L1-llama index+Internlm2 RAG实践-CSDN博客

本文链接：https://blog.csdn.net/m0_73516569/article/details/141436544

一、部署模型

创建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)

效果不好

二、RAG

创建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)

微调成功

三、开始提问

创建app.py

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 HuggingFaceLLM

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

    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()

    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)

可以开始对话