跳到主要内容
这将帮助您开始使用 SQL Database 工具包。有关所有 SQLDatabaseToolkit 功能和配置的详细文档，请参阅 API 参考。 SQLDatabaseToolkit 中的工具旨在与 SQL 数据库交互。 一个常见的应用是使智能体能够使用关系数据库中的数据回答问题，可能以迭代方式（例如，从错误中恢复）。 ⚠️ 安全注意事项 ⚠️ 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。请确保您的数据库连接权限始终尽可能狭窄地符合您的链/智能体的需求。这将减轻但不能消除构建模型驱动系统的风险。

​
设置

要启用单个工具的自动化跟踪，请设置您的 LangSmith API 密钥 
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

​
安装

此工具包位于 langchain-community 包中 
pip install -qU  langchain-community
出于演示目的，我们将访问 LangChain Hub 中的一个提示。我们还需要 langgraph 来演示工具包与智能体的用法。这不是使用工具包所必需的。 
pip install -qU langchainhub langgraph

​
实例化

SQLDatabaseToolkit 工具包需要 下面，我们使用这些对象实例化工具包。首先，让我们创建一个数据库对象。 本指南使用基于 这些说明 的示例 Chinook 数据库。 下面我们将使用 requests 库拉取 .sql 文件并创建一个内存中的 SQLite 数据库。请注意，这种方法是轻量级的，但短暂且非线程安全。如果您愿意，可以按照说明将文件本地保存为 Chinook.db 并通过 db = SQLDatabase.from_uri("sqlite:///Chinook.db") 实例化数据库。
import sqlite3

import requests
from langchain_community.utilities.sql_database import SQLDatabase
from sqlalchemy import create_engine
from sqlalchemy.pool import StaticPool


def get_engine_for_chinook_db():
    """Pull sql file, populate in-memory database, and create engine."""
    url = "https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql"
    response = requests.get(url)
    sql_script = response.text

    connection = sqlite3.connect(":memory:", check_same_thread=False)
    connection.executescript(sql_script)
    return create_engine(
        "sqlite://",
        creator=lambda: connection,
        poolclass=StaticPool,
        connect_args={"check_same_thread": False},
    )


engine = get_engine_for_chinook_db()

db = SQLDatabase(engine)
我们还需要一个 LLM 或聊天模型 
# | output: false
# | echo: false

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(temperature=0)
我们现在可以实例化工具包 
from langchain_community.agent_toolkits.sql.toolkit import SQLDatabaseToolkit

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

​
工具

查看可用工具 
toolkit.get_tools()

[QuerySQLDatabaseTool(description="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.", db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x103d5fa60>),
 InfoSQLDatabaseTool(description='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', db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x103d5fa60>),
 ListSQLDatabaseTool(db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x103d5fa60>),
 QuerySQLCheckerTool(description='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!', db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x103d5fa60>, llm=ChatOpenAI(client=<openai.resources.chat.completions.Completions object at 0x10742d720>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x10742f7f0>, root_client=<openai.OpenAI object at 0x103d5fac0>, root_async_client=<openai.AsyncOpenAI object at 0x10742d780>, temperature=0.0, model_kwargs={}, openai_api_key=SecretStr('**********')), llm_chain=LLMChain(verbose=False, prompt=PromptTemplate(input_variables=['dialect', 'query'], input_types={}, partial_variables={}, template='\n{query}\nDouble check the {dialect} query above for common mistakes, including:\n- Using NOT IN with NULL values\n- Using UNION when UNION ALL should have been used\n- Using BETWEEN for exclusive ranges\n- Data type mismatch in predicates\n- Properly quoting identifiers\n- Using the correct number of arguments for functions\n- Casting to the correct data type\n- Using the proper columns for joins\n\nIf there are any of the above mistakes, rewrite the query. If there are no mistakes, just reproduce the original query.\n\nOutput the final SQL query only.\n\nSQL Query: '), llm=ChatOpenAI(client=<openai.resources.chat.completions.Completions object at 0x10742d720>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x10742f7f0>, root_client=<openai.OpenAI object at 0x103d5fac0>, root_async_client=<openai.AsyncOpenAI object at 0x10742d780>, temperature=0.0, model_kwargs={}, openai_api_key=SecretStr('**********')), output_parser=StrOutputParser(), llm_kwargs={}))]
您可以直接使用单个工具 
from langchain_community.tools.sql_database.tool import (
    InfoSQLDatabaseTool,
    ListSQLDatabaseTool,
    QuerySQLCheckerTool,
    QuerySQLDatabaseTool,
)

​
在代理中使用

按照 SQL Q&A 教程，下面我们为简单的问答智能体配备工具包中的工具。首先我们拉取一个相关提示并用其所需参数填充它 
from langchain_classic import hub

prompt_template = hub.pull("langchain-ai/sql-agent-system-prompt")

assert len(prompt_template.messages) == 1
print(prompt_template.input_variables)

['dialect', 'top_k']

system_message = prompt_template.format(dialect="SQLite", top_k=5)
然后我们实例化智能体 
from langchain.agents import create_agent

agent = create_agent(llm, toolkit.get_tools(), system_prompt=system_message)
并向其发出查询 
example_query = "Which country's customers spent the most?"

events = agent.stream(
    {"messages": [("user", example_query)]},
    stream_mode="values",
)
for event in events:
    event["messages"][-1].pretty_print()

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

Which country's customers spent the most?
================================== Ai Message ==================================
Tool Calls:
  sql_db_list_tables (call_EBPjyfzqXzFutDn8BklYACLj)
 Call ID: call_EBPjyfzqXzFutDn8BklYACLj
  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_kGcnKpxRVFIY8dPjYIJbRoVU)
 Call ID: call_kGcnKpxRVFIY8dPjYIJbRoVU
  Args:
    table_names: Customer, Invoice, InvoiceLine
================================= Tool Message =================================
Name: sql_db_schema


CREATE TABLE "Customer" (
 "CustomerId" INTEGER NOT NULL,
 "FirstName" NVARCHAR(40) NOT NULL,
 "LastName" NVARCHAR(20) NOT NULL,
 "Company" NVARCHAR(80),
 "Address" NVARCHAR(70),
 "City" NVARCHAR(40),
 "State" NVARCHAR(40),
 "Country" NVARCHAR(40),
 "PostalCode" NVARCHAR(10),
 "Phone" NVARCHAR(24),
 "Fax" NVARCHAR(24),
 "Email" NVARCHAR(60) NOT NULL,
 "SupportRepId" INTEGER,
 PRIMARY KEY ("CustomerId"),
 FOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")
)

/*
3 rows from Customer table:
CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId
1 Luís Gonçalves Embraer - Empresa Brasileira de Aeronáutica S.A. Av. Brigadeiro Faria Lima, 2170 São José dos Campos SP Brazil 12227-000 +55 (12) 3923-5555 +55 (12) 3923-5566 luisg@embraer.com.br 3
2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 +49 0711 2842222 None leonekohler@surfeu.de 5
3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 +1 (514) 721-4711 None ftremblay@gmail.com 3
*/


CREATE TABLE "Invoice" (
 "InvoiceId" INTEGER NOT NULL,
 "CustomerId" INTEGER NOT NULL,
 "InvoiceDate" DATETIME NOT NULL,
 "BillingAddress" NVARCHAR(70),
 "BillingCity" NVARCHAR(40),
 "BillingState" NVARCHAR(40),
 "BillingCountry" NVARCHAR(40),
 "BillingPostalCode" NVARCHAR(10),
 "Total" NUMERIC(10, 2) NOT NULL,
 PRIMARY KEY ("InvoiceId"),
 FOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")
)

/*
3 rows from Invoice table:
InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total
1 2 2021-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98
2 4 2021-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96
3 8 2021-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94
*/


CREATE TABLE "InvoiceLine" (
 "InvoiceLineId" INTEGER NOT NULL,
 "InvoiceId" INTEGER NOT NULL,
 "TrackId" INTEGER NOT NULL,
 "UnitPrice" NUMERIC(10, 2) NOT NULL,
 "Quantity" INTEGER NOT NULL,
 PRIMARY KEY ("InvoiceLineId"),
 FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
 FOREIGN KEY("InvoiceId") REFERENCES "Invoice" ("InvoiceId")
)

/*
3 rows from InvoiceLine table:
InvoiceLineId InvoiceId TrackId UnitPrice Quantity
1 1 2 0.99 1
2 1 4 0.99 1
3 2 6 0.99 1
*/
================================== Ai Message ==================================
Tool Calls:
  sql_db_query (call_cTfI7OrY64FzJaDd49ILFWw7)
 Call ID: call_cTfI7OrY64FzJaDd49ILFWw7
  Args:
    query: SELECT c.Country, SUM(i.Total) AS TotalSpent FROM Customer c JOIN Invoice i ON c.CustomerId = i.CustomerId GROUP BY c.Country ORDER BY TotalSpent DESC LIMIT 1
================================= Tool Message =================================
Name: sql_db_query

[('USA', 523.06)]
================================== Ai Message ==================================

Customers from the USA spent the most, with a total amount spent of $523.06.
我们还可以观察智能体从错误中恢复 
example_query = "Who are the top 3 best selling artists?"

events = agent.stream(
    {"messages": [("user", example_query)]},
    stream_mode="values",
)
for event in events:
    event["messages"][-1].pretty_print()

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

Who are the top 3 best selling artists?
================================== Ai Message ==================================
Tool Calls:
  sql_db_query (call_xAkvYiRFM7nCMKXsDNvk1OMx)
 Call ID: call_xAkvYiRFM7nCMKXsDNvk1OMx
  Args:
    query: SELECT artist_name, SUM(quantity) AS total_sold FROM sales GROUP BY artist_name ORDER BY total_sold DESC LIMIT 3
================================= Tool Message =================================
Name: sql_db_query

Error: (sqlite3.OperationalError) no such table: sales
[SQL: SELECT artist_name, SUM(quantity) AS total_sold FROM sales GROUP BY artist_name ORDER BY total_sold DESC LIMIT 3]
(Background on this error at: https://sqlalche.me/e/20/e3q8)
================================== Ai Message ==================================
Tool Calls:
  sql_db_list_tables (call_K4Zvbowsq7XPgGFepbvc5G7i)
 Call ID: call_K4Zvbowsq7XPgGFepbvc5G7i
  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_tUztueSK7VO2klZ99xT4ZVhM)
 Call ID: call_tUztueSK7VO2klZ99xT4ZVhM
  Args:
    table_names: Artist, Album, InvoiceLine
================================= Tool Message =================================
Name: sql_db_schema


CREATE TABLE "Album" (
 "AlbumId" INTEGER NOT NULL,
 "Title" NVARCHAR(160) NOT NULL,
 "ArtistId" INTEGER NOT NULL,
 PRIMARY KEY ("AlbumId"),
 FOREIGN KEY("ArtistId") REFERENCES "Artist" ("ArtistId")
)

/*
3 rows from Album table:
AlbumId Title ArtistId
1 For Those About To Rock We Salute You 1
2 Balls to the Wall 2
3 Restless and Wild 2
*/


CREATE TABLE "Artist" (
 "ArtistId" INTEGER NOT NULL,
 "Name" NVARCHAR(120),
 PRIMARY KEY ("ArtistId")
)

/*
3 rows from Artist table:
ArtistId Name
1 AC/DC
2 Accept
3 Aerosmith
*/


CREATE TABLE "InvoiceLine" (
 "InvoiceLineId" INTEGER NOT NULL,
 "InvoiceId" INTEGER NOT NULL,
 "TrackId" INTEGER NOT NULL,
 "UnitPrice" NUMERIC(10, 2) NOT NULL,
 "Quantity" INTEGER NOT NULL,
 PRIMARY KEY ("InvoiceLineId"),
 FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
 FOREIGN KEY("InvoiceId") REFERENCES "Invoice" ("InvoiceId")
)

/*
3 rows from InvoiceLine table:
InvoiceLineId InvoiceId TrackId UnitPrice Quantity
1 1 2 0.99 1
2 1 4 0.99 1
3 2 6 0.99 1
*/
================================== Ai Message ==================================
Tool Calls:
  sql_db_query (call_tVtLQIRPmCM6pukgpHFfq86A)
 Call ID: call_tVtLQIRPmCM6pukgpHFfq86A
  Args:
    query: SELECT Artist.Name AS artist_name, SUM(InvoiceLine.Quantity) AS total_sold FROM Artist JOIN Album ON Artist.ArtistId = Album.ArtistId JOIN Track ON Album.AlbumId = Track.AlbumId JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY total_sold DESC LIMIT 3
================================= Tool Message =================================
Name: sql_db_query

[('Iron Maiden', 140), ('U2', 107), ('Metallica', 91)]
================================== Ai Message ==================================

The top 3 best selling artists are:
1. Iron Maiden - 140 units sold
2. U2 - 107 units sold
3. Metallica - 91 units sold

​
特定功能

SQLDatabaseToolkit 实现了一个 .get_context 方法，方便在提示或其他上下文中使用。 ⚠️ 免责声明 ⚠️：智能体可能会生成插入/更新/删除查询。当不期望这种情况时，请使用自定义提示或创建没有写入权限的 SQL 用户。 最终用户可能会通过问一个简单的问题（例如“运行尽可能大的查询”）来使您的 SQL 数据库过载。生成的查询可能如下所示：
SELECT * FROM "public"."users"
    JOIN "public"."user_permissions" ON "public"."users".id = "public"."user_permissions".user_id
    JOIN "public"."projects" ON "public"."users".id = "public"."projects".user_id
    JOIN "public"."events" ON "public"."projects".id = "public"."events".project_id;
对于事务性 SQL 数据库，如果上述其中一个表包含数百万行，则查询可能会给使用相同数据库的其他应用程序带来麻烦。 大多数面向数据仓库的数据库支持用户级配额，以限制资源使用。

​
API 参考

有关所有 SQLDatabaseToolkit 功能和配置的详细文档，请参阅 API 参考。
在 GitHub 上编辑此页面源文件。
以编程方式连接这些文档到 Claude、VSCode 等，通过 MCP 获取实时答案。
© . This site is unofficial and not affiliated with LangChain, Inc.