【书生实战营】L1G4000 - Llamaindex RAG实践

准备

下载 Sentence Transformer 模型

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

# 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')

python download_hf.py

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

基于 LlamaIndex 构建自己的 RAG 知识库 - 使用浦语API

环境部署

conda create -n llamaindex python=3.10
conda activate llamaindex
pip install einops==0.7.0 protobuf==5.26.1
pip install llama-index==0.11.20
pip install llama-index-llms-replicate==0.3.0
pip install llama-index-llms-openai-like==0.2.0
pip install llama-index-embeddings-huggingface==0.3.1
pip install llama-index-embeddings-instructor==0.2.1
pip install torch==2.5.0 torchvision==0.20.0 torchaudio==2.5.0 --index-url https://download.pytorch.org/whl/cu121

使用RAG前

#cd ~/llamaindex_demo
#touch test_internlm.py
from openai import OpenAI

base_url = "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
api_key = "sk-请填写准确的 token！"
model="internlm2.5-latest"

# base_url = "https://api.siliconflow.cn/v1"
# api_key = "sk-请填写准确的 token！"
# model="internlm/internlm2_5-7b-chat"

client = OpenAI(
    api_key=api_key , 
    base_url=base_url,
)

chat_rsp = client.chat.completions.create(
    model=model,
    messages=[{"role": "user", "content": "xtuner是什么？"}],
)

for choice in chat_rsp.choices:
    print(choice.message.content)

使用RAG

import os 
os.environ['NLTK_DATA'] = '/root/nltk_data'

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.core.settings import Settings
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.legacy.callbacks import CallbackManager
from llama_index.llms.openai_like import OpenAILike


# Create an instance of CallbackManager
callback_manager = CallbackManager()

api_base_url =  "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
model = "internlm2.5-latest"
api_key = "请填写 API Key"

# api_base_url =  "https://api.siliconflow.cn/v1"
# model = "internlm/internlm2_5-7b-chat"
# api_key = "请填写 API Key"



llm =OpenAILike(model=model, api_base=api_base_url, api_key=api_key, is_chat_model=True,callback_manager=callback_manager)


#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_model

#初始化llm
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)

基于 LlamaIndex 构建自己的 RAG 知识库 - 使用本地模型

环境部署

conda create -n llamaindex python=3.10
conda activate llamaindex
# python 相关基础依赖包
pip install einops==0.7.0 protobuf==5.26.1
# 安装 Llamaindex 和相关的包：
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

# 安装 LlamaIndex 词嵌入向量依赖：
pip install llama-index-embeddings-huggingface==0.2.0 llama-index-embeddings-instructor==0.1.3

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

下载 Sentence Transformer 模型

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

# 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')

python download_hf.py

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

LlamaIndex HuggingFaceLLM

把 InternLM2 1.8B 软连接出来

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

cd ~/llamaindex_demo
touch llamaindex_internlm.py

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)

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

回复结果，效果并不好：

使用RAG

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 ./

#cd ~/llamaindex_demo
#touch llamaindex_RAG.py

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings

from 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_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}
)
#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)

借助RAG得到更好的回答。

LlamaIndex WEB

pip install streamlit==1.36.0

#cd ~/llamaindex_demo
#touch app.py
import streamlit as st
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.legacy.callbacks import CallbackManager
from llama_index.llms.openai_like import OpenAILike

# Create an instance of CallbackManager
callback_manager = CallbackManager()

api_base_url =  "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
model = "internlm2.5-latest"
api_key = "eyJ0eXBlIjoiSldUIiwiYWxnIjoiSFM1MTIifQ.eyJqdGkiOiI1MDE5MjIxMSIsInJvbCI6IlJPTEVfUkVHSVNURVIiLCJpc3MiOiJPcGVuWExhYiIsImlhdCI6MTczMTQ3NDgxMiwiY2xpZW50SWQiOiJlYm1ydm9kNnlvMG5semFlazF5cCIsInBob25lIjoiMTkxMjE3NTE2NDAiLCJ1dWlkIjoiN2UyMDNmMjUtMGVjZS00YTVjLTgyYWYtYWQ2MTRiMzEwMDM2IiwiZW1haWwiOiIiLCJleHAiOjE3NDcwMjY4MTJ9.GLkZABg2ua1gUOq8xziYrhHLD-Z5J3yxVXxsj2ErgLVLMq4aA6mYhFndw_WGDFpneO1g1Pfv0fNYT26N2uCoYw"

# api_base_url =  "https://api.siliconflow.cn/v1"
# model = "internlm/internlm2_5-7b-chat"
# api_key = "请填写 API Key"

llm =OpenAILike(model=model, api_base=api_base_url, api_key=api_key, is_chat_model=True,callback_manager=callback_manager)



st.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_model

    #用初始化llm
    Settings.llm = llm

    documents = 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

部署：暂无