SQLDatabase Toolkit

This will help you get started with the SQL Databasetoolkit. For detailed documentation of allSQLDatabaseToolkit features and configurations head to theAPI reference.

Tools within theSQLDatabaseToolkit are designed to interact with aSQL database.

A common application is to enable agents to answer questions using data in a relational database, potentially in an iterative fashion (e.g., recovering from errors).

⚠️ Security note ⚠️

Building Q&A systems of SQL databases requires executing model-generated SQL queries. There are inherent risks in doing this. Make sure that your database connection permissions are always scoped as narrowly as possible for your chain/agent's needs. This will mitigate though not eliminate the risks of building a model-driven system. For more on general security best practices,see here.

Setup

To enable automated tracing of individual tools, set yourLangSmith API key:

# os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
# os.environ["LANGSMITH_TRACING"] = "true"

Installation

This toolkit lives in thelangchain-community package:

%pip install--upgrade--quiet  langchain-community

For demonstration purposes, we will access a prompt in the LangChainHub. We will also requirelanggraph to demonstrate the use of the toolkit with an agent. This is not required to use the toolkit.

%pip install--upgrade--quiet langchainhub langgraph

Instantiation

TheSQLDatabaseToolkit toolkit requires:

aSQLDatabase object;
a LLM or chat model (for instantiating theQuerySQLCheckerTool tool).

Below, we instantiate the toolkit with these objects. Let's first create a database object.

This guide uses the exampleChinook database based onthese instructions.

Below we will use therequests library to pull the.sql file and create an in-memory SQLite database. Note that this approach is lightweight, but ephemeral and not thread-safe. If you'd prefer, you can follow the instructions to save the file locally asChinook.db and instantiate the database viadb = SQLDatabase.from_uri("sqlite:///Chinook.db").

import sqlite3

import requests
from langchain_community.utilities.sql_databaseimport SQLDatabase
from sqlalchemyimport create_engine
from sqlalchemy.poolimport StaticPool


defget_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)

API Reference:SQLDatabase

We will also need a LLM or chat model:

Selectchat model:

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

import getpass
import os

ifnot os.environ.get("GOOGLE_API_KEY"):
  os.environ["GOOGLE_API_KEY"]= getpass.getpass("Enter API key for Google Gemini: ")

from langchain.chat_modelsimport init_chat_model

llm= init_chat_model("gemini-2.0-flash", model_provider="google_genai")

We can now instantiate the toolkit:

from langchain_community.agent_toolkits.sql.toolkitimport SQLDatabaseToolkit

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

API Reference:SQLDatabaseToolkit

Tools

View available tools:

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={}))]

You can use the individual tools directly:

from langchain_community.tools.sql_database.toolimport(
    InfoSQLDatabaseTool,
    ListSQLDatabaseTool,
    QuerySQLCheckerTool,
    QuerySQLDatabaseTool,
)

API Reference:InfoSQLDatabaseTool |ListSQLDatabaseTool |QuerySQLCheckerTool |QuerySQLDatabaseTool

Use within an agent

Following theSQL Q&A Tutorial, below we equip a simple question-answering agent with the tools in our toolkit. First we pull a relevant prompt and populate it with its required parameters:

from langchainimport hub

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

assertlen(prompt_template.messages)==1
print(prompt_template.input_variables)

API Reference:hub

['dialect', 'top_k']

system_message= prompt_template.format(dialect="SQLite", top_k=5)

We then instantiate the agent:

from langgraph.prebuiltimport create_react_agent

agent_executor= create_react_agent(llm, toolkit.get_tools(), prompt=system_message)

API Reference:create_react_agent

And issue it a query:

example_query="Which country's customers spent the most?"

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

================================[1m Human Message [0m=================================

Which country's customers spent the most?
==================================[1m Ai Message [0m==================================
Tool Calls:
  sql_db_list_tables (call_EBPjyfzqXzFutDn8BklYACLj)
 Call ID: call_EBPjyfzqXzFutDn8BklYACLj
  Args:
=================================[1m Tool Message [0m=================================
Name: sql_db_list_tables

Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track
==================================[1m Ai Message [0m==================================
Tool Calls:
  sql_db_schema (call_kGcnKpxRVFIY8dPjYIJbRoVU)
 Call ID: call_kGcnKpxRVFIY8dPjYIJbRoVU
  Args:
    table_names: Customer, Invoice, InvoiceLine
=================================[1m Tool Message [0m=================================
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:
CustomerIdFirstNameLastNameCompanyAddressCityStateCountryPostalCodePhoneFaxEmailSupportRepId
1LuísGonçalvesEmbraer - Empresa Brasileira de Aeronáutica S.A.Av. Brigadeiro Faria Lima, 2170São José dos CamposSPBrazil12227-000+55 (12) 3923-5555+55 (12) 3923-5566luisg@embraer.com.br3
2LeonieKöhlerNoneTheodor-Heuss-Straße 34StuttgartNoneGermany70174+49 0711 2842222Noneleonekohler@surfeu.de5
3FrançoisTremblayNone1498 rue BélangerMontréalQCCanadaH2G 1A7+1 (514) 721-4711Noneftremblay@gmail.com3
*/


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:
InvoiceIdCustomerIdInvoiceDateBillingAddressBillingCityBillingStateBillingCountryBillingPostalCodeTotal
122021-01-01 00:00:00Theodor-Heuss-Straße 34StuttgartNoneGermany701741.98
242021-01-02 00:00:00Ullevålsveien 14OsloNoneNorway01713.96
382021-01-03 00:00:00Grétrystraat 63BrusselsNoneBelgium10005.94
*/


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:
InvoiceLineIdInvoiceIdTrackIdUnitPriceQuantity
1120.991
2140.991
3260.991
*/
==================================[1m Ai Message [0m==================================
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
=================================[1m Tool Message [0m=================================
Name: sql_db_query

[('USA', 523.06)]
==================================[1m Ai Message [0m==================================

Customers from the USA spent the most, with a total amount spent of $523.06.

We can also observe the agent recover from an error:

example_query="Who are the top 3 best selling artists?"

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

================================[1m Human Message [0m=================================

Who are the top 3 best selling artists?
==================================[1m Ai Message [0m==================================
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
=================================[1m Tool Message [0m=================================
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)
==================================[1m Ai Message [0m==================================
Tool Calls:
  sql_db_list_tables (call_K4Zvbowsq7XPgGFepbvc5G7i)
 Call ID: call_K4Zvbowsq7XPgGFepbvc5G7i
  Args:
=================================[1m Tool Message [0m=================================
Name: sql_db_list_tables

Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track
==================================[1m Ai Message [0m==================================
Tool Calls:
  sql_db_schema (call_tUztueSK7VO2klZ99xT4ZVhM)
 Call ID: call_tUztueSK7VO2klZ99xT4ZVhM
  Args:
    table_names: Artist, Album, InvoiceLine
=================================[1m Tool Message [0m=================================
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:
AlbumIdTitleArtistId
1For Those About To Rock We Salute You1
2Balls to the Wall2
3Restless and Wild2
*/


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

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


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:
InvoiceLineIdInvoiceIdTrackIdUnitPriceQuantity
1120.991
2140.991
3260.991
*/
==================================[1m Ai Message [0m==================================
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
=================================[1m Tool Message [0m=================================
Name: sql_db_query

[('Iron Maiden', 140), ('U2', 107), ('Metallica', 91)]
==================================[1m Ai Message [0m==================================

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

Specific functionality

SQLDatabaseToolkit implements a.get_context method as a convenience for use in prompts or other contexts.

⚠️ Disclaimer ⚠️ : The agent may generate insert/update/delete queries. When this is not expected, use a custom prompt or create a SQL users without write permissions.

The final user might overload your SQL database by asking a simple question such as "run the biggest query possible". The generated query might look like:

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;

For a transactional SQL database, if one of the table above contains millions of rows, the query might cause trouble to other applications using the same database.

Most datawarehouse oriented databases support user-level quota, for limiting resource usage.

API reference

For detailed documentation of all SQLDatabaseToolkit features and configurations head to theAPI reference.

Toolconceptual guide
Toolhow-to guides

Movatterモバイル変換

SQLDatabase Toolkit

Setup

Installation

Instantiation

Tools

Use within an agent

Specific functionality

API reference

Related

Movatterモバイル変換

Setup​

Installation​

Instantiation​

Tools​

Use within an agent​

Specific functionality​

API reference​

Related​

Setup

Installation

Instantiation

Tools

Use within an agent

Specific functionality

API reference

Related