llamaindex+Internlm2 RAG实践

1、环境、模型准备

conda create -n llamaindex python=3.10

conda activate llamaindex

conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia

pip install llama-index==0.10.38 llama-index-llms-huggingface==0.2.0 "transformers[torch]==4.41.1" "huggingface_hub[inference]==0.23.1" huggingface_hub==0.23.1 sentence-transformers==2.7.0 sentencepiece==0.2.0

2、下载 Sentence Transformer 模型

cd ~
mkdir llamaindex_demo
mkdir model
cd ~/llamaindex_demo
touch download_hf.py

# 在llamaindex环境下
# 在/root/llamaindex_demo目录下
python download_hf.py

3、下载 NLTK 相关资源 

cd /root
git clone https://gitee.com/yzy0612/nltk_data.git  --branch gh-pages
cd nltk_data
mv packages/*  ./
cd tokenizers
unzip punkt.zip
cd ../taggers
unzip averaged_perceptron_tagger.zip

4、 LlamaIndex HuggingFaceLLM

cd ~/model
ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b/ ./

cd ~/llamaindex_demo
touch llamaindex_internlm.py

# 增加依赖项
pip install protobuf     
pip install einops

conda activate llamaindex
cd ~/llamaindex_demo/
python llamaindex_internlm.py

 结果明显不对。

5、 LlamaIndex RAG

# 安装依赖
conda activate llamaindex
pip install llama-index-embeddings-huggingface llama-index-embeddings-instructor


# 创建文件
cd ~/llamaindex_demo
touch llamaindex_RAG.py

conda activate llamaindex
cd ~/llamaindex_demo/
python llamaindex_RAG.py