from langchain_community.utilities import SQLDatabasedb = SQLDatabase.from_uri("sqlite:///Chinook.db")# 通过LLM 获取查询语句from langchain.chains import create_sql_query_chainfrom langchain_openai import ChatOpenAIllm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)from langchain_community.tools.sql_database.tool import QuerySQLDataBaseTool# 执行查询动作execute_query = QuerySQLDataBaseTool(db=db)# 获取sql 查询语句write_query = create_sql_query_chain(llm, db)# 先生成查询语句，再执行查询动作chain = write_query | execute_queryresponse = chain.invoke({"question": "How many employees are there"})print(response)

from operator import itemgetterfrom langchain_core.output_parsers import StrOutputParserfrom langchain_core.prompts import PromptTemplatefrom langchain_core.runnables import RunnablePassthrough# 定义提示词，其中有 question、query、result 三个变量answer_prompt = PromptTemplate.from_template("""Given the following user question, corresponding SQL query, and SQL result, answer the user question.
Question: {question}SQL Query: {query}SQL Result: {result}Answer: """)
answer = answer_prompt | llm | StrOutputParser()# query通过write_query链的执行结果获取# result 通过 execute_query链获取chain = (RunnablePassthrough.assign(query=write_query).assign(result=itemgetter("query") | execute_query)| answer)print(chain.invoke({"question": "How many employees are there"}))