环境配置
选择30%A100做本次任务
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 einops
pip install protobuf安装Llamaindex
conda activate llamaindex
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下载 Sentence Transformer 模型
Sentence Transformer模型是一种用于句子嵌入（sentence embedding）技术的深度学习模型，旨在将句子或文本段落转换为固定长度的向量表示。这种表示可以用于多种自然语言处理任务，例如文本相似度计算、检索和分类等。
cd ~
mkdir llamaindex_demo
mkdir model
cd ~/llamaindex_demo
touch download_hf.py粘贴到download_hf.py
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')执行该脚本
cd /root/llamaindex_demo
conda activate llamaindex
python download_hf.py下载 NLTK
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对原始internlm2-chat-1_8b进行测试
首先把InternLM2 1.8B 软连接出来
cd ~/model
ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-1_8b/ ./创建一个python文件：
cd ~/llamaindex_demo
touch llamaindex_internlm.py将一下代码粘贴到llamaindex_internlm.py中
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)运行查看结果：
conda activate llamaindex
cd ~/llamaindex_demo/
python llamaindex_internlm.py输出：
xtuner是一款用于播放音乐的软件，它支持多种音频格式，包括MP3、WAV、WMA、FLAC、AAC、APE、OGG、WMA、WAV、WMA
模型并不能很好的回答出正确答案。
RAG增强internlm2-chat-1_8b测试
首先安装词嵌入向量依赖：
conda activate llamaindex
pip install llama-index-embeddings-huggingface llama-index-embeddings-instructor然后获取知识库：
cd ~/llamaindex_demo
mkdir data
cd data
git clone https://github.com/InternLM/xtuner.git
mv xtuner/README_zh-CN.md ./创建一个pythonllamaindex_RAG.py文件：
cd ~/llamaindex_demo
touch llamaindex_RAG.py将以下代码粘贴到llamaindex_RAG.py中:
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settingsfrom llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.llms.huggingface import HuggingFaceLLM#初始化一个HuggingFaceEmbedding对象，用于将文本转换为向量表示
embed_model = HuggingFaceEmbedding(
#指定了一个预训练的sentence-transformer模型的路径model_name="/root/model/sentence-transformer"
)
#将创建的嵌入模型赋值给全局设置的embed_model属性，
#这样在后续的索引构建过程中就会使用这个模型。
Settings.embed_model = embed_modelllm = 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}
)
#设置全局的llm属性，这样在索引查询时会使用这个模型。
Settings.llm = llm#从指定目录读取所有文档，并加载数据到内存中
documents = SimpleDirectoryReader("/root/llamaindex_demo/data").load_data()
#创建一个VectorStoreIndex，并使用之前加载的文档来构建索引。
# 此索引将文档转换为向量，并存储这些向量以便于快速检索。
index = VectorStoreIndex.from_documents(documents)
# 创建一个查询引擎，这个引擎可以接收查询并返回相关文档的响应。
query_engine = index.as_query_engine()
response = query_engine.query("xtuner是什么?")print(response)conda activate llamaindex
cd ~/llamaindex_demo/
python llamaindex_RAG.py输出：
LlamaIndex web
pip install streamlit==1.36.0
#创建py文件
cd ~/llamaindex_demo
touch app.py
粘贴
import streamlit as st
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.llms.huggingface import HuggingFaceLLMst.set_page_config(page_title="llama_index_demo", page_icon="🦜🔗")
st.title("llama_index_demo")# 初始化模型
@st.cache_resource
def init_models():embed_model = HuggingFaceEmbedding(model_name="/root/model/sentence-transformer")Settings.embed_model = embed_modelllm = 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 = llmdocuments = SimpleDirectoryReader("/root/llamaindex_demo/data").load_data()index = VectorStoreIndex.from_documents(documents)query_engine = index.as_query_engine()return query_engine# 检查是否需要初始化模型
if 'query_engine' not in st.session_state:st.session_state['query_engine'] = init_models()def greet2(question):response = st.session_state['query_engine'].query(question)return response# Store LLM generated responses
if "messages" not in st.session_state.keys():st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}] # Display or clear chat messages
for message in st.session_state.messages:with st.chat_message(message["role"]):st.write(message["content"])def clear_chat_history():st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]st.sidebar.button('Clear Chat History', on_click=clear_chat_history)# Function for generating LLaMA2 response
def generate_llama_index_response(prompt_input):return greet2(prompt_input)# User-provided prompt
if prompt := st.chat_input():st.session_state.messages.append({"role": "user", "content": prompt})with st.chat_message("user"):st.write(prompt)# Gegenerate_llama_index_response last message is not from assistant
if st.session_state.messages[-1]["role"] != "assistant":with st.chat_message("assistant"):with st.spinner("Thinking..."):response = generate_llama_index_response(prompt)placeholder = st.empty()placeholder.markdown(response)message = {"role": "assistant", "content": response}st.session_state.messages.append(message)运行
streamlit run app.py访问：
ssh -CNg -L 8501:127.0.0.1:8501 root@ssh.intern-ai.org.cn -p 48693(需要换成自己的端口号)
