【langchain学习】使用Langchain生成多视角查询

使用Langchain生成多视角查询

1. 导入所需库：

   from langchain.prompts import ChatPromptTemplate
   from langchain_core.output_parsers import StrOutputParser
   from langchain_core.runnables import RunnablePassthrough
   from config import llm
   

2. 设置提示模板：

   prompt = ChatPromptTemplate.from_template(
       """
       You are an intelligent assistant. Your task is to generate 5 questions based on the provided question in different wording and different perspectives to retrieve relevant documents from a vector database. By generating multiple perspectives on the user question, your goal is to help the user overcome some of the limitations of the distance-based similarity search. Provide these alternative questions separated by newlines. Original question: {question}
       """
   )
   

3. 定义查询生成过程：

   generate_queries = (
       {"question": RunnablePassthrough()}
       | prompt
       | llm
       | StrOutputParser()
       | (lambda x: x.split("\n"))
   )
   

4. 调用生成多视角查询：

   result = generate_queries.invoke("温格高是如何赢下2023年环法自行车赛的？")
   print(result)
   

5. 示例输出：

   [
       "温格高在2023年环法自行车赛中采用了哪些策略？",
       "2023年环法自行车赛温格高获胜的关键因素是什么？",
       "温格高在2023年环法自行车赛中面对哪些挑战？",
       "温格高是如何准备2023年环法自行车赛的？",
       "2023年环法自行车赛温格高的表现有哪些亮点？"
   ]