+            from vllm import AsyncLLMEngine
+            from vllm.engine.arg_utils import AsyncEngineArgs
+
+            args.tokenizer = args.model_path
+            args.tokenizer_mode = 'auto'
+            args.trust_remote_code = True
+            args.download_dir = None
+            args.load_format = 'auto'
+            args.dtype = 'auto'
+            args.seed = 0
+            args.worker_use_ray = False
+            args.pipeline_parallel_size = 1
+            args.tensor_parallel_size = 1
+            args.block_size = 16
+            args.swap_space = 4  # GiB
+            args.gpu_memory_utilization = 0.90
+            args.max_num_batched_tokens = None  # 一个批次中的最大令牌（tokens）数量，这个取决于你的显卡和大模型设置，设置太大显存会不够
+            args.max_num_seqs = 256
+            args.disable_log_stats = False
+            args.conv_template = None
+            args.limit_worker_concurrency = 5
+            args.no_register = False
+            args.num_gpus = 1  # vllm worker的切分是tensor并行，这里填写显卡的数量
+            args.engine_use_ray = False
+            args.disable_log_requests = False
+
+            # 0.2.1 vllm后要加的参数, 但是这里不需要
+            args.max_model_len = None
+            args.revision = None
+            args.quantization = None
+            args.max_log_len = None
+            args.tokenizer_revision = None
+
+            # 0.2.2 vllm需要新加的参���
+            args.max_paddings = 256
+
+            if args.model_path:
+                args.model = args.model_path
+            if args.num_gpus > 1:
+                args.tensor_parallel_size = args.num_gpus
+
+            for k, v in kwargs.items():
+                setattr(args, k, v)
+
+            engine_args = AsyncEngineArgs.from_cli_args(args)
+            engine = AsyncLLMEngine.from_engine_args(engine_args)
+
+            worker = VLLMWorker(
+                controller_addr=args.controller_address,
+                worker_addr=args.worker_address,
+                worker_id=worker_id,
+                model_path=args.model_path,
+                model_names=args.model_names,
+                limit_worker_concurrency=args.limit_worker_concurrency,
+                no_register=args.no_register,
+                llm_engine=engine,
+                conv_template=args.conv_template,
+            )
+            sys.modules["fastchat.serve.vllm_worker"].engine = engine
+            sys.modules["fastchat.serve.vllm_worker"].worker = worker
+            sys.modules["fastchat.serve.vllm_worker"].logger.setLevel(log_level)
+
+        else:
+            from fastchat.serve.model_worker import app, GptqConfig, AWQConfig, ModelWorker, worker_id
+
+            args.gpus = "0"  # GPU的编号,如果有多个GPU，可以设置为"0,1,2,3"
+            args.max_gpu_memory = "22GiB"
+            args.num_gpus = 1  # model worker的切分是model并行，这里填写显卡的数量
+
+            args.load_8bit = False
+            args.cpu_offloading = None
+            args.gptq_ckpt = None
+            args.gptq_wbits = 16
+            args.gptq_groupsize = -1
+            args.gptq_act_order = False
+            args.awq_ckpt = None
+            args.awq_wbits = 16
+            args.awq_groupsize = -1
+            args.model_names = [""]
+            args.conv_template = None
+            args.limit_worker_concurrency = 5
+            args.stream_interval = 2
+            args.no_register = False
+            args.embed_in_truncate = False
+            for k, v in kwargs.items():
+                setattr(args, k, v)
+            if args.gpus:
+                if args.num_gpus is None:
+                    args.num_gpus = len(args.gpus.split(','))
+                if len(args.gpus.split(",")) < args.num_gpus:
+                    raise ValueError(
+                        f"Larger --num-gpus ({args.num_gpus}) than --gpus {args.gpus}!"
+                    )
+                os.environ["CUDA_VISIBLE_DEVICES"] = args.gpus
+            gptq_config = GptqConfig(
+                ckpt=args.gptq_ckpt or args.model_path,
+                wbits=args.gptq_wbits,
+                groupsize=args.gptq_groupsize,
+                act_order=args.gptq_act_order,
+            )
+            awq_config = AWQConfig(
+                ckpt=args.awq_ckpt or args.model_path,
+                wbits=args.awq_wbits,
+                groupsize=args.awq_groupsize,
+            )
+
+            worker = ModelWorker(
+                controller_addr=args.controller_address,
+                worker_addr=args.worker_address,
+                worker_id=worker_id,
+                model_path=args.model_path,
+                model_names=args.model_names,
+                limit_worker_concurrency=args.limit_worker_concurrency,
+                no_register=args.no_register,
+                device=args.device,
+                num_gpus=args.num_gpus,
+                max_gpu_memory=args.max_gpu_memory,
+                load_8bit=args.load_8bit,
+                cpu_offloading=args.cpu_offloading,
+                gptq_config=gptq_config,
+                awq_config=awq_config,
+                stream_interval=args.stream_interval,
+                conv_template=args.conv_template,
+                embed_in_truncate=args.embed_in_truncate,
+            )
+            sys.modules["fastchat.serve.model_worker"].args = args
+            sys.modules["fastchat.serve.model_worker"].gptq_config = gptq_config
+            # sys.modules["fastchat.serve.model_worker"].worker = worker
+            sys.modules["fastchat.serve.model_worker"].logger.setLevel(log_level)
+
+    MakeFastAPIOffline(app)
+    app.title = f"FastChat LLM Server ({args.model_names[0]})"
+    app._worker = worker
+    return app
+
+
+def create_openai_api_app(
+        controller_address: str,
+        api_keys: List = [],
+        log_level: str = "INFO",
+) -> FastAPI:
+    import fastchat.constants
+    fastchat.constants.LOGDIR = LOG_PATH
+    from fastchat.serve.openai_api_server import app, CORSMiddleware, app_settings
+    from fastchat.utils import build_logger
+    logger = build_logger("openai_api", "openai_api.log")
+    logger.setLevel(log_level)
+
+    app.add_middleware(
+        CORSMiddleware,
+        allow_credentials=True,
+        allow_origins=["*"],
+        allow_methods=["*"],
+        allow_headers=["*"],
+    )
+
+    sys.modules["fastchat.serve.openai_api_server"].logger = logger
+    app_settings.controller_address = controller_address
+    app_settings.api_keys = api_keys
+
+    MakeFastAPIOffline(app)
+    app.title = "FastChat OpeanAI API Server"
+    return app
+
+
+def _set_app_event(app: FastAPI, started_event: mp.Event = None):
+    @app.on_event("startup")
+    async def on_startup():
+        if started_event is not None:
+            started_event.set()
+
+
+def run_controller(log_level: str = "INFO", started_event: mp.Event = None):
+    import uvicorn
+    import httpx
+    from fastapi import Body
+    import time
+    import sys
+    from server.utils import set_httpx_config
+    set_httpx_config()
+
+    app = create_controller_app(
+        dispatch_method=FSCHAT_CONTROLLER.get("dispatch_method"),
+        log_level=log_level,
+    )
+    _set_app_event(app, started_event)
+
+    # add interface to release and load model worker
+    @app.post("/release_worker")
+    def release_worker(
+            model_name: str = Body(..., description="要释放模型的名称", samples=["chatglm-6b"]),
+            # worker_address: str = Body(None, description="要释放模型的地址，与名称二选一", samples=[FSCHAT_CONTROLLER_address()]),
+            new_model_name: str = Body(None, description="释放后加载该模型"),
+            keep_origin: bool = Body(False, description="不释放原模型，加载新模型")
+    ) -> Dict:
+        available_models = app._controller.list_models()
+        if new_model_name in available_models:
+            msg = f"要切换的LLM模型 {new_model_name} 已经存在"
+            logger.info(msg)
+            return {"code": 500, "msg": msg}
+
+        if new_model_name:
+            logger.info(f"开始切换LLM模型：从 {model_name} 到 {new_model_name}")
+        else:
+            logger.info(f"即将停止LLM模型： {model_name}")
+
+        if model_name not in available_models:
+            msg = f"the model {model_name} is not available"
+            logger.error(msg)
+            return {"code": 500, "msg": msg}
+
+        worker_address = app._controller.get_worker_address(model_name)
+        if not worker_address:
+            msg = f"can not find model_worker address for {model_name}"
+            logger.error(msg)
+            return {"code": 500, "msg": msg}
+
+        with get_httpx_client() as client:
+            r = client.post(worker_address + "/release",
+                            json={"new_model_name": new_model_name, "keep_origin": keep_origin})
+            if r.status_code != 200:
+                msg = f"failed to release model: {model_name}"
+                logger.error(msg)
+                return {"code": 500, "msg": msg}
+
+        if new_model_name:
+            timer = HTTPX_DEFAULT_TIMEOUT  # wait for new model_worker register
+            while timer > 0:
+                models = app._controller.list_models()
+                if new_model_name in models:
+                    break
+                time.sleep(1)
+                timer -= 1
+            if timer > 0:
+                msg = f"sucess change model from {model_name} to {new_model_name}"
+                logger.info(msg)
+                return {"code": 200, "msg": msg}
+            else:
+                msg = f"failed change model from {model_name} to {new_model_name}"
+                logger.error(msg)
+                return {"code": 500, "msg": msg}
+        else:
+            msg = f"sucess to release model: {model_name}"
+            logger.info(msg)
+            return {"code": 200, "msg": msg}
+
+    host = FSCHAT_CONTROLLER["host"]
+    port = FSCHAT_CONTROLLER["port"]
+
+    if log_level == "ERROR":
+        sys.stdout = sys.__stdout__
+        sys.stderr = sys.__stderr__
+
+    uvicorn.run(app, host=host, port=port, log_level=log_level.lower())
+
+
+def run_model_worker(
+        model_name: str = LLM_MODELS[0],
+        controller_address: str = "",
+        log_level: str = "INFO",
+        q: mp.Queue = None,
+        started_event: mp.Event = None,
+):
+    import uvicorn
+    from fastapi import Body
+    import sys
+    from server.utils import set_httpx_config
+    set_httpx_config()
+
+    kwargs = get_model_worker_config(model_name)
+    host = kwargs.pop("host")
+    port = kwargs.pop("port")
+    kwargs["model_names"] = [model_name]
+    kwargs["controller_address"] = controller_address or fschat_controller_address()
+    kwargs["worker_address"] = fschat_model_worker_address(model_name)
+    model_path = kwargs.get("model_path", "")
+    kwargs["model_path"] = model_path
+
+    app = create_model_worker_app(log_level=log_level, **kwargs)
+    _set_app_event(app, started_event)
+    if log_level == "ERROR":
+        sys.stdout = sys.__stdout__
+        sys.stderr = sys.__stderr__
+
+    # add interface to release and load model
+    @app.post("/release")
+    def release_model(
+            new_model_name: str = Body(None, description="释放后加载该模型"),
+            keep_origin: bool = Body(False, description="不释放原模型，加载新模型")
+    ) -> Dict:
+        if keep_origin:
+            if new_model_name:
+                q.put([model_name, "start", new_model_name])
+        else:
+            if new_model_name:
+                q.put([model_name, "replace", new_model_name])
+            else:
+                q.put([model_name, "stop", None])
+        return {"code": 200, "msg": "done"}
+
+    uvicorn.run(app, host=host, port=port, log_level=log_level.lower())
+
+
+def run_openai_api(log_level: str = "INFO", started_event: mp.Event = None):
+    import uvicorn
+    import sys
+    from server.utils import set_httpx_config
+    set_httpx_config()
+
+    controller_addr = fschat_controller_address()
+    app = create_openai_api_app(controller_addr, log_level=log_level)
+    _set_app_event(app, started_event)
+
+    host = FSCHAT_OPENAI_API["host"]
+    port = FSCHAT_OPENAI_API["port"]
+    if log_level == "ERROR":
+        sys.stdout = sys.__stdout__
+        sys.stderr = sys.__stderr__
+    uvicorn.run(app, host=host, port=port)
+
+
+def run_api_server(started_event: mp.Event = None, run_mode: str = None):
+    from server.api import create_app
+    import uvicorn
+    from server.utils import set_httpx_config
+    set_httpx_config()
+
+    app = create_app(run_mode=run_mode)
+    _set_app_event(app, started_event)
+
+    host = API_SERVER["host"]
+    port = API_SERVER["port"]
+
+    uvicorn.run(app, host=host, port=port)
+
+
+def run_webui(started_event: mp.Event = None, run_mode: str = None):
+    from server.utils import set_httpx_config
+    set_httpx_config()
+
+    host = WEBUI_SERVER["host"]
+    port = WEBUI_SERVER["port"]
+
+    cmd = ["streamlit", "run", "webui.py",
+           "--server.address", host,
+           "--server.port", str(port),
+           "--theme.base", "light",
+           "--theme.primaryColor", "#165dff",
+           "--theme.secondaryBackgroundColor", "#f5f5f5",
+           "--theme.textColor", "#000000",
+           ]
+    if run_mode == "lite":
+        cmd += [
+            "--",
+            "lite",
+        ]
+    p = subprocess.Popen(cmd)
+    started_event.set()
+    p.wait()
+
+
+def parse_args() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-a",
+        "--all-webui",
+        action="store_true",
+        help="run fastchat's controller/openai_api/model_worker servers, run api.py and webui.py",
+        dest="all_webui",
+    )
+    parser.add_argument(
+        "--all-api",
+        action="store_true",
+        help="run fastchat's controller/openai_api/model_worker servers, run api.py",
+        dest="all_api",
+    )
+    parser.add_argument(
+        "--llm-api",
+        action="store_true",
+        help="run fastchat's controller/openai_api/model_worker servers",
+        dest="llm_api",
+    )
+    parser.add_argument(
+        "-o",
+        "--openai-api",
+        action="store_true",
+        help="run fastchat's controller/openai_api servers",
+        dest="openai_api",
+    )
+    parser.add_argument(
+        "-m",
+        "--model-worker",
+        action="store_true",
+        help="run fastchat's model_worker server with specified model name. "
+             "specify --model-name if not using default LLM_MODELS",
+        dest="model_worker",
+    )
+    parser.add_argument(
+        "-n",
+        "--model-name",
+        type=str,
+        nargs="+",
+        default=LLM_MODELS,
+        help="specify model name for model worker. "
+             "add addition names with space seperated to start multiple model workers.",
+        dest="model_name",
+    )
+    parser.add_argument(
+        "-c",
+        "--controller",
+        type=str,
+        help="specify controller address the worker is registered to. default is FSCHAT_CONTROLLER",
+        dest="controller_address",
+    )
+    parser.add_argument(
+        "--api",
+        action="store_true",
+        help="run api.py server",
+        dest="api",
+    )
+    parser.add_argument(
+        "-p",
+        "--api-worker",
+        action="store_true",
+        help="run online model api such as zhipuai",
+        dest="api_worker",
+    )
+    parser.add_argument(
+        "-w",
+        "--webui",
+        action="store_true",
+        help="run webui.py server",
+        dest="webui",
+    )
+    parser.add_argument(
+        "-q",
+        "--quiet",
+        action="store_true",
+        help="减少fastchat服务log信息",
+        dest="quiet",
+    )
+    parser.add_argument(
+        "-i",
+        "--lite",
+        action="store_true",
+        help="以Lite模式运行：仅支持在线API的LLM对话、搜索引擎对话",
+        dest="lite",
+    )
+    args = parser.parse_args()
+    return args, parser
+
+
+def dump_server_info(after_start=False, args=None):
+    import platform
+    import langchain
+    import fastchat
+    from server.utils import api_address, webui_address
+
+    print("\n")
+    print("=" * 30 + "Langchain-Chatchat Configuration" + "=" * 30)
+    print(f"操作系统：{platform.platform()}.")
+    print(f"python版本：{sys.version}")
+    print(f"项目版本：{VERSION}")
+    print(f"langchain版本：{langchain.__version__}. fastchat版本：{fastchat.__version__}")
+    print("\n")
+
+    models = LLM_MODELS
+    if args and args.model_name:
+        models = args.model_name
+
+    print(f"当前使用的分词器：{TEXT_SPLITTER_NAME}")
+    print(f"当前启动的LLM模型：{models} @ {llm_device()}")
+
+    for model in models:
+        pprint(get_model_worker_config(model))
+    print(f"当前Embbedings模型： {EMBEDDING_MODEL} @ {embedding_device()}")
+
+    if after_start:
+        print("\n")
+        print(f"服务端运行信息：")
+        if args.openai_api:
+            print(f"    OpenAI API Server: {fschat_openai_api_address()}")
+        if args.api:
+            print(f"    Chatchat  API  Server: {api_address()}")
+        if args.webui:
+            print(f"    Chatchat WEBUI Server: {webui_address()}")
+    print("=" * 30 + "Langchain-Chatchat Configuration" + "=" * 30)
+    print("\n")
+
+
+async def start_main_server():
+    import time
+    import signal
+
+    def handler(signalname):
+        """
+        Python 3.9 has `signal.strsignal(signalnum)` so this closure would not be needed.
+        Also, 3.8 includes `signal.valid_signals()` that can be used to create a mapping for the same purpose.
+        """
+
+        def f(signal_received, frame):
+            raise KeyboardInterrupt(f"{signalname} received")
+
+        return f
+
+    # This will be inherited by the child process if it is forked (not spawned)
+    signal.signal(signal.SIGINT, handler("SIGINT"))
+    signal.signal(signal.SIGTERM, handler("SIGTERM"))
+
+    mp.set_start_method("spawn")
+    manager = mp.Manager()
+    run_mode = None
+
+    queue = manager.Queue()
+    args, parser = parse_args()
+
+    if args.all_webui:
+        args.openai_api = True
+        args.model_worker = True
+        args.api = True
+        args.api_worker = True
+        args.webui = True
+
+    elif args.all_api:
+        args.openai_api = True
+        args.model_worker = True
+        args.api = True
+        args.api_worker = True
+        args.webui = False
+
+    elif args.llm_api:
+        args.openai_api = True
+        args.model_worker = True
+        args.api_worker = True
+        args.api = False
+        args.webui = False
+
+    if args.lite:
+        args.model_worker = False
+        run_mode = "lite"
+
+    dump_server_info(args=args)
+
+    if len(sys.argv) > 1:
+        logger.info(f"正在启动服务：")
+        logger.info(f"如需查看 llm_api 日志，请前往 {LOG_PATH}")
+
+    processes = {"online_api": {}, "model_worker": {}}
+
+    def process_count():
+        return len(processes) + len(processes["online_api"]) + len(processes["model_worker"]) - 2
+
+    if args.quiet or not log_verbose:
+        log_level = "ERROR"
+    else:
+        log_level = "INFO"
+
+    controller_started = manager.Event()
+    if args.openai_api:
+        process = Process(
+            target=run_controller,
+            name=f"controller",
+            kwargs=dict(log_level=log_level, started_event=controller_started),
+            daemon=True,
+        )
+        processes["controller"] = process
+
+        process = Process(
+            target=run_openai_api,
+            name=f"openai_api",
+            daemon=True,
+        )
+        processes["openai_api"] = process
+
+    model_worker_started = []
+    if args.model_worker:
+        for model_name in args.model_name:
+            config = get_model_worker_config(model_name)
+            if not config.get("online_api"):
+                e = manager.Event()
+                model_worker_started.append(e)
+                process = Process(
+                    target=run_model_worker,
+                    name=f"model_worker - {model_name}",
+                    kwargs=dict(model_name=model_name,
+                                controller_address=args.controller_address,
+                                log_level=log_level,
+                                q=queue,
+                                started_event=e),
+                    daemon=True,
+                )
+                processes["model_worker"][model_name] = process
+
+    if args.api_worker:
+        for model_name in args.model_name:
+            config = get_model_worker_config(model_name)
+            if (config.get("online_api")
+                    and config.get("worker_class")
+                    and model_name in FSCHAT_MODEL_WORKERS):
+                e = manager.Event()
+                model_worker_started.append(e)
+                process = Process(
+                    target=run_model_worker,
+                    name=f"api_worker - {model_name}",
+                    kwargs=dict(model_name=model_name,
+                                controller_address=args.controller_address,
+                                log_level=log_level,
+                                q=queue,
+                                started_event=e),
+                    daemon=True,
+                )
+                processes["online_api"][model_name] = process
+
+    api_started = manager.Event()
+    if args.api:
+        process = Process(
+            target=run_api_server,
+            name=f"API Server",
+            kwargs=dict(started_event=api_started, run_mode=run_mode),
+            daemon=True,
+        )
+        processes["api"] = process
+
+    webui_started = manager.Event()
+    if args.webui:
+        process = Process(
+            target=run_webui,
+            name=f"WEBUI Server",
+            kwargs=dict(started_event=webui_started, run_mode=run_mode),
+            daemon=True,
+        )
+        processes["webui"] = process
+
+    if process_count() == 0:
+        parser.print_help()
+    else:
+        try:
+            # 保证任务收到SIGINT后，能够正常退出
+            if p := processes.get("controller"):
+                p.start()
+                p.name = f"{p.name} ({p.pid})"
+                controller_started.wait()  # 等待controller启动完成
+
+            if p := processes.get("openai_api"):
+                p.start()
+                p.name = f"{p.name} ({p.pid})"
+
+            for n, p in processes.get("model_worker", {}).items():
+                p.start()
+                p.name = f"{p.name} ({p.pid})"
+
+            for n, p in processes.get("online_api", []).items():
+                p.start()
+                p.name = f"{p.name} ({p.pid})"
+
+            # 等待所有model_worker启动完成
+            for e in model_worker_started:
+                e.wait()
+
+            if p := processes.get("api"):
+                p.start()
+                p.name = f"{p.name} ({p.pid})"
+                api_started.wait()  # 等待api.py启动完成
+
+            if p := processes.get("webui"):
+                p.start()
+                p.name = f"{p.name} ({p.pid})"
+                webui_started.wait()  # 等待webui.py启动完成
+
+            dump_server_info(after_start=True, args=args)
+
+            while True:
+                cmd = queue.get()  # 收到切换模型的消息
+                e = manager.Event()
+                if isinstance(cmd, list):
+                    model_name, cmd, new_model_name = cmd
+                    if cmd == "start":  # 运行新模型
+                        logger.info(f"准备启动新模型进程：{new_model_name}")
+                        process = Process(
+                            target=run_model_worker,
+                            name=f"model_worker - {new_model_name}",
+                            kwargs=dict(model_name=new_model_name,
+                                        controller_address=args.controller_address,
+                                        log_level=log_level,
+                                        q=queue,
+                                        started_event=e),
+                            daemon=True,
+                        )
+                        process.start()
+                        process.name = f"{process.name} ({process.pid})"
+                        processes["model_worker"][new_model_name] = process
+                        e.wait()
+                        logger.info(f"成功启动新模型进程：{new_model_name}")
+                    elif cmd == "stop":
+                        if process := processes["model_worker"].get(model_name):
+                            time.sleep(1)
+                            process.terminate()
+                            process.join()
+                            logger.info(f"停止模型进程：{model_name}")
+                        else:
+                            logger.error(f"未找到模型进程：{model_name}")
+                    elif cmd == "replace":
+                        if process := processes["model_worker"].pop(model_name, None):
+                            logger.info(f"停止模型进程：{model_name}")
+                            start_time = datetime.now()
+                            time.sleep(1)
+                            process.terminate()
+                            process.join()
+                            process = Process(
+                                target=run_model_worker,
+                                name=f"model_worker - {new_model_name}",
+                                kwargs=dict(model_name=new_model_name,
+                                            controller_address=args.controller_address,
+                                            log_level=log_level,
+                                            q=queue,
+                                            started_event=e),
+                                daemon=True,
+                            )
+                            process.start()
+                            process.name = f"{process.name} ({process.pid})"
+                            processes["model_worker"][new_model_name] = process
+                            e.wait()
+                            timing = datetime.now() - start_time
+                            logger.info(f"成功启动新模型进程：{new_model_name}。用时：{timing}。")
+                        else:
+                            logger.error(f"未找到模型进程：{model_name}")
+
+            # for process in processes.get("model_worker", {}).values():
+            #     process.join()
+            # for process in processes.get("online_api", {}).values():
+            #     process.join()
+
+            # for name, process in processes.items():
+            #     if name not in ["model_worker", "online_api"]:
+            #         if isinstance(p, dict):
+            #             for work_process in p.values():
+            #                 work_process.join()
+            #         else:
+            #             process.join()
+        except Exception as e:
+            logger.error(e)
+            logger.warning("Caught KeyboardInterrupt! Setting stop event...")
+        finally:
+            # Send SIGINT if process doesn't exit quickly enough, and kill it as last resort
+            # .is_alive() also implicitly joins the process (good practice in linux)
+            # while alive_procs := [p for p in processes.values() if p.is_alive()]:
+
+            for p in processes.values():
+                logger.warning("Sending SIGKILL to %s", p)
+                # Queues and other inter-process communication primitives can break when
+                # process is killed, but we don't care here
+
+                if isinstance(p, dict):
+                    for process in p.values():
+                        process.kill()
+                else:
+                    p.kill()
+
+            for p in processes.values():
+                logger.info("Process status: %s", p)
+
+
+if __name__ == "__main__":
+    create_tables()
+    if sys.version_info < (3, 10):
+        loop = asyncio.get_event_loop()
+    else:
+        try:
+            loop = asyncio.get_running_loop()
+        except RuntimeError:
+            loop = asyncio.new_event_loop()
+
+        asyncio.set_event_loop(loop)
+
+    loop.run_until_complete(start_main_server())
+
+# 服务启动后接口调用示例：
+# import openai
+# openai.api_key = "EMPTY" # Not support yet
+# openai.api_base = "http://localhost:8888/v1"
+
+# model = "chatglm3-6b"
+
+# # create a chat completion
+# completion = openai.ChatCompletion.create(
+#   model=model,
+#   messages=[{"role": "user", "content": "Hello! What is your name?"}]
+# )
+# # print the completion
+# print(completion.choices[0].message.content)

webui.py

@@ -0,0 +1,64 @@
+import streamlit as st
+from webui_pages.utils import *
+from streamlit_option_menu import option_menu
+from webui_pages.dialogue.dialogue import dialogue_page, chat_box
+from webui_pages.knowledge_base.knowledge_base import knowledge_base_page
+import os
+import sys
+from configs import VERSION
+from server.utils import api_address
+
+
+api = ApiRequest(base_url=api_address())
+
+if __name__ == "__main__":
+    is_lite = "lite" in sys.argv
+
+    st.set_page_config(
+        "Langchain-Chatchat WebUI",
+        os.path.join("img", "chatchat_icon_blue_square_v2.png"),
+        initial_sidebar_state="expanded",
+        menu_items={
+            'Get Help': 'https://github.com/chatchat-space/Langchain-Chatchat',
+            'Report a bug': "https://github.com/chatchat-space/Langchain-Chatchat/issues",
+            'About': f"""欢迎使用 Langchain-Chatchat WebUI {VERSION}！"""
+        }
+    )
+
+    pages = {
+        "对话": {
+            "icon": "chat",
+            "func": dialogue_page,
+        },
+        "知识库管理": {
+            "icon": "hdd-stack",
+            "func": knowledge_base_page,
+        },
+    }
+
+    with st.sidebar:
+        st.image(
+            os.path.join(
+                "img",
+                "logo-long-chatchat-trans-v2.png"
+            ),
+            use_column_width=True
+        )
+        st.caption(
+            f"""<p align="right">当前版本：{VERSION}</p>""",
+            unsafe_allow_html=True,
+        )
+        options = list(pages)
+        icons = [x["icon"] for x in pages.values()]
+
+        default_index = 0
+        selected_page = option_menu(
+            "",
+            options=options,
+            icons=icons,
+            # menu_icon="chat-quote",
+            default_index=default_index,
+        )
+
+    if selected_page in pages:
+        pages[selected_page]["func"](api=api, is_lite=is_lite)