书生大模型实战营L1：第四关：InternLM + LlamaIndex RAG 实践

from openai import OpenAIbase_url = "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"api_key = "此处填写自己的KEY"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)

import osos.environ['NLTK_DATA'] = '/root/nltk_data'from llama_index.core import VectorStoreIndex, SimpleDirectoryReaderfrom llama_index.core.settings import Settingsfrom llama_index.embeddings.huggingface import HuggingFaceEmbeddingfrom llama_index.legacy.callbacks import CallbackManagerfrom llama_index.llms.openai_like import OpenAILikeCreate an instance of CallbackManagercallback_manager = CallbackManager()api_base_url =  "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"model = "internlm2.5-latest"api_key = "填写自己的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llmSettings.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)

import streamlit as stfrom llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settingsfrom llama_index.embeddings.huggingface import HuggingFaceEmbeddingfrom llama_index.legacy.callbacks import CallbackManagerfrom llama_index.llms.openai_like import OpenAILike           # Create an instance of CallbackManagercallback_manager = CallbackManager()           api_base_url =  "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"model = "internlm2.5-latest"api_key = "填写你的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)st.set_page_config(page_title="llama_index_demo", page_icon="🦜🔗")st.title("llama_index_demo")           # 初始化模型@st.cache_resourcedef 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 responsesif "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 messagesfor 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 promptif 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 assistantif 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)