LangChain入门(五)-使用GPT3.5模型构建油管频道问答机器人

柔光的暖阳◎ 2024-03-22 12:02 23阅读 0赞

**目录**

一、安装依赖

二、使用示例

--------------------

#### 一、安装依赖 ####

pip install youtube-transcript-api

#### 二、使用示例 ####

import os
    
    from langchain.document_loaders import YoutubeLoader
    from langchain.embeddings.openai import OpenAIEmbeddings
    from langchain.vectorstores import Chroma
    from langchain.text_splitter import RecursiveCharacterTextSplitter
    from langchain.chains import ChatVectorDBChain, ConversationalRetrievalChain
    
    from langchain.chat_models import ChatOpenAI
    from langchain.prompts.chat import (
        ChatPromptTemplate,
        SystemMessagePromptTemplate,
        HumanMessagePromptTemplate
    )
    
    # openAI的Key
    os.environ["OPENAI_API_KEY"] = '************************'
    
    # 加载 youtube 频道
    loader = YoutubeLoader.from_youtube_url('https://www.youtube.com/watch?v=Dj60HHy-Kqk')
    # 将数据转成 document
    documents = loader.load()
    
    # 初始化文本分割器
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1000,
        chunk_overlap=20
    )
    
    # 分割 youtube documents
    documents = text_splitter.split_documents(documents)
    
    # 初始化 openai embeddings
    embeddings = OpenAIEmbeddings()
    
    # 将数据存入向量存储
    vector_store = Chroma.from_documents(documents, embeddings)
    # 通过向量存储初始化检索器
    retriever = vector_store.as_retriever()
    
    system_template = """
    Use the following context to answer the user's question.
    If you don't know the answer, say you don't, don't try to make it up. And answer in Chinese.
    -----------
    {context}
    -----------
    {chat_history}
    """
    
    # 构建初始 messages 列表，这里可以理解为是 openai 传入的 messages 参数
    messages = [
        SystemMessagePromptTemplate.from_template(system_template),
        HumanMessagePromptTemplate.from_template('{question}')
    ]
    
    # 初始化 prompt 对象
    prompt = ChatPromptTemplate.from_messages(messages)
    
    # 初始化问答链
    qa = ConversationalRetrievalChain.from_llm(llm=ChatOpenAI(temperature=0.1, max_tokens=2048),
                                               retriever=retriever, condense_question_prompt=prompt)
    
    chat_history = []
    while True:
        question = input('问题：')
        # 开始发送问题 chat_history 为必须参数,用于存储对话历史
        result = qa({'question': question, 'chat_history': chat_history})
        chat_history.append((question, result['answer']))
        print(result['answer'])

#### 结尾、扫一扫下方微信名片即可+博主徽信哦 **↓↓ ↓↓ ↓↓ ↓↓ ↓↓ ↓↓ ↓↓ ↓↓ ↓↓↓** ####