构建一个 SQL 智能体

概述

在本教程中，您将学习如何构建一个智能体，该智能体可以使用LangChain 智能体回答有关SQL数据库的问题。在较高层面上，智能体将：

Fetch the available tables and schemas from the database

Decide which tables are relevant to the question

Fetch the schemas for the relevant tables

Generate a query based on the question and information from the schemas

Double-check the query for common mistakes using an LLM

Execute the query and return the results

Correct mistakes surfaced by the database engine until the query is successful

Formulate a response based on the results

构建基于SQL数据库的问答系统需要执行由模型生成的SQL查询。这样做存在固有的风险。请确保您的数据库连接权限始终尽可能窄地针对智能体的需求进行设置。这将减轻，但不会消除，构建基于模型驱动系统的风险。

概念

我们将介绍以下概念：

工具用于从 SQL 数据库读取
LangChain 智能体
人机协同处理

安装

pip install langchain  langgraph  langchain-community

LangSmith

设置 LangSmith 以检查您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. 选择一个大型语言模型

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("openai:gpt-4.1")

👉 Read the Anthropic chat model integration docs

pip install -U "langchain[anthropic]"

import os
from langchain.chat_models import init_chat_model

os.environ["ANTHROPIC_API_KEY"] = "sk-..."

model = init_chat_model("anthropic:claude-sonnet-4-5")

👉 Read the Azure chat model integration docs

pip install -U "langchain[openai]"

import os
from langchain.chat_models import init_chat_model

os.environ["AZURE_OPENAI_API_KEY"] = "..."
os.environ["AZURE_OPENAI_ENDPOINT"] = "..."
os.environ["OPENAI_API_VERSION"] = "2025-03-01-preview"

model = init_chat_model(
    "azure_openai:gpt-4.1",
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
)

👉 Read the Google GenAI chat model integration docs

pip install -U "langchain[google-genai]"

import os
from langchain.chat_models import init_chat_model

os.environ["GOOGLE_API_KEY"] = "..."

model = init_chat_model("google_genai:gemini-2.5-flash-lite")

👉 Read the AWS Bedrock chat model integration docs

pip install -U "langchain[aws]"

from langchain.chat_models import init_chat_model

# Follow the steps here to configure your credentials:
# https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

model = init_chat_model(
    "anthropic.claude-3-5-sonnet-20240620-v1:0",
    model_provider="bedrock_converse",
)

以下示例中的输出使用了 OpenAI。

2. 配置数据库

您将为本次教程创建一个 SQLite数据库。SQLite是一种轻量级数据库，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店的示例数据库。为了方便，我们已经将数据库（Chinook.db）托管在公共GCS存储桶中。

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数据库包装器来与数据库交互。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. 添加数据库交互工具

使用 langchain_community 包中提供的 SQLDatabase 包装器与数据库进行交互。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. 使用 `create_agent`

使用 create_agent 以最少的代码构建一个 ReAct 智能体。智能体会解析请求并生成一个 SQL 命令，工具将执行该命令。如果命令有错误，错误信息将返回给模型。然后模型可以检查原始请求和新的错误信息，并生成新的命令。这可以一直持续到 LLM 成功生成命令或达到结束计数。向模型提供反馈（在这种情况下为错误信息）的模式非常强大。使用描述性系统提示初始化智能体以自定义其行为：

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,
)

现在，创建一个包含模型、工具和提示的智能体：

from langchain.agents import create_agent


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

6. 运行智能体

在样本查询上运行智能体并观察其行为：

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."

智能体正确地编写了一个查询，检查了该查询，并运行它以告知其最终响应。

您可以检查上述运行的各个方面，包括采取的步骤、调用的工具、LLM 看到的提示等，更多详情请参阅 LangSmith 跟踪。

（可选）使用 Studio

工作室提供了“客户端”循环以及内存，因此您可以将其作为聊天界面运行并查询数据库。您可以提出诸如“告诉我数据库的架构”或“显示前5位客户的发票”等问题。您将看到生成的SQL命令和结果输出。如何开始此操作的详细信息如下。

Run your agent in Studio

除了之前提到的包之外，您还需要：

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

在您将要运行的目录中，您需要一个包含以下内容的 langgraph.json 文件：

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

创建一个文件 sql_agent.py 并插入以下内容：

#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("openai: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. 实施人工审核

在执行智能体的SQL查询之前检查其查询，以避免任何未预期的行为或低效，这是一种谨慎的做法。 LangChain智能体支持内置的人机协同中间件，以便对智能体工具调用进行监督。让我们配置智能体，在调用sql_db_query工具时暂停以供人工审查：

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(), 
)

我们为智能体添加了一个检查点，允许执行暂停和恢复。有关此功能以及可用的中间件配置的详细信息，请参阅人工干预指南。

在运行智能体后，它现在将暂停以进行审查，然后执行 sql_db_query 工具：

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: 
            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;'}

我们可以通过使用命令来继续执行，在这种情况下接受查询：

from langgraph.types import Command 

for step in agent.stream(
    Command(resume=[{"type": "accept"}]), 
    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:
            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."

请参阅人机交互指南以获取详细信息。

下一步

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

在GitHub上编辑此页面的源代码.

通过MCP将这些文档编程连接到Claude、VSCode等，以获取实时答案。

教程

概念概述

其他资源

概述

概念

安装

安装

LangSmith

1. 选择一个大型语言模型

2. 配置数据库

3. 添加数据库交互工具

5. 使用 `create_agent`

6. 运行智能体

（可选）使用 Studio

6. 实施人工审核

下一步

教程

概念概述

其他资源

​概述

​概念

​安装

​安装

​LangSmith

​1. 选择一个大型语言模型

​2. 配置数据库

​3. 添加数据库交互工具

​5. 使用 create_agent

​6. 运行智能体

​（可选）使用 Studio

​6. 实施人工审核

​下一步

概述

概念

安装

安装

LangSmith

1. 选择一个大型语言模型

2. 配置数据库

3. 添加数据库交互工具

5. 使用 `create_agent`

6. 运行智能体

（可选）使用 Studio

6. 实施人工审核

下一步