用 LangChain 构建 SQL Agent

pip install langchain langgraph
pip install -U "langchain[openai]"

import os
from langchain.chat_models import init_chat_model

os.environ["OPENAI_API_KEY"] = "sk-..."
model = init_chat_model("gpt-5.5")

import pathlib
import requests
import sqlite3

url = "https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db"
local_path = pathlib.Path("Chinook.db")
if not local_path.exists():
    response = requests.get(url, timeout=60)
    response.raise_for_status()
    local_path.write_bytes(response.content)

con = sqlite3.connect("Chinook.db")
cursor = con.cursor()
cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
tables = [row[0] for row in cursor.fetchall() if not row[0].startswith("sqlite_")]
print(tables)
con.close()

import sqlite3
from langchain.tools import tool

@tool
def sql_db_list_tables() -> str:
    """Input is an empty string, output is a comma-separated list of tables in the database."""
    con = sqlite3.connect("Chinook.db")
    try:
        cursor = con.cursor()
        cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
        tables = [row[0] for row in cursor.fetchall() if not row[0].startswith("sqlite_")]
        return ", ".join(tables)
    finally:
        con.close()

@tool
def sql_db_schema(table_names: str) -> str:
    """Input to this tool is a comma-separated list of tables, output is the schema and sample rows for those tables.
    Be sure that the tables actually exist by calling sql_db_list_tables first!
    Example Input: table1, table2, table3"""
    con = sqlite3.connect("Chinook.db")
    try:
        cursor = con.cursor()
        cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
        valid_tables = {row[0] for row in cursor.fetchall() if not row[0].startswith("sqlite_")}
        results = []
        for table in table_names.split(","):
            table = table.strip()
            if table not in valid_tables:
                results.append(f"Error: table_names {{{table!r}}} not found in database")
                continue
            cursor.execute("SELECT sql FROM sqlite_master WHERE type='table' AND name=?;", (table,))
            schema_row = cursor.fetchone()
            if schema_row:
                results.append(schema_row[0])
        return "\n\n".join(results)
    finally:
        con.close()

@tool
def sql_db_query(query: str) -> str:
    """Input to this tool is a detailed and correct SQL query, output is a result from the database."""
    con = sqlite3.connect("Chinook.db")
    try:
        cursor = con.cursor()
        cursor.execute(query)
        return str(cursor.fetchall())
    except Exception as e:
        return f"Error: {e}"
    finally:
        con.close()

@tool
def sql_db_query_checker(query: str) -> str:
    """Use this tool to double check if your query is correct before executing it.
    Always use this tool before executing a query with sql_db_query!"""
    trigger_prompt = f"""{query}
Double check the sqlite query above for common mistakes...
Output the final SQL query only.
SQL Query: """
    response = model.invoke(trigger_prompt)
    return response.text.strip()

tools = [sql_db_list_tables, sql_db_schema, sql_db_query, sql_db_query_checker]

from langchain.agents import create_agent

system_prompt = """
You are an agent designed to interact with a SQL database.
Given an input question, create a syntactically correct {dialect} query to run,
then look at the results of the query and return the answer. Unless the user
specifies a specific number of examples they wish to obtain, always limit your
query to at most {top_k} results.

You MUST double check your query before executing it. If you get an error while
executing a query, rewrite the query and try again.

DO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the
database.

To start you should ALWAYS look at the tables in the database to see what you
can query. Do NOT skip this step.

Then you should query the schema of the most relevant tables.
""".format(dialect="sqlite", top_k=5)

agent = create_agent(
    model,
    tools,
    system_prompt=system_prompt,
)

question = "Which genre on average has the longest tracks?"

stream = agent.stream_events(
    {"messages": [{"role": "user", "content": question}]},
    version="v3",
)
for kind, item in stream.interleave("messages", "tool_calls"):
    if kind == "messages":
        for token in item.text:
            print(token, end="", flush=True)
    elif kind == "tool_calls":
        print(f"\nTool call: {item.tool_name}({item.input})")
        print(f"\nTool result: {item.output}")