Update README.md

修复glm-4 无法流式输出的bug

.dockerignore

@@ -0,0 +1,19 @@
+.idea
+# Langchain-Chatchat
+docs
+.github
+tests
+Dockerfile
+.dockerignore
+.gitignore
+.gitmodules
+README.md
+README_en.md
+README_ja.md
+LICENSE
+requirements_api.txt
+requirements_lite.txt
+requirements_webui.txt
+# bge-large-zh-v1.5
+bge-large-zh-v1.5/README.md
+# chatglm3-6b

.github/ISSUE_TEMPLATE/bug_report.md

@@ -23,10 +23,11 @@ assignees: ''
 描述实际发生的结果 / Describe the actual result.
 
 **环境信息 / Environment Information**
-- langchain-ChatGLM 版本/commit 号：(例如：v1.0.0 或 commit 123456) / langchain-ChatGLM version/commit number: (e.g., v1.0.0 or commit 123456)
+- langchain-ChatGLM 版本/commit 号：(例如：v2.0.1 或 commit 123456) / langchain-ChatGLM version/commit number: (e.g., v2.0.1 or commit 123456)
 - 是否使用 Docker 部署（是/否）：是 / Is Docker deployment used (yes/no): yes
-- 使用的模型（ChatGLM-6B / ClueAI/ChatYuan-large-v2 等）：ChatGLM-6B / Model used (ChatGLM-6B / ClueAI/ChatYuan-large-v2, etc.): ChatGLM-6B
-- 使用的 Embedding 模型（GanymedeNil/text2vec-large-chinese 等）：GanymedeNil/text2vec-large-chinese / Embedding model used (GanymedeNil/text2vec-large-chinese, etc.): GanymedeNil/text2vec-large-chinese
+- 使用的模型（ChatGLM2-6B / Qwen-7B 等）：ChatGLM-6B / Model used (ChatGLM2-6B / Qwen-7B, etc.): ChatGLM2-6B
+- 使用的 Embedding 模型（moka-ai/m3e-base 等）：moka-ai/m3e-base / Embedding model used (moka-ai/m3e-base, etc.): moka-ai/m3e-base
+- 使用的向量库类型 (faiss / milvus / pg_vector 等)： faiss / Vector library used (faiss, milvus, pg_vector, etc.): faiss
 - 操作系统及版本 / Operating system and version:
 - Python 版本 / Python version:
 - 其他相关环境信息 / Other relevant environment information:

.github/workflows/close-issue.yml

@@ -0,0 +1,22 @@
+name: Close inactive issues
+on:
+  schedule:
+    - cron: "30 21 * * *"
+
+jobs:
+  close-issues:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+      - uses: actions/stale@v5
+        with:
+          days-before-issue-stale: 30
+          days-before-issue-close: 14
+          stale-issue-label: "stale"
+          stale-issue-message: "这个问题已经被标记为 `stale` ，因为它已经超过 30 天没有任何活动。"
+          close-issue-message: "这个问题已经被自动关闭，因为它被标为 `stale` 后超过 14 天没有任何活动。"
+          days-before-pr-stale: -1
+          days-before-pr-close: -1
+          repo-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docker-build.yaml

@@ -0,0 +1,155 @@
+name: docker-build
+on:
+  push:
+    branches:
+      - master
+    paths-ignore:
+      - 'README.md'
+      - 'README_en.md'
+      - 'README_ja.md'
+env:
+  TZ: Asia/Shanghai
+jobs:
+  docker-build:
+    runs-on: ubuntu-latest
+    # if: github.event.pull_request.merged == true
+    steps:
+      - name: Optimize Disk Space
+        uses: hugoalh/disk-space-optimizer-ghaction@v0.8.0
+        with:
+          operate_sudo: "True"
+          general_include: ".+"
+          general_exclude: |-
+            ^GCC$
+            ^G\+\+$
+            Clang
+            LLVM
+          docker_include: ".+"
+          docker_prune: "True"
+          docker_clean: "True"
+          apt_prune: "True"
+          apt_clean: "True"
+          homebrew_prune: "True"
+          homebrew_clean: "True"
+          npm_prune: "True"
+          npm_clean: "True"
+          os_swap: "True"
+      - name: Remove Unnecessary Tools And Files
+        env:
+          DEBIAN_FRONTEND: noninteractive
+        run: |
+          sudo apt-get remove -y '^dotnet-.*' '^llvm-.*' 'php.*' azure-cli google-chrome-stable firefox powershell mono-devel
+          sudo apt-get autoremove --purge -y
+          sudo find /var/log -name "*.gz" -type f -delete
+          sudo rm -rf /var/cache/apt/archives
+          sudo rm -rf /tmp/*
+          sudo rm -rf /etc/apt/sources.list.d/* /usr/share/dotnet /usr/local/lib/android /opt/ghc /etc/mysql /etc/php
+          sudo -E apt-get -y purge azure-cli* docker* ghc* zulu* hhvm* llvm* firefox* google* dotnet* aspnetcore* powershell* openjdk* adoptopenjdk* mysql* php* mongodb* moby* snap* || true
+          sudo rm -rf /etc/apt/sources.list.d/* /usr/local/lib/android /opt/ghc /usr/share/dotnet /usr/local/graalvm /usr/local/.ghcup \
+          /usr/local/share/powershell /usr/local/share/chromium /usr/local/lib/node_modules
+          sudo rm -rf /etc/apt/sources.list.d/* /usr/share/dotnet /usr/local/lib/android /opt/ghc /etc/mysql /etc/php
+          sudo -E apt-get -y purge azure-cli* docker* ghc* zulu* hhvm* llvm* firefox* google* dotnet* aspnetcore* powershell* openjdk* adoptopenjdk* mysql* php* mongodb* moby* snap* || true
+          sudo -E apt-get -qq update
+          sudo -E apt-get -qq install libfuse-dev $(curl -fsSL git.io/depends-ubuntu-2204)
+          sudo -E apt-get -qq autoremove --purge
+          sudo -E apt-get -qq clean
+          sudo apt-get clean
+          rm -rf /opt/hostedtoolcache
+          sudo timedatectl set-timezone "$TZ"
+      - name: Free Up Disk Space
+        uses: easimon/maximize-build-space@master
+        with:
+          root-reserve-mb: 62464 # 给 / 预留 61GiB 空间( docker 预留)
+          swap-size-mb: 1
+          remove-dotnet: 'true'
+          remove-android: 'true'
+          remove-haskell: 'true'
+          remove-codeql: 'true'
+          remove-docker-images: 'true'
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+      - name: Get Latest Release
+        id: get_version
+        run: |
+          VERSION=$(curl --silent "https://api.github.com/repos/${{ github.repository }}/releases/latest" | jq -r .tag_name)
+          echo "RELEASE_VERSION=${VERSION}" >> $GITHUB_ENV
+      - name: Set Image Tag
+        id: imageTag
+        run: echo "::set-output name=image_tag::$RELEASE_VERSION-$(date +%Y%m%d)-$(git rev-parse --short HEAD)"
+      - name: Set Up QEMU
+        uses: docker/setup-qemu-action@v2
+      - name: Set Up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      - name: Clone Model
+        run: |
+          sudo mkdir -p $GITHUB_WORKSPACE/bge-large-zh-v1.5
+          cd $GITHUB_WORKSPACE/bge-large-zh-v1.5
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/.gitattributes &> /dev/null
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/config.json &> /dev/null
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/config_sentence_transformers.json &> /dev/null
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/modules.json &> /dev/null
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/pytorch_model.bin &> /dev/null
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/sentence_bert_config.json &> /dev/null
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/special_tokens_map.json &> /dev/null
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/tokenizer.json &> /dev/null
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/tokenizer_config.json &> /dev/null
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/vocab.txt &> /dev/null
+          sudo mkdir -p $GITHUB_WORKSPACE/bge-large-zh-v1.5/1_Pooling
+          cd $GITHUB_WORKSPACE/bge-large-zh-v1.5/1_Pooling
+          sudo wget https://huggingface.co/BAAI/bge-large-zh-v1.5/resolve/main/1_Pooling/config.json &> /dev/null
+          sudo mkdir -p $GITHUB_WORKSPACE/chatglm3-6b
+          cd $GITHUB_WORKSPACE/chatglm3-6b
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/config.json &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/configuration_chatglm.py &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/model-00001-of-00007.safetensors &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/model-00002-of-00007.safetensors &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/model-00003-of-00007.safetensors &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/model-00004-of-00007.safetensors &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/model-00005-of-00007.safetensors &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/model-00006-of-00007.safetensors &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/model-00007-of-00007.safetensors &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/model.safetensors.index.json &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/modeling_chatglm.py &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/pytorch_model.bin.index.json &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/quantization.py &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/special_tokens_map.json &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/tokenization_chatglm.py &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/tokenizer.model &> /dev/null
+          sudo wget https://huggingface.co/THUDM/chatglm3-6b/resolve/main/tokenizer_config.json &> /dev/null
+          du -sh $GITHUB_WORKSPACE
+          du -sh $GITHUB_WORKSPACE/*
+          du -sh $GITHUB_WORKSPACE/bge-large-zh-v1.5/*       
+          du -sh $GITHUB_WORKSPACE/chatglm3-6b/*
+      - name: Show Runner Disk
+        run: df -hT
+      - name: Docker Build
+        run: |
+          docker build -t uswccr.ccs.tencentyun.com/chatchat/chatchat:${{ steps.imageTag.outputs.image_tag }} -f Dockerfile .
+      - name: Show Images Size
+        run: docker images
+      - name: Login To Tencent CCR
+        uses: docker/login-action@v2
+        with:
+          registry: uswccr.ccs.tencentyun.com
+          username: ${{ secrets.CCR_REGISTRY_USERNAME }}
+          password: ${{ secrets.CCR_REGISTRY_PASSWORD }}
+      - name: Docker Push
+        run: docker push uswccr.ccs.tencentyun.com/chatchat/chatchat:${{ steps.imageTag.outputs.image_tag }}
+#      - name: Login to Docker Hub
+#        uses: docker/login-action@v2
+#        with:
+#          username: ${{ secrets.DOCKERHUB_USERNAME }}
+#          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Update README.md
+        run: |
+          sed -i "s|uswccr.ccs.tencentyun.com/chatchat/chatchat:[^ ]*|uswccr.ccs.tencentyun.com/chatchat/chatchat:${{ steps.imageTag.outputs.image_tag }}|g" README.md
+          sed -i "s|uswccr.ccs.tencentyun.com/chatchat/chatchat:[^ ]*|uswccr.ccs.tencentyun.com/chatchat/chatchat:${{ steps.imageTag.outputs.image_tag }}|g" README_en.md
+          sed -i "s|uswccr.ccs.tencentyun.com/chatchat/chatchat:[^ ]*|uswccr.ccs.tencentyun.com/chatchat/chatchat:${{ steps.imageTag.outputs.image_tag }}|g" README_ja.md
+          git config --local user.email "action@github.com"
+          git config --local user.name "GitHub Action"
+          git commit -am "feat:update docker image:tag"
+      - name: Push README.md
+        uses: ad-m/github-push-action@master
+        with:
+          github_token: ${{ secrets.GH_PAT }}
+          branch: ${{ github.ref }}

.gitignore

@@ -1,6 +1,17 @@
+*.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__/
-*/**/__pycache__/
 *.py[cod]
 *$py.class
 
@@ -86,21 +97,21 @@ 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
+.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
+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
+poetry.lock
 
 # pdm
 #   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
@@ -159,18 +170,11 @@ cython_debug/
 #  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
 
-# Other files
-output/*
-log/*
-.chroma
-vector_store/*
-content/*
-api_content/*
+# Test File
+test.py
+configs/*.py
 
-llm/*
-embedding/*
 
-pyrightconfig.json
-loader/tmp_files
-flagged/*

.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

CONTRIBUTING.md

@@ -1,22 +0,0 @@
-# 贡献指南
-
-欢迎！我们是一个非常友好的社区，非常高兴您想要帮助我们让这个应用程序变得更好。但是，请您遵循一些通用准则以保持组织有序。
-
-1. 确保为您要修复的错误或要添加的功能创建了一个[问题](https://github.com/imClumsyPanda/langchain-ChatGLM/issues)，尽可能保持它们小。
-2. 请使用 `git pull --rebase` 来拉取和衍合上游的更新。
-3. 将提交合并为格式良好的提交。在提交说明中单独一行提到要解决的问题，如`Fix #<bug>`（有关更多可以使用的关键字，请参见[将拉取请求链接到问题](https://docs.github.com/en/issues/tracking-your-work-with-issues/linking-a-pull-request-to-an-issue)）。
-4. 推送到`dev`。在说明中提到正在解决的问题。
-
----
-
-# Contribution Guide
-
-Welcome! We're a pretty friendly community, and we're thrilled that you want to help make this app even better. However, we ask that you follow some general guidelines to keep things organized around here.
-
-1. Make sure an [issue](https://github.com/imClumsyPanda/langchain-ChatGLM/issues) is created for the bug you're about to fix, or feature you're about to add. Keep them as small as possible.
-
-2. Please use `git pull --rebase` to fetch and merge updates from the upstream.
-
-3. Rebase commits into well-formatted commits. Mention the issue being resolved in the commit message on a line all by itself like `Fixes #<bug>` (refer to [Linking a pull request to an issue](https://docs.github.com/en/issues/tracking-your-work-with-issues/linking-a-pull-request-to-an-issue) for more keywords you can use).
-
-4. Push into `dev`.  Mention which bug is being resolved in the description.

Dockerfile

@@ -1,36 +1,27 @@
-FROM python:3.8
-
-MAINTAINER "chatGLM"
-
-COPY agent /chatGLM/agent
-
-COPY chains /chatGLM/chains
-
-COPY configs /chatGLM/configs
-
-COPY content /chatGLM/content
-
-COPY models /chatGLM/models
-
-COPY nltk_data /chatGLM/content
-
-COPY requirements.txt /chatGLM/
-
-COPY cli_demo.py /chatGLM/
-
-COPY textsplitter /chatGLM/
-
-COPY webui.py /chatGLM/
-
-WORKDIR /chatGLM
-
-RUN pip install --user torch torchvision tensorboard cython -i https://pypi.tuna.tsinghua.edu.cn/simple
-# RUN pip install --user 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
-
-# RUN pip install --user 'git+https://github.com/facebookresearch/fvcore'
-# install detectron2
-# RUN git clone https://github.com/facebookresearch/detectron2
-
-RUN pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/ --trusted-host pypi.tuna.tsinghua.edu.cn
-
-CMD ["python","-u", "webui.py"]
+# Base Image
+FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04
+# Labels
+LABEL maintainer=chatchat
+# Environment Variables
+ENV HOME=/Langchain-Chatchat
+# Commands
+WORKDIR /
+RUN ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime && \
+    echo "Asia/Shanghai" > /etc/timezone && \
+    apt-get update -y && \
+    apt-get install -y --no-install-recommends python3.11 python3-pip curl libgl1 libglib2.0-0 jq && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/* && \
+    rm -f /usr/bin/python3 && \
+    ln -s /usr/bin/python3.11 /usr/bin/python3 && \
+    mkdir -p $HOME
+# Copy the application files
+COPY . $HOME
+WORKDIR $HOME
+# Install dependencies from requirements.txt
+RUN pip3 install -r requirements.txt -i https://pypi.org/simple && \
+    python3 copy_config_example.py && \
+    sed -i 's|MODEL_ROOT_PATH = ""|MODEL_ROOT_PATH = "/Langchain-Chatchat"|' configs/model_config.py && \
+    python3 init_database.py --recreate-vs
+EXPOSE 22 7861 8501
+ENTRYPOINT ["python3", "startup.py", "-a"]

Dockerfile-cuda

@@ -1,13 +0,0 @@
-FROM  nvidia/cuda:12.1.0-runtime-ubuntu20.04
-LABEL MAINTAINER="chatGLM"
-
-COPY . /chatGLM/
-
-WORKDIR /chatGLM
-
-RUN apt-get update -y && apt-get install python3 python3-pip curl -y  && apt-get clean
-RUN curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && python3 get-pip.py 
-
-RUN pip3 install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple --trusted-host pypi.tuna.tsinghua.edu.cn && rm -rf `pip3 cache dir`
-
-CMD ["python3","-u", "webui.py"]

README.md

@@ -1,16 +1,51 @@
-# 基于本地知识库的 ChatGLM 等大语言模型应用实现
+![](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。
+
+### ⚠️ 重要提示
+
+`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`。
+`0.2.10` 的后续 bug 修复将会直接推送到`master`分支，而不再进行版本更新。
+
+---
+
+## 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
 
-🌍 [_READ THIS IN ENGLISH_](README_en.md)
+🤖️ 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。
 
-🤖️ 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。
 
-💡 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。现已支持使用 [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B)、 [ClueAI/ChatYuan-large-v2](https://huggingface.co/ClueAI/ChatYuan-large-v2) 等大语言模型的接入。
+✅ 依托于本项目支持的开源 LLM 与 Embedding 模型，本项目可实现全部使用**开源**模型**离线私有部署**。与此同时，本项目也支持
+OpenAI GPT API 的调用，并将在后续持续扩充对各类模型及模型 API 的接入。
 
-✅ 本项目中 Embedding 默认选用的是 [GanymedeNil/text2vec-large-chinese](https://huggingface.co/GanymedeNil/text2vec-large-chinese/tree/main)，LLM 默认选用的是 [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B)。依托上述模型，本项目可实现全部使用**开源**模型**离线私有部署**。
+⛓️ 本项目实现原理如下图所示，过程包括加载文件 -> 读取文本 -> 文本分割 -> 文本向量化 -> 问句向量化 ->
+在文本向量中匹配出与问句向量最相似的 `top k`个 -> 匹配出的文本作为上下文和问题一起添加到 `prompt`中 -> 提交给 `LLM`生成回答。
 
-⛓️ 本项目实现原理如下图所示，过程包括加载文件 -> 读取文本 -> 文本分割 -> 文本向量化 -> 问句向量化 -> 在文本向量中匹配出与问句向量最相似的`top k`个 -> 匹配出的文本作为上下文和问题一起添加到`prompt`中 -> 提交给`LLM`生成回答。
+📺 [原理介绍视频](https://www.bilibili.com/video/BV13M4y1e7cN/?share_source=copy_web&vd_source=e6c5aafe684f30fbe41925d61ca6d514)
 
 ![实现原理图](img/langchain+chatglm.png)
 
@@ -18,209 +53,154 @@
 
 ![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/imClumsyPanda/langchain-ChatGLM/langchain-ChatGLM)
+🌐 [AutoDL 镜像](https://www.codewithgpu.com/i/chatchat-space/Langchain-Chatchat/Langchain-Chatchat) 中 `0.2.10`
 
-📓 [ModelWhale 在线运行项目](https://www.heywhale.com/mw/project/643977aa446c45f4592a1e59)
+版本所使用代码已更新至本项目 `v0.2.10` 版本。
 
-## 变更日志
+🐳 [Docker 镜像](isafetech/chatchat:0.2.10) 已经更新到 ```0.2.10``` 版本。
 
-参见 [变更日志](docs/CHANGELOG.md)。
-
-## 硬件需求
-
-- ChatGLM-6B 模型硬件需求
-
-    注：如未将模型下载至本地，请执行前检查`$HOME/.cache/huggingface/`文件夹剩余空间，模型文件下载至本地需要 15 GB 存储空间。
-    注：一些其它的可选启动项见[项目启动选项](docs/StartOption.md)
-    模型下载方法可参考 [常见问题](docs/FAQ.md) 中 Q8。
-  
-    | **量化等级**   | **最低 GPU 显存**（推理） | **最低 GPU 显存**（高效参数微调） |
-    | -------------- | ------------------------- | --------------------------------- |
-    | FP16（无量化） | 13 GB                     | 14 GB                             |
-    | INT8           | 8 GB                     | 9 GB                             |
-    | INT4           | 6 GB                      | 7 GB                              |
-
-- MOSS 模型硬件需求
-    
-    注：如未将模型下载至本地，请执行前检查`$HOME/.cache/huggingface/`文件夹剩余空间，模型文件下载至本地需要 70 GB 存储空间
-
-    模型下载方法可参考 [常见问题](docs/FAQ.md) 中 Q8。
-
-    | **量化等级**  | **最低 GPU 显存**（推理） | **最低 GPU 显存**（高效参数微调） |
-    |-------------------|-----------------------| --------------------------------- |
-    | FP16（无量化） | 68 GB             | -                     |
-    | INT8      | 20 GB          | -                     |
-
-- Embedding 模型硬件需求
-
-    本项目中默认选用的 Embedding 模型 [GanymedeNil/text2vec-large-chinese](https://huggingface.co/GanymedeNil/text2vec-large-chinese/tree/main) 约占用显存 3GB，也可修改为在 CPU 中运行。
-
-## 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 - 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。
-
-vue前端需要node18环境
-
-### 从本地加载模型
-
-请参考 [THUDM/ChatGLM-6B#从本地加载模型](https://github.com/THUDM/ChatGLM-6B#从本地加载模型)
-
-### 1. 安装环境
-
-参见 [安装指南](docs/INSTALL.md)。
-
-### 2. 设置模型默认参数
-
-在开始执行 Web UI 或命令行交互前，请先检查 [configs/model_config.py](configs/model_config.py) 中的各项模型参数设计是否符合需求。
-
-### 3. 执行脚本体验 Web UI 或命令行交互
-
-> 注：鉴于环境部署过程中可能遇到问题，建议首先测试命令行脚本。建议命令行脚本测试可正常运行后再运行 Web UI。
-
-执行 [cli_demo.py](cli_demo.py) 脚本体验**命令行交互**：
-```shell
-$ python cli_demo.py
-```
-
-或执行 [webui.py](webui.py) 脚本体验 **Web 交互**
+🌲 本次更新后同时支持DockerHub、阿里云、腾讯云镜像源：
 
 ```shell
-$ python webui.py
+docker run -d --gpus all -p 80:8501 isafetech/chatchat:0.2.10
+docker run -d --gpus all -p 80:8501 uswccr.ccs.tencentyun.com/chatchat/chatchat:0.2.10
+docker run -d --gpus all -p 80:8501 registry.cn-beijing.aliyuncs.com/chatchat/chatchat:0.2.10
 ```
 
-或执行 [api.py](api.py) 利用 fastapi 部署 API
+🧩 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
-$ python api.py
+
+# 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。
 ```
-或成功部署 API 后，执行以下脚本体验基于 VUE 的前端页面
+
+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
-$ cd views 
+$ python copy_config_example.py
+$ python init_database.py --recreate-vs
+ ```
 
-$ pnpm i
+### 4. 一键启动
 
-$ npm run dev
+按照以下命令启动项目
+
+```shell
+$ python startup.py -a
 ```
 
-VUE 前端界面如下图所示：
-1. `对话` 界面
-![](img/vue_0521_0.png)
-2. `知识库问答` 界面
-![](img/vue_0521_1.png)
-3. `Bing搜索` 界面
-![](img/vue_0521_2.png)
+### 5. 启动界面示例
 
-WebUI 界面如下图所示：
-1. `对话` Tab 界面
-![](img/webui_0521_0.png)
-2. `知识库测试 Beta` Tab 界面
-![](img/webui_0510_1.png)
-3. `模型配置` Tab 界面
-![](img/webui_0510_2.png)
+如果正常启动，你将能看到以下界面
 
-Web UI 可以实现如下功能：
+1. FastAPI Docs 界面
 
-1. 运行前自动读取`configs/model_config.py`中`LLM`及`Embedding`模型枚举及默认模型设置运行模型，如需重新加载模型，可在 `模型配置` Tab 重新选择后点击 `重新加载模型` 进行模型加载；
-2. 可手动调节保留对话历史长度、匹配知识库文段数量，可根据显存大小自行调节；
-3. `对话` Tab 具备模式选择功能，可选择 `LLM对话` 与 `知识库问答` 模式进行对话，支持流式对话；
-4. 添加 `配置知识库` 功能，支持选择已有知识库或新建知识库，并可向知识库中**新增**上传文件/文件夹，使用文件上传组件选择好文件后点击 `上传文件并加载知识库`，会将所选上传文档数据加载至知识库中，并基于更新后知识库进行问答；
-5. 新增 `知识库测试 Beta` Tab，可用于测试不同文本切分方法与检索相关度阈值设置，暂不支持将测试参数作为 `对话` Tab 设置参数。
-6. 后续版本中将会增加对知识库的修改或删除，及知识库中已导入文件的查看。
+![](img/fastapi_docs_026.png)
 
-### 常见问题
+2. Web UI 启动界面示例：
 
-参见 [常见问题](docs/FAQ.md)。
+- Web UI 对话界面：
 
-## Demo
+![img](img/LLM_success.png)
 
-以问题`chatglm-6b 的局限性具体体现在哪里，如何实现改进`为例：
+- Web UI 知识库管理页面：
 
-未使用 langchain 接入本地文档时：
+![](img/init_knowledge_base.jpg)
 
->ChatGLM-6B 是一个基于 GPT-3 的聊天机器人,它的局限性主要体现在以下几个方面:
->1. 语言模型的精度:GPT-3 是一种大型的语言模型,它的精度比较高,但是仍然有一些局限性。例如,它可能无法准确地理解某些方言、口音或者复杂的句子结构。
->2. 知识图谱的完整性:GPT-3 可以生成一些知识图谱,但是其完整性和准确性可能不够。例如,它可能无法准确地理解某些领域的专业知识和术语。
->3. 对话生成的连贯性:GPT-3 可以生成一些连贯的对话,但是其生成的对话可能不够自然。例如,它可能会生成一些虚假的、不连贯的对话或者误解用户的意图。
->
->为了改进 ChatGLM-6B,可以考虑以下几个方面:
->1. 提高语言模型的精度:可以通过增加训练数据、使用更好的语言模型架构、优化模型训练过程等方式来提高语言模型的精度。
->2. 增强知识图谱的完整性:可以通过增加知识图谱的维度、使用更好的知识图谱构建方法、优化知识图谱的匹配算法等方式来增强知识图谱的完整性。
->3. 提高对话生成的连贯性:可以通过增加对话生成模型的上下文信息、使用更好的上下文信息提取方法、优化对话生成模型的算法等方式来提高对话生成的连贯性。
->4. 引入更多的人类反馈:人类反馈可以帮助 ChatGLM-6B 更好地理解用户的意图和需求,从而提高对话生成的质量和准确性。可以通过引入更多的人类客服、使用人类反馈收集器等方式来引入更多的人类反馈。
+### 注意
 
-使用 langchain 接入 ChatGLM-6B 项目的 README.md 文件后 ChatGLM 的回答：
->ChatGLM-6B 是一个基于深度学习的自然语言处理模型,它在回答问题方面表现出色。但是,它也有一些局限性,具体如下:
->1. 语言理解有限:ChatGLM-6B 只学习了中文自然语言,对于其他语言可能会存在理解上的局限性。
->2. 知识储备不足:ChatGLM-6B 的训练数据集只包含了中文语料,因此它可能无法回答一些非中文的问题或者某些特定领域的问题。
->3. 数据量有限:ChatGLM-6B 的训练数据集只有几百万条记录,因此它可能无法回答一些非常具体或者复杂的问题。
->
->为了改进 ChatGLM-6B,可以考虑以下几个方面:
->1. 学习更多的语言知识:可以学习其他语言的自然语言处理技术,扩大语言理解的范围。
->2. 扩大知识储备:可以收集更多的中文语料,或者使用其他语言的数据集来扩充知识储备。
->3. 增加数据量:可以使用更大的数据集来训练 ChatGLM-6B,提高模型的表现。
->4. 引入更多的评估指标:可以引入更多的评估指标来评估模型的表现,从而发现 ChatGLM-6B 存在的不足和局限性。
->5. 改进模型架构:可以改进 ChatGLM-6B 的模型架构,提高模型的性能和表现。例如,可以使用更大的神经网络或者改进的卷积神经网络结构。
+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/)
 
-## 路线图
 
-- [ ] Langchain 应用
-  - [x] 接入非结构化文档（已支持 md、pdf、docx、txt 文件格式）
-  - [x] jpg 与 png 格式图片的 OCR 文字识别
-  - [x] 搜索引擎接入
-  - [ ] 本地网页接入
-  - [ ] 结构化数据接入（如 csv、Excel、SQL 等）
-  - [ ] 知识图谱/图数据库接入
-  - [ ] Agent 实现
-- [ ] 增加更多 LLM 模型支持
-  - [x] [THUDM/chatglm-6b](https://huggingface.co/THUDM/chatglm-6b)
-  - [x] [THUDM/chatglm-6b-int8](https://huggingface.co/THUDM/chatglm-6b-int8)
-  - [x] [THUDM/chatglm-6b-int4](https://huggingface.co/THUDM/chatglm-6b-int4)
-  - [x] [THUDM/chatglm-6b-int4-qe](https://huggingface.co/THUDM/chatglm-6b-int4-qe)
-  - [x] [ClueAI/ChatYuan-large-v2](https://huggingface.co/ClueAI/ChatYuan-large-v2)
-  - [x] [fnlp/moss-moon-003-sft](https://huggingface.co/fnlp/moss-moon-003-sft)
-- [ ] 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)
-- [ ] Web UI
-  - [x] 利用 gradio 实现 Web UI DEMO
-  - [x] 添加输出内容及错误提示
-  - [x] 引用标注
-  - [ ] 增加知识库管理
-    - [x] 选择知识库开始问答
-    - [x] 上传文件/文件夹至知识库
-    - [x] 知识库测试
-    - [ ] 删除知识库中文件
-  - [x] 支持搜索引擎问答
-- [ ] 增加 API 支持
-  - [x] 利用 fastapi 实现 API 部署方式
-  - [ ] 实现调用 API 的 Web UI Demo
-- [x] VUE 前端
+---
 
-## 项目交流群
-![二维码](img/qr_code_21.jpg)
+## 项目里程碑
 
-🎉 langchain-ChatGLM 项目交流群，如果你也对本项目感兴趣，欢迎加入群聊参与讨论交流。
++ `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 ···
+
+---
+
+## 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_108.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

@@ -1,247 +1,207 @@
-# ChatGLM Application with Local Knowledge Implementation
+![](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.
+Subsequent bug fixes for `0.2.10` will be pushed directly to the `master` branch without version updates.
+
+
+---
+
+## 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 `0.2.10` the codes are update to v0.2.10.
+
+🐳 [Docker image](isafetech/chatchat:0.2.10) is supported to ```0.2.10```.
+
+🌲 The latest update also provides support for image sources from DockerHub, Ali Cloud, and Tencent Cloud:
+
+```shell
+docker run -d --gpus all -p 80:8501 isafetech/chatchat:0.2.10
+docker run -d --gpus all -p 80:8501 uswccr.ccs.tencentyun.com/chatchat/chatchat:0.2.10
+docker run -d --gpus all -p 80:8501 registry.cn-beijing.aliyuncs.com/chatchat/chatchat:0.2.10
+```
+
+## 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)
 
-🌍 [_中文文档_](README.md)
+### WeChat Group
 
-🤖️ This is a ChatGLM application based on local knowledge, implemented using [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B) and [langchain](https://github.com/hwchase17/langchain).
+<img src="img/qr_code_90.jpg" alt="二维码" width="300" height="300" />
 
-💡 Inspired by [document.ai](https://github.com/GanymedeNil/document.ai) and [Alex Zhangji](https://github.com/AlexZhangji)'s [ChatGLM-6B Pull Request](https://github.com/THUDM/ChatGLM-6B/pull/216), this project establishes a local knowledge question-answering application using open-source models.
+### WeChat Official Account
 
-✅ The embeddings used in this project are [GanymedeNil/text2vec-large-chinese](https://huggingface.co/GanymedeNil/text2vec-large-chinese/tree/main), and the LLM is [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B). Relying on these models, this project enables the use of **open-source** models for **offline private deployment**.
-
-⛓️ The implementation principle of this project is illustrated in the figure below. The process includes loading files -> reading text -> text segmentation -> text vectorization -> question vectorization -> matching the top k most similar text vectors to the question vector -> adding the matched text to `prompt` along with the question as context -> submitting to `LLM` to generate an answer.
-
-![Implementation schematic diagram](img/langchain+chatglm.png)
-
-🚩 This project does not involve fine-tuning or training; however, fine-tuning or training can be employed to optimize the effectiveness of this project.
-
-📓 [ModelWhale online notebook](https://www.heywhale.com/mw/project/643977aa446c45f4592a1e59)
-
-## Changelog
-
-**[2023/04/15]**
-
-   1. refactor the project structure to keep the command line demo [cli_demo.py](cli_demo.py) and the Web UI demo [webui.py](webui.py) in the root directory.
-   2. Improve the Web UI by modifying it to first load the model according to the default option of [configs/model_config.py](configs/model_config.py) after running the Web UI, and adding error messages, etc.
-   3. Update FAQ.
-
-**[2023/04/12]**
-
-   1. Replaced the sample files in the Web UI to avoid issues with unreadable files due to encoding problems in Ubuntu;
-   2. Replaced the prompt template in `knowledge_based_chatglm.py` to prevent confusion in the content returned by ChatGLM, which may arise from the prompt template containing Chinese and English bilingual text.
-
-**[2023/04/11]**
-
-   1. Added Web UI V0.1 version (thanks to [@liangtongt](https://github.com/liangtongt));
-   2. Added Frequently Asked Questions in `README.md` (thanks to [@calcitem](https://github.com/calcitem) and [@bolongliu](https://github.com/bolongliu));
-   3. Enhanced automatic detection for the availability of `cuda`, `mps`, and `cpu` for LLM and Embedding model running devices;
-   4. Added a check for `filepath` in `knowledge_based_chatglm.py`. In addition to supporting single file import, it now supports a single folder path as input. After input, it will traverse each file in the folder and display a command-line message indicating the success of each file load.
-
-5. **[2023/04/09]**
-
-   1. Replaced the previously selected `ChatVectorDBChain` with `RetrievalQA` in `langchain`, effectively reducing the issue of stopping due to insufficient video memory after asking 2-3 times;
-   2. Added `EMBEDDING_MODEL`, `VECTOR_SEARCH_TOP_K`, `LLM_MODEL`, `LLM_HISTORY_LEN`, `REPLY_WITH_SOURCE` parameter value settings in `knowledge_based_chatglm.py`;
-   3. Added `chatglm-6b-int4` and `chatglm-6b-int4-qe`, which require less GPU memory, as LLM model options;
-   4. Corrected code errors in `README.md` (thanks to [@calcitem](https://github.com/calcitem)).
-
-**[2023/04/07]**
-
-   1. Resolved the issue of doubled video memory usage when loading the ChatGLM model (thanks to [@suc16](https://github.com/suc16) and [@myml](https://github.com/myml));
-   2. Added a mechanism to clear video memory;
-   3. Added `nghuyong/ernie-3.0-nano-zh` and `nghuyong/ernie-3.0-base-zh` as Embedding model options, which consume less video memory resources than `GanymedeNil/text2vec-large-chinese` (thanks to [@lastrei](https://github.com/lastrei)).
-
-## How to Use
-
-### Hardware Requirements
-
-- ChatGLM-6B Model Hardware Requirements
-  
-     | **Quantization Level** | **Minimum GPU Memory** (inference) | **Minimum GPU Memory** (efficient parameter fine-tuning) |
-     | -------------- | ------------------------- | --------------------------------- |
-     | FP16 (no quantization) | 13 GB | 14 GB |
-     | INT8 | 8 GB | 9 GB |
-     | INT4 | 6 GB | 7 GB |
-
-- Embedding Model Hardware Requirements
-
-     The default Embedding model [GanymedeNil/text2vec-large-chinese](https://huggingface.co/GanymedeNil/text2vec-large-chinese/tree/main) in this project occupies around 3GB of video memory and can also be configured to run on a CPU.
-### Software Requirements
-
-This repository has been tested with Python 3.8 and CUDA 11.7 environments.
-
-### 1. Setting up the environment
-
-* Environment check
-
-```shell
-# First, make sure your machine has Python 3.8 or higher installed
-$ python --version
-Python 3.8.13
-
-# If your version is lower, you can use conda to install the environment
-$ conda create -p /your_path/env_name python=3.8
-
-# Activate the environment
-$ source activate /your_path/env_name
-
-# Deactivate the environment
-$ source deactivate /your_path/env_name
-
-# Remove the environment
-$ conda env remove -p  /your_path/env_name
-```
-
-* Project dependencies
-
-```shell
-
-# Clone the repository
-$ git clone https://github.com/imClumsyPanda/langchain-ChatGLM.git
-
-# Install dependencies
-$ pip install -r requirements.txt
-```
-
-Note: When using langchain.document_loaders.UnstructuredFileLoader for unstructured file integration, you may need to install other dependency packages according to the documentation. Please refer to [langchain documentation](https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/unstructured_file.html).
-
-### 2. Run Scripts to Experience Web UI or Command Line Interaction
-
-Execute [webui.py](webui.py) script to experience **Web interaction** <img src="https://img.shields.io/badge/Version-0.1-brightgreen">
-```commandline
-python webui.py
-
-```
-Or execute [api.py](api.py) script to deploy web api.
-```shell
-$ python api.py
-```
-Note: Before executing, check the remaining space in the `$HOME/.cache/huggingface/` folder, at least 15G.
-
-Or execute following command to run VUE after api.py executed
-```shell
-$ cd views 
-
-$ pnpm i
-
-$ npm run dev
-```
-
-VUE interface screenshots:
-
-![](img/vue_0521_0.png)
-
-![](img/vue_0521_1.png)
-
-![](img/vue_0521_2.png)
-
-Web UI interface screenshots:
-
-![img.png](img/webui_0521_0.png)
-
-![](img/webui_0510_1.png)
-
-![](img/webui_0510_2.png)
-
-The Web UI supports the following features:
-
-1. Automatically reads the `LLM` and `embedding` model enumerations in `configs/model_config.py`, allowing you to select and reload the model by clicking `重新加载模型`.
-2. The length of retained dialogue history can be manually adjusted according to the available video memory.
-3. Adds a file upload function. Select the uploaded file through the drop-down box, click `加载文件` to load the file, and change the loaded file at any time during the process.
-
-Alternatively, execute the [knowledge_based_chatglm.py](https://chat.openai.com/chat/cli_demo.py) script to experience **command line interaction**:
-
-```commandline
-python knowledge_based_chatglm.py
-```
-
-### FAQ
-
-Q1: What file formats does this project support?
-
-A1: Currently, this project has been tested with txt, docx, and md file formats. For more file formats, please refer to the [langchain documentation](https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/unstructured_file.html). It is known that if the document contains special characters, there might be issues with loading the file.
-
-Q2: How can I resolve the `detectron2` dependency issue when reading specific file formats?
-
-A2: As the installation process for this package can be problematic and it is only required for some file formats, it is not included in `requirements.txt`. You can install it with the following command:
-
-```commandline
-pip install "detectron2@git+https://github.com/facebookresearch/detectron2.git@v0.6#egg=detectron2"
-```
-
-Q3: How can I solve the `Resource punkt not found.` error?
-
-A3: Unzip the `packages/tokenizers` folder from https://github.com/nltk/nltk_data/raw/gh-pages/packages/tokenizers/punkt.zip, and place it in the `nltk_data/tokenizers` storage path.
-
-The `nltk_data` storage path can be found using `nltk.data.path`.
-
-Q4: How can I solve the `Resource averaged_perceptron_tagger not found.` error?
-
-A4: Download https://github.com/nltk/nltk_data/blob/gh-pages/packages/taggers/averaged_perceptron_tagger.zip, extract it, and place it in the `nltk_data/taggers` storage path.
-
-The `nltk_data` storage path can be found using `nltk.data.path`.
-
-Q5: Can this project run in Google Colab?
-
-A5: You can try running the chatglm-6b-int4 model in Google Colab. Please note that if you want to run the Web UI in Colab, you need to set the `share` parameter in `demo.queue(concurrency_count=3).launch(server_name='0.0.0.0', share=False, inbrowser=False)` to `True`.
-
-This issue is related to the system environment. For more details, please refer to [Issues with installing packages using pip in Anaconda](docs/Issue-with-Installing-Packages-Using-pip-in-Anaconda.md).
-
-## DEMO
-
-Using the question "What are the limitations of ChatGLM-6B and how can they be improved?" as an example:
-
-Without using langchain to access local documents:
-
-> ChatGLM-6B is a chatbot based on GPT-3, and its limitations are mainly reflected in the following aspects:
->
->   1. Language model accuracy: Although GPT-3 is a large language model with relatively high accuracy, it still has some limitations. For instance, it may not be able to accurately understand certain dialects, accents, or complex sentence structures.
->   2. Completeness of the knowledge graph: GPT-3 can generate some knowledge graphs, but its completeness and accuracy may not be sufficient. For example, it may struggle to accurately understand specific domain expertise and terminology.
->   3. Coherence of dialogue generation: While GPT-3 can generate somewhat coherent dialogues, they may not always be natural. For instance, it may generate false, incoherent dialogue or misinterpret the user's intent.
->
->   To improve ChatGLM-6B, consider the following aspects:
->
->   1. Enhance the accuracy of the language model: The accuracy of the language model can be improved by increasing the training data, using better language model architectures, and optimizing the model training process.
->   2. Strengthen the integrity of the knowledge graph: The integrity of the knowledge graph can be enhanced by increasing its dimensions, employing better knowledge graph construction methods, and optimizing the knowledge graph's matching algorithm.
->   3. Boost the coherence of dialogue generation: The coherence of dialogue generation can be improved by augmenting the context information of the dialogue generation model, utilizing better context information extraction methods, and optimizing the dialogue generation model's algorithm.
->   4. Incorporate more human feedback: Human feedback can help ChatGLM-6B better understand users' intentions and needs, thereby improving the quality and accuracy of dialogue generation. More human feedback can be introduced by involving more human agents and using human feedback collectors.
-
-ChatGLM's answer after using LangChain to access the README.md file of the ChatGLM-6B project:
->ChatGLM-6B is a deep learning-based natural language processing model that excels at answering questions. However, it also has some limitations, as follows:
->1. Limited language understanding: ChatGLM-6B has been primarily trained on Chinese natural language, and its understanding of other languages may be limited.
->2. Insufficient knowledge base: The training dataset of ChatGLM-6B contains only a Chinese corpus, so it may not be able to answer non-Chinese questions or queries in specific domains.
->3. Limited data volume: ChatGLM-6B's training dataset has only a few million records, which may hinder its ability to answer very specific or complex questions.
->
->To improve ChatGLM-6B, consider the following aspects:
->1. Expand language knowledge: Learn natural language processing techniques in other languages to broaden the model's language understanding capabilities.
->2. Broaden the knowledge base: Collect more Chinese corpora or use datasets in other languages to expand the model's knowledge base.
->3. Increase data volume: Use larger datasets to train ChatGLM-6B, which can improve the model's performance.
->4. Introduce more evaluation metrics: Incorporate additional evaluation metrics to assess the model's performance, which can help identify the shortcomings and limitations of ChatGLM-6B.
->5. Enhance the model architecture: Improve ChatGLM-6B's model architecture to boost its performance and capabilities. For example, employ larger neural networks or refined convolutional neural network structures.
-
-## Roadmap
-
-- [x] Implement LangChain + ChatGLM-6B for local knowledge application
-- [x] Unstructured file access based on langchain
-   - [x].md
-   - [x].pdf
-   - [x].docx
-   - [x].txt
-- [ ] Add support for more LLM models
-   - [x] THUDM/chatglm-6b
-   - [x] THUDM/chatglm-6b-int4
-   - [x] THUDM/chatglm-6b-int4-qe
-- [ ] Add Web UI DEMO
-   - [x] Implement Web UI DEMO using Gradio
-   - [x] Add output and error messages
-   - [x] Citation callout
-   - [ ] Knowledge base management
-     - [x] QA based on selected knowledge base
-     - [x] Add files/folder to knowledge base
-     - [ ] Add files/folder to knowledge base
-   - [ ] Implement Web UI DEMO using Streamlit
-- [ ] Add support for API deployment
-  - [x] Use fastapi to implement API
-  - [ ] Implement Web UI DEMO for API calls
+<img src="img/official_wechat_mp_account.png" alt="图片" width="900" height="300" />

README_ja.md

@@ -0,0 +1,200 @@
+![](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)
+
+ChatGLM などの大規模な言語モデルや Langchain などのアプリケーション フレームワークに基づいた、オープン
+ソースのオフライン展開可能な検索拡張生成 (RAG) 大規模モデル ナレッジ ベース プロジェクトです。
+
+⚠️`0.2.10` は `0.2.x` シリーズの最終バージョンとなり、`0.2.x`
+シリーズはアップデートと技術サポートを終了し、より適用性の高い `Langchain-Chachat 0.3.x` の開発に努めます。 。
+`0.2.10` のその後のバグ修正は、バージョン更新なしで `master` ブランチに直接プッシュされます。
+
+---
+
+## 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、`0.2.10` では v0.2.10
+にアップデートされました。
+
+🐳 [Docker イメージ](isafetech/chatchat:0.2.10)
+
+🌲 今回のアップデートにより、DockerHub、阿里雲、騰訊のクラウドにも対応しました。より広範なクラウド環境で利用可能となりました。
+
+```shell
+docker run -d --gpus all -p 80:8501 isafetech/chatchat:0.2.10
+docker run -d --gpus all -p 80:8501 uswccr.ccs.tencentyun.com/chatchat/chatchat:0.2.10
+docker run -d --gpus all -p 80:8501 registry.cn-beijing.aliyuncs.com/chatchat/chatchat:0.2.10
+```
+
+## 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/) をご参照ください。
+
+## 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 3.11.7
+```
+
+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。
+
+---
+
+## プロジェクトのマイルストーン
+
++ `2023 年 4 月`: `Langchain-ChatGLM 0.1.0` がリリースされ、ChatGLM-6B モデルに基づくローカル ナレッジ ベースの質問と回答がサポートされました。
++ `2023 年 8 月`: `Langchain-ChatGLM` は `Langchain-Chatchat` に名前変更され、モデル読み込みソリューションとして `fastchat` を使用し、より多くのモデルとデータベースをサポートする `0.2.0` がリリースされました。
++ `2023 年 10 月`: `Langchain-Chachat 0.2.5` リリース、エージェント コンテンツ、オープンソース プロジェクトを`Founder Park & Zhipu AI & Zilliz`で開始
+  開催したハッカソンでは3位に入賞しました。
++ `2023 年 12 月`: `Langchain-Chachat`オープンソース プロジェクトは **20,000** つ以上のスターを獲得しました。
++ `2024 年 1 月`: `LangChain 0.1.x` がリリースされ、`Langchain-Chachat 0.2.x` が安定版 `0.2.10` をリリースしました。
+  今後はアップデートと技術サポートを停止し、より適用性の高い`Langchain-Chachat 0.3.x`の開発に努める予定です。
+
++ 🔥 これからのChatchatストーリーを一緒に楽しみにしましょう···
+
+---
+
+## 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_90.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" />

agent/__init__.py

@@ -1 +0,0 @@
-from agent.bing_search import bing_search

agent/bing_search.py

@@ -1,19 +0,0 @@
-#coding=utf8
-
-from langchain.utilities import BingSearchAPIWrapper
-from configs.model_config import BING_SEARCH_URL, BING_SUBSCRIPTION_KEY
-
-
-def bing_search(text, result_len=3):
-    if not (BING_SEARCH_URL and BING_SUBSCRIPTION_KEY):
-        return [{"snippet": "please set BING_SUBSCRIPTION_KEY and BING_SEARCH_URL in os ENV",
-                 "title": "env inof not fould",
-                 "link": "https://python.langchain.com/en/latest/modules/agents/tools/examples/bing_search.html"}]
-    search = BingSearchAPIWrapper(bing_subscription_key=BING_SUBSCRIPTION_KEY,
-                                  bing_search_url=BING_SEARCH_URL)
-    return search.results(text, result_len)
-
-
-if __name__ == "__main__":
-    r = bing_search('python')
-    print(r)

api.py

@@ -1,405 +0,0 @@
-import argparse
-import json
-import os
-import shutil
-from typing import List, Optional
-import urllib
-
-import nltk
-import pydantic
-import uvicorn
-from fastapi import Body, FastAPI, File, Form, Query, UploadFile, WebSocket
-from fastapi.middleware.cors import CORSMiddleware
-from pydantic import BaseModel
-from typing_extensions import Annotated
-from starlette.responses import RedirectResponse
-
-from chains.local_doc_qa import LocalDocQA
-from configs.model_config import (VS_ROOT_PATH, UPLOAD_ROOT_PATH, EMBEDDING_DEVICE,
-                                  EMBEDDING_MODEL, NLTK_DATA_PATH,
-                                  VECTOR_SEARCH_TOP_K, LLM_HISTORY_LEN, OPEN_CROSS_DOMAIN)
-import models.shared as shared
-from models.loader.args import parser
-from models.loader import LoaderCheckPoint
-
-nltk.data.path = [NLTK_DATA_PATH] + nltk.data.path
-
-
-class BaseResponse(BaseModel):
-    code: int = pydantic.Field(200, description="HTTP status code")
-    msg: str = pydantic.Field("success", description="HTTP status message")
-
-    class Config:
-        schema_extra = {
-            "example": {
-                "code": 200,
-                "msg": "success",
-            }
-        }
-
-
-class ListDocsResponse(BaseResponse):
-    data: List[str] = pydantic.Field(..., description="List of document names")
-
-    class Config:
-        schema_extra = {
-            "example": {
-                "code": 200,
-                "msg": "success",
-                "data": ["doc1.docx", "doc2.pdf", "doc3.txt"],
-            }
-        }
-
-
-class ChatMessage(BaseModel):
-    question: str = pydantic.Field(..., description="Question text")
-    response: str = pydantic.Field(..., description="Response text")
-    history: List[List[str]] = pydantic.Field(..., description="History text")
-    source_documents: List[str] = pydantic.Field(
-        ..., description="List of source documents and their scores"
-    )
-
-    class Config:
-        schema_extra = {
-            "example": {
-                "question": "工伤保险如何办理？",
-                "response": "根据已知信息，可以总结如下：\n\n1. 参保单位为员工缴纳工伤保险费，以保障员工在发生工伤时能够获得相应的待遇。\n2. 不同地区的工伤保险缴费规定可能有所不同，需要向当地社保部门咨询以了解具体的缴费标准和规定。\n3. 工伤从业人员及其近亲属需要申请工伤认定，确认享受的待遇资格，并按时缴纳工伤保险费。\n4. 工伤保险待遇包括工伤医疗、康复、辅助器具配置费用、伤残待遇、工亡待遇、一次性工亡补助金等。\n5. 工伤保险待遇领取资格认证包括长期待遇领取人员认证和一次性待遇领取人员认证。\n6. 工伤保险基金支付的待遇项目包括工伤医疗待遇、康复待遇、辅助器具配置费用、一次性工亡补助金、丧葬补助金等。",
-                "history": [
-                    [
-                        "工伤保险是什么？",
-                        "工伤保险是指用人单位按照国家规定，为本单位的职工和用人单位的其他人员，缴纳工伤保险费，由保险机构按照国家规定的标准，给予工伤保险待遇的社会保险制度。",
-                    ]
-                ],
-                "source_documents": [
-                    "出处 [1] 广州市单位从业的特定人员参加工伤保险办事指引.docx：\n\n\t( 一)  从业单位  (组织)  按“自愿参保”原则，  为未建 立劳动关系的特定从业人员单项参加工伤保险 、缴纳工伤保 险费。",
-                    "出处 [2] ...",
-                    "出处 [3] ...",
-                ],
-            }
-        }
-
-
-def get_folder_path(local_doc_id: str):
-    return os.path.join(UPLOAD_ROOT_PATH, local_doc_id)
-
-
-def get_vs_path(local_doc_id: str):
-    return os.path.join(VS_ROOT_PATH, local_doc_id)
-
-
-def get_file_path(local_doc_id: str, doc_name: str):
-    return os.path.join(UPLOAD_ROOT_PATH, local_doc_id, doc_name)
-
-
-async def upload_file(
-        file: UploadFile = File(description="A single binary file"),
-        knowledge_base_id: str = Form(..., description="Knowledge Base Name", example="kb1"),
-):
-    saved_path = get_folder_path(knowledge_base_id)
-    if not os.path.exists(saved_path):
-        os.makedirs(saved_path)
-
-    file_content = await file.read()  # 读取上传文件的内容
-
-    file_path = os.path.join(saved_path, file.filename)
-    if os.path.exists(file_path) and os.path.getsize(file_path) == len(file_content):
-        file_status = f"文件 {file.filename} 已存在。"
-        return BaseResponse(code=200, msg=file_status)
-
-    with open(file_path, "wb") as f:
-        f.write(file_content)
-
-    vs_path = get_vs_path(knowledge_base_id)
-    vs_path, loaded_files = local_doc_qa.init_knowledge_vector_store([file_path], vs_path)
-    if len(loaded_files) > 0:
-        file_status = f"文件 {file.filename} 已上传至新的知识库，并已加载知识库，请开始提问。"
-        return BaseResponse(code=200, msg=file_status)
-    else:
-        file_status = "文件上传失败，请重新上传"
-        return BaseResponse(code=500, msg=file_status)
-
-
-async def upload_files(
-        files: Annotated[
-            List[UploadFile], File(description="Multiple files as UploadFile")
-        ],
-        knowledge_base_id: str = Form(..., description="Knowledge Base Name", example="kb1"),
-):
-    saved_path = get_folder_path(knowledge_base_id)
-    if not os.path.exists(saved_path):
-        os.makedirs(saved_path)
-    filelist = []
-    for file in files:
-        file_content = ''
-        file_path = os.path.join(saved_path, file.filename)
-        file_content = file.file.read()
-        if os.path.exists(file_path) and os.path.getsize(file_path) == len(file_content):
-            continue
-        with open(file_path, "ab+") as f:
-            f.write(file_content)
-        filelist.append(file_path)
-    if filelist:
-        vs_path, loaded_files = local_doc_qa.init_knowledge_vector_store(filelist, get_vs_path(knowledge_base_id))
-        if len(loaded_files):
-            file_status = f"已上传 {'、'.join([os.path.split(i)[-1] for i in loaded_files])} 至知识库，并已加载知识库，请开始提问"
-            return BaseResponse(code=200, msg=file_status)
-    file_status = "文件未成功加载，请重新上传文件"
-    return BaseResponse(code=500, msg=file_status)
-
-
-async def list_docs(
-        knowledge_base_id: Optional[str] = Query(default=None, description="Knowledge Base Name", example="kb1")
-):
-    if knowledge_base_id:
-        local_doc_folder = get_folder_path(knowledge_base_id)
-        if not os.path.exists(local_doc_folder):
-            return {"code": 1, "msg": f"Knowledge base {knowledge_base_id} not found"}
-        all_doc_names = [
-            doc
-            for doc in os.listdir(local_doc_folder)
-            if os.path.isfile(os.path.join(local_doc_folder, doc))
-        ]
-        return ListDocsResponse(data=all_doc_names)
-    else:
-        if not os.path.exists(UPLOAD_ROOT_PATH):
-            all_doc_ids = []
-        else:
-            all_doc_ids = [
-                folder
-                for folder in os.listdir(UPLOAD_ROOT_PATH)
-                if os.path.isdir(os.path.join(UPLOAD_ROOT_PATH, folder))
-            ]
-
-        return ListDocsResponse(data=all_doc_ids)
-
-
-async def delete_docs(
-        knowledge_base_id: str = Query(...,
-                                       description="Knowledge Base Name(注意此方法仅删除上传的文件并不会删除知识库(FAISS)内数据)",
-                                       example="kb1"),
-        doc_name: Optional[str] = Query(
-            None, description="doc name", example="doc_name_1.pdf"
-        ),
-):
-    knowledge_base_id = urllib.parse.unquote(knowledge_base_id)
-    if not os.path.exists(os.path.join(UPLOAD_ROOT_PATH, knowledge_base_id)):
-        return {"code": 1, "msg": f"Knowledge base {knowledge_base_id} not found"}
-    if doc_name:
-        doc_path = get_file_path(knowledge_base_id, doc_name)
-        if os.path.exists(doc_path):
-            os.remove(doc_path)
-            return BaseResponse(code=200, msg=f"document {doc_name} delete success")
-        else:
-            return BaseResponse(code=1, msg=f"document {doc_name} not found")
-
-        remain_docs = await list_docs(knowledge_base_id)
-        remain_docs = remain_docs.json()
-        if len(remain_docs["data"]) == 0:
-            shutil.rmtree(get_folder_path(knowledge_base_id), ignore_errors=True)
-        else:
-            local_doc_qa.init_knowledge_vector_store(
-                get_folder_path(knowledge_base_id), get_vs_path(knowledge_base_id)
-            )
-    else:
-        shutil.rmtree(get_folder_path(knowledge_base_id))
-        return BaseResponse(code=200, msg=f"Knowledge Base {knowledge_base_id} delete success")
-
-
-async def local_doc_chat(
-        knowledge_base_id: str = Body(..., description="Knowledge Base Name", example="kb1"),
-        question: str = Body(..., description="Question", example="工伤保险是什么？"),
-        history: List[List[str]] = Body(
-            [],
-            description="History of previous questions and answers",
-            example=[
-                [
-                    "工伤保险是什么？",
-                    "工伤保险是指用人单位按照国家规定，为本单位的职工和用人单位的其他人员，缴纳工伤保险费，由保险机构按照国家规定的标准，给予工伤保险待遇的社会保险制度。",
-                ]
-            ],
-        ),
-):
-    vs_path = os.path.join(VS_ROOT_PATH, knowledge_base_id)
-    if not os.path.exists(vs_path):
-        # return BaseResponse(code=1, msg=f"Knowledge base {knowledge_base_id} not found")
-        return ChatMessage(
-            question=question,
-            response=f"Knowledge base {knowledge_base_id} not found",
-            history=history,
-            source_documents=[],
-        )
-    else:
-        for resp, history in local_doc_qa.get_knowledge_based_answer(
-                query=question, vs_path=vs_path, chat_history=history, streaming=True
-        ):
-            pass
-        source_documents = [
-            f"""出处 [{inum + 1}] {os.path.split(doc.metadata['source'])[-1]}：\n\n{doc.page_content}\n\n"""
-            f"""相关度：{doc.metadata['score']}\n\n"""
-            for inum, doc in enumerate(resp["source_documents"])
-        ]
-
-        return ChatMessage(
-            question=question,
-            response=resp["result"],
-            history=history,
-            source_documents=source_documents,
-        )
-
-
-async def bing_search_chat(
-        question: str = Body(..., description="Question", example="工伤保险是什么？"),
-        history: Optional[List[List[str]]] = Body(
-            [],
-            description="History of previous questions and answers",
-            example=[
-                [
-                    "工伤保险是什么？",
-                    "工伤保险是指用人单位按照国家规定，为本单位的职工和用人单位的其他人员，缴纳工伤保险费，由保险机构按照国家规定的标准，给予工伤保险待遇的社会保险制度。",
-                ]
-            ],
-        ),
-):
-    for resp, history in local_doc_qa.get_search_result_based_answer(
-            query=question, chat_history=history, streaming=True
-    ):
-        pass
-    source_documents = [
-        f"""出处 [{inum + 1}] [{doc.metadata["source"]}]({doc.metadata["source"]}) \n\n{doc.page_content}\n\n"""
-        for inum, doc in enumerate(resp["source_documents"])
-    ]
-
-    return ChatMessage(
-        question=question,
-        response=resp["result"],
-        history=history,
-        source_documents=source_documents,
-    )
-
-async def chat(
-        question: str = Body(..., description="Question", example="工伤保险是什么？"),
-        history: List[List[str]] = Body(
-            [],
-            description="History of previous questions and answers",
-            example=[
-                [
-                    "工伤保险是什么？",
-                    "工伤保险是指用人单位按照国家规定，为本单位的职工和用人单位的其他人员，缴纳工伤保险费，由保险机构按照国家规定的标准，给予工伤保险待遇的社会保险制度。",
-                ]
-            ],
-        ),
-):
-    for answer_result in local_doc_qa.llm.generatorAnswer(prompt=question, history=history,
-                                                          streaming=True):
-        resp = answer_result.llm_output["answer"]
-        history = answer_result.history
-        pass
-
-    return ChatMessage(
-        question=question,
-        response=resp,
-        history=history,
-        source_documents=[],
-    )
-
-
-async def stream_chat(websocket: WebSocket, knowledge_base_id: str):
-    await websocket.accept()
-    turn = 1
-    while True:
-        input_json = await websocket.receive_json()
-        question, history, knowledge_base_id = input_json[""], input_json["history"], input_json["knowledge_base_id"]
-        vs_path = os.path.join(VS_ROOT_PATH, knowledge_base_id)
-
-        if not os.path.exists(vs_path):
-            await websocket.send_json({"error": f"Knowledge base {knowledge_base_id} not found"})
-            await websocket.close()
-            return
-
-        await websocket.send_json({"question": question, "turn": turn, "flag": "start"})
-
-        last_print_len = 0
-        for resp, history in local_doc_qa.get_knowledge_based_answer(
-                query=question, vs_path=vs_path, chat_history=history, streaming=True
-        ):
-            await websocket.send_text(resp["result"][last_print_len:])
-            last_print_len = len(resp["result"])
-
-        source_documents = [
-            f"""出处 [{inum + 1}] {os.path.split(doc.metadata['source'])[-1]}：\n\n{doc.page_content}\n\n"""
-            f"""相关度：{doc.metadata['score']}\n\n"""
-            for inum, doc in enumerate(resp["source_documents"])
-        ]
-
-        await websocket.send_text(
-            json.dumps(
-                {
-                    "question": question,
-                    "turn": turn,
-                    "flag": "end",
-                    "sources_documents": source_documents,
-                },
-                ensure_ascii=False,
-            )
-        )
-        turn += 1
-
-
-async def document():
-    return RedirectResponse(url="/docs")
-
-
-
-
-
-def api_start(host, port):
-    global app
-    global local_doc_qa
-
-    llm_model_ins = shared.loaderLLM()
-    llm_model_ins.set_history_len(LLM_HISTORY_LEN)
-
-    app = FastAPI()
-    # Add CORS middleware to allow all origins
-    # 在config.py中设置OPEN_DOMAIN=True，允许跨域
-    # set OPEN_DOMAIN=True in config.py to allow cross-domain
-    if OPEN_CROSS_DOMAIN:
-        app.add_middleware(
-            CORSMiddleware,
-            allow_origins=["*"],
-            allow_credentials=True,
-            allow_methods=["*"],
-            allow_headers=["*"],
-        )
-    app.websocket("/local_doc_qa/stream-chat/{knowledge_base_id}")(stream_chat)
-
-    app.get("/", response_model=BaseResponse)(document)
-
-    app.post("/chat", response_model=ChatMessage)(chat)
-
-    app.post("/local_doc_qa/upload_file", response_model=BaseResponse)(upload_file)
-    app.post("/local_doc_qa/upload_files", response_model=BaseResponse)(upload_files)
-    app.post("/local_doc_qa/local_doc_chat", response_model=ChatMessage)(local_doc_chat)
-    app.post("/local_doc_qa/bing_search_chat", response_model=ChatMessage)(bing_search_chat)
-    app.get("/local_doc_qa/list_files", response_model=ListDocsResponse)(list_docs)
-    app.delete("/local_doc_qa/delete_file", response_model=BaseResponse)(delete_docs)
-
-    local_doc_qa = LocalDocQA()
-    local_doc_qa.init_cfg(
-        llm_model=llm_model_ins,
-        embedding_model=EMBEDDING_MODEL,
-        embedding_device=EMBEDDING_DEVICE,
-        top_k=VECTOR_SEARCH_TOP_K,
-    )
-    uvicorn.run(app, host=host, port=port)
-
-
-if __name__ == "__main__":
-    parser.add_argument("--host", type=str, default="0.0.0.0")
-    parser.add_argument("--port", type=int, default=7861)
-    # 初始化消息
-    args = None
-    args = parser.parse_args()
-    args_dict = vars(args)
-    shared.loaderCheckPoint = LoaderCheckPoint(args_dict)
-    api_start(args.host, args.port)

chains/llmchain_with_history.py

@@ -0,0 +1,22 @@
+from server.utils import get_ChatOpenAI
+from configs.model_config import LLM_MODELS, TEMPERATURE
+from langchain.chains import LLMChain
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    HumanMessagePromptTemplate,
+)
+
+model = get_ChatOpenAI(model_name=LLM_MODELS[0], temperature=TEMPERATURE)
+
+
+human_prompt = "{input}"
+human_message_template = HumanMessagePromptTemplate.from_template(human_prompt)
+
+chat_prompt = ChatPromptTemplate.from_messages(
+    [("human", "我们来玩成语接龙，我先来，生龙活虎"),
+     ("ai", "虎头虎脑"),
+     ("human", "{input}")])
+
+
+chain = LLMChain(prompt=chat_prompt, llm=model, verbose=True)
+print(chain({"input": "恼羞成怒"}))

chains/local_doc_qa.py

@@ -1,349 +0,0 @@
-from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.document_loaders import UnstructuredFileLoader, TextLoader
-from configs.model_config import *
-import datetime
-from textsplitter import ChineseTextSplitter
-from typing import List, Tuple, Dict
-from langchain.docstore.document import Document
-import numpy as np
-from utils import torch_gc
-from tqdm import tqdm
-from pypinyin import lazy_pinyin
-from loader import UnstructuredPaddleImageLoader, UnstructuredPaddlePDFLoader
-from models.base import (BaseAnswer,
-                         AnswerResult,
-                         AnswerResultStream,
-                         AnswerResultQueueSentinelTokenListenerQueue)
-from models.loader.args import parser
-from models.loader import LoaderCheckPoint
-import models.shared as shared
-from agent import bing_search
-from langchain.docstore.document import Document
-
-
-def load_file(filepath, sentence_size=SENTENCE_SIZE):
-    if filepath.lower().endswith(".md"):
-        loader = UnstructuredFileLoader(filepath, mode="elements")
-        docs = loader.load()
-    elif filepath.lower().endswith(".txt"):
-        loader = TextLoader(filepath, autodetect_encoding=True)
-        textsplitter = ChineseTextSplitter(pdf=False, sentence_size=sentence_size)
-        docs = loader.load_and_split(textsplitter)
-    elif filepath.lower().endswith(".pdf"):
-        loader = UnstructuredPaddlePDFLoader(filepath)
-        textsplitter = ChineseTextSplitter(pdf=True, sentence_size=sentence_size)
-        docs = loader.load_and_split(textsplitter)
-    elif filepath.lower().endswith(".jpg") or filepath.lower().endswith(".png"):
-        loader = UnstructuredPaddleImageLoader(filepath, mode="elements")
-        textsplitter = ChineseTextSplitter(pdf=False, sentence_size=sentence_size)
-        docs = loader.load_and_split(text_splitter=textsplitter)
-    else:
-        loader = UnstructuredFileLoader(filepath, mode="elements")
-        textsplitter = ChineseTextSplitter(pdf=False, sentence_size=sentence_size)
-        docs = loader.load_and_split(text_splitter=textsplitter)
-    write_check_file(filepath, docs)
-    return docs
-
-
-def write_check_file(filepath, docs):
-    folder_path = os.path.join(os.path.dirname(filepath), "tmp_files")
-    if not os.path.exists(folder_path):
-        os.makedirs(folder_path)
-    fp = os.path.join(folder_path, 'load_file.txt')
-    with open(fp, 'a+', encoding='utf-8') as fout:
-        fout.write("filepath=%s,len=%s" % (filepath, len(docs)))
-        fout.write('\n')
-        for i in docs:
-            fout.write(str(i))
-            fout.write('\n')
-        fout.close()
-
-
-def generate_prompt(related_docs: List[str],
-                    query: str,
-                    prompt_template: str = PROMPT_TEMPLATE, ) -> str:
-    context = "\n".join([doc.page_content for doc in related_docs])
-    prompt = prompt_template.replace("{question}", query).replace("{context}", context)
-    return prompt
-
-
-def seperate_list(ls: List[int]) -> List[List[int]]:
-    lists = []
-    ls1 = [ls[0]]
-    for i in range(1, len(ls)):
-        if ls[i - 1] + 1 == ls[i]:
-            ls1.append(ls[i])
-        else:
-            lists.append(ls1)
-            ls1 = [ls[i]]
-    lists.append(ls1)
-    return lists
-
-
-def similarity_search_with_score_by_vector(
-        self, embedding: List[float], k: int = 4
-) -> List[Tuple[Document, float]]:
-    scores, indices = self.index.search(np.array([embedding], dtype=np.float32), k)
-    docs = []
-    id_set = set()
-    store_len = len(self.index_to_docstore_id)
-    for j, i in enumerate(indices[0]):
-        if i == -1 or 0 < self.score_threshold < scores[0][j]:
-            # This happens when not enough docs are returned.
-            continue
-        _id = self.index_to_docstore_id[i]
-        doc = self.docstore.search(_id)
-        if not self.chunk_conent:
-            if not isinstance(doc, Document):
-                raise ValueError(f"Could not find document for id {_id}, got {doc}")
-            doc.metadata["score"] = int(scores[0][j])
-            docs.append(doc)
-            continue
-        id_set.add(i)
-        docs_len = len(doc.page_content)
-        for k in range(1, max(i, store_len - i)):
-            break_flag = False
-            for l in [i + k, i - k]:
-                if 0 <= l < len(self.index_to_docstore_id):
-                    _id0 = self.index_to_docstore_id[l]
-                    doc0 = self.docstore.search(_id0)
-                    if docs_len + len(doc0.page_content) > self.chunk_size:
-                        break_flag = True
-                        break
-                    elif doc0.metadata["source"] == doc.metadata["source"]:
-                        docs_len += len(doc0.page_content)
-                        id_set.add(l)
-            if break_flag:
-                break
-    if not self.chunk_conent:
-        return docs
-    if len(id_set) == 0 and self.score_threshold > 0:
-        return []
-    id_list = sorted(list(id_set))
-    id_lists = seperate_list(id_list)
-    for id_seq in id_lists:
-        for id in id_seq:
-            if id == id_seq[0]:
-                _id = self.index_to_docstore_id[id]
-                doc = self.docstore.search(_id)
-            else:
-                _id0 = self.index_to_docstore_id[id]
-                doc0 = self.docstore.search(_id0)
-                doc.page_content += " " + doc0.page_content
-        if not isinstance(doc, Document):
-            raise ValueError(f"Could not find document for id {_id}, got {doc}")
-        doc_score = min([scores[0][id] for id in [indices[0].tolist().index(i) for i in id_seq if i in indices[0]]])
-        doc.metadata["score"] = int(doc_score)
-        docs.append(doc)
-    torch_gc()
-    return docs
-
-
-def search_result2docs(search_results):
-    docs = []
-    for result in search_results:
-        doc = Document(page_content=result["snippet"] if "snippet" in result.keys() else "",
-                       metadata={"source": result["link"] if "link" in result.keys() else "",
-                                 "filename": result["title"] if "title" in result.keys() else ""})
-        docs.append(doc)
-    return docs
-
-
-class LocalDocQA:
-    llm: BaseAnswer = None
-    embeddings: object = None
-    top_k: int = VECTOR_SEARCH_TOP_K
-    chunk_size: int = CHUNK_SIZE
-    chunk_conent: bool = True
-    score_threshold: int = VECTOR_SEARCH_SCORE_THRESHOLD
-
-    def init_cfg(self,
-                 embedding_model: str = EMBEDDING_MODEL,
-                 embedding_device=EMBEDDING_DEVICE,
-                 llm_model: BaseAnswer = None,
-                 top_k=VECTOR_SEARCH_TOP_K,
-                 ):
-        self.llm = llm_model
-        self.embeddings = HuggingFaceEmbeddings(model_name=embedding_model_dict[embedding_model],
-                                                model_kwargs={'device': embedding_device})
-        self.top_k = top_k
-
-    def init_knowledge_vector_store(self,
-                                    filepath: str or List[str],
-                                    vs_path: str or os.PathLike = None,
-                                    sentence_size=SENTENCE_SIZE):
-        loaded_files = []
-        failed_files = []
-        if isinstance(filepath, str):
-            if not os.path.exists(filepath):
-                print("路径不存在")
-                return None
-            elif os.path.isfile(filepath):
-                file = os.path.split(filepath)[-1]
-                try:
-                    docs = load_file(filepath, sentence_size)
-                    logger.info(f"{file} 已成功加载")
-                    loaded_files.append(filepath)
-                except Exception as e:
-                    logger.error(e)
-                    logger.info(f"{file} 未能成功加载")
-                    return None
-            elif os.path.isdir(filepath):
-                docs = []
-                for file in tqdm(os.listdir(filepath), desc="加载文件"):
-                    fullfilepath = os.path.join(filepath, file)
-                    try:
-                        docs += load_file(fullfilepath, sentence_size)
-                        loaded_files.append(fullfilepath)
-                    except Exception as e:
-                        logger.error(e)
-                        failed_files.append(file)
-
-                if len(failed_files) > 0:
-                    logger.info("以下文件未能成功加载：")
-                    for file in failed_files:
-                        logger.info(f"{file}\n")
-
-        else:
-            docs = []
-            for file in filepath:
-                try:
-                    docs += load_file(file)
-                    logger.info(f"{file} 已成功加载")
-                    loaded_files.append(file)
-                except Exception as e:
-                    logger.error(e)
-                    logger.info(f"{file} 未能成功加载")
-        if len(docs) > 0:
-            logger.info("文件加载完毕，正在生成向量库")
-            if vs_path and os.path.isdir(vs_path):
-                vector_store = FAISS.load_local(vs_path, self.embeddings)
-                vector_store.add_documents(docs)
-                torch_gc()
-            else:
-                if not vs_path:
-                    vs_path = os.path.join(VS_ROOT_PATH,
-                                           f"""{"".join(lazy_pinyin(os.path.splitext(file)[0]))}_FAISS_{datetime.datetime.now().strftime("%Y%m%d_%H%M%S")}""")
-                vector_store = FAISS.from_documents(docs, self.embeddings)  # docs 为Document列表
-                torch_gc()
-
-            vector_store.save_local(vs_path)
-            return vs_path, loaded_files
-        else:
-            logger.info("文件均未成功加载，请检查依赖包或替换为其他文件再次上传。")
-            return None, loaded_files
-
-    def one_knowledge_add(self, vs_path, one_title, one_conent, one_content_segmentation, sentence_size):
-        try:
-            if not vs_path or not one_title or not one_conent:
-                logger.info("知识库添加错误，请确认知识库名字、标题、内容是否正确！")
-                return None, [one_title]
-            docs = [Document(page_content=one_conent + "\n", metadata={"source": one_title})]
-            if not one_content_segmentation:
-                text_splitter = ChineseTextSplitter(pdf=False, sentence_size=sentence_size)
-                docs = text_splitter.split_documents(docs)
-            if os.path.isdir(vs_path):
-                vector_store = FAISS.load_local(vs_path, self.embeddings)
-                vector_store.add_documents(docs)
-            else:
-                vector_store = FAISS.from_documents(docs, self.embeddings)  ##docs 为Document列表
-            torch_gc()
-            vector_store.save_local(vs_path)
-            return vs_path, [one_title]
-        except Exception as e:
-            logger.error(e)
-            return None, [one_title]
-
-    def get_knowledge_based_answer(self, query, vs_path, chat_history=[], streaming: bool = STREAMING):
-        vector_store = FAISS.load_local(vs_path, self.embeddings)
-        FAISS.similarity_search_with_score_by_vector = similarity_search_with_score_by_vector
-        vector_store.chunk_size = self.chunk_size
-        vector_store.chunk_conent = self.chunk_conent
-        vector_store.score_threshold = self.score_threshold
-        related_docs_with_score = vector_store.similarity_search_with_score(query, k=self.top_k)
-        torch_gc()
-        prompt = generate_prompt(related_docs_with_score, query)
-
-        for answer_result in self.llm.generatorAnswer(prompt=prompt, history=chat_history,
-                                                      streaming=streaming):
-            resp = answer_result.llm_output["answer"]
-            history = answer_result.history
-            history[-1][0] = query
-            response = {"query": query,
-                        "result": resp,
-                        "source_documents": related_docs_with_score}
-            yield response, history
-
-    # query      查询内容
-    # vs_path    知识库路径
-    # chunk_conent   是否启用上下文关联
-    # score_threshold    搜索匹配score阈值
-    # vector_search_top_k   搜索知识库内容条数，默认搜索5条结果
-    # chunk_sizes    匹配单段内容的连接上下文长度
-    def get_knowledge_based_conent_test(self, query, vs_path, chunk_conent,
-                                        score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
-                                        vector_search_top_k=VECTOR_SEARCH_TOP_K, chunk_size=CHUNK_SIZE):
-        vector_store = FAISS.load_local(vs_path, self.embeddings)
-        FAISS.similarity_search_with_score_by_vector = similarity_search_with_score_by_vector
-        vector_store.chunk_conent = chunk_conent
-        vector_store.score_threshold = score_threshold
-        vector_store.chunk_size = chunk_size
-        related_docs_with_score = vector_store.similarity_search_with_score(query, k=vector_search_top_k)
-        if not related_docs_with_score:
-            response = {"query": query,
-                        "source_documents": []}
-            return response, ""
-        torch_gc()
-        prompt = "\n".join([doc.page_content for doc in related_docs_with_score])
-        response = {"query": query,
-                    "source_documents": related_docs_with_score}
-        return response, prompt
-
-    def get_search_result_based_answer(self, query, chat_history=[], streaming: bool = STREAMING):
-        results = bing_search(query)
-        result_docs = search_result2docs(results)
-        prompt = generate_prompt(result_docs, query)
-
-        for answer_result in self.llm.generatorAnswer(prompt=prompt, history=chat_history,
-                                                      streaming=streaming):
-            resp = answer_result.llm_output["answer"]
-            history = answer_result.history
-            history[-1][0] = query
-            response = {"query": query,
-                        "result": resp,
-                        "source_documents": result_docs}
-            yield response, history
-
-
-if __name__ == "__main__":
-    # 初始化消息
-    args = None
-    args = parser.parse_args(args=['--model-dir', '/media/checkpoint/', '--model', 'chatglm-6b', '--no-remote-model'])
-
-    args_dict = vars(args)
-    shared.loaderCheckPoint = LoaderCheckPoint(args_dict)
-    llm_model_ins = shared.loaderLLM()
-    llm_model_ins.set_history_len(LLM_HISTORY_LEN)
-
-    local_doc_qa = LocalDocQA()
-    local_doc_qa.init_cfg(llm_model=llm_model_ins)
-    query = "本项目使用的embedding模型是什么，消耗多少显存"
-    vs_path = "/media/gpt4-pdf-chatbot-langchain/dev-langchain-ChatGLM/vector_store/test"
-    last_print_len = 0
-    # for resp, history in local_doc_qa.get_knowledge_based_answer(query=query,
-    #                                                              vs_path=vs_path,
-    #                                                              chat_history=[],
-    #                                                              streaming=True):
-    for resp, history in local_doc_qa.get_search_result_based_answer(query=query,
-                                                                     chat_history=[],
-                                                                     streaming=True):
-        print(resp["result"][last_print_len:], end="", flush=True)
-        last_print_len = len(resp["result"])
-    source_text = [f"""出处 [{inum + 1}] {doc.metadata['source'] if doc.metadata['source'].startswith("http") 
-                   else os.path.split(doc.metadata['source'])[-1]}：\n\n{doc.page_content}\n\n"""
-                   # f"""相关度：{doc.metadata['score']}\n\n"""
-                   for inum, doc in
-                   enumerate(resp["source_documents"])]
-    logger.info("\n\n" + "\n\n".join(source_text))
-    pass

chains/modules/embeddings.py

@@ -1,34 +0,0 @@
-from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-
-from typing import Any, List
-
-
-class MyEmbeddings(HuggingFaceEmbeddings):
-    def __init__(self, **kwargs: Any):
-        super().__init__(**kwargs)
-        
-    def embed_documents(self, texts: List[str]) -> List[List[float]]:
-        """Compute doc embeddings using a HuggingFace transformer model.
-
-        Args:
-            texts: The list of texts to embed.
-
-        Returns:
-            List of embeddings, one for each text.
-        """
-        texts = list(map(lambda x: x.replace("\n", " "), texts))
-        embeddings = self.client.encode(texts, normalize_embeddings=True)
-        return embeddings.tolist()
-
-    def embed_query(self, text: str) -> List[float]:
-        """Compute query embeddings using a HuggingFace transformer model.
-
-        Args:
-            text: The text to embed.
-
-        Returns:
-            Embeddings for the text.
-        """
-        text = text.replace("\n", " ")
-        embedding = self.client.encode(text, normalize_embeddings=True)
-        return embedding.tolist()

chains/modules/vectorstores.py

@@ -1,121 +0,0 @@
-from langchain.vectorstores import FAISS
-from typing import Any, Callable, List, Optional, Tuple, Dict
-from langchain.docstore.document import Document
-from langchain.docstore.base import Docstore
-
-from langchain.vectorstores.utils import maximal_marginal_relevance
-from langchain.embeddings.base import Embeddings
-import uuid
-from langchain.docstore.in_memory import InMemoryDocstore
-
-import numpy as np
-
-def dependable_faiss_import() -> Any:
-    """Import faiss if available, otherwise raise error."""
-    try:
-        import faiss
-    except ImportError:
-        raise ValueError(
-            "Could not import faiss python package. "
-            "Please install it with `pip install faiss` "
-            "or `pip install faiss-cpu` (depending on Python version)."
-        )
-    return faiss
-
-class FAISSVS(FAISS):
-    def __init__(self, 
-                 embedding_function: Callable[..., Any], 
-                 index: Any, 
-                 docstore: Docstore, 
-                 index_to_docstore_id: Dict[int, str]):
-        super().__init__(embedding_function, index, docstore, index_to_docstore_id)
-
-    def max_marginal_relevance_search_by_vector(
-        self, embedding: List[float], k: int = 4, fetch_k: int = 20, **kwargs: Any
-    ) -> List[Tuple[Document, float]]:
-        """Return docs selected using the maximal marginal relevance.
-
-        Maximal marginal relevance optimizes for similarity to query AND diversity
-        among selected documents.
-
-        Args:
-            embedding: Embedding to look up documents similar to.
-            k: Number of Documents to return. Defaults to 4.
-            fetch_k: Number of Documents to fetch to pass to MMR algorithm.
-
-        Returns:
-            List of Documents with scores selected by maximal marginal relevance.
-        """
-        scores, indices = self.index.search(np.array([embedding], dtype=np.float32), fetch_k)
-        # -1 happens when not enough docs are returned.
-        embeddings = [self.index.reconstruct(int(i)) for i in indices[0] if i != -1]
-        mmr_selected = maximal_marginal_relevance(
-            np.array([embedding], dtype=np.float32), embeddings, k=k
-        )
-        selected_indices = [indices[0][i] for i in mmr_selected]
-        selected_scores = [scores[0][i] for i in mmr_selected]
-        docs = []
-        for i, score in zip(selected_indices, selected_scores):
-            if i == -1:
-                # This happens when not enough docs are returned.
-                continue
-            _id = self.index_to_docstore_id[i]
-            doc = self.docstore.search(_id)
-            if not isinstance(doc, Document):
-                raise ValueError(f"Could not find document for id {_id}, got {doc}")
-            docs.append((doc, score))
-        return docs
-
-    def max_marginal_relevance_search(
-        self,
-        query: str,
-        k: int = 4,
-        fetch_k: int = 20,
-        **kwargs: Any,
-    ) -> List[Tuple[Document, float]]:
-        """Return docs selected using the maximal marginal relevance.
-
-        Maximal marginal relevance optimizes for similarity to query AND diversity
-        among selected documents.
-
-        Args:
-            query: Text to look up documents similar to.
-            k: Number of Documents to return. Defaults to 4.
-            fetch_k: Number of Documents to fetch to pass to MMR algorithm.
-
-        Returns:
-            List of Documents with scores selected by maximal marginal relevance.
-        """
-        embedding = self.embedding_function(query)
-        docs = self.max_marginal_relevance_search_by_vector(embedding, k, fetch_k)
-        return docs
-    
-    @classmethod
-    def __from(
-        cls,
-        texts: List[str],
-        embeddings: List[List[float]],
-        embedding: Embeddings,
-        metadatas: Optional[List[dict]] = None,
-        **kwargs: Any,
-    ) -> FAISS:
-        faiss = dependable_faiss_import()
-        index = faiss.IndexFlatIP(len(embeddings[0]))
-        index.add(np.array(embeddings, dtype=np.float32))
-
-        # # my code, for speeding up search
-        # quantizer = faiss.IndexFlatL2(len(embeddings[0]))
-        # index = faiss.IndexIVFFlat(quantizer, len(embeddings[0]), 100)
-        # index.train(np.array(embeddings, dtype=np.float32))
-        # index.add(np.array(embeddings, dtype=np.float32))
-
-        documents = []
-        for i, text in enumerate(texts):
-            metadata = metadatas[i] if metadatas else {}
-            documents.append(Document(page_content=text, metadata=metadata))
-        index_to_id = {i: str(uuid.uuid4()) for i in range(len(documents))}
-        docstore = InMemoryDocstore(
-            {index_to_id[i]: doc for i, doc in enumerate(documents)}
-        )
-        return cls(embedding.embed_query, index, docstore, index_to_id)
-

chains/text_load.py

@@ -1,52 +0,0 @@
-import os
-import pinecone 
-from tqdm import tqdm
-from langchain.llms import OpenAI
-from langchain.text_splitter import SpacyTextSplitter
-from langchain.document_loaders import TextLoader
-from langchain.document_loaders import DirectoryLoader
-from langchain.indexes import VectorstoreIndexCreator
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.vectorstores import Pinecone
-
-#一些配置文件
-openai_key="你的key" # 注册 openai.com 后获得
-pinecone_key="你的key" # 注册 app.pinecone.io 后获得
-pinecone_index="你的库" #app.pinecone.io 获得
-pinecone_environment="你的Environment"  # 登录pinecone后，在indexes页面 查看Environment
-pinecone_namespace="你的Namespace" #如果不存在自动创建
-
-#科学上网你懂得
-os.environ['HTTP_PROXY'] = 'http://127.0.0.1:7890'
-os.environ['HTTPS_PROXY'] = 'http://127.0.0.1:7890'
-
-#初始化pinecone
-pinecone.init(
-    api_key=pinecone_key,
-    environment=pinecone_environment
-)
-index = pinecone.Index(pinecone_index)
-
-#初始化OpenAI的embeddings
-embeddings = OpenAIEmbeddings(openai_api_key=openai_key)
-
-#初始化text_splitter
-text_splitter = SpacyTextSplitter(pipeline='zh_core_web_sm',chunk_size=1000,chunk_overlap=200)
-
-# 读取目录下所有后缀是txt的文件
-loader = DirectoryLoader('../docs', glob="**/*.txt", loader_cls=TextLoader)
-
-#读取文本文件
-documents = loader.load()
-
-# 使用text_splitter对文档进行分割
-split_text = text_splitter.split_documents(documents)
-try:
-	for document in tqdm(split_text):
-		# 获取向量并储存到pinecone
-		Pinecone.from_documents([document], embeddings, index_name=pinecone_index)
-except Exception as e:
-    print(f"Error: {e}")
-    quit()
-
-

cli.bat

@@ -1,2 +0,0 @@
-@echo off
-python cli.py %*

cli.py

@@ -1,59 +0,0 @@
-import click
-
-from api import api_start as api_start
-from configs.model_config import llm_model_dict, embedding_model_dict
-
-
-@click.group()
-@click.version_option(version='1.0.0')
-@click.pass_context
-def cli(ctx):
-    pass
-
-
-@cli.group()
-def llm():
-    pass
-
-
-@llm.command(name="ls")
-def llm_ls():
-    for k in llm_model_dict.keys():
-        print(k)
-
-
-@cli.group()
-def embedding():
-    pass
-
-
-@embedding.command(name="ls")
-def embedding_ls():
-    for k in embedding_model_dict.keys():
-        print(k)
-
-
-@cli.group()
-def start():
-    pass
-
-
-@start.command(name="api", context_settings=dict(help_option_names=['-h', '--help']))
-@click.option('-i', '--ip', default='0.0.0.0', show_default=True, type=str, help='api_server listen address.')
-@click.option('-p', '--port', default=7861, show_default=True, type=int, help='api_server listen port.')
-def start_api(ip, port):
-    api_start(host=ip, port=port)
-
-
-@start.command(name="cli", context_settings=dict(help_option_names=['-h', '--help']))
-def start_cli():
-    import cli_demo
-    cli_demo.main()
-
-
-@start.command(name="webui", context_settings=dict(help_option_names=['-h', '--help']))
-def start_webui():
-    import webui
-
-
-cli()

cli.sh

@@ -1,2 +0,0 @@
-#!/bin/bash
-python cli.py "$@"

cli_demo.py

@@ -1,56 +0,0 @@
-from configs.model_config import *
-from chains.local_doc_qa import LocalDocQA
-import os
-import nltk
-from models.loader.args import parser
-import models.shared as shared
-from models.loader import LoaderCheckPoint
-nltk.data.path = [NLTK_DATA_PATH] + nltk.data.path
-
-# Show reply with source text from input document
-REPLY_WITH_SOURCE = True
-
-
-def main():
-    args = None
-    args = parser.parse_args()
-    args_dict = vars(args)
-    shared.loaderCheckPoint = LoaderCheckPoint(args_dict)
-    llm_model_ins = shared.loaderLLM()
-    llm_model_ins.history_len = LLM_HISTORY_LEN
-
-    local_doc_qa = LocalDocQA()
-    local_doc_qa.init_cfg(llm_model=llm_model_ins,
-                          embedding_model=EMBEDDING_MODEL,
-                          embedding_device=EMBEDDING_DEVICE,
-                          top_k=VECTOR_SEARCH_TOP_K)
-    vs_path = None
-    while not vs_path:
-        filepath = input("Input your local knowledge file path 请输入本地知识文件路径：")
-        # 判断 filepath 是否为空，如果为空的话，重新让用户输入,防止用户误触回车
-        if not filepath:
-            continue
-        vs_path, _ = local_doc_qa.init_knowledge_vector_store(filepath)
-    history = []
-    while True:
-        query = input("Input your question 请输入问题：")
-        last_print_len = 0
-        for resp, history in local_doc_qa.get_knowledge_based_answer(query=query,
-                                                                     vs_path=vs_path,
-                                                                     chat_history=history,
-                                                                     streaming=STREAMING):
-            if STREAMING:
-                print(resp["result"][last_print_len:], end="", flush=True)
-                last_print_len = len(resp["result"])
-            else:
-                print(resp["result"])
-        if REPLY_WITH_SOURCE:
-            source_text = [f"""出处 [{inum + 1}] {os.path.split(doc.metadata['source'])[-1]}：\n\n{doc.page_content}\n\n"""
-                           # f"""相关度：{doc.metadata['score']}\n\n"""
-                           for inum, doc in
-                           enumerate(resp["source_documents"])]
-            print("\n\n" + "\n\n".join(source_text))
-
-
-if __name__ == "__main__":
-    main()

configs/__init__.py

@@ -0,0 +1,8 @@
+from .basic_config import *
+from .model_config import *
+from .kb_config import *
+from .server_config import *
+from .prompt_config import *
+
+
+VERSION = "v0.2.10"

configs/basic_config.py.example

@@ -0,0 +1,32 @@
+import logging
+import os
+import langchain
+import tempfile
+import shutil
+
+
+# 是否显示详细日志
+log_verbose = False
+langchain.verbose = False
+
+# 通常情况下不需要更改以下内容
+
+# 日志格式
+LOG_FORMAT = "%(asctime)s - %(filename)s[line:%(lineno)d] - %(levelname)s: %(message)s"
+logger = logging.getLogger()
+logger.setLevel(logging.INFO)
+logging.basicConfig(format=LOG_FORMAT)
+
+
+# 日志存储路径
+LOG_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "logs")
+if not os.path.exists(LOG_PATH):
+    os.mkdir(LOG_PATH)
+
+# 临时文件目录，主要用于文件对话
+BASE_TEMP_DIR = os.path.join(tempfile.gettempdir(), "chatchat")
+try:
+    shutil.rmtree(BASE_TEMP_DIR)
+except Exception:
+    pass
+os.makedirs(BASE_TEMP_DIR, exist_ok=True)

configs/kb_config.py.example

@@ -0,0 +1,146 @@
+import os
+
+# 默认使用的知识库
+DEFAULT_KNOWLEDGE_BASE = "samples"
+
+# 默认向量库/全文检索引擎类型。可选：faiss, milvus(离线) & zilliz(在线), pgvector, chromadb 全文检索引擎es
+DEFAULT_VS_TYPE = "faiss"
+
+# 缓存向量库数量（针对FAISS）
+CACHED_VS_NUM = 1
+
+# 缓存临时向量库数量（针对FAISS），用于文件对话
+CACHED_MEMO_VS_NUM = 10
+
+# 知识库中单段文本长度(不适用MarkdownHeaderTextSplitter)
+CHUNK_SIZE = 250
+
+# 知识库中相邻文本重合长度(不适用MarkdownHeaderTextSplitter)
+OVERLAP_SIZE = 50
+
+# 知识库匹配向量数量
+VECTOR_SEARCH_TOP_K = 3
+
+# 知识库匹配的距离阈值，一般取值范围在0-1之间，SCORE越小，距离越小从而相关度越高。
+# 但有用户报告遇到过匹配分值超过1的情况，为了兼容性默认设为1，在WEBUI中调整范围为0-2
+SCORE_THRESHOLD = 1.0
+
+# 默认搜索引擎。可选：bing, duckduckgo, metaphor
+DEFAULT_SEARCH_ENGINE = "duckduckgo"
+
+# 搜索引擎匹配结题数量
+SEARCH_ENGINE_TOP_K = 3
+
+
+# Bing 搜索必备变量
+# 使用 Bing 搜索需要使用 Bing Subscription Key,需要在azure port中申请试用bing search
+# 具体申请方式请见
+# https://learn.microsoft.com/en-us/bing/search-apis/bing-web-search/create-bing-search-service-resource
+# 使用python创建bing api 搜索实例详见:
+# https://learn.microsoft.com/en-us/bing/search-apis/bing-web-search/quickstarts/rest/python
+BING_SEARCH_URL = "https://api.bing.microsoft.com/v7.0/search"
+# 注意不是bing Webmaster Tools的api key，
+
+# 此外，如果是在服务器上，报Failed to establish a new connection: [Errno 110] Connection timed out
+# 是因为服务器加了防火墙，需要联系管理员加白名单，如果公司的服务器的话，就别想了GG
+BING_SUBSCRIPTION_KEY = ""
+
+# metaphor搜索需要KEY
+METAPHOR_API_KEY = ""
+
+# 心知天气 API KEY，用于天气Agent。申请：https://www.seniverse.com/
+SENIVERSE_API_KEY = ""
+
+# 是否开启中文标题加强，以及标题增强的相关配置
+# 通过增加标题判断，判断哪些文本为标题，并在metadata中进行标记；
+# 然后将文本与往上一级的标题进行拼合，实现文本信息的增强。
+ZH_TITLE_ENHANCE = False
+
+# PDF OCR 控制：只对宽高超过页面一定比例（图片宽/页面宽，图片高/页面高）的图片进行 OCR。
+# 这样可以避免 PDF 中一些小图片的干扰，提高非扫描版 PDF 处理速度
+PDF_OCR_THRESHOLD = (0.6, 0.6)
+
+# 每个知识库的初始化介绍，用于在初始化知识库时显示和Agent调用，没写则没有介绍，不会被Agent调用。
+KB_INFO = {
+    "知识库名称": "知识库介绍",
+    "samples": "关于本项目issue的解答",
+}
+
+
+# 通常情况下不需要更改以下内容
+
+# 知识库默认存储路径
+KB_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "knowledge_base")
+if not os.path.exists(KB_ROOT_PATH):
+    os.mkdir(KB_ROOT_PATH)
+# 数据库默认存储路径。
+# 如果使用sqlite，可以直接修改DB_ROOT_PATH；如果使用其它数据库，请直接修改SQLALCHEMY_DATABASE_URI。
+DB_ROOT_PATH = os.path.join(KB_ROOT_PATH, "info.db")
+SQLALCHEMY_DATABASE_URI = f"sqlite:///{DB_ROOT_PATH}"
+
+# 可选向量库类型及对应配置
+kbs_config = {
+    "faiss": {
+    },
+    "milvus": {
+        "host": "127.0.0.1",
+        "port": "19530",
+        "user": "",
+        "password": "",
+        "secure": False,
+    },
+    "zilliz": {
+        "host": "in01-a7ce524e41e3935.ali-cn-hangzhou.vectordb.zilliz.com.cn",
+        "port": "19530",
+        "user": "",
+        "password": "",
+        "secure": True,
+        },
+    "pg": {
+        "connection_uri": "postgresql://postgres:postgres@127.0.0.1:5432/langchain_chatchat",
+    },
+
+    "es": {
+        "host": "127.0.0.1",
+        "port": "9200",
+        "index_name": "test_index",
+        "user": "",
+        "password": ""
+    },
+    "milvus_kwargs":{
+        "search_params":{"metric_type": "L2"}, #在此处增加search_params
+        "index_params":{"metric_type": "L2","index_type": "HNSW"} # 在此处增加index_params
+    },
+    "chromadb": {}
+}
+
+# TextSplitter配置项，如果你不明白其中的含义，就不要修改。
+text_splitter_dict = {
+    "ChineseRecursiveTextSplitter": {
+        "source": "huggingface",   # 选择tiktoken则使用openai的方法
+        "tokenizer_name_or_path": "",
+    },
+    "SpacyTextSplitter": {
+        "source": "huggingface",
+        "tokenizer_name_or_path": "gpt2",
+    },
+    "RecursiveCharacterTextSplitter": {
+        "source": "tiktoken",
+        "tokenizer_name_or_path": "cl100k_base",
+    },
+    "MarkdownHeaderTextSplitter": {
+        "headers_to_split_on":
+            [
+                ("#", "head1"),
+                ("##", "head2"),
+                ("###", "head3"),
+                ("####", "head4"),
+            ]
+    },
+}
+
+# TEXT_SPLITTER 名称
+TEXT_SPLITTER_NAME = "ChineseRecursiveTextSplitter"
+
+# Embedding模型定制词语的词表文件
+EMBEDDING_KEYWORD_FILE = "embedding_keywords.txt"

configs/model_config.py

@@ -1,130 +0,0 @@
-import torch.cuda
-import torch.backends
-import os
-import logging
-import uuid
-
-LOG_FORMAT = "%(levelname) -5s %(asctime)s" "-1d: %(message)s"
-logger = logging.getLogger()
-logger.setLevel(logging.INFO)
-logging.basicConfig(format=LOG_FORMAT)
-
-embedding_model_dict = {
-    "ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
-    "ernie-base": "nghuyong/ernie-3.0-base-zh",
-    "text2vec-base": "shibing624/text2vec-base-chinese",
-    "text2vec": "GanymedeNil/text2vec-large-chinese",
-}
-
-# Embedding model name
-EMBEDDING_MODEL = "text2vec"
-
-# Embedding running device
-EMBEDDING_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
-
-
-# supported LLM models
-# llm_model_dict 处理了loader的一些预设行为，如加载位置，模型名称，模型处理器实例
-llm_model_dict = {
-    "chatglm-6b-int4-qe": {
-        "name": "chatglm-6b-int4-qe",
-        "pretrained_model_name": "THUDM/chatglm-6b-int4-qe",
-        "local_model_path": None,
-        "provides": "ChatGLM"
-    },
-    "chatglm-6b-int4": {
-        "name": "chatglm-6b-int4",
-        "pretrained_model_name": "THUDM/chatglm-6b-int4",
-        "local_model_path": None,
-        "provides": "ChatGLM"
-    },
-    "chatglm-6b-int8": {
-        "name": "chatglm-6b-int8",
-        "pretrained_model_name": "THUDM/chatglm-6b-int8",
-        "local_model_path": None,
-        "provides": "ChatGLM"
-    },
-    "chatglm-6b": {
-        "name": "chatglm-6b",
-        "pretrained_model_name": "THUDM/chatglm-6b",
-        "local_model_path": None,
-        "provides": "ChatGLM"
-    },
-
-    "chatyuan": {
-        "name": "chatyuan",
-        "pretrained_model_name": "ClueAI/ChatYuan-large-v2",
-        "local_model_path": None,
-        "provides": None
-    },
-    "moss": {
-        "name": "moss",
-        "pretrained_model_name": "fnlp/moss-moon-003-sft",
-        "local_model_path": None,
-        "provides": "MOSSLLM"
-    }
-}
-
-# LLM model name
-LLM_MODEL = "chatglm-6b"
-
-# LLM lora path，默认为空，如果有请直接指定文件夹路径
-LLM_LORA_PATH = ""
-USE_LORA = True if LLM_LORA_PATH else False
-
-# LLM streaming reponse
-STREAMING = True
-
-# Use p-tuning-v2 PrefixEncoder
-USE_PTUNING_V2 = False
-
-# LLM running device
-LLM_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
-
-
-VS_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "vector_store")
-
-UPLOAD_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "content")
-
-# 基于上下文的prompt模版，请务必保留"{question}"和"{context}"
-PROMPT_TEMPLATE = """已知信息：
-{context} 
-
-根据上述已知信息，简洁和专业的来回答用户的问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题” 或 “没有提供足够的相关信息”，不允许在答案中添加编造成分，答案请使用中文。 问题是：{question}"""
-
-# 文本分句长度
-SENTENCE_SIZE = 100
-
-# 匹配后单段上下文长度
-CHUNK_SIZE = 250
-
-# LLM input history length
-LLM_HISTORY_LEN = 3
-
-# return top-k text chunk from vector store
-VECTOR_SEARCH_TOP_K = 5
-
-# 知识检索内容相关度 Score, 数值范围约为0-1100，如果为0，则不生效，经测试设置为小于500时，匹配结果更精准
-VECTOR_SEARCH_SCORE_THRESHOLD = 0
-
-NLTK_DATA_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "nltk_data")
-
-FLAG_USER_NAME = uuid.uuid4().hex
-
-logger.info(f"""
-loading model config
-llm device: {LLM_DEVICE}
-embedding device: {EMBEDDING_DEVICE}
-dir: {os.path.dirname(os.path.dirname(__file__))}
-flagging username: {FLAG_USER_NAME}
-""")
-
-# 是否开启跨域，默认为False，如果需要开启，请设置为True
-# is open cross domain
-OPEN_CROSS_DOMAIN = False
-
-# Bing 搜索必备变量
-# 使用 Bing 搜索需要使用 Bing Subscription Key
-# 具体申请方式请见 https://learn.microsoft.com/en-us/bing/search-apis/bing-web-search/quickstarts/rest/python
-BING_SEARCH_URL = "https://api.bing.microsoft.com/v7.0/search"
-BING_SUBSCRIPTION_KEY = ""

configs/model_config.py.example

@@ -0,0 +1,327 @@
+import os
+
+# 可以指定一个绝对路径，统一存放所有的Embedding和LLM模型。
+# 每个模型可以是一个单独的目录，也可以是某个目录下的二级子目录。
+# 如果模型目录名称和 MODEL_PATH 中的 key 或 value 相同，程序会自动检测加载，无需修改 MODEL_PATH 中的路径。
+MODEL_ROOT_PATH = ""
+
+# 选用的 Embedding 名称
+EMBEDDING_MODEL = "bge-large-zh-v1.5"
+
+# Embedding 模型运行设备。设为 "auto" 会自动检测(会有警告)，也可手动设定为 "cuda","mps","cpu","xpu" 其中之一。
+EMBEDDING_DEVICE = "auto"
+
+# 选用的reranker模型
+RERANKER_MODEL = "bge-reranker-large"
+# 是否启用reranker模型
+USE_RERANKER = False
+RERANKER_MAX_LENGTH = 1024
+
+# 如果需要在 EMBEDDING_MODEL 中增加自定义的关键字时配置
+EMBEDDING_KEYWORD_FILE = "keywords.txt"
+EMBEDDING_MODEL_OUTPUT_PATH = "output"
+
+# 要运行的 LLM 名称，可以包括本地模型和在线模型。列表中本地模型将在启动项目时全部加载。
+# 列表中第一个模型将作为 API 和 WEBUI 的默认模型。
+# 在这里，我们使用目前主流的两个离线模型，其中，chatglm3-6b 为默认加载模型。
+# 如果你的显存不足，可使用 Qwen-1_8B-Chat, 该模型 FP16 仅需 3.8G显存。
+
+LLM_MODELS = ["chatglm3-6b", "zhipu-api", "openai-api"]
+Agent_MODEL = None
+
+# LLM 模型运行设备。设为"auto"会自动检测(会有警告)，也可手动设定为 "cuda","mps","cpu","xpu" 其中之一。
+LLM_DEVICE = "auto"
+
+HISTORY_LEN = 3
+
+MAX_TOKENS = 2048
+
+TEMPERATURE = 0.7
+
+ONLINE_LLM_MODEL = {
+    "openai-api": {
+        "model_name": "gpt-4",
+        "api_base_url": "https://api.openai.com/v1",
+        "api_key": "",
+        "openai_proxy": "",
+    },
+
+    # 智谱AI API,具体注册及api key获取请前往 http://open.bigmodel.cn
+    "zhipu-api": {
+        "api_key": "",
+        "version": "glm-4",
+        "provider": "ChatGLMWorker",
+    },
+
+    # 具体注册及api key获取请前往 https://api.minimax.chat/
+    "minimax-api": {
+        "group_id": "",
+        "api_key": "",
+        "is_pro": False,
+        "provider": "MiniMaxWorker",
+    },
+
+    # 具体注册及api key获取请前往 https://xinghuo.xfyun.cn/
+    "xinghuo-api": {
+        "APPID": "",
+        "APISecret": "",
+        "api_key": "",
+        "version": "v3.5", # 你使用的讯飞星火大模型版本，可选包括 "v3.5","v3.0", "v2.0", "v1.5"
+        "provider": "XingHuoWorker",
+    },
+
+    # 百度千帆 API，申请方式请参考 https://cloud.baidu.com/doc/WENXINWORKSHOP/s/4lilb2lpf
+    "qianfan-api": {
+        "version": "ERNIE-Bot",  # 注意大小写。当前支持 "ERNIE-Bot" 或 "ERNIE-Bot-turbo"， 更多的见官方文档。
+        "version_url": "",  # 也可以不填写version，直接填写在千帆申请模型发布的API地址
+        "api_key": "",
+        "secret_key": "",
+        "provider": "QianFanWorker",
+    },
+
+    # 火山方舟 API，文档参考 https://www.volcengine.com/docs/82379
+    "fangzhou-api": {
+        "version": "", # 对应火山方舟的 endpoint_id
+        "version_url": "",
+        "api_key": "",
+        "secret_key": "",
+        "provider": "FangZhouWorker",
+    },
+
+    # 阿里云通义千问 API，文档参考 https://help.aliyun.com/zh/dashscope/developer-reference/api-details
+    "qwen-api": {
+        "version": "qwen-max",
+        "api_key": "",
+        "provider": "QwenWorker",
+        "embed_model": "text-embedding-v1"  # embedding 模型名称
+    },
+
+    # 百川 API，申请方式请参考 https://www.baichuan-ai.com/home#api-enter
+    "baichuan-api": {
+        "version": "Baichuan2-53B",
+        "api_key": "",
+        "secret_key": "",
+        "provider": "BaiChuanWorker",
+    },
+
+    # Azure API
+    "azure-api": {
+        "deployment_name": "",  # 部署容器的名字
+        "resource_name": "",  # https://{resource_name}.openai.azure.com/openai/ 填写resource_name的部分，其他部分不要填写
+        "api_version": "",  # API的版本，不是模型版本
+        "api_key": "",
+        "provider": "AzureWorker",
+    },
+
+    # 昆仑万维天工 API https://model-platform.tiangong.cn/
+    "tiangong-api": {
+        "version": "SkyChat-MegaVerse",
+        "api_key": "",
+        "secret_key": "",
+        "provider": "TianGongWorker",
+    },
+
+    # Gemini API https://makersuite.google.com/app/apikey
+    "gemini-api": {
+        "api_key": "",
+        "provider": "GeminiWorker",
+    },
+
+    # Claude API : https://www.anthropic.com/api
+    # Available models: 
+    # Claude 3 Opus:    claude-3-opus-20240229 
+    # Claude 3 Sonnet	claude-3-sonnet-20240229
+    # Claude 3 Haiku	claude-3-haiku-20240307
+    "claude-api": {
+        "api_key": "",
+        "version": "2023-06-01",
+        "model_name":"claude-3-opus-20240229", 
+        "provider": "ClaudeWorker",
+    }
+
+}
+
+# 在以下字典中修改属性值，以指定本地embedding模型存储位置。支持3种设置方法：
+# 1、将对应的值修改为模型绝对路径
+# 2、不修改此处的值（以 text2vec 为例）：
+#       2.1 如果{MODEL_ROOT_PATH}下存在如下任一子目录：
+#           - text2vec
+#           - GanymedeNil/text2vec-large-chinese
+#           - text2vec-large-chinese
+#       2.2 如果以上本地路径不存在，则使用huggingface模型
+
+MODEL_PATH = {
+    "embed_model": {
+        "ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
+        "ernie-base": "nghuyong/ernie-3.0-base-zh",
+        "text2vec-base": "shibing624/text2vec-base-chinese",
+        "text2vec": "GanymedeNil/text2vec-large-chinese",
+        "text2vec-paraphrase": "shibing624/text2vec-base-chinese-paraphrase",
+        "text2vec-sentence": "shibing624/text2vec-base-chinese-sentence",
+        "text2vec-multilingual": "shibing624/text2vec-base-multilingual",
+        "text2vec-bge-large-chinese": "shibing624/text2vec-bge-large-chinese",
+        "m3e-small": "moka-ai/m3e-small",
+        "m3e-base": "moka-ai/m3e-base",
+        "m3e-large": "moka-ai/m3e-large",
+
+        "bge-small-zh": "BAAI/bge-small-zh",
+        "bge-base-zh": "BAAI/bge-base-zh",
+        "bge-large-zh": "BAAI/bge-large-zh",
+        "bge-large-zh-noinstruct": "BAAI/bge-large-zh-noinstruct",
+        "bge-base-zh-v1.5": "BAAI/bge-base-zh-v1.5",
+        "bge-large-zh-v1.5": "BAAI/bge-large-zh-v1.5",
+
+        "bge-m3": "BAAI/bge-m3",
+
+        "piccolo-base-zh": "sensenova/piccolo-base-zh",
+        "piccolo-large-zh": "sensenova/piccolo-large-zh",
+        "nlp_gte_sentence-embedding_chinese-large": "damo/nlp_gte_sentence-embedding_chinese-large",
+        "text-embedding-ada-002": "your OPENAI_API_KEY",
+    },
+
+    "llm_model": {
+        "chatglm2-6b": "THUDM/chatglm2-6b",
+        "chatglm2-6b-32k": "THUDM/chatglm2-6b-32k",
+        "chatglm3-6b": "THUDM/chatglm3-6b",
+        "chatglm3-6b-32k": "THUDM/chatglm3-6b-32k",
+
+        "Orion-14B-Chat": "OrionStarAI/Orion-14B-Chat",
+        "Orion-14B-Chat-Plugin": "OrionStarAI/Orion-14B-Chat-Plugin",
+        "Orion-14B-LongChat": "OrionStarAI/Orion-14B-LongChat",
+
+        "Llama-2-7b-chat-hf": "meta-llama/Llama-2-7b-chat-hf",
+        "Llama-2-13b-chat-hf": "meta-llama/Llama-2-13b-chat-hf",
+        "Llama-2-70b-chat-hf": "meta-llama/Llama-2-70b-chat-hf",
+
+        "Qwen-1_8B-Chat": "Qwen/Qwen-1_8B-Chat",
+        "Qwen-7B-Chat": "Qwen/Qwen-7B-Chat",
+        "Qwen-14B-Chat": "Qwen/Qwen-14B-Chat",
+        "Qwen-72B-Chat": "Qwen/Qwen-72B-Chat",
+
+        # Qwen1.5 模型 VLLM可能出现问题
+        "Qwen1.5-0.5B-Chat": "Qwen/Qwen1.5-0.5B-Chat",
+        "Qwen1.5-1.8B-Chat": "Qwen/Qwen1.5-1.8B-Chat",
+        "Qwen1.5-4B-Chat": "Qwen/Qwen1.5-4B-Chat",
+        "Qwen1.5-7B-Chat": "Qwen/Qwen1.5-7B-Chat",
+        "Qwen1.5-14B-Chat": "Qwen/Qwen1.5-14B-Chat",
+        "Qwen1.5-72B-Chat": "Qwen/Qwen1.5-72B-Chat",
+
+        "baichuan-7b-chat": "baichuan-inc/Baichuan-7B-Chat",
+        "baichuan-13b-chat": "baichuan-inc/Baichuan-13B-Chat",
+        "baichuan2-7b-chat": "baichuan-inc/Baichuan2-7B-Chat",
+        "baichuan2-13b-chat": "baichuan-inc/Baichuan2-13B-Chat",
+
+        "internlm-7b": "internlm/internlm-7b",
+        "internlm-chat-7b": "internlm/internlm-chat-7b",
+        "internlm2-chat-7b": "internlm/internlm2-chat-7b",
+        "internlm2-chat-20b": "internlm/internlm2-chat-20b",
+
+        "BlueLM-7B-Chat": "vivo-ai/BlueLM-7B-Chat",
+        "BlueLM-7B-Chat-32k": "vivo-ai/BlueLM-7B-Chat-32k",
+
+        "Yi-34B-Chat": "https://huggingface.co/01-ai/Yi-34B-Chat",
+
+        "agentlm-7b": "THUDM/agentlm-7b",
+        "agentlm-13b": "THUDM/agentlm-13b",
+        "agentlm-70b": "THUDM/agentlm-70b",
+
+        "falcon-7b": "tiiuae/falcon-7b",
+        "falcon-40b": "tiiuae/falcon-40b",
+        "falcon-rw-7b": "tiiuae/falcon-rw-7b",
+
+        "aquila-7b": "BAAI/Aquila-7B",
+        "aquilachat-7b": "BAAI/AquilaChat-7B",
+        "open_llama_13b": "openlm-research/open_llama_13b",
+        "vicuna-13b-v1.5": "lmsys/vicuna-13b-v1.5",
+        "koala": "young-geng/koala",
+        "mpt-7b": "mosaicml/mpt-7b",
+        "mpt-7b-storywriter": "mosaicml/mpt-7b-storywriter",
+        "mpt-30b": "mosaicml/mpt-30b",
+        "opt-66b": "facebook/opt-66b",
+        "opt-iml-max-30b": "facebook/opt-iml-max-30b",
+        "gpt2": "gpt2",
+        "gpt2-xl": "gpt2-xl",
+        "gpt-j-6b": "EleutherAI/gpt-j-6b",
+        "gpt4all-j": "nomic-ai/gpt4all-j",
+        "gpt-neox-20b": "EleutherAI/gpt-neox-20b",
+        "pythia-12b": "EleutherAI/pythia-12b",
+        "oasst-sft-4-pythia-12b-epoch-3.5": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
+        "dolly-v2-12b": "databricks/dolly-v2-12b",
+        "stablelm-tuned-alpha-7b": "stabilityai/stablelm-tuned-alpha-7b",
+    },
+
+    "reranker": {
+        "bge-reranker-large": "BAAI/bge-reranker-large",
+        "bge-reranker-base": "BAAI/bge-reranker-base",
+    }
+}
+
+# 通常情况下不需要更改以下内容
+
+# nltk 模型存储路径
+NLTK_DATA_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "nltk_data")
+
+# 使用VLLM可能导致模型推理能力下降，无法完成Agent任务
+VLLM_MODEL_DICT = {
+    "chatglm2-6b": "THUDM/chatglm2-6b",
+    "chatglm2-6b-32k": "THUDM/chatglm2-6b-32k",
+    "chatglm3-6b": "THUDM/chatglm3-6b",
+    "chatglm3-6b-32k": "THUDM/chatglm3-6b-32k",
+
+    "Llama-2-7b-chat-hf": "meta-llama/Llama-2-7b-chat-hf",
+    "Llama-2-13b-chat-hf": "meta-llama/Llama-2-13b-chat-hf",
+    "Llama-2-70b-chat-hf": "meta-llama/Llama-2-70b-chat-hf",
+
+    "Qwen-1_8B-Chat": "Qwen/Qwen-1_8B-Chat",
+    "Qwen-7B-Chat": "Qwen/Qwen-7B-Chat",
+    "Qwen-14B-Chat": "Qwen/Qwen-14B-Chat",
+    "Qwen-72B-Chat": "Qwen/Qwen-72B-Chat",
+
+    "baichuan-7b-chat": "baichuan-inc/Baichuan-7B-Chat",
+    "baichuan-13b-chat": "baichuan-inc/Baichuan-13B-Chat",
+    "baichuan2-7b-chat": "baichuan-inc/Baichuan-7B-Chat",
+    "baichuan2-13b-chat": "baichuan-inc/Baichuan-13B-Chat",
+
+    "BlueLM-7B-Chat": "vivo-ai/BlueLM-7B-Chat",
+    "BlueLM-7B-Chat-32k": "vivo-ai/BlueLM-7B-Chat-32k",
+
+    "internlm-7b": "internlm/internlm-7b",
+    "internlm-chat-7b": "internlm/internlm-chat-7b",
+    "internlm2-chat-7b": "internlm/Models/internlm2-chat-7b",
+    "internlm2-chat-20b": "internlm/Models/internlm2-chat-20b",
+
+    "aquila-7b": "BAAI/Aquila-7B",
+    "aquilachat-7b": "BAAI/AquilaChat-7B",
+
+    "falcon-7b": "tiiuae/falcon-7b",
+    "falcon-40b": "tiiuae/falcon-40b",
+    "falcon-rw-7b": "tiiuae/falcon-rw-7b",
+    "gpt2": "gpt2",
+    "gpt2-xl": "gpt2-xl",
+    "gpt-j-6b": "EleutherAI/gpt-j-6b",
+    "gpt4all-j": "nomic-ai/gpt4all-j",
+    "gpt-neox-20b": "EleutherAI/gpt-neox-20b",
+    "pythia-12b": "EleutherAI/pythia-12b",
+    "oasst-sft-4-pythia-12b-epoch-3.5": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
+    "dolly-v2-12b": "databricks/dolly-v2-12b",
+    "stablelm-tuned-alpha-7b": "stabilityai/stablelm-tuned-alpha-7b",
+    "open_llama_13b": "openlm-research/open_llama_13b",
+    "vicuna-13b-v1.3": "lmsys/vicuna-13b-v1.3",
+    "koala": "young-geng/koala",
+    "mpt-7b": "mosaicml/mpt-7b",
+    "mpt-7b-storywriter": "mosaicml/mpt-7b-storywriter",
+    "mpt-30b": "mosaicml/mpt-30b",
+    "opt-66b": "facebook/opt-66b",
+    "opt-iml-max-30b": "facebook/opt-iml-max-30b",
+
+}
+
+SUPPORT_AGENT_MODEL = [
+    "openai-api",  # GPT4 模型
+    "qwen-api",  # Qwen Max模型
+    "zhipu-api",  # 智谱AI GLM4模型
+    "Qwen",  # 所有Qwen系列本地模型
+    "chatglm3-6b",
+    "internlm2-chat-20b",
+    "Orion-14B-Chat-Plugin",
+]

configs/prompt_config.py.example

@@ -0,0 +1,127 @@
+# prompt模板使用Jinja2语法，简单点就是用双大括号代替f-string的单大括号
+# 本配置文件支持热加载，修改prompt模板后无需重启服务。
+
+# LLM对话支持的变量：
+#   - input: 用户输入内容
+
+# 知识库和搜索引擎对话支持的变量：
+#   - context: 从检索结果拼接的知识文本
+#   - question: 用户提出的问题
+
+# Agent对话支持的变量：
+
+#   - tools: 可用的工具列表
+#   - tool_names: 可用的工具名称列表
+#   - history: 用户和Agent的对话历史
+#   - input: 用户输入内容
+#   - agent_scratchpad: Agent的思维记录
+
+PROMPT_TEMPLATES = {
+    "llm_chat": {
+        "default":
+            '{{ input }}',
+
+        "with_history":
+            'The following is a friendly conversation between a human and an AI. '
+            'The AI is talkative and provides lots of specific details from its context. '
+            'If the AI does not know the answer to a question, it truthfully says it does not know.\n\n'
+            'Current conversation:\n'
+            '{history}\n'
+            'Human: {input}\n'
+            'AI:',
+
+        "py":
+            '你是一个聪明的代码助手，请你给我写出简单的py代码。 \n'
+            '{{ input }}',
+    },
+
+
+    "knowledge_base_chat": {
+        "default":
+            '<指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，'
+            '不允许在答案中添加编造成分，答案请使用中文。 </指令>\n'
+            '<已知信息>{{ context }}</已知信息>\n'
+            '<问题>{{ question }}</问题>\n',
+
+        "text":
+            '<指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，答案请使用中文。 </指令>\n'
+            '<已知信息>{{ context }}</已知信息>\n'
+            '<问题>{{ question }}</问题>\n',
+
+        "empty":  # 搜不到知识库的时候使用
+            '请你回答我的问题:\n'
+            '{{ question }}\n\n',
+    },
+
+
+    "search_engine_chat": {
+        "default":
+            '<指令>这是我搜索到的互联网信息，请你根据这些信息进行提取并有调理，简洁的回答问题。'
+            '如果无法从中得到答案，请说 “无法搜索到能回答问题的内容”。 </指令>\n'
+            '<已知信息>{{ context }}</已知信息>\n'
+            '<问题>{{ question }}</问题>\n',
+
+        "search":
+            '<指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，答案请使用中文。 </指令>\n'
+            '<已知信息>{{ context }}</已知信息>\n'
+            '<问题>{{ question }}</问题>\n',
+    },
+
+
+    "agent_chat": {
+        "default":
+            'Answer the following questions as best you can. If it is in order, you can use some tools appropriately. '
+            'You have access to the following tools:\n\n'
+            '{tools}\n\n'
+            'Use the following format:\n'
+            'Question: the input question you must answer1\n'
+            'Thought: you should always think about what to do and what tools to use.\n'
+            'Action: the action to take, should be one of [{tool_names}]\n'
+            'Action Input: the input to the action\n'
+            'Observation: the result of the action\n'
+            '... (this Thought/Action/Action Input/Observation can be repeated zero or more times)\n'
+            'Thought: I now know the final answer\n'
+            'Final Answer: the final answer to the original input question\n'
+            'Begin!\n\n'
+            'history: {history}\n\n'
+            'Question: {input}\n\n'
+            'Thought: {agent_scratchpad}\n',
+
+        "ChatGLM3":
+            'You can answer using the tools, or answer directly using your knowledge without using the tools. '
+            'Respond to the human as helpfully and accurately as possible.\n'
+            'You have access to the following tools:\n'
+            '{tools}\n'
+            'Use a json blob to specify a tool by providing an action key (tool name) '
+            'and an action_input key (tool input).\n'
+            'Valid "action" values: "Final Answer" or  [{tool_names}]'
+            'Provide only ONE action per $JSON_BLOB, as shown:\n\n'
+            '```\n'
+            '{{{{\n'
+            '  "action": $TOOL_NAME,\n'
+            '  "action_input": $INPUT\n'
+            '}}}}\n'
+            '```\n\n'
+            'Follow this format:\n\n'
+            'Question: input question to answer\n'
+            'Thought: consider previous and subsequent steps\n'
+            'Action:\n'
+            '```\n'
+            '$JSON_BLOB\n'
+            '```\n'
+            'Observation: action result\n'
+            '... (repeat Thought/Action/Observation N times)\n'
+            'Thought: I know what to respond\n'
+            'Action:\n'
+            '```\n'
+            '{{{{\n'
+            '  "action": "Final Answer",\n'
+            '  "action_input": "Final response to human"\n'
+            '}}}}\n'
+            'Begin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. '
+            'Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:.\n'
+            'history: {history}\n\n'
+            'Question: {input}\n\n'
+            'Thought: {agent_scratchpad}',
+    }
+}

configs/server_config.py.example

@@ -0,0 +1,139 @@
+import sys
+from configs.model_config import LLM_DEVICE
+
+# httpx 请求默认超时时间（秒）。如果加载模型或对话较慢，出现超时错误，可以适当加大该值。
+HTTPX_DEFAULT_TIMEOUT = 300.0
+
+# API 是否开启跨域，默认为False，如果需要开启，请设置为True
+# is open cross domain
+OPEN_CROSS_DOMAIN = False
+
+# 各服务器默认绑定host。如改为"0.0.0.0"需要修改下方所有XX_SERVER的host
+DEFAULT_BIND_HOST = "0.0.0.0" if sys.platform != "win32" else "127.0.0.1"
+
+# webui.py server
+WEBUI_SERVER = {
+    "host": DEFAULT_BIND_HOST,
+    "port": 8501,
+}
+
+# api.py server
+API_SERVER = {
+    "host": DEFAULT_BIND_HOST,
+    "port": 7861,
+}
+
+# fastchat openai_api server
+FSCHAT_OPENAI_API = {
+    "host": DEFAULT_BIND_HOST,
+    "port": 20000,
+}
+
+# fastchat model_worker server
+# 这些模型必须是在model_config.MODEL_PATH或ONLINE_MODEL中正确配置的。
+# 在启动startup.py时，可用通过`--model-name xxxx yyyy`指定模型，不指定则为LLM_MODELS
+FSCHAT_MODEL_WORKERS = {
+    # 所有模型共用的默认配置，可在模型专项配置中进行覆盖。
+    "default": {
+        "host": DEFAULT_BIND_HOST,
+        "port": 20002,
+        "device": LLM_DEVICE,
+        # False,'vllm',使用的推理加速框架,使用vllm如果出现HuggingFace通信问题，参见doc/FAQ
+        # vllm对一些模型支持还不成熟，暂时默认关闭
+        "infer_turbo": False,
+
+        # model_worker多卡加载需要配置的参数
+        # "gpus": None, # 使用的GPU，以str的格式指定，如"0,1"，如失效请使用CUDA_VISIBLE_DEVICES="0,1"等形式指定
+        # "num_gpus": 1, # 使用GPU的数量
+        # "max_gpu_memory": "20GiB", # 每个GPU占用的最大显存
+
+        # 以下为model_worker非常用参数，可根据需要配置
+        # "load_8bit": False, # 开启8bit量化
+        # "cpu_offloading": None,
+        # "gptq_ckpt": None,
+        # "gptq_wbits": 16,
+        # "gptq_groupsize": -1,
+        # "gptq_act_order": False,
+        # "awq_ckpt": None,
+        # "awq_wbits": 16,
+        # "awq_groupsize": -1,
+        # "model_names": LLM_MODELS,
+        # "conv_template": None,
+        # "limit_worker_concurrency": 5,
+        # "stream_interval": 2,
+        # "no_register": False,
+        # "embed_in_truncate": False,
+
+        # 以下为vllm_worker配置参数,注意使用vllm必须有gpu，仅在Linux测试通过
+
+        # tokenizer = model_path # 如果tokenizer与model_path不一致在此处添加
+        # 'tokenizer_mode':'auto',
+        # 'trust_remote_code':True,
+        # 'download_dir':None,
+        # 'load_format':'auto',
+        # 'dtype':'auto',
+        # 'seed':0,
+        # 'worker_use_ray':False,
+        # 'pipeline_parallel_size':1,
+        # 'tensor_parallel_size':1,
+        # 'block_size':16,
+        # 'swap_space':4 , # GiB
+        # 'gpu_memory_utilization':0.90,
+        # 'max_num_batched_tokens':2560,
+        # 'max_num_seqs':256,
+        # 'disable_log_stats':False,
+        # 'conv_template':None,
+        # 'limit_worker_concurrency':5,
+        # 'no_register':False,
+        # 'num_gpus': 1
+        # 'engine_use_ray': False,
+        # 'disable_log_requests': False
+
+    },
+    "chatglm3-6b": {
+        "device": "cuda",
+    },
+    "Qwen1.5-0.5B-Chat": {
+        "device": "cuda",
+    },
+    # 以下配置可以不用修改，在model_config中设置启动的模型
+    "zhipu-api": {
+        "port": 21001,
+    },
+    "minimax-api": {
+        "port": 21002,
+    },
+    "xinghuo-api": {
+        "port": 21003,
+    },
+    "qianfan-api": {
+        "port": 21004,
+    },
+    "fangzhou-api": {
+        "port": 21005,
+    },
+    "qwen-api": {
+        "port": 21006,
+    },
+    "baichuan-api": {
+        "port": 21007,
+    },
+    "azure-api": {
+        "port": 21008,
+    },
+    "tiangong-api": {
+        "port": 21009,
+    },
+    "gemini-api": {
+        "port": 21010,
+    },
+    "claude-api": {
+        "port": 21011,
+    },
+}
+
+FSCHAT_CONTROLLER = {
+    "host": DEFAULT_BIND_HOST,
+    "port": 20001,
+    "dispatch_method": "shortest_queue",
+}

content/samples/README.md

@@ -1,212 +0,0 @@
-# 基于本地知识的 ChatGLM 应用实现
-
-## 介绍
-
-🌍 [_READ THIS IN ENGLISH_](README_en.md)
-
-🤖️ 一种利用 [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B) + [langchain](https://github.com/hwchase17/langchain) 实现的基于本地知识的 ChatGLM 应用。增加 [clue-ai/ChatYuan](https://github.com/clue-ai/ChatYuan) 项目的模型 [ClueAI/ChatYuan-large-v2](https://huggingface.co/ClueAI/ChatYuan-large-v2) 的支持。
-
-💡 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，建立了全部基于开源模型实现的本地知识问答应用。
-
-✅ 本项目中 Embedding 默认选用的是 [GanymedeNil/text2vec-large-chinese](https://huggingface.co/GanymedeNil/text2vec-large-chinese/tree/main)，LLM 默认选用的是 [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B)。依托上述模型，本项目可实现全部使用**开源**模型**离线私有部署**。
-
-⛓️ 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。
-
-![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/imClumsyPanda/langchain-ChatGLM/langchain-ChatGLM)
-
-📓 [ModelWhale 在线运行项目](https://www.heywhale.com/mw/project/643977aa446c45f4592a1e59)
-
-## 变更日志
-
-参见 [变更日志](docs/CHANGELOG.md)。
-
-## 硬件需求
-
-- ChatGLM-6B 模型硬件需求
-
-    注：如未将模型下载至本地，请执行前检查`$HOME/.cache/huggingface/`文件夹剩余空间，模型文件下载至本地需要 15 GB 存储空间。
-
-    模型下载方法可参考 [常见问题](docs/FAQ.md) 中 Q8。
-  
-    | **量化等级**   | **最低 GPU 显存**（推理） | **最低 GPU 显存**（高效参数微调） |
-    | -------------- | ------------------------- | --------------------------------- |
-    | FP16（无量化） | 13 GB                     | 14 GB                             |
-    | INT8           | 8 GB                     | 9 GB                             |
-    | INT4           | 6 GB                      | 7 GB                              |
-
-- MOSS 模型硬件需求
-    
-    注：如未将模型下载至本地，请执行前检查`$HOME/.cache/huggingface/`文件夹剩余空间，模型文件下载至本地需要 70 GB 存储空间
-
-    模型下载方法可参考 [常见问题](docs/FAQ.md) 中 Q8。
-
-    | **量化等级**  | **最低 GPU 显存**（推理） | **最低 GPU 显存**（高效参数微调） |
-    |-------------------|-----------------------| --------------------------------- |
-    | FP16（无量化） | 68 GB             | -                     |
-    | INT8      | 20 GB          | -                     |
-
-- Embedding 模型硬件需求
-
-    本项目中默认选用的 Embedding 模型 [GanymedeNil/text2vec-large-chinese](https://huggingface.co/GanymedeNil/text2vec-large-chinese/tree/main) 约占用显存 3GB，也可修改为在 CPU 中运行。
-
-## 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 - 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。
-
-vue前端需要node18环境
-### 从本地加载模型
-
-请参考 [THUDM/ChatGLM-6B#从本地加载模型](https://github.com/THUDM/ChatGLM-6B#从本地加载模型)
-
-### 1. 安装环境
-
-参见 [安装指南](docs/INSTALL.md)。
-
-### 2. 设置模型默认参数
-
-在开始执行 Web UI 或命令行交互前，请先检查 [configs/model_config.py](configs/model_config.py) 中的各项模型参数设计是否符合需求。
-
-### 3. 执行脚本体验 Web UI 或命令行交互
-
-> 注：鉴于环境部署过程中可能遇到问题，建议首先测试命令行脚本。建议命令行脚本测试可正常运行后再运行 Web UI。
-
-执行 [cli_demo.py](cli_demo.py) 脚本体验**命令行交互**：
-```shell
-$ python cli_demo.py
-```
-
-或执行 [webui.py](webui.py) 脚本体验 **Web 交互**
-
-```shell
-$ python webui.py
-```
-
-或执行 [api.py](api.py) 利用 fastapi 部署 API
-```shell
-$ python api.py
-```
-或成功部署 API 后，执行以下脚本体验基于 VUE 的前端页面
-```shell
-$ cd views 
-
-$ pnpm i
-
-$ npm run dev
-```
-
-执行后效果如下图所示：
-1. `对话` Tab 界面
-![](img/webui_0510_0.png)
-2. `知识库测试 Beta` Tab 界面
-![](img/webui_0510_1.png)
-3. `模型配置` Tab 界面
-![](img/webui_0510_2.png)
-
-Web UI 可以实现如下功能：
-
-1. 运行前自动读取`configs/model_config.py`中`LLM`及`Embedding`模型枚举及默认模型设置运行模型，如需重新加载模型，可在 `模型配置` Tab 重新选择后点击 `重新加载模型` 进行模型加载；
-2. 可手动调节保留对话历史长度、匹配知识库文段数量，可根据显存大小自行调节；
-3. `对话` Tab 具备模式选择功能，可选择 `LLM对话` 与 `知识库问答` 模式进行对话，支持流式对话；
-4. 添加 `配置知识库` 功能，支持选择已有知识库或新建知识库，并可向知识库中**新增**上传文件/文件夹，使用文件上传组件选择好文件后点击 `上传文件并加载知识库`，会将所选上传文档数据加载至知识库中，并基于更新后知识库进行问答；
-5. 新增 `知识库测试 Beta` Tab，可用于测试不同文本切分方法与检索相关度阈值设置，暂不支持将测试参数作为 `对话` Tab 设置参数。
-6. 后续版本中将会增加对知识库的修改或删除，及知识库中已导入文件的查看。
-
-### 常见问题
-
-参见 [常见问题](docs/FAQ.md)。
-
-## Demo
-
-以问题`chatglm-6b 的局限性具体体现在哪里，如何实现改进`为例：
-
-未使用 langchain 接入本地文档时：
-
->ChatGLM-6B 是一个基于 GPT-3 的聊天机器人,它的局限性主要体现在以下几个方面:
->1. 语言模型的精度:GPT-3 是一种大型的语言模型,它的精度比较高,但是仍然有一些局限性。例如,它可能无法准确地理解某些方言、口音或者复杂的句子结构。
->2. 知识图谱的完整性:GPT-3 可以生成一些知识图谱,但是其完整性和准确性可能不够。例如,它可能无法准确地理解某些领域的专业知识和术语。
->3. 对话生成的连贯性:GPT-3 可以生成一些连贯的对话,但是其生成的对话可能不够自然。例如,它可能会生成一些虚假的、不连贯的对话或者误解用户的意图。
->
->为了改进 ChatGLM-6B,可以考虑以下几个方面:
->1. 提高语言模型的精度:可以通过增加训练数据、使用更好的语言模型架构、优化模型训练过程等方式来提高语言模型的精度。
->2. 增强知识图谱的完整性:可以通过增加知识图谱的维度、使用更好的知识图谱构建方法、优化知识图谱的匹配算法等方式来增强知识图谱的完整性。
->3. 提高对话生成的连贯性:可以通过增加对话生成模型的上下文信息、使用更好的上下文信息提取方法、优化对话生成模型的算法等方式来提高对话生成的连贯性。
->4. 引入更多的人类反馈:人类反馈可以帮助 ChatGLM-6B 更好地理解用户的意图和需求,从而提高对话生成的质量和准确性。可以通过引入更多的人类客服、使用人类反馈收集器等方式来引入更多的人类反馈。
-
-使用 langchain 接入 ChatGLM-6B 项目的 README.md 文件后 ChatGLM 的回答：
->ChatGLM-6B 是一个基于深度学习的自然语言处理模型,它在回答问题方面表现出色。但是,它也有一些局限性,具体如下:
->1. 语言理解有限:ChatGLM-6B 只学习了中文自然语言,对于其他语言可能会存在理解上的局限性。
->2. 知识储备不足:ChatGLM-6B 的训练数据集只包含了中文语料,因此它可能无法回答一些非中文的问题或者某些特定领域的问题。
->3. 数据量有限:ChatGLM-6B 的训练数据集只有几百万条记录,因此它可能无法回答一些非常具体或者复杂的问题。
->
->为了改进 ChatGLM-6B,可以考虑以下几个方面:
->1. 学习更多的语言知识:可以学习其他语言的自然语言处理技术,扩大语言理解的范围。
->2. 扩大知识储备:可以收集更多的中文语料,或者使用其他语言的数据集来扩充知识储备。
->3. 增加数据量:可以使用更大的数据集来训练 ChatGLM-6B,提高模型的表现。
->4. 引入更多的评估指标:可以引入更多的评估指标来评估模型的表现,从而发现 ChatGLM-6B 存在的不足和局限性。
->5. 改进模型架构:可以改进 ChatGLM-6B 的模型架构,提高模型的性能和表现。例如,可以使用更大的神经网络或者改进的卷积神经网络结构。
-
-## 路线图
-
-- [ ] Langchain 应用
-  - [x] 接入非结构化文档（已支持 md、pdf、docx、txt 文件格式）
-  - [ ] 搜索引擎与本地网页接入
-  - [ ] 结构化数据接入（如 csv、Excel、SQL 等）
-  - [ ] 知识图谱/图数据库接入
-  - [ ] Agent 实现
-- [ ] 增加更多 LLM 模型支持
-  - [x] [THUDM/chatglm-6b](https://huggingface.co/THUDM/chatglm-6b)
-  - [x] [THUDM/chatglm-6b-int8](https://huggingface.co/THUDM/chatglm-6b-int8)
-  - [x] [THUDM/chatglm-6b-int4](https://huggingface.co/THUDM/chatglm-6b-int4)
-  - [x] [THUDM/chatglm-6b-int4-qe](https://huggingface.co/THUDM/chatglm-6b-int4-qe)
-  - [x] [ClueAI/ChatYuan-large-v2](https://huggingface.co/ClueAI/ChatYuan-large-v2)
-  - [x] [fnlp/moss-moon-003-sft](https://huggingface.co/fnlp/moss-moon-003-sft)
-- [ ] 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)
-- [ ] Web UI
-  - [x] 利用 gradio 实现 Web UI DEMO
-  - [x] 添加输出内容及错误提示
-  - [x] 引用标注
-  - [ ] 增加知识库管理
-    - [x] 选择知识库开始问答
-    - [x] 上传文件/文件夹至知识库
-    - [ ] 删除知识库中文件
-  - [ ] 利用 streamlit 实现 Web UI Demo
-- [ ] 增加 API 支持
-  - [x] 利用 fastapi 实现 API 部署方式
-  - [ ] 实现调用 API 的 Web UI Demo
-
-## 项目交流群
-![二维码](img/qr_code_17.jpg)
-
-🎉 langchain-ChatGLM 项目交流群，如果你也对本项目感兴趣，欢迎加入群聊参与讨论交流。

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)

docs/CHANGELOG.md

@@ -1,32 +0,0 @@
-## 变更日志
-
-**[2023/04/15]**
-
-1. 重构项目结构，在根目录下保留命令行 Demo [cli_demo.py](../cli_demo.py) 和 Web UI Demo [webui.py](../webui.py)；
-2. 对 Web UI 进行改进，修改为运行 Web UI 后首先按照 [configs/model_config.py](../configs/model_config.py) 默认选项加载模型，并增加报错提示信息等；
-3. 对常见问题进行补充说明。
-
-**[2023/04/12]**
-
-1. 替换 Web UI 中的样例文件，避免出现 Ubuntu 中出现因文件编码无法读取的问题；
-2. 替换`knowledge_based_chatglm.py`中的 prompt 模版，避免出现因 prompt 模版包含中英双语导致 chatglm 返回内容错乱的问题。
-
-**[2023/04/11]** 
-
-1. 加入 Web UI V0.1 版本（感谢 [@liangtongt](https://github.com/liangtongt)）；
-2. `README.md`中增加常见问题（感谢 [@calcitem](https://github.com/calcitem) 和 [@bolongliu](https://github.com/bolongliu)）；
-3. 增加 LLM 和 Embedding 模型运行设备是否可用`cuda`、`mps`、`cpu`的自动判断。
-4. 在`knowledge_based_chatglm.py`中增加对`filepath`的判断，在之前支持单个文件导入的基础上，现支持单个文件夹路径作为输入，输入后将会遍历文件夹中各个文件，并在命令行中显示每个文件是否成功加载。
-
-**[2023/04/09]**
-
-1. 使用`langchain`中的`RetrievalQA`替代之前选用的`ChatVectorDBChain`，替换后可以有效减少提问 2-3 次后因显存不足而停止运行的问题；
-2. 在`knowledge_based_chatglm.py`中增加`EMBEDDING_MODEL`、`VECTOR_SEARCH_TOP_K`、`LLM_MODEL`、`LLM_HISTORY_LEN`、`REPLY_WITH_SOURCE`参数值设置；
-3. 增加 GPU 显存需求更小的`chatglm-6b-int4`、`chatglm-6b-int4-qe`作为 LLM 模型备选项；
-4. 更正`README.md`中的代码错误（感谢 [@calcitem](https://github.com/calcitem)）。
-
-**[2023/04/07]** 
-
-1. 解决加载 ChatGLM 模型时发生显存占用为双倍的问题 (感谢 [@suc16](https://github.com/suc16) 和 [@myml](https://github.com/myml)) ；
-2. 新增清理显存机制；
-3. 新增`nghuyong/ernie-3.0-nano-zh`和`nghuyong/ernie-3.0-base-zh`作为 Embedding 模型备选项，相比`GanymedeNil/text2vec-large-chinese`占用显存资源更少 (感谢 [@lastrei](https://github.com/lastrei))。

docs/ES部署指南.md

@@ -0,0 +1,29 @@
+
+# 实现基于ES的数据插入、检索、删除、更新
+```shell
+author: 唐国梁Tommy
+e-mail: flytang186@qq.com
+
+如果遇到任何问题，可以与我联系，我这边部署后服务是没有问题的。
+```
+
+## 第1步：ES docker部署
+```shell
+docker network create elastic
+docker run -id --name elasticsearch --net elastic -p 9200:9200 -p 9300:9300 -e "discovery.type=single-node" -e "xpack.security.enabled=false" -e "xpack.security.http.ssl.enabled=false" -t docker.elastic.co/elasticsearch/elasticsearch:8.8.2
+```
+
+### 第2步：Kibana docker部署
+**注意：Kibana版本与ES保持一致**
+```shell
+docker pull docker.elastic.co/kibana/kibana:{version} 
+docker run --name kibana --net elastic -p 5601:5601 docker.elastic.co/kibana/kibana:{version}
+```
+
+### 第3步：核心代码
+```shell
+1. 核心代码路径
+server/knowledge_base/kb_service/es_kb_service.py
+
+2. 需要在 configs/model_config.py 中 配置 ES参数（IP， PORT）等；
+```

docs/FAQ.md

@@ -1,121 +0,0 @@
-### 常见问题
-
-Q1: 本项目支持哪些文件格式？
-
-A1: 目前已测试支持 txt、docx、md、pdf 格式文件，更多文件格式请参考 [langchain 文档](https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/unstructured_file.html)。目前已知文档中若含有特殊字符，可能存在文件无法加载的问题。
-
----
-
-Q2: 执行 `pip install -r requirements.txt` 过程中，安装 `detectron2` 时发生报错怎么办？
-
-A2: 如果不需要对 `pdf` 格式文件读取，可不安装 `detectron2`；如需对 `pdf` 文件进行高精度文本提取，建议按照如下方法安装：
-
-```commandline
-$ git clone https://github.com/facebookresearch/detectron2.git
-$ cd detectron2
-$ pip install -e .
-```
-
----
-
-Q3: 使用过程中 Python 包`nltk`发生了`Resource punkt not found.`报错，该如何解决？
-
-A3: 方法一：https://github.com/nltk/nltk_data/raw/gh-pages/packages/tokenizers/punkt.zip 中的 `packages/tokenizers` 解压，放到  `nltk_data/tokenizers` 存储路径下。
-
- `nltk_data` 存储路径可以通过 `nltk.data.path` 查询。
- 
- 方法二：执行python代码
-``` 
-import nltk
-nltk.download()
-``` 
-
----
-
-Q4: 使用过程中 Python 包`nltk`发生了`Resource averaged_perceptron_tagger not found.`报错，该如何解决？
-
-A4: 方法一：将 https://github.com/nltk/nltk_data/blob/gh-pages/packages/taggers/averaged_perceptron_tagger.zip 下载，解压放到 `nltk_data/taggers` 存储路径下。
-
- `nltk_data` 存储路径可以通过 `nltk.data.path` 查询。  
- 
-方法二：执行python代码
-``` 
-import nltk
-nltk.download()
-``` 
----
-
-Q5: 本项目可否在 colab 中运行？
-
-A5: 可以尝试使用 chatglm-6b-int4 模型在 colab 中运行，需要注意的是，如需在 colab 中运行 Web UI，需将`webui.py`中`demo.queue(concurrency_count=3).launch(
-    server_name='0.0.0.0', share=False, inbrowser=False)`中参数`share`设置为`True`。
-
----
-
-Q6: 在 Anaconda 中使用 pip 安装包无效如何解决？
-
-A6: 此问题是系统环境问题，详细见  [在Anaconda中使用pip安装包无效问题](在Anaconda中使用pip安装包无效问题.md)
-
----
-
-Q7: 本项目中所需模型如何下载至本地？
-
-A7: 本项目中使用的模型均为`huggingface.com`中可下载的开源模型，以默认选择的`chatglm-6b`和`text2vec-large-chinese`模型为例，下载模型可执行如下代码：
-
-```shell
-# 安装 git lfs
-$ git lfs install
-
-# 下载 LLM 模型
-$ git clone https://huggingface.co/THUDM/chatglm-6b /your_path/chatglm-6b
-
-# 下载 Embedding 模型
-$ git clone https://huggingface.co/GanymedeNil/text2vec-large-chinese /your_path/text2vec
-
-# 模型需要更新时，可打开模型所在文件夹后拉取最新模型文件/代码
-$ git pull
-```
-
----
-
-Q8: `huggingface.com`中模型下载速度较慢怎么办？
-
-A8: 可使用本项目用到的模型权重文件百度网盘地址：
-
-- ernie-3.0-base-zh.zip 链接: https://pan.baidu.com/s/1CIvKnD3qzE-orFouA8qvNQ?pwd=4wih
-- ernie-3.0-nano-zh.zip 链接: https://pan.baidu.com/s/1Fh8fgzVdavf5P1omAJJ-Zw?pwd=q6s5
-- text2vec-large-chinese.zip 链接: https://pan.baidu.com/s/1sMyPzBIXdEzHygftEoyBuA?pwd=4xs7
-- chatglm-6b-int4-qe.zip 链接: https://pan.baidu.com/s/1DDKMOMHtNZccOOBGWIOYww?pwd=22ji
-- chatglm-6b-int4.zip 链接: https://pan.baidu.com/s/1pvZ6pMzovjhkA6uPcRLuJA?pwd=3gjd
-- chatglm-6b.zip 链接: https://pan.baidu.com/s/1B-MpsVVs1GHhteVBetaquw?pwd=djay
-
----
-
-Q9: 下载完模型后，如何修改代码以执行本地模型？
-
-A9: 模型下载完成后，请在 [configs/model_config.py](../configs/model_config.py) 文件中，对`embedding_model_dict`和`llm_model_dict`参数进行修改，如把`llm_model_dict`从
-
-```python
-embedding_model_dict = {
-    "ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
-    "ernie-base": "nghuyong/ernie-3.0-base-zh",
-    "text2vec": "GanymedeNil/text2vec-large-chinese"
-}
-```
-
-修改为
-
-```python
-embedding_model_dict = {
-                        "ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
-                        "ernie-base": "nghuyong/ernie-3.0-base-zh",
-                        "text2vec": "/Users/liuqian/Downloads/ChatGLM-6B/text2vec-large-chinese"
-}
-```
----
-
-Q10: 执行`python cli_demo.py`过程中，显卡内存爆了，提示"OutOfMemoryError: CUDA out of memory"
-
-A10: 将 `VECTOR_SEARCH_TOP_K` 和 `LLM_HISTORY_LEN` 的值调低，比如 `VECTOR_SEARCH_TOP_K = 5` 和 `LLM_HISTORY_LEN = 2`，这样由 `query` 和 `context` 拼接得到的 `prompt` 会变短，会减少内存的占用。
-
----

docs/INSTALL.md

@@ -1,47 +0,0 @@
-# 安装
-
-## 环境检查
-
-```shell
-# 首先，确信你的机器安装了 Python 3.8 及以上版本
-$ python --version
-Python 3.8.13
-
-# 如果低于这个版本，可使用conda安装环境
-$ conda create -p /your_path/env_name python=3.8
-
-# 激活环境
-$ source activate /your_path/env_name
-$ pip3 install --upgrade pip
-
-# 关闭环境
-$ source deactivate /your_path/env_name
-
-# 删除环境
-$ conda env remove -p  /your_path/env_name
-```
-
-## 项目依赖
-
-```shell
-# 拉取仓库
-$ git clone https://github.com/imClumsyPanda/langchain-ChatGLM.git
-
-# 进入目录
-$ cd langchain-ChatGLM
-
-# 项目中 pdf 加载由先前的 detectron2 替换为使用 paddleocr，如果之前有安装过 detectron2 需要先完成卸载避免引发 tools 冲突
-$ pip uninstall detectron2
-
-# 检查paddleocr依赖，linux环境下paddleocr依赖libX11，libXext
-$ yum install libX11
-$ yum install libXext
-
-# 安装依赖
-$ pip install -r requirements.txt
-
-# 验证paddleocr是否成功，首次运行会下载约18M模型到~/.paddleocr
-$ python loader/image_loader.py
-
-```
-注：使用 `langchain.document_loaders.UnstructuredFileLoader` 进行非结构化文件接入时，可能需要依据文档进行其他依赖包的安装，请参考 [langchain 文档](https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/unstructured_file.html)。

docs/Issue-with-Installing-Packages-Using-pip-in-Anaconda.md

@@ -1,114 +0,0 @@
-## Issue with Installing Packages Using pip in Anaconda
-
-## Problem
-
-Recently, when running open-source code, I encountered an issue: after creating a virtual environment with conda and switching to the new environment, using pip to install packages would be "ineffective." Here, "ineffective" means that the packages installed with pip are not in this new environment.
-
-------
-
-## Analysis
-
-1. First, create a test environment called test: `conda create -n test`
-2. Activate the test environment: `conda activate test`
-3. Use pip to install numpy: `pip install numpy`. You'll find that numpy already exists in the default environment.
-
-```powershell
-Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
-Requirement already satisfied: numpy in c:\programdata\anaconda3\lib\site-packages (1.20.3)
-```
-
-4. Check the information of pip: `pip show pip`
-
-```powershell
-Name: pip
-Version: 21.2.4
-Summary: The PyPA recommended tool for installing Python packages.
-Home-page: https://pip.pypa.io/
-Author: The pip developers
-Author-email: distutils-sig@python.org
-License: MIT
-Location: c:\programdata\anaconda3\lib\site-packages
-Requires:
-Required-by:
-```
-
-5. We can see that the current pip is in the default conda environment. This explains why the package is not in the new virtual environment when we directly use pip to install packages - because the pip being used belongs to the default environment, the installed package either already exists or is installed directly into the default environment.
-
-------
-
-## Solution
-
-1. We can directly use the conda command to install new packages, but sometimes conda may not have certain packages/libraries, so we still need to use pip to install.
-2. We can first use the conda command to install the pip package for the current virtual environment, and then use pip to install new packages.
-
-```powershell
-# Use conda to install the pip package
-(test) PS C:\Users\Administrator> conda install pip
-Collecting package metadata (current_repodata.json): done
-Solving environment: done
-....
-done
-
-# Display the information of the current pip, and find that pip is in the test environment
-(test) PS C:\Users\Administrator> pip show pip
-Name: pip
-Version: 21.2.4
-Summary: The PyPA recommended tool for installing Python packages.
-Home-page: https://pip.pypa.io/
-Author: The pip developers
-Author-email: distutils-sig@python.org
-License: MIT
-Location: c:\programdata\anaconda3\envs\test\lib\site-packages
-Requires:
-Required-by:
-
-# Now use pip to install the numpy package, and it is installed successfully
-(test) PS C:\Users\Administrator> pip install numpy
-Looking in indexes: 
-https://pypi.tuna.tsinghua.edu.cn/simple
-Collecting numpy
-  Using cached https://pypi.tuna.tsinghua.edu.cn/packages/4b/23/140ec5a509d992fe39db17200e96c00fd29603c1531ce633ef93dbad5e9e/numpy-1.22.2-cp39-cp39-win_amd64.whl (14.7 MB)
-Installing collected packages: numpy
-Successfully installed numpy-1.22.2
-
-# Use pip list to view the currently installed packages, no problem
-(test) PS C:\Users\Administrator> pip list
-Package      Version
------------- ---------
-certifi      2021.10.8
-numpy        1.22.2
-pip          21.2.4
-setuptools   58.0.4
-wheel        0.37.1
-wincertstore 0.2
-```
-
-## Supplement
-
-1. The reason I didn't notice this problem before might be because the packages installed in the virtual environment were of a specific version, which overwrote the packages in the default environment. The main issue was actually a lack of careful observation:), otherwise, I could have noticed `Successfully uninstalled numpy-xxx` **default version** and `Successfully installed numpy-1.20.3` **specified version**.
-2. During testing, I found that if the Python version is specified when creating a new package, there shouldn't be this issue. I guess this is because pip will be installed in the virtual environment, while in our case, including pip, no packages were installed, so the default environment's pip was used.
-3. There's a question: I should have specified the Python version when creating a new virtual environment before, but I still used the default environment's pip package. However, I just couldn't reproduce the issue successfully on two different machines, which led to the second point mentioned above.
-4. After encountering the problem mentioned in point 3, I solved it by using `python -m pip install package-name`, adding `python -m` before pip. As for why, you can refer to the answer on [StackOverflow](https://stackoverflow.com/questions/41060382/using-pip-to-install-packages-to-anaconda-environment):
-
->1. If you have a non-conda pip as your default pip but conda python as your default python (as below):
->
->```shell
->>which -a pip
->/home/<user>/.local/bin/pip   
->/home/<user>/.conda/envs/newenv/bin/pip
->/usr/bin/pip
->
->>which -a python
->/home/<user>/.conda/envs/newenv/bin/python
->/usr/bin/python
->```
->
->2. Then, instead of calling `pip install <package>` directly, you can use the module flag -m in python so that it installs with the anaconda python
->
->```shell
->python -m pip install <package>
->```
->
->3. This will install the package to the anaconda library directory rather than the library directory associated with the (non-anaconda) pip
->4. The reason for doing this is as follows: the pip command references a specific pip file/shortcut (which -a pip will tell you which one). Similarly, the python command references a specific python file (which -a python will tell you which one). For one reason or another, these two commands can become out of sync, so your "default" pip is in a different folder than your default python and therefore is associated with different versions of python.
->5. In contrast, the python -m pip construct does not use the shortcut that the pip command points to. Instead, it asks python to find its pip version and use that version to install a package.

docs/StartOption.md

@@ -1,76 +0,0 @@
-
-#### 项目启动选项
-```test
-usage: langchina-ChatGLM [-h] [--no-remote-model] [--model MODEL] [--lora LORA] [--model-dir MODEL_DIR] [--lora-dir LORA_DIR] [--cpu] [--auto-devices] [--gpu-memory GPU_MEMORY [GPU_MEMORY ...]] [--cpu-memory CPU_MEMORY]
-                         [--load-in-8bit] [--bf16]
-
-基于langchain和chatGML的LLM文档阅读器
-
-options:
-  -h, --help            show this help message and exit
-  --no-remote-model     remote in the model on loader checkpoint, if your load local model to add the ` --no-remote-model`
-  --model MODEL         Name of the model to load by default.
-  --lora LORA           Name of the LoRA to apply to the model by default.
-  --model-dir MODEL_DIR
-                        Path to directory with all the models
-  --lora-dir LORA_DIR   Path to directory with all the loras
-  --cpu                 Use the CPU to generate text. Warning: Training on CPU is extremely slow.
-  --auto-devices        Automatically split the model across the available GPU(s) and CPU.
-  --gpu-memory GPU_MEMORY [GPU_MEMORY ...]
-                        Maxmimum GPU memory in GiB to be allocated per GPU. Example: --gpu-memory 10 for a single GPU, --gpu-memory 10 5 for two GPUs. You can also set values in MiB like --gpu-memory 3500MiB.
-  --cpu-memory CPU_MEMORY
-                        Maximum CPU memory in GiB to allocate for offloaded weights. Same as above.
-  --load-in-8bit        Load the model with 8-bit precision.
-  --bf16                Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.
-
-```
-
-#### 示例
-
-- 1、加载本地模型
-
-```text
---model-dir 本地checkpoint存放文件夹
---model  模型名称
---no-remote-model 不从远程加载模型
-```
-```shell
-$  python cli_demo.py --model-dir /media/mnt/ --model chatglm-6b --no-remote-model
-```
-
-- 2、低精度加载模型
-```text
---model-dir 本地checkpoint存放文件夹
---model  模型名称
---no-remote-model 不从远程加载模型
---load-in-8bit   以8位精度加载模型
-```
-```shell
-$ python cli_demo.py --model-dir /media/mnt/ --model chatglm-6b --no-remote-model --load-in-8bit   
-```
-
-
-- 3、使用cpu预测模型
-```text
---model-dir 本地checkpoint存放文件夹
---model  模型名称
---no-remote-model 不从远程加载模型
---cpu   使用CPU生成文本。警告：CPU上的训练非常缓慢。
-```
-```shell
-$ python cli_demo.py --model-dir /media/mnt/ --model chatglm-6b --no-remote-model --cpu 
-```
-
-
-
-- 3、加载lora微调文件
-```text
---model-dir 本地checkpoint存放文件夹
---model  模型名称
---no-remote-model 不从远程加载模型
---lora-dir   本地lora存放文件夹
---lora lora名称
-```
-```shell
-$ python cli_demo.py --model-dir /media/mnt/ --model chatglm-6b --no-remote-model --lora-dir  /media/mnt/loras --lora chatglm-step100
-```

docs/cli.md

@@ -1,49 +0,0 @@
-## 命令行工具
-
-windows cli.bat  
-linux cli.sh
-
-## 命令列表
-
-### llm 管理
-
-llm 支持列表
-
-```shell
-cli.bat llm ls
-```
-
-### embedding 管理
-
-embedding 支持列表
-
-```shell
-cli.bat embedding ls
-```
-
-### start 启动管理
-
-查看启动选择
-
-```shell
-cli.bat start
-```
-
-启动命令行交互
-
-```shell
-cli.bat start cli
-```
-
-启动Web 交互
-
-```shell
-cli.bat start webui
-```
-
-启动api服务
-
-```shell
-cli.bat start api 
-```
-

docs/在Anaconda中使用pip安装包无效问题.md

@@ -1,125 +0,0 @@
-##  在 Anaconda 中使用 pip 安装包无效问题
-
-##  问题
-
-最近在跑开源代码的时候遇到的问题：使用 conda 创建虚拟环境并切换到新的虚拟环境后，再使用 pip 来安装包会“无效”。这里的“无效”指的是使用 pip 安装的包不在这个新的环境中。
-
-------
-
-## 分析
-
-1、首先创建一个测试环境 test，`conda create -n test`
-
-2、激活该测试环境，`conda activate test`
-
-3、使用 pip 安装 numpy，`pip install numpy`，会发现 numpy 已经存在默认的环境中
-
-```powershell
-Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
-Requirement already satisfied: numpy in c:\programdata\anaconda3\lib\site-packages (1.20.3)
-```
-
-4、这时候看一下 pip 的信息，`pip show pip`
-
-```powershell
-Name: pip
-Version: 21.2.4
-Summary: The PyPA recommended tool for installing Python packages.
-Home-page: https://pip.pypa.io/
-Author: The pip developers
-Author-email: distutils-sig@python.org
-License: MIT
-Location: c:\programdata\anaconda3\lib\site-packages
-Requires:
-Required-by:
-```
-
-5、可以发现当前 pip 是在默认的 conda 环境中。这也就解释了当我们直接使用 pip 安装包时为什么包不在这个新的虚拟环境中，因为使用的 pip 属于默认环境，安装的包要么已经存在，要么直接装到默认环境中去了。
-
-------
-
-## 解决
-
-1、我们可以直接使用 conda 命令安装新的包，但有些时候 conda 可能没有某些包/库，所以还是得用 pip 安装
-
-2、我们可以先使用 conda 命令为当前虚拟环境安装 pip 包，再使用 pip 安装新的包
-
-```powershell
-# 使用 conda 安装 pip 包
-(test) PS C:\Users\Administrator> conda install pip
-Collecting package metadata (current_repodata.json): done
-Solving environment: done
-....
-done
-
-# 显示当前 pip 的信息，发现 pip 在测试环境 test 中
-(test) PS C:\Users\Administrator> pip show pip
-Name: pip
-Version: 21.2.4
-Summary: The PyPA recommended tool for installing Python packages.
-Home-page: https://pip.pypa.io/
-Author: The pip developers
-Author-email: distutils-sig@python.org
-License: MIT
-Location: c:\programdata\anaconda3\envs\test\lib\site-packages
-Requires:
-Required-by:
-
-# 再使用 pip 安装 numpy 包，成功安装
-(test) PS C:\Users\Administrator> pip install numpy
-Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
-Collecting numpy
-  Using cached https://pypi.tuna.tsinghua.edu.cn/packages/4b/23/140ec5a509d992fe39db17200e96c00fd29603c1531ce633ef93dbad5e9e/numpy-1.22.2-cp39-cp39-win_amd64.whl (14.7 MB)
-Installing collected packages: numpy
-Successfully installed numpy-1.22.2
-
-# 使用 pip list 查看当前安装的包，没有问题
-(test) PS C:\Users\Administrator> pip list
-Package      Version
------------- ---------
-certifi      2021.10.8
-numpy        1.22.2
-pip          21.2.4
-setuptools   58.0.4
-wheel        0.37.1
-wincertstore 0.2
-```
-
-------
-
-## 补充
-
-1、之前没有发现这个问题可能时因为在虚拟环境中安装的包是指定版本的，覆盖了默认环境中的包。其实主要还是观察不仔细：），不然可以发现 `Successfully uninstalled numpy-xxx`【默认版本】 以及 `Successfully installed numpy-1.20.3`【指定版本】
-
-2、测试时发现如果在新建包的时候指定了 python 版本的话应该是没有这个问题的，猜测时因为会在虚拟环境中安装好 pip ，而我们这里包括 pip 在内啥包也没有装，所以使用的是默认环境的 pip
-
-3、有个问题，之前我在创建新的虚拟环境时应该指定了 python 版本，但还是使用的默认环境的 pip 包，但是刚在在两台机器上都没有复现成功，于是有了上面的第 2 点
-
-4、出现了第 3 点的问题后，我当时是使用 `python -m pip install package-name` 解决的，在 pip 前面加上了 python -m。至于为什么，可以参考 [StackOverflow](https://stackoverflow.com/questions/41060382/using-pip-to-install-packages-to-anaconda-environment) 上的回答：
-
-> 1、如果你有一个非 conda 的 pip 作为你的默认 pip，但是 conda 的 python 是你的默认 python（如下）：
->
-> ```shell
-> >which -a pip
-> /home/<user>/.local/bin/pip   
-> /home/<user>/.conda/envs/newenv/bin/pip
-> /usr/bin/pip
-> 
-> >which -a python
-> /home/<user>/.conda/envs/newenv/bin/python
-> /usr/bin/python
-> ```
->
-> 2、然后，而不是直接调用 `pip install <package>`，你可以在 python 中使用模块标志 -m，以便它使用 anaconda python 进行安装
->
-> ```shell
->python -m pip install <package>
-> ```
->
-> 3、这将把包安装到 anaconda 库目录，而不是与（非anaconda） pip 关联的库目录
-> 
-> 4、这样做的原因如下：命令 pip 引用了一个特定的 pip 文件 / 快捷方式（which -a pip 会告诉你是哪一个）。类似地，命令 python 引用一个特定的 python 文件（which -a python 会告诉你是哪个）。由于这样或那样的原因，这两个命令可能变得不同步，因此你的“默认” pip 与你的默认 python 位于不同的文件夹中，因此与不同版本的 python 相关联。
->
-> 5、与此相反，python -m pip 构造不使用 pip 命令指向的快捷方式。相反，它要求 python 找到它的pip 版本，并使用该版本安装一个包。
-
--   

document_loaders/FilteredCSVloader.py

@@ -0,0 +1,84 @@
+## 指定制定列的csv文件加载器
+
+from langchain.document_loaders import CSVLoader
+import csv
+from io import TextIOWrapper
+from typing import Dict, List, Optional
+from langchain.docstore.document import Document
+from langchain.document_loaders.helpers import detect_file_encodings
+
+
+class FilteredCSVLoader(CSVLoader):
+    def __init__(
+            self,
+            file_path: str,
+            columns_to_read: List[str],
+            source_column: Optional[str] = None,
+            metadata_columns: List[str] = [],
+            csv_args: Optional[Dict] = None,
+            encoding: Optional[str] = None,
+            autodetect_encoding: bool = False,
+    ):
+        super().__init__(
+            file_path=file_path,
+            source_column=source_column,
+            metadata_columns=metadata_columns,
+            csv_args=csv_args,
+            encoding=encoding,
+            autodetect_encoding=autodetect_encoding,
+        )
+        self.columns_to_read = columns_to_read
+
+    def load(self) -> List[Document]:
+        """Load data into document objects."""
+
+        docs = []
+        try:
+            with open(self.file_path, newline="", encoding=self.encoding) as csvfile:
+                docs = self.__read_file(csvfile)
+        except UnicodeDecodeError as e:
+            if self.autodetect_encoding:
+                detected_encodings = detect_file_encodings(self.file_path)
+                for encoding in detected_encodings:
+                    try:
+                        with open(
+                            self.file_path, newline="", encoding=encoding.encoding
+                        ) as csvfile:
+                            docs = self.__read_file(csvfile)
+                            break
+                    except UnicodeDecodeError:
+                        continue
+            else:
+                raise RuntimeError(f"Error loading {self.file_path}") from e
+        except Exception as e:
+            raise RuntimeError(f"Error loading {self.file_path}") from e
+
+        return docs
+
+    def __read_file(self, csvfile: TextIOWrapper) -> List[Document]:
+        docs = []
+        csv_reader = csv.DictReader(csvfile, **self.csv_args)  # type: ignore
+        for i, row in enumerate(csv_reader):
+            content = []
+            for col in self.columns_to_read:
+                if col in row:
+                    content.append(f'{col}:{str(row[col])}')
+                else:
+                    raise ValueError(f"Column '{self.columns_to_read[0]}' not found in CSV file.")
+            content = '\n'.join(content)
+            # Extract the source if available
+            source = (
+                row.get(self.source_column, None)
+                if self.source_column is not None
+                else self.file_path
+            )
+            metadata = {"source": source, "row": i}
+
+            for col in self.metadata_columns:
+                if col in row:
+                    metadata[col] = row[col]
+
+            doc = Document(page_content=content, metadata=metadata)
+            docs.append(doc)
+
+        return docs

document_loaders/__init__.py

@@ -0,0 +1,4 @@
+from .mypdfloader import RapidOCRPDFLoader
+from .myimgloader import RapidOCRLoader
+from .mydocloader import RapidOCRDocLoader
+from .mypptloader import RapidOCRPPTLoader

document_loaders/mydocloader.py

@@ -0,0 +1,71 @@
+from langchain.document_loaders.unstructured import UnstructuredFileLoader
+from typing import List
+import tqdm
+
+
+class RapidOCRDocLoader(UnstructuredFileLoader):
+    def _get_elements(self) -> List:
+        def doc2text(filepath):
+            from docx.table import _Cell, Table
+            from docx.oxml.table import CT_Tbl
+            from docx.oxml.text.paragraph import CT_P
+            from docx.text.paragraph import Paragraph
+            from docx import Document, ImagePart
+            from PIL import Image
+            from io import BytesIO
+            import numpy as np
+            from rapidocr_onnxruntime import RapidOCR
+            ocr = RapidOCR()
+            doc = Document(filepath)
+            resp = ""
+
+            def iter_block_items(parent):
+                from docx.document import Document
+                if isinstance(parent, Document):
+                    parent_elm = parent.element.body
+                elif isinstance(parent, _Cell):
+                    parent_elm = parent._tc
+                else:
+                    raise ValueError("RapidOCRDocLoader parse fail")
+
+                for child in parent_elm.iterchildren():
+                    if isinstance(child, CT_P):
+                        yield Paragraph(child, parent)
+                    elif isinstance(child, CT_Tbl):
+                        yield Table(child, parent)
+
+            b_unit = tqdm.tqdm(total=len(doc.paragraphs)+len(doc.tables),
+                               desc="RapidOCRDocLoader block index: 0")
+            for i, block in enumerate(iter_block_items(doc)):
+                b_unit.set_description(
+                    "RapidOCRDocLoader  block index: {}".format(i))
+                b_unit.refresh()
+                if isinstance(block, Paragraph):
+                    resp += block.text.strip() + "\n"
+                    images = block._element.xpath('.//pic:pic')  # 获取所有图片
+                    for image in images:
+                        for img_id in image.xpath('.//a:blip/@r:embed'):  # 获取图片id
+                            part = doc.part.related_parts[img_id]  # 根据图片id获取对应的图片
+                            if isinstance(part, ImagePart):
+                                image = Image.open(BytesIO(part._blob))
+                                result, _ = ocr(np.array(image))
+                                if result:
+                                    ocr_result = [line[1] for line in result]
+                                    resp += "\n".join(ocr_result)
+                elif isinstance(block, Table):
+                    for row in block.rows:
+                        for cell in row.cells:
+                            for paragraph in cell.paragraphs:
+                                resp += paragraph.text.strip() + "\n"
+                b_unit.update(1)
+            return resp
+
+        text = doc2text(self.file_path)
+        from unstructured.partition.text import partition_text
+        return partition_text(text=text, **self.unstructured_kwargs)
+
+
+if __name__ == '__main__':
+    loader = RapidOCRDocLoader(file_path="../tests/samples/ocr_test.docx")
+    docs = loader.load()
+    print(docs)

document_loaders/myimgloader.py

@@ -0,0 +1,25 @@
+from typing import List
+from langchain.document_loaders.unstructured import UnstructuredFileLoader
+from document_loaders.ocr import get_ocr
+
+
+class RapidOCRLoader(UnstructuredFileLoader):
+    def _get_elements(self) -> List:
+        def img2text(filepath):
+            resp = ""
+            ocr = get_ocr()
+            result, _ = ocr(filepath)
+            if result:
+                ocr_result = [line[1] for line in result]
+                resp += "\n".join(ocr_result)
+            return resp
+
+        text = img2text(self.file_path)
+        from unstructured.partition.text import partition_text
+        return partition_text(text=text, **self.unstructured_kwargs)
+
+
+if __name__ == "__main__":
+    loader = RapidOCRLoader(file_path="../tests/samples/ocr_test.jpg")
+    docs = loader.load()
+    print(docs)

document_loaders/mypdfloader.py

@@ -0,0 +1,87 @@
+from typing import List
+from langchain.document_loaders.unstructured import UnstructuredFileLoader
+import cv2
+from PIL import Image
+import numpy as np
+from configs import PDF_OCR_THRESHOLD
+from document_loaders.ocr import get_ocr
+import tqdm
+
+
+class RapidOCRPDFLoader(UnstructuredFileLoader):
+    def _get_elements(self) -> List:
+        def rotate_img(img, angle):
+            '''
+            img   --image
+            angle --rotation angle
+            return--rotated img
+            '''
+            
+            h, w = img.shape[:2]
+            rotate_center = (w/2, h/2)
+            #获取旋转矩阵
+            # 参数1为旋转中心点;
+            # 参数2为旋转角度,正值-逆时针旋转;负值-顺时针旋转
+            # 参数3为各向同性的比例因子,1.0原图，2.0变成原来的2倍，0.5变成原来的0.5倍
+            M = cv2.getRotationMatrix2D(rotate_center, angle, 1.0)
+            #计算图像新边界
+            new_w = int(h * np.abs(M[0, 1]) + w * np.abs(M[0, 0]))
+            new_h = int(h * np.abs(M[0, 0]) + w * np.abs(M[0, 1]))
+            #调整旋转矩阵以考虑平移
+            M[0, 2] += (new_w - w) / 2
+            M[1, 2] += (new_h - h) / 2
+
+            rotated_img = cv2.warpAffine(img, M, (new_w, new_h))
+            return rotated_img
+        
+        def pdf2text(filepath):
+            import fitz # pyMuPDF里面的fitz包，不要与pip install fitz混淆
+            import numpy as np
+            ocr = get_ocr()
+            doc = fitz.open(filepath)
+            resp = ""
+
+            b_unit = tqdm.tqdm(total=doc.page_count, desc="RapidOCRPDFLoader context page index: 0")
+            for i, page in enumerate(doc):
+                b_unit.set_description("RapidOCRPDFLoader context page index: {}".format(i))
+                b_unit.refresh()
+                text = page.get_text("")
+                resp += text + "\n"
+
+                img_list = page.get_image_info(xrefs=True)
+                for img in img_list:
+                    if xref := img.get("xref"):
+                        bbox = img["bbox"]
+                        # 检查图片尺寸是否超过设定的阈值
+                        if ((bbox[2] - bbox[0]) / (page.rect.width) < PDF_OCR_THRESHOLD[0]
+                            or (bbox[3] - bbox[1]) / (page.rect.height) < PDF_OCR_THRESHOLD[1]):
+                            continue
+                        pix = fitz.Pixmap(doc, xref)
+                        samples = pix.samples
+                        if int(page.rotation)!=0:  #如果Page有旋转角度，则旋转图片
+                            img_array = np.frombuffer(pix.samples, dtype=np.uint8).reshape(pix.height, pix.width, -1)
+                            tmp_img = Image.fromarray(img_array);
+                            ori_img = cv2.cvtColor(np.array(tmp_img),cv2.COLOR_RGB2BGR)
+                            rot_img = rotate_img(img=ori_img, angle=360-page.rotation)
+                            img_array = cv2.cvtColor(rot_img, cv2.COLOR_RGB2BGR)
+                        else:
+                            img_array = np.frombuffer(pix.samples, dtype=np.uint8).reshape(pix.height, pix.width, -1)
+
+                        result, _ = ocr(img_array)
+                        if result:
+                            ocr_result = [line[1] for line in result]
+                            resp += "\n".join(ocr_result)
+
+                # 更新进度
+                b_unit.update(1)
+            return resp
+
+        text = pdf2text(self.file_path)
+        from unstructured.partition.text import partition_text
+        return partition_text(text=text, **self.unstructured_kwargs)
+
+
+if __name__ == "__main__":
+    loader = RapidOCRPDFLoader(file_path="/Users/tonysong/Desktop/test.pdf")
+    docs = loader.load()
+    print(docs)

document_loaders/mypptloader.py

@@ -0,0 +1,59 @@
+from langchain.document_loaders.unstructured import UnstructuredFileLoader
+from typing import List
+import tqdm
+
+
+class RapidOCRPPTLoader(UnstructuredFileLoader):
+    def _get_elements(self) -> List:
+        def ppt2text(filepath):
+            from pptx import Presentation
+            from PIL import Image
+            import numpy as np
+            from io import BytesIO
+            from rapidocr_onnxruntime import RapidOCR
+            ocr = RapidOCR()
+            prs = Presentation(filepath)
+            resp = ""
+
+            def extract_text(shape):
+                nonlocal resp
+                if shape.has_text_frame:
+                    resp += shape.text.strip() + "\n"
+                if shape.has_table:
+                    for row in shape.table.rows:
+                        for cell in row.cells:
+                            for paragraph in cell.text_frame.paragraphs:
+                                resp += paragraph.text.strip() + "\n"
+                if shape.shape_type == 13:  # 13 表示图片
+                    image = Image.open(BytesIO(shape.image.blob))
+                    result, _ = ocr(np.array(image))
+                    if result:
+                        ocr_result = [line[1] for line in result]
+                        resp += "\n".join(ocr_result)
+                elif shape.shape_type == 6:  # 6 表示组合
+                    for child_shape in shape.shapes:
+                        extract_text(child_shape)
+
+            b_unit = tqdm.tqdm(total=len(prs.slides),
+                               desc="RapidOCRPPTLoader slide index: 1")
+            # 遍历所有幻灯片
+            for slide_number, slide in enumerate(prs.slides, start=1):
+                b_unit.set_description(
+                    "RapidOCRPPTLoader slide index: {}".format(slide_number))
+                b_unit.refresh()
+                sorted_shapes = sorted(slide.shapes,
+                                       key=lambda x: (x.top, x.left))  # 从上到下、从左到右遍历
+                for shape in sorted_shapes:
+                    extract_text(shape)
+                b_unit.update(1)
+            return resp
+
+        text = ppt2text(self.file_path)
+        from unstructured.partition.text import partition_text
+        return partition_text(text=text, **self.unstructured_kwargs)
+
+
+if __name__ == '__main__':
+    loader = RapidOCRPPTLoader(file_path="../tests/samples/ocr_test.pptx")
+    docs = loader.load()
+    print(docs)

document_loaders/ocr.py

@@ -0,0 +1,18 @@
+from typing import TYPE_CHECKING
+
+
+if TYPE_CHECKING:
+    try:
+        from rapidocr_paddle import RapidOCR
+    except ImportError:
+        from rapidocr_onnxruntime import RapidOCR
+
+
+def get_ocr(use_cuda: bool = True) -> "RapidOCR":
+    try:
+        from rapidocr_paddle import RapidOCR
+        ocr = RapidOCR(det_use_cuda=use_cuda, cls_use_cuda=use_cuda, rec_use_cuda=use_cuda)
+    except ImportError:
+        from rapidocr_onnxruntime import RapidOCR
+        ocr = RapidOCR()
+    return ocr

embeddings/add_embedding_keywords.py

@@ -0,0 +1,79 @@
+'''
+该功能是为了将关键词加入到embedding模型中，以便于在embedding模型中进行关键词的embedding
+该功能的实现是通过修改embedding模型的tokenizer来实现的
+该功能仅仅对EMBEDDING_MODEL参数对应的的模型有效，输出后的模型保存在原本模型
+感谢@CharlesJu1和@charlesyju的贡献提出了想法和最基础的PR
+
+保存的模型的位置位于原本嵌入模型的目录下，模型的名称为原模型名称+Merge_Keywords_时间戳
+'''
+import sys
+
+sys.path.append("..")
+import os
+import torch
+
+from datetime import datetime
+from configs import (
+    MODEL_PATH,
+    EMBEDDING_MODEL,
+    EMBEDDING_KEYWORD_FILE,
+)
+
+from safetensors.torch import save_model
+from sentence_transformers import SentenceTransformer
+from langchain_core._api import deprecated
+
+
+@deprecated(
+        since="0.3.0",
+        message="自定义关键词 Langchain-Chatchat 0.3.x 重写, 0.2.x中相关功能将废弃",
+        removal="0.3.0"
+    )
+def get_keyword_embedding(bert_model, tokenizer, key_words):
+    tokenizer_output = tokenizer(key_words, return_tensors="pt", padding=True, truncation=True)
+    input_ids = tokenizer_output['input_ids']
+    input_ids = input_ids[:, 1:-1]
+
+    keyword_embedding = bert_model.embeddings.word_embeddings(input_ids)
+    keyword_embedding = torch.mean(keyword_embedding, 1)
+    return keyword_embedding
+
+
+def add_keyword_to_model(model_name=EMBEDDING_MODEL, keyword_file: str = "", output_model_path: str = None):
+    key_words = []
+    with open(keyword_file, "r") as f:
+        for line in f:
+            key_words.append(line.strip())
+
+    st_model = SentenceTransformer(model_name)
+    key_words_len = len(key_words)
+    word_embedding_model = st_model._first_module()
+    bert_model = word_embedding_model.auto_model
+    tokenizer = word_embedding_model.tokenizer
+    key_words_embedding = get_keyword_embedding(bert_model, tokenizer, key_words)
+
+    embedding_weight = bert_model.embeddings.word_embeddings.weight
+    embedding_weight_len = len(embedding_weight)
+    tokenizer.add_tokens(key_words)
+    bert_model.resize_token_embeddings(len(tokenizer), pad_to_multiple_of=32)
+    embedding_weight = bert_model.embeddings.word_embeddings.weight
+    with torch.no_grad():
+        embedding_weight[embedding_weight_len:embedding_weight_len + key_words_len, :] = key_words_embedding
+
+    if output_model_path:
+        os.makedirs(output_model_path, exist_ok=True)
+        word_embedding_model.save(output_model_path)
+        safetensors_file = os.path.join(output_model_path, "model.safetensors")
+        metadata = {'format': 'pt'}
+        save_model(bert_model, safetensors_file, metadata)
+        print("save model to {}".format(output_model_path))
+
+
+def add_keyword_to_embedding_model(path: str = EMBEDDING_KEYWORD_FILE):
+    keyword_file = os.path.join(path)
+    model_name = MODEL_PATH["embed_model"][EMBEDDING_MODEL]
+    model_parent_directory = os.path.dirname(model_name)
+    current_time = datetime.now().strftime('%Y%m%d_%H%M%S')
+    output_model_name = "{}_Merge_Keywords_{}".format(EMBEDDING_MODEL, current_time)
+    output_model_path = os.path.join(model_parent_directory, output_model_name)
+    add_keyword_to_model(model_name, keyword_file, output_model_path)

embeddings/embedding_keywords.txt

@@ -0,0 +1,3 @@
+Langchain-Chatchat
+数据科学与大数据技术
+人工智能与先进计算

fastchat/api/__init__.py

@@ -1 +0,0 @@
-from .fastchat_api import *

fastchat/api/conversation.py

@@ -1,261 +0,0 @@
-"""
-Conversation prompt template.
-
-Now we support
-- Vicuna
-- Koala
-- OpenAssistant/oasst-sft-1-pythia-12b
-- StabilityAI/stablelm-tuned-alpha-7b
-- databricks/dolly-v2-12b
-- THUDM/chatglm-6b
-- Alpaca/LLaMa
-"""
-
-import dataclasses
-from enum import auto, Enum
-from typing import List, Tuple, Any
-
-
-class SeparatorStyle(Enum):
-    """Different separator style."""
-
-    SINGLE = auto()
-    TWO = auto()
-    DOLLY = auto()
-    OASST_PYTHIA = auto()
-
-
-@dataclasses.dataclass
-class Conversation:
-    """A class that keeps all conversation history."""
-
-    system: str
-    roles: List[str]
-    messages: List[List[str]]
-    offset: int
-    sep_style: SeparatorStyle = SeparatorStyle.SINGLE
-    sep: str = "###"
-    sep2: str = None
-
-    # Used for gradio server
-    skip_next: bool = False
-    conv_id: Any = None
-
-    def get_prompt(self):
-        if self.sep_style == SeparatorStyle.SINGLE:
-            ret = self.system
-            for role, message in self.messages:
-                if message:
-                    ret += self.sep + " " + role + ": " + message
-                else:
-                    ret += self.sep + " " + role + ":"
-            return ret
-        elif self.sep_style == SeparatorStyle.TWO:
-            seps = [self.sep, self.sep2]
-            ret = self.system + seps[0]
-            for i, (role, message) in enumerate(self.messages):
-                if message:
-                    ret += role + ": " + message + seps[i % 2]
-                else:
-                    ret += role + ":"
-            return ret
-        elif self.sep_style == SeparatorStyle.DOLLY:
-            seps = [self.sep, self.sep2]
-            ret = self.system
-            for i, (role, message) in enumerate(self.messages):
-                if message:
-                    ret += role + ":\n" + message + seps[i % 2]
-                    if i % 2 == 1:
-                        ret += "\n\n"
-                else:
-                    ret += role + ":\n"
-            return ret
-        elif self.sep_style == SeparatorStyle.OASST_PYTHIA:
-            ret = self.system
-            for role, message in self.messages:
-                if message:
-                    ret += role + message + self.sep
-                else:
-                    ret += role
-            return ret
-        else:
-            raise ValueError(f"Invalid style: {self.sep_style}")
-
-    def append_message(self, role, message):
-        self.messages.append([role, message])
-
-    def to_gradio_chatbot(self):
-        ret = []
-        for i, (role, msg) in enumerate(self.messages[self.offset :]):
-            if i % 2 == 0:
-                ret.append([msg, None])
-            else:
-                ret[-1][-1] = msg
-        return ret
-
-    def copy(self):
-        return Conversation(
-            system=self.system,
-            roles=self.roles,
-            messages=[[x, y] for x, y in self.messages],
-            offset=self.offset,
-            sep_style=self.sep_style,
-            sep=self.sep,
-            sep2=self.sep2,
-            conv_id=self.conv_id,
-        )
-
-    def dict(self):
-        return {
-            "system": self.system,
-            "roles": self.roles,
-            "messages": self.messages,
-            "offset": self.offset,
-            "sep": self.sep,
-            "sep2": self.sep2,
-            "conv_id": self.conv_id,
-        }
-
-
-conv_one_shot = Conversation(
-    system="A chat between a curious human and an artificial intelligence assistant. "
-    "The assistant gives helpful, detailed, and polite answers to the human's questions.",
-    roles=("Human", "Assistant"),
-    messages=(
-        (
-            "Human",
-            "What are the key differences between renewable and non-renewable energy sources?",
-        ),
-        (
-            "Assistant",
-            "Renewable energy sources are those that can be replenished naturally in a relatively "
-            "short amount of time, such as solar, wind, hydro, geothermal, and biomass. "
-            "Non-renewable energy sources, on the other hand, are finite and will eventually be "
-            "depleted, such as coal, oil, and natural gas. Here are some key differences between "
-            "renewable and non-renewable energy sources:\n"
-            "1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable "
-            "energy sources are finite and will eventually run out.\n"
-            "2. Environmental impact: Renewable energy sources have a much lower environmental impact "
-            "than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, "
-            "and other negative effects.\n"
-            "3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically "
-            "have lower operational costs than non-renewable sources.\n"
-            "4. Reliability: Renewable energy sources are often more reliable and can be used in more remote "
-            "locations than non-renewable sources.\n"
-            "5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different "
-            "situations and needs, while non-renewable sources are more rigid and inflexible.\n"
-            "6. Sustainability: Renewable energy sources are more sustainable over the long term, while "
-            "non-renewable sources are not, and their depletion can lead to economic and social instability.",
-        ),
-    ),
-    offset=2,
-    sep_style=SeparatorStyle.SINGLE,
-    sep="###",
-)
-
-
-conv_vicuna_v1_1 = Conversation(
-    system="A chat between a curious user and an artificial intelligence assistant. "
-    "The assistant gives helpful, detailed, and polite answers to the user's questions.",
-    roles=("USER", "ASSISTANT"),
-    messages=(),
-    offset=0,
-    sep_style=SeparatorStyle.TWO,
-    sep=" ",
-    sep2="</s>",
-)
-
-
-conv_koala_v1 = Conversation(
-    system="BEGINNING OF CONVERSATION:",
-    roles=("USER", "GPT"),
-    messages=(),
-    offset=0,
-    sep_style=SeparatorStyle.TWO,
-    sep=" ",
-    sep2="</s>",
-)
-
-conv_dolly = Conversation(
-    system="Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n",
-    roles=("### Instruction", "### Response"),
-    messages=(),
-    offset=0,
-    sep_style=SeparatorStyle.DOLLY,
-    sep="\n\n",
-    sep2="### End",
-)
-
-conv_oasst = Conversation(
-    system="",
-    roles=("<|prompter|>", "<|assistant|>"),
-    messages=(),
-    offset=0,
-    sep_style=SeparatorStyle.OASST_PYTHIA,
-    sep="<|endoftext|>",
-)
-
-conv_stablelm = Conversation(
-    system="""<|SYSTEM|># StableLM Tuned (Alpha version)
-- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
-- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
-- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
-- StableLM will refuse to participate in anything that could harm a human.
-""",
-    roles=("<|USER|>", "<|ASSISTANT|>"),
-    messages=(),
-    offset=0,
-    sep_style=SeparatorStyle.OASST_PYTHIA,
-    sep="",
-)
-
-conv_templates = {
-    "conv_one_shot": conv_one_shot,
-    "vicuna_v1.1": conv_vicuna_v1_1,
-    "koala_v1": conv_koala_v1,
-    "dolly": conv_dolly,
-    "oasst": conv_oasst,
-}
-
-
-def get_default_conv_template(model_name):
-    model_name = model_name.lower()
-    if "vicuna" in model_name or "output" in model_name:
-        return conv_vicuna_v1_1
-    elif "koala" in model_name:
-        return conv_koala_v1
-    elif "dolly-v2" in model_name:
-        return conv_dolly
-    elif "oasst" in model_name and "pythia" in model_name:
-        return conv_oasst
-    elif "stablelm" in model_name:
-        return conv_stablelm
-    return conv_one_shot
-
-
-def compute_skip_echo_len(model_name, conv, prompt):
-    model_name = model_name.lower()
-    if "chatglm" in model_name:
-        skip_echo_len = len(conv.messages[-2][1]) + 1
-    elif "dolly-v2" in model_name:
-        special_toks = ["### Instruction:", "### Response:", "### End"]
-        skip_echo_len = len(prompt)
-        for tok in special_toks:
-            skip_echo_len -= prompt.count(tok) * len(tok)
-    elif "oasst" in model_name and "pythia" in model_name:
-        special_toks = ["<|prompter|>", "<|assistant|>", "<|endoftext|>"]
-        skip_echo_len = len(prompt)
-        for tok in special_toks:
-            skip_echo_len -= prompt.count(tok) * len(tok)
-    elif "stablelm" in model_name:
-        special_toks = ["<|SYSTEM|>", "<|USER|>", "<|ASSISTANT|>"]
-        skip_echo_len = len(prompt)
-        for tok in special_toks:
-            skip_echo_len -= prompt.count(tok) * len(tok)
-    else:
-        skip_echo_len = len(prompt) + 1 - prompt.count("</s>") * 3
-    return skip_echo_len
-
-
-if __name__ == "__main__":
-    print(default_conversation.get_prompt())

fastchat/api/fastchat_api.py

@@ -1,459 +0,0 @@
-"""Wrapper around FastChat APIs."""
-from __future__ import annotations
-
-import logging
-import sys
-import warnings
-from typing import (
-    AbstractSet,
-    Any,
-    Callable,
-    Collection,
-    Dict,
-    Generator,
-    List,
-    Literal,
-    Mapping,
-    Optional,
-    Set,
-    Tuple,
-    Union,
-)
-
-from pydantic import Extra, Field, root_validator
-from tenacity import (
-    before_sleep_log,
-    retry,
-    retry_if_exception_type,
-    stop_after_attempt,
-    wait_exponential,
-)
-
-from langchain.llms.base import BaseLLM
-from langchain.schema import Generation, LLMResult
-from langchain.utils import get_from_dict_or_env
-
-import requests
-import json
-
-
-logger = logging.getLogger(__name__)
-FAST_CHAT_API = "http://localhost:21002/worker_generate_stream"
-
-
-def _streaming_response_template() -> Dict[str, Any]:
-    """
-    :return: 响应结构
-    """
-    return {
-        "text": "",
-        "error_code": 0,
-    }
-
-
-def _update_response(response: Dict[str, Any], stream_response: Dict[str, Any]) -> None:
-    """Update response from the stream response."""
-    response["text"] += stream_response["text"]
-    response["error_code"] += stream_response["error_code"]
-
-
-class BaseFastChat(BaseLLM):
-    """Wrapper around FastChat large language models."""
-
-    model_name: str = "text-davinci-003"
-    """Model name to use."""
-    temperature: float = 0.7
-    """What sampling temperature to use."""
-    max_new_tokens: int = 200
-    stop: int = 20
-    batch_size: int = 20
-    """Maximum number of retries to make when generating."""
-    streaming: bool = False
-    """Penalizes repeated tokens."""
-    n: int = 1
-    """Whether to stream the results or not."""
-    allowed_special: Union[Literal["all"], AbstractSet[str]] = set()
-    """Set of special tokens that are allowed。"""
-    disallowed_special: Union[Literal["all"], Collection[str]] = "all"
-    """Set of special tokens that are not allowed。"""
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.ignore
-
-    @root_validator(pre=True)
-    def build_extra(cls, values: Dict[str, Any]) -> Dict[str, Any]:
-        """Build extra kwargs from additional params that were passed in."""
-        all_required_field_names = {field.alias for field in cls.__fields__.values()}
-
-        extra = values.get("model_kwargs", {})
-        for field_name in list(values):
-            if field_name not in all_required_field_names:
-                if field_name in extra:
-                    raise ValueError(f"Found {field_name} supplied twice.")
-                logger.warning(
-                    f"""WARNING! {field_name} is not default parameter.
-                    {field_name} was transfered to model_kwargs.
-                    Please confirm that {field_name} is what you intended."""
-                )
-                extra[field_name] = values.pop(field_name)
-        values["model_kwargs"] = extra
-        return values
-
-    @property
-    def _default_params(self) -> Dict[str, Any]:
-        """Get the default parameters for calling FastChat API."""
-        normal_params = {
-            "model": self.model_name,
-            "prompt": '',
-            "max_new_tokens": self.max_new_tokens,
-            "temperature": self.temperature,
-        }
-
-        return {**normal_params}
-
-    def _generate(
-            self, prompts: List[str], stop: Optional[List[str]] = None
-    ) -> LLMResult:
-        """Call out to FastChat's endpoint with k unique prompts.
-
-        Args:
-            prompts: The prompts to pass into the model.
-            stop: Optional list of stop words to use when generating.
-
-        Returns:
-            The full LLM output.
-
-        Example:
-            .. code-block:: python
-
-                response = fastchat.generate(["Tell me a joke."])
-        """
-        # TODO: write a unit test for this
-        params = self._invocation_params
-        sub_prompts = self.get_sub_prompts(params, prompts)
-        choices = []
-        token_usage: Dict[str, int] = {}
-        headers = {"User-Agent": "fastchat Client"}
-        for _prompts in sub_prompts:
-
-            params["prompt"] = _prompts[0]
-
-            if stop is not None:
-                if "stop" in params:
-                    raise ValueError("`stop` found in both the input and default params.")
-                params["stop"] = stop
-
-            if self.streaming:
-                if len(_prompts) > 1:
-                    raise ValueError("Cannot stream results with multiple prompts.")
-
-                response_template = _streaming_response_template()
-                response = requests.post(
-                    FAST_CHAT_API,
-                    headers=headers,
-                    json=params,
-                    stream=True,
-                    )
-                for stream_resp in response.iter_lines(
-                        chunk_size=8192, decode_unicode=False, delimiter=b"\0"
-                ):
-                    if stream_resp:
-                        data = json.loads(stream_resp.decode("utf-8"))
-                        skip_echo_len = len(_prompts[0])
-                        output = data["text"][skip_echo_len:].strip()
-                        data["text"] = output
-                        self.callback_manager.on_llm_new_token(
-                            output,
-                            verbose=self.verbose,
-                            logprobs=data["error_code"],
-                        )
-                        _update_response(response_template, data)
-                choices.append(response_template)
-            else:
-                response_template = _streaming_response_template()
-                response = requests.post(
-                    FAST_CHAT_API,
-                    headers=headers,
-                    json=params,
-                    stream=True,
-                    )
-                for stream_resp in response.iter_lines(
-                        chunk_size=8192, decode_unicode=False, delimiter=b"\0"
-                ):
-                    if stream_resp:
-                        data = json.loads(stream_resp.decode("utf-8"))
-                        skip_echo_len = len(_prompts[0])
-                        output = data["text"][skip_echo_len:].strip()
-                        data["text"] = output
-                        _update_response(response_template, data)
-
-                choices.append(response_template)
-
-        return self.create_llm_result(choices, prompts, token_usage)
-
-    async def _agenerate(
-            self, prompts: List[str], stop: Optional[List[str]] = None
-    ) -> LLMResult:
-        """Call out to FastChat's endpoint async with k unique prompts."""
-        params = self._invocation_params
-        sub_prompts = self.get_sub_prompts(params, prompts)
-        choices = []
-        token_usage: Dict[str, int] = {}
-
-        headers = {"User-Agent": "fastchat Client"}
-        for _prompts in sub_prompts:
-
-            params["prompt"] = _prompts[0]
-            if stop is not None:
-                if "stop" in params:
-                    raise ValueError("`stop` found in both the input and default params.")
-                params["stop"] = stop
-
-            if self.streaming:
-                if len(_prompts) > 1:
-                    raise ValueError("Cannot stream results with multiple prompts.")
-
-                response_template = _streaming_response_template()
-                response = requests.post(
-                    FAST_CHAT_API,
-                    headers=headers,
-                    json=params,
-                    stream=True,
-                    )
-                for stream_resp in response.iter_lines(
-                        chunk_size=8192, decode_unicode=False, delimiter=b"\0"
-                ):
-                    if stream_resp:
-                        data = json.loads(stream_resp.decode("utf-8"))
-                        skip_echo_len = len(_prompts[0])
-                        output = data["text"][skip_echo_len:].strip()
-                        data["text"] = output
-                        self.callback_manager.on_llm_new_token(
-                            output,
-                            verbose=self.verbose,
-                            logprobs=data["error_code"],
-                        )
-                        _update_response(response_template, data)
-                choices.append(response_template)
-            else:
-                response_template = _streaming_response_template()
-                response = requests.post(
-                    FAST_CHAT_API,
-                    headers=headers,
-                    json=params,
-                    stream=True,
-                    )
-                for stream_resp in response.iter_lines(
-                        chunk_size=8192, decode_unicode=False, delimiter=b"\0"
-                ):
-                    if stream_resp:
-                        data = json.loads(stream_resp.decode("utf-8"))
-                        skip_echo_len = len(_prompts[0])
-                        output = data["text"][skip_echo_len:].strip()
-                        data["text"] = output
-                        _update_response(response_template, data)
-
-                choices.append(response_template)
-
-        return self.create_llm_result(choices, prompts, token_usage)
-
-    def get_sub_prompts(
-            self,
-            params: Dict[str, Any],
-            prompts: List[str],
-    ) -> List[List[str]]:
-        """Get the sub prompts for llm call."""
-        if params["max_new_tokens"] == -1:
-            if len(prompts) != 1:
-                raise ValueError(
-                    "max_new_tokens set to -1 not supported for multiple inputs."
-                )
-            params["max_new_tokens"] = self.max_new_tokens_for_prompt(prompts[0])
-        # append pload
-        sub_prompts = [
-            prompts[i: i + self.batch_size]
-            for i in range(0, len(prompts), self.batch_size)
-        ]
-
-        return sub_prompts
-
-    def create_llm_result(
-            self, choices: Any, prompts: List[str], token_usage: Dict[str, int]
-    ) -> LLMResult:
-        """Create the LLMResult from the choices and prompts."""
-        generations = []
-        for i, _ in enumerate(prompts):
-            sub_choices = choices[i * self.n: (i + 1) * self.n]
-            generations.append(
-                [
-                    Generation(
-                        text=choice["text"],
-                        generation_info=dict(
-                            finish_reason='over',
-                            logprobs=choice["text"],
-                        ),
-                    )
-                    for choice in sub_choices
-                ]
-            )
-        llm_output = {"token_usage": token_usage, "model_name": self.model_name}
-        return LLMResult(generations=generations, llm_output=llm_output)
-
-    def stream(self, prompt: str, stop: Optional[List[str]] = None) -> Generator:
-        """Call FastChat with streaming flag and return the resulting generator.
-
-        BETA: this is a beta feature while we figure out the right abstraction.
-        Once that happens, this interface could change.
-
-        Args:
-            prompt: The prompts to pass into the model.
-            stop: Optional list of stop words to use when generating.
-
-        Returns:
-            A generator representing the stream of tokens from OpenAI.
-
-        Example:
-            .. code-block:: python
-
-                generator = fastChat.stream("Tell me a joke.")
-                for token in generator:
-                    yield token
-        """
-        params = self._invocation_params
-        params["prompt"] = prompt
-        if stop is not None:
-            if "stop" in params:
-                raise ValueError("`stop` found in both the input and default params.")
-            params["stop"] = stop
-
-        headers = {"User-Agent": "fastchat Client"}
-        response = requests.post(
-            FAST_CHAT_API,
-            headers=headers,
-            json=params,
-            stream=True,
-        )
-        for stream_resp in response.iter_lines(
-                chunk_size=8192, decode_unicode=False, delimiter=b"\0"
-        ):
-            if stream_resp:
-                data = json.loads(stream_resp.decode("utf-8"))
-                skip_echo_len = len(_prompts[0])
-                output = data["text"][skip_echo_len:].strip()
-                data["text"] = output
-                yield data
-
-    @property
-    def _invocation_params(self) -> Dict[str, Any]:
-        """Get the parameters used to invoke the model."""
-        return self._default_params
-
-    @property
-    def _identifying_params(self) -> Mapping[str, Any]:
-        """Get the identifying parameters."""
-        return {**{"model_name": self.model_name}, **self._default_params}
-
-    @property
-    def _llm_type(self) -> str:
-        """Return type of llm."""
-        return "fastChat"
-
-    def get_num_tokens(self, text: str) -> int:
-        """Calculate num tokens with tiktoken package."""
-        # tiktoken NOT supported for Python < 3.8
-        if sys.version_info[1] < 8:
-            return super().get_num_tokens(text)
-        try:
-            import tiktoken
-        except ImportError:
-            raise ValueError(
-                "Could not import tiktoken python package. "
-                "This is needed in order to calculate get_num_tokens. "
-                "Please install it with `pip install tiktoken`."
-            )
-
-        enc = tiktoken.encoding_for_model(self.model_name)
-
-        tokenized_text = enc.encode(
-            text,
-            allowed_special=self.allowed_special,
-            disallowed_special=self.disallowed_special,
-        )
-
-        # calculate the number of tokens in the encoded text
-        return len(tokenized_text)
-
-    def modelname_to_contextsize(self, modelname: str) -> int:
-        """Calculate the maximum number of tokens possible to generate for a model.
-
-        Args:
-            modelname: The modelname we want to know the context size for.
-
-        Returns:
-            The maximum context size
-
-        Example:
-            .. code-block:: python
-
-                max_new_tokens = openai.modelname_to_contextsize("text-davinci-003")
-        """
-        model_token_mapping = {
-            "vicuna-13b": 2049,
-            "koala": 2049,
-            "dolly-v2": 2049,
-            "oasst": 2049,
-            "stablelm": 2049,
-        }
-
-        context_size = model_token_mapping.get(modelname, None)
-
-        if context_size is None:
-            raise ValueError(
-                f"Unknown model: {modelname}. Please provide a valid OpenAI model name."
-                "Known models are: " + ", ".join(model_token_mapping.keys())
-            )
-
-        return context_size
-
-    def max_new_tokens_for_prompt(self, prompt: str) -> int:
-        """Calculate the maximum number of tokens possible to generate for a prompt.
-
-        Args:
-            prompt: The prompt to pass into the model.
-
-        Returns:
-            The maximum number of tokens to generate for a prompt.
-
-        Example:
-            .. code-block:: python
-
-                max_new_tokens = openai.max_token_for_prompt("Tell me a joke.")
-        """
-        num_tokens = self.get_num_tokens(prompt)
-
-        # get max context size for model by name
-        max_size = self.modelname_to_contextsize(self.model_name)
-        return max_size - num_tokens
-
-
-class FastChat(BaseFastChat):
-    """Wrapper around OpenAI large language models.
-
-    To use, you should have the ``openai`` python package installed, and the
-    environment variable ``OPENAI_API_KEY`` set with your API key.
-
-    Any parameters that are valid to be passed to the openai.create call can be passed
-    in, even if not explicitly saved on this class.
-
-    Example:
-        .. code-block:: python
-
-            from langchain.llms import OpenAI
-            openai = FastChat(model_name="vicuna")
-    """
-
-    @property
-    def _invocation_params(self) -> Dict[str, Any]:
-        return {**{"model": self.model_name}, **super()._invocation_params}

img/partners/zhenfund.svg

@@ -0,0 +1,9 @@
+<svg width="654" height="213" viewBox="0 0 654 213" fill="none" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<rect x="654" width="213" height="654" transform="rotate(90 654 0)" fill="url(#pattern0)"/>
+<defs>
+<pattern id="pattern0" patternContentUnits="objectBoundingBox" width="1" height="1">
+<use xlink:href="#image0_237_57" transform="matrix(0.0204695 0 0 0.00666667 -0.00150228 0)"/>
+</pattern>
+<image id="image0_237_57" width="49" height="150" xlink:href="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAADEAAACWCAYAAAB3hWBKAAAMyElEQVR4Ae1de5AcRRk/AR88C2MgIdzdfB0jIioFIoggGkoeCbnt3lAVtUALygdCUSWI0X8M3LcHiUHkEQoIuem7aKR4pCJSFFqQ6cvyCMnMXngVBORhBaG0ohaiIgqCrPX1bO/OzM7uzcztZAO1VzU1szPf1/39+uvn933d19fX+9vNSgAFuwo53J/rVYDzcoWNAtaiYNVcLw5X5guCA+YKgAoodxAFODdXEByeKhVA5KyJ/nlI2mh1CfZaAOSzLeka/GMB+uqIGDgpVwBTJX7VabP2DQqEAlZNxUPfUcCWOh9nz685pu/9SfhyoRnh1tF1YQSrljhckCSjUsFaGORDbn0zCV8uNCVuLQoLw3iSjLCvbw/k7I0GL9yehC8XmpKArzYEYdWSsBYnzQgFbG/wwmNJ+TpOh8I6qyGI7ipXJMkEl/R9ADm8XuflbHMSvlxoRoasz9cFaQyIG1CwpSXOTsUizG+6CoNDyOGuEB+H1bkImCRRnN+3Fwp4NSRQA0ziUb40NPjlJPnlRlPi7IfTAsHZxtyES5qw7mkEjGcCwmErnt4/I2leudONFAePGebwIxRsHQoot5/1snuwAMVqX9/7chesl0GvBHolkK0E/JEbHsvUQ+mJI7s0W84d4kLBrsgqvOEr8S6CuJLP3D88G822Fu8qCBSDp5jSnM69uyA4403CF+C8pklf3EQw8O6KM5jVodqdPpkR0f/pCAgvfSpd5qBZ7LBgf68D4ewPXRYpW/YoGK0fGtPuxXMPy5ZSF7lKnH0nBEKw5V0UJ1vWP1k0+GEU7M06EM52rl/St2e21LrERdNp5DBRB6HNkmyy/VQ8YqAuwLldEt/PFgV7KQQg2D6SPnPA7oLg7K0eCF39uqwJmjIkMCK3NkiTobkI87tanXqZ90qggyWAwjoh7ay1iZ73z+ugSOmTQs52TruLFdb16XPuIEcPRH1Ef7drgrNfYhGO6mDlyD8p5OzqYBvK3f2bB6QrxJyBIAgU8Os88sk9TW01r7cH9iaZfnLPtNMZlDhcFNRGiVtndzqP3NPDAhwfBIEcbss9005ngBzOD4EQsL3TeaRKjxpmqqVoyH9dt5K8nCrTThOjYH8Ol2pdsIYZp9GI499x9lCn5UqVXidAkNknVaadJp4WCA7vIGc3dN3EQ9EDWZanJW79AAtweKcLtZfebl8COhClEf6GyNkXd3uhowKWBHw/1I1ytixKQ79rJs1ADC27IY6uK+90Iwz09a3cU9TLhMAK2NIVgeMy7YGIK5VuvOtpohulHpdnTxNxpdKNd+8NTTQNdjDWZE8twvwSt04OjRMcnoqja3q3aHBu7sqJaiIkaGAQzPw+7/0TVEI9EEk01dNEwtaECw/tb2qMgVCfaX/bFQ07IdYeWa8EeiVQKwHPkWd5jv2Yp2Q1y+UqO1VcrA5jHbI+E1XANUv6976cs49H30/521P28iyCB3nSgKDdAcjhGdrysGLxoR8pcRg2/g3kek/g2JRCBwk2bx7b33PsN4ICZXlOCuL6hfM+iII9iQXrKvKfLz/TOgQ53IHcGiH3gJ67cUgHYlKNn5JF6ChPUhBITkoBt+s9S4IVDIgVC2cfhILdqCPg0oJwHVtEBfIc+1bPsTHNVdk0/qWghuOekVujyOFvtXC9paUACEM/wgdPxNQglH1kGIT9rEmwk3cSGDn7J1UhSrdm/73N98TC9rotWMAqFDCeKu9yubyXq+zX6kAcO5e42BJnS5DD76khN4GgNYuxTgrr+tQgKEHPkffUQShZdTeu/ViqkkhAjEsO2g85PIoCtmFhzj6hNiEaWz5x8dzDUlcnDULJc4IgqMtNIFdqkuWczdJBkxzWxIEg+zAKeDgTCNe95QBX2W8ZIK6yd1aruEdqKRMw4BA7DnXgpLW83sVSb0VB9gJeoB1jmUBQ3p6S6w0IuruOPZ6md5p07MQxgCVh/RiFv+EW+cAc3eUW4Sg9htBgl7ZhEwDXketcZf87CCL1s2MnjovVRmsOjw4PDX4hqjzaeJgpViRYlVILb+ZaKUBEBe/I7/cKCMdz7Punc1UmxrobK94RdfYS6ZVAcwnQIDfpyKOp349envqFnvc0c+0mb6rr1+/pKftbniNfatXNViZkwYi7rbzmcG9ibNhVtuMq2f0dYdu2rdnHVbLcSvjG+9EhA0Kvyc0YoWS1smn0k+ZbqztNAmk2G/yOHH5LE0K9VY4miNMY7G5oCNraUBDUxBP3rTs4yOM6csoTVPAMmE1L0RAIAb/Rs1oOm0pF9o1Ma+xtD645xHXk2xGB3nYd6dbGjf+Zb0EQJIir5IvmmzchrwkKF33WEz86/4azv4QCxAS8ghyuq81uz/dBMBnlb/vbVfapdUH0xE8+75btfsMUnFNNbhoLHRHjOnKz4XWVbBsDSNUEuXUmctiEgt2NBbgYOdw6zFkFOXvePxsHVmbShKdk0QhC94qyv24A0N1z5L8a3xttwv9m32u+UQMP8sU96+qkjQRwszZgC1iJAu7V6wwdGNkpEBtHQ+HSSUFQ1YsTPPiuFQgU7EF/1ad3mXmp1xNRTXhKnhPM2HPs101pR9uE58hJ88117LuCfHHPbUAsR84kcrYZs6yxPWWfZAShu+vYz2wv37ifEaKVJlw1dnKIT9lTHm7VGoR1gh9nW6tOaRdFNQtgvQfygcintWmTbE/K/m9dWLJHKblS91pKvlN/T+DV2MkGeNy91uv8DMmyQcYCDj/3Sx5eoLN0/P2vGdsEZegp+86gQBmeH48TPPguBMKYZ/SdPYcF9hXk8B9/fU222JRdLGXkKnuWp+xnMwhfpTaTZLSmfHR14mx9GJw/YlNb8Pf7ZVxjayDa4iE3pAHiKrmjokaPDQrV7lkfbCUGjwjSoICV2kCweNbByNktmU37wUQrE6MnuI5c6jpylPr+6GqP5lgVx76WeiqyHgZ5e8+9EnivlQD1MtHVXOLfajz/KJt2BV4pr53tKntjmp6pmdb+abs8cv/mOfbWZqFaL47iabsIgqpQvFC7BoQ+wm+6Gw1p/bCrQGARDtQW8YUzDjDVCzl8DTmbJDcwXSjgMhrZzfdE94oaOzsKgpyRiZhTEmERgLyjwwKepg2HtZDuJ5Gzh5DDtTWX1x30nCrpaHUiB0uqBFIQ+yDgduSwAgXs8H3X7GrtFi4CUFKXFwc+Smc+p0i2r69mb/qr0QZZyLdsWb93qkQSEl9esBg5VIgcOawmrdQOyaINuNlBUIKekmMGRO1eTChXYrIRAZ/THiEOt2FhzkwdFsFhgg7ZpcMTzflQmTRBUjQ55B05mVi6hIR+xABc45/WAjv02qEIByJnzyGHX+lzaykSjo5+TeuMJxl2lNd+yHXkK0Ft0Gw2oXypyHDhjAP0sZXcuoQYa435d/6GXCjTnY62bErUc6QKCpjPc7LBjsyVly6YfSyFP5SEdSEumjWXutkmoaMvPEfelI/gwQGxPQhtPKPqQtE0ZLqkSBs6Pj8mmDI23slV8qJug9ANm8P9NEaEo6Dh1ZBZk2jiqlNFyQXdBmFqhx6hBazS1g2KuqGD2Ws9lqGJvZMdKfGUOsa5kog34VTcN+EPfNYISoez0wZ16mp7Z8+aUundd0UJuI59fDDgpOLYF0wnkmZbec3MYHrk58gdh+vYF0d7KPIGPVKWmU4D2urYnwin136c6AjAOBAkhO8JGrskrVZ2KxCmNEkrW8tr9XQ4SantliA0GDIOK/t71Wp1yrPCOw0CFw3OHSlA+7DUmOr0qNFC891+cCqtaGd8wI/tqanbBA1qtDCK07Q+fJezZTRvarlXPDp/Ik8oRSe7jvxjMwhZJQ+Rq+wLW2kliyboQAZcNPApWi8gHdAQ2aukTfv6ZHl2ZBxQ8jmHJoHGnas9Rc0ru3rkPrl5Kw+MD0QTnSaIZ7RVQx99DDf7R73qY5BfjjrrQ/lGq1PUotFOK7Xg3+8GE8wGAm5Czo6subkuQw4LdOg1nVdLz4K9aIJ/g3nVn6cCQYSkFfJLxFYv3R3LstFKJhCC3ehPAMlLCpdhgZ1mQJQEnN5qt34qEIaYZq0to20c+Q9vQn67uWHLtv/2KvQPbDg80hEQUZ+0AWDuNa/q6lZa8ZSM9m5tQVC6tLXAaEI3Yq0JHa28gbRCFkCTf+w9SXWKY2yrlZRdLPKp2gT8qa0JMysIAvbEfev2dZVN4UQh33VYS1OPE4Eu9nHqZmv7Ye9Gzh7wn+FhFHBnXGHqd9MBYRKd3CRPJI9pWHhjLEgAol6dAv8aKDhWcLZMN/QhdpzJM3TvBAhKkEycrrJXNWslAQgKD2qxvdPvbtkyvculZtIMAcjjh6vGjwitvROusVvJQiYdY8psRfOuff9/T15+hUcbNtcAAAAASUVORK5CYII="/>
+</defs>
+</svg>