构建 SQL 智能体

概述

在本教程中，您将学习如何使用 LangChain 智能体构建可以回答有关 SQL 数据库的问题的智能体。在高层次上，智能体将：

从数据库获取可用的表和模式

决定哪些表与问题相关

获取相关表的模式

基于问题和模式中的信息生成查询

使用 LLM 仔细检查查询中的常见错误

执行查询并返回结果

纠正数据库引擎发现的错误，直到查询成功

基于结果制定响应

构建 SQL 数据库的问答系统需要执行模型生成的 SQL 查询。这样做存在固有风险。确保您的数据库连接权限始终尽可能狭窄地限定为智能体的需求。这将减轻（但不会消除）构建模型驱动系统的风险。

概念

我们将涵盖以下概念：

用于从 SQL 数据库读取的工具
LangChain 智能体
人在回路过程

设置

安装

pip install langchain  langgraph  langchain-community

LangSmith

设置 LangSmith 以检查链或智能体内部发生的情况。然后设置以下环境变量：

export LANGSMITH_TRACING="true"
export LANGSMITH_API_KEY="..."

1. 选择 LLM

选择支持工具调用的模型：

OpenAI
Anthropic
Azure
Google Gemini
AWS Bedrock

👉 Read the OpenAI chat model integration docs

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-4.1")

下面示例中显示的输出使用了 OpenAI。

2. 配置数据库

您将为本教程创建一个 SQLite 数据库。SQLite 是一个轻量级数据库，易于设置和使用。我们将加载 chinook 数据库，这是一个代表数字媒体商店的示例数据库。为方便起见，我们已将数据库（Chinook.db）托管在公共 GCS 存储桶上。

import requests, pathlib

url = "https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db"
local_path = pathlib.Path("Chinook.db")

if local_path.exists():
    print(f"{local_path} already exists, skipping download.")
else:
    response = requests.get(url)
    if response.status_code == 200:
        local_path.write_bytes(response.content)
        print(f"File downloaded and saved as {local_path}")
    else:
        print(f"Failed to download the file. Status code: {response.status_code}")

我们将使用 langchain_community 包中提供的便捷 SQL 数据库包装器与数据库交互。该包装器提供了一个简单的接口来执行 SQL 查询并获取结果：

from langchain_community.utilities import SQLDatabase

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

print(f"Dialect: {db.dialect}")
print(f"Available tables: {db.get_usable_table_names()}")
print(f'Sample output: {db.run("SELECT * FROM Artist LIMIT 5;")}')

Dialect: sqlite
Available tables: ['Album', 'Artist', 'Customer', 'Employee', 'Genre', 'Invoice', 'InvoiceLine', 'MediaType', 'Playlist', 'PlaylistTrack', 'Track']
Sample output: [(1, 'AC/DC'), (2, 'Accept'), (3, 'Aerosmith'), (4, 'Alanis Morissette'), (5, 'Alice In Chains')]

3. Add tools for database interactions

使用 langchain_community 包中提供的 SQLDatabase 包装器与数据库交互。该包装器提供了一个简单的接口来执行 SQL 查询并获取结果：

from langchain_community.agent_toolkits import SQLDatabaseToolkit

toolkit = SQLDatabaseToolkit(db=db, llm=model)

tools = toolkit.get_tools()

for tool in tools:
    print(f"{tool.name}: {tool.description}\n")

sql_db_query: Input to this tool is a detailed and correct SQL query, output is a result from the database. If the query is not correct, an error message will be returned. If an error is returned, rewrite the query, check the query, and try again. If you encounter an issue with Unknown column 'xxxx' in 'field list', use sql_db_schema to query the correct table fields.

sql_db_schema: 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

sql_db_list_tables: Input is an empty string, output is a comma-separated list of tables in the database.

sql_db_query_checker: 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!

5. Use `create_agent`

Use create_agent to build a ReAct agent with minimal code. The agent will interpret the request and generate a SQL command, which the tools will execute. If the command has an error, the error message is returned to the model. The model can then examine the original request and the new error message and generate a new command. This can continue until the LLM generates the command successfully or reaches an end count. This pattern of providing a model with feedback - error messages in this case - is very powerful. Initialize the agent with a descriptive system prompt to customize its behavior:

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 can order the results by a relevant column to return the most interesting
examples in the database. Never query for all the columns from a specific table,
only ask for the relevant columns given the question.

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=db.dialect,
    top_k=5,
)

Now, create an agent with the model, tools, and prompt:

from langchain.agents import create_agent


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

6. Run the agent

Run the agent on a sample query and observe its behavior:

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

for step in agent.stream(
    {"messages": [{"role": "user", "content": question}]},
    stream_mode="values",
):
    step["messages"][-1].pretty_print()

================================ Human Message =================================

Which genre on average has the longest tracks?
================================== Ai Message ==================================
Tool Calls:
  sql_db_list_tables (call_BQsWg8P65apHc8BTJ1NPDvnM)
 Call ID: call_BQsWg8P65apHc8BTJ1NPDvnM
  Args:
================================= Tool Message =================================
Name: sql_db_list_tables

Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track
================================== Ai Message ==================================
Tool Calls:
  sql_db_schema (call_i89tjKECFSeERbuACYm4w0cU)
 Call ID: call_i89tjKECFSeERbuACYm4w0cU
  Args:
    table_names: Track, Genre
================================= Tool Message =================================
Name: sql_db_schema


CREATE TABLE "Genre" (
	"GenreId" INTEGER NOT NULL,
	"Name" NVARCHAR(120),
	PRIMARY KEY ("GenreId")
)

/*
3 rows from Genre table:
GenreId	Name
1	Rock
2	Jazz
3	Metal
*/


CREATE TABLE "Track" (
	"TrackId" INTEGER NOT NULL,
	"Name" NVARCHAR(200) NOT NULL,
	"AlbumId" INTEGER,
	"MediaTypeId" INTEGER NOT NULL,
	"GenreId" INTEGER,
	"Composer" NVARCHAR(220),
	"Milliseconds" INTEGER NOT NULL,
	"Bytes" INTEGER,
	"UnitPrice" NUMERIC(10, 2) NOT NULL,
	PRIMARY KEY ("TrackId"),
	FOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"),
	FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
	FOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")
)

/*
3 rows from Track table:
TrackId	Name	AlbumId	MediaTypeId	GenreId	Composer	Milliseconds	Bytes	UnitPrice
1	For Those About To Rock (We Salute You)	1	1	1	Angus Young, Malcolm Young, Brian Johnson	343719	11170334	0.99
2	Balls to the Wall	2	2	1	U. Dirkschneider, W. Hoffmann, H. Frank, P. Baltes, S. Kaufmann, G. Hoffmann	342562	5510424	0.99
3	Fast As a Shark	3	2	1	F. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman	230619	3990994	0.99
*/
================================== Ai Message ==================================
Tool Calls:
  sql_db_query_checker (call_G64yYm6R6UauiVPCXJZMA49b)
 Call ID: call_G64yYm6R6UauiVPCXJZMA49b
  Args:
    query: SELECT Genre.Name, AVG(Track.Milliseconds) AS AverageLength FROM Track INNER JOIN Genre ON Track.GenreId = Genre.GenreId GROUP BY Genre.Name ORDER BY AverageLength DESC LIMIT 5;
================================= Tool Message =================================
Name: sql_db_query_checker

SELECT Genre.Name, AVG(Track.Milliseconds) AS AverageLength FROM Track INNER JOIN Genre ON Track.GenreId = Genre.GenreId GROUP BY Genre.Name ORDER BY AverageLength DESC LIMIT 5;
================================== Ai Message ==================================
Tool Calls:
  sql_db_query (call_AnO3SrhD0ODJBxh6dHMwvHwZ)
 Call ID: call_AnO3SrhD0ODJBxh6dHMwvHwZ
  Args:
    query: SELECT Genre.Name, AVG(Track.Milliseconds) AS AverageLength FROM Track INNER JOIN Genre ON Track.GenreId = Genre.GenreId GROUP BY Genre.Name ORDER BY AverageLength DESC LIMIT 5;
================================= Tool Message =================================
Name: sql_db_query

[('Sci Fi & Fantasy', 2911783.0384615385), ('Science Fiction', 2625549.076923077), ('Drama', 2575283.78125), ('TV Shows', 2145041.0215053763), ('Comedy', 1585263.705882353)]
================================== Ai Message ==================================

On average, the genre with the longest tracks is "Sci Fi & Fantasy" with an average track length of approximately 2,911,783 milliseconds. This is followed by "Science Fiction," "Drama," "TV Shows," and "Comedy."

The agent correctly wrote a query, checked the query, and ran it to inform its final response.

You can inspect all aspects of the above run, including steps taken, tools invoked, what prompts were seen by the LLM, and more in the LangSmith trace.

(Optional) Use Studio

Studio provides a “client side” loop as well as memory so you can run this as a chat interface and query the database. You can ask questions like “Tell me the scheme of the database” or “Show me the invoices for the 5 top customers”. You will see the SQL command that is generated and the resulting output. The details of how to get that started are below.

Run your agent in Studio

In addition to the previously mentioned packages, you will need to:

pip install -U langgraph-cli[inmem]>=0.4.0

In directory you will run in, you will need a langgraph.json file with the following contents:

{
  "dependencies": ["."],
  "graphs": {
      "agent": "./sql_agent.py:agent",
      "graph": "./sql_agent_langgraph.py:graph"
  },
  "env": ".env"
}

Create a file sql_agent.py and insert this:

#sql_agent.py for studio
import pathlib

from langchain.agents import create_agent
from langchain.chat_models import init_chat_model
from langchain_community.agent_toolkits import SQLDatabaseToolkit
from langchain_community.utilities import SQLDatabase
import requests


# Initialize an LLM
model = init_chat_model("gpt-4.1")

# Get the database, store it locally
url = "https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db"
local_path = pathlib.Path("Chinook.db")

if local_path.exists():
    print(f"{local_path} already exists, skipping download.")
else:
    response = requests.get(url)
    if response.status_code == 200:
        local_path.write_bytes(response.content)
        print(f"File downloaded and saved as {local_path}")
    else:
        print(f"Failed to download the file. Status code: {response.status_code}")

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

# Create the tools
toolkit = SQLDatabaseToolkit(db=db, llm=model)

tools = toolkit.get_tools()

for tool in tools:
    print(f"{tool.name}: {tool.description}\n")

# Use 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 can order the results by a relevant column to return the most interesting
examples in the database. Never query for all the columns from a specific table,
only ask for the relevant columns given the question.

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=db.dialect,
    top_k=5,
)

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

6. Implement human-in-the-loop review

It can be prudent to check the agent’s SQL queries before they are executed for any unintended actions or inefficiencies. LangChain agents feature support for built-in human-in-the-loop middleware to add oversight to agent tool calls. Let’s configure the agent to pause for human review on calling the sql_db_query tool:

from langchain.agents import create_agent
from langchain.agents.middleware import HumanInTheLoopMiddleware 
from langgraph.checkpoint.memory import InMemorySaver 


agent = create_agent(
    model,
    tools,
    system_prompt=system_prompt,
    middleware=[ 
        HumanInTheLoopMiddleware( 
            interrupt_on={"sql_db_query": True}, 
            description_prefix="Tool execution pending approval", 
        ), 
    ], 
    checkpointer=InMemorySaver(), 
)

We’ve added a checkpointer to our agent to allow execution to be paused and resumed. See the human-in-the-loop guide for detalis on this as well as available middleware configurations.

On running the agent, it will now pause for review before executing the sql_db_query tool:

question = "Which genre on average has the longest tracks?"
config = {"configurable": {"thread_id": "1"}} 

for step in agent.stream(
    {"messages": [{"role": "user", "content": question}]},
    config, 
    stream_mode="values",
):
    if "messages" in step:
        step["messages"][-1].pretty_print()
    elif "__interrupt__" in step: 
        print("INTERRUPTED:") 
        interrupt = step["__interrupt__"][0] 
        for request in interrupt.value["action_requests"]: 
            print(request["description"]) 
    else:
        pass

...

INTERRUPTED:
Tool execution pending approval

Tool: sql_db_query
Args: {'query': 'SELECT g.Name AS Genre, AVG(t.Milliseconds) AS AvgTrackLength FROM Track t JOIN Genre g ON t.GenreId = g.GenreId GROUP BY g.Name ORDER BY AvgTrackLength DESC LIMIT 1;'}

We can resume execution, in this case accepting the query, using Command:

from langgraph.types import Command 

for step in agent.stream(
    Command(resume={"decisions": [{"type": "approve"}]}), 
    config,
    stream_mode="values",
):
    if "messages" in step:
        step["messages"][-1].pretty_print()
    elif "__interrupt__" in step:
        print("INTERRUPTED:")
        interrupt = step["__interrupt__"][0]
        for request in interrupt.value["action_requests"]:
            print(request["description"])
    else:
        pass

================================== Ai Message ==================================
Tool Calls:
  sql_db_query (call_7oz86Epg7lYRqi9rQHbZPS1U)
 Call ID: call_7oz86Epg7lYRqi9rQHbZPS1U
  Args:
    query: SELECT Genre.Name, AVG(Track.Milliseconds) AS AvgDuration FROM Track JOIN Genre ON Track.GenreId = Genre.GenreId GROUP BY Genre.Name ORDER BY AvgDuration DESC LIMIT 5;
================================= Tool Message =================================
Name: sql_db_query

[('Sci Fi & Fantasy', 2911783.0384615385), ('Science Fiction', 2625549.076923077), ('Drama', 2575283.78125), ('TV Shows', 2145041.0215053763), ('Comedy', 1585263.705882353)]
================================== Ai Message ==================================

The genre with the longest average track length is "Sci Fi & Fantasy" with an average duration of about 2,911,783 milliseconds, followed by "Science Fiction" and "Drama."

Refer to the human-in-the-loop guide for details.

后续步骤

要进行更深入的定制，请查看本教程，了解如何直接使用 LangGraph 原语实现 SQL 智能体。

Edit the source of this page on GitHub.

Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.

Tutorials

Conceptual overviews

Additional resources

概述

概念

设置

安装

LangSmith

1. 选择 LLM

2. 配置数据库

3. Add tools for database interactions

5. Use `create_agent`

6. Run the agent

(Optional) Use Studio

6. Implement human-in-the-loop review

后续步骤

Tutorials

Conceptual overviews

Additional resources

​概述

​概念

​设置

​安装

​LangSmith

​1. 选择 LLM

​2. 配置数据库

​3. Add tools for database interactions

​5. Use create_agent

​6. Run the agent

​(Optional) Use Studio

​6. Implement human-in-the-loop review

​后续步骤

概述

概念

设置

安装

LangSmith

1. 选择 LLM

2. 配置数据库

3. Add tools for database interactions

5. Use `create_agent`

6. Run the agent

(Optional) Use Studio

6. Implement human-in-the-loop review

后续步骤