1.任务要求

基于 LlamaIndex 构建自己的 RAG 知识库，寻找一个问题 A 在使用 LlamaIndex 之前InternLM2-Chat-1.8B模型不会回答，借助 LlamaIndex 后 InternLM2-Chat-1.8B 模型具备回答 A 的能力，截图保存。
来源： https://github.com/InternLM/Tutorial/blob/camp3/docs/L1/LlamaIndex/task.md

2.RAG的介绍

https://blog.csdn.net/weixin_57128596/article/details/137186479?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522172279340116800184147362%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fblog.%2522%257D&request_id=172279340116800184147362&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2_blogfirst_rank_ecpm_v1~rank_v31_ecpm-5-137186479-null-null.nonecase&utm_term=RAG&spm=1018.2226.3001.4450

3.完成结果

1.环境

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
这里的下载我们使用了代理

import os

# 设置环境变量
os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'

# 下载模型
os.system('huggingface-cli download --resume-download sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 --local-dir /root/model/sentence-transformer')

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.将下游的LLM软链接出来：

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

5.对比测试：
不带RAG：

from llama_index.llms.huggingface import HuggingFaceLLM
from llama_index.core.llms import ChatMessage
llm = HuggingFaceLLM(
    model_name="/root/model/internlm2-chat-1_8b",
    tokenizer_name="/root/model/internlm2-chat-1_8b",
    model_kwargs={"trust_remote_code":True},
    tokenizer_kwargs={"trust_remote_code":True}
)

rsp = llm.chat(messages=[ChatMessage(content="xtuner是什么？")])
print(rsp)

带RAG:

pip install llama-index-embeddings-huggingface llama-index-embeddings-instructor

mkdir data
cd data
git clone https://github.com/InternLM/xtuner.git
mv xtuner/README_zh-CN.md ./

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings

from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.llms.huggingface import HuggingFaceLLM

embed_model = HuggingFaceEmbedding(
    model_name="/root/model/sentence-transformer"
)

Settings.embed_model = embed_model

llm = HuggingFaceLLM(
    model_name="/root/model/internlm2-chat-1_8b",
    tokenizer_name="/root/model/internlm2-chat-1_8b",
    model_kwargs={"trust_remote_code":True},
    tokenizer_kwargs={"trust_remote_code":True}
)
Settings.llm = llm

documents = SimpleDirectoryReader("/root/llamaindex_demo/data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
response = query_engine.query("xtuner是什么?")

print(response)

Web端：
用Streamlit命令run即可：

streamlit run app.py