书生大模型实战营(第三期闯关大挑战) 学习笔记
进阶岛 第五关 茴香豆:企业级知识库问答工具
环境搭建
创建茴香豆专用 conda 环境
studio-conda -o internlm-base -t huixiangdou
激活环境
conda activate huixiangdou
安装茴香豆
下载茴香豆
cd /root
# 克隆代码仓库
git clone https://github.com/internlm/huixiangdou && cd huixiangdou
git checkout 79fa810
安装依赖
apt update
apt install python-dev libxml2-dev libxslt1-dev antiword unrtf poppler-utils pstotext tesseract-ocr flac ffmpeg lame libmad0 libsox-fmt-mp3 sox libjpeg-dev swig libpulse-dev
# python requirements
pip install BCEmbedding==0.15 cmake==3.30.2 lit==18.1.8 sentencepiece==0.2.0 protobuf==5.27.3 accelerate==0.33.0
pip install -r requirements.txt
下载模型文件
# 创建模型文件夹
cd /root && mkdir models
# 复制BCE模型
ln -s /root/share/new_models/maidalun1020/bce-embedding-base_v1 /root/models/bce-embedding-base_v1
ln -s /root/share/new_models/maidalun1020/bce-reranker-base_v1 /root/models/bce-reranker-base_v1
# 复制大模型参数
ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2_5-7b-chat /root/models/internlm2_5-7b-chat
更改配置文件
sed -i '9s#.*#embedding_model_path = "/root/models/bce-embedding-base_v1"#' /root/huixiangdou/config.ini
sed -i '15s#.*#reranker_model_path = "/root/models/bce-reranker-base_v1"#' /root/huixiangdou/config.ini
sed -i '43s#.*#local_llm_path = "/root/models/internlm2_5-7b-chat"#' /root/huixiangdou/config.ini
知识库创建
cd /root/huixiangdou && mkdir repodir
git clone https://github.com/internlm/huixiangdou --depth=1 repodir/huixiangdou
git clone https://github.com/open-mmlab/mmpose --depth=1 repodir/mmpose
# Save the features of repodir to workdir, and update the positive and negative example thresholds into `config.ini`
mkdir workdir
python3 -m huixiangdou.service.feature_store
测试知识助手
命令行运行
conda activate huixiangdou
cd /root/huixiangdou
python3 -m huixiangdou.main --standalone
Gradio UI 界面测试
conda activate huixiangdou
cd /root/huixiangdou
python3 -m huixiangdou.gradio
换一个知识库试试,外部文件为 2024大模型训练数据白皮书_阿里研究院.pdf