我们需要下载一个 LangChain 官方提供的本地小数据库。

安装依赖

SQL:
https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql
Shell:
pip install --upgrade --quiet  langchain-core langchain-community langchain-openai

导入数据

我这里使用 Navicat 导入数据,你也可以通过别的方式导入(当然你有现成的数据库也可以,但是不要太大了,不然会消耗很多Token)。

LangChain-08 Query SQL DB 通过GPT自动查询SQL_ai

编写代码

这里我使用了 GPR 3.5 Turbo,效果不理想的话可以试试GPT 4 或者 GPT 4 Turbo

from langchain_core.prompts import ChatPromptTemplate
from langchain_community.utilities import SQLDatabase
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI


template = """Based on the table schema below, write a SQL query that would answer the user's question:
{schema}

Question: {question}
SQL Query:"""
prompt = ChatPromptTemplate.from_template(template)

db = SQLDatabase.from_uri("sqlite:///./Chinook.db")


def get_schema(_):
    return db.get_table_info()


def run_query(query):
    return db.run(query)


model = ChatOpenAI(
    model="gpt-3.5-turbo",
)

sql_response = (
    RunnablePassthrough.assign(schema=get_schema)
    | prompt
    | model.bind(stop=["\nSQLResult:"])
    | StrOutputParser()
)

message = sql_response.invoke({"question": "How many employees are there?"})
print(f"message: {message}")

运行结果

➜ python3 test08.py
message: SELECT COUNT(*) AS totalEmployees
FROM Employee;

LangChain-08 Query SQL DB 通过GPT自动查询SQL_python_02