SQLDatabase toolkit 集成

使用 LangChain Python 集成 the SQLDatabase toolkit。

这将帮助你开始使用 the SQL Database toolkit. 所有 SQLDatabaseToolkit 功能和配置的详细文档请前往 API reference.

Tools within the SQLDatabaseToolkit are designed to interact with a SQL database.

A common application is to enable agents 提供自然语言接口swer 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.

设置

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

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

安装

This toolkit lives in the langchain-community package:

pip install -qU  langchain-community

For demonstration purposes, we will access a prompt in the LangChain Hub. We will also require langgraph to demonstrate the use of the toolkit 与智能体配合使用。 This is not required to use the 工具包。

pip install -qU langchainhub langgraph

Instantiation

The SQLDatabaseToolkit toolkit requires:

• a SQLDatabase object;
• a LLM or chat model (for instantiating the QuerySQLCheckerTool tool).

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

This guide uses the example Chinook database based on these instructions.

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

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)

We will also need a LLM or chat model:

# | output: false
# | echo: false

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(temperature=0)

We can now instantiate the toolkit:

from langchain_community.agent_toolkits.sql.toolkit import SQLDatabaseToolkit

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

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.tool import (
    InfoSQLDatabaseTool,
    ListSQLDatabaseTool,
    QuerySQLCheckerTool,
    QuerySQLDatabaseTool,
)

Use within an agent

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

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)

We then instantiate the agent:

from langchain.agents import create_agent

agent = create_agent(llm, toolkit.get_tools(), system_prompt=system_message)

And issue it a query:

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 [phone] [phone] [e-mail] 3
2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 [phone] None [e-mail] 5
3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 [phone] None [e-mail] 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.

We can also observe the agent recover from an error:

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

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 参考

所有 SQLDatabaseToolkit 功能和配置的详细文档请前往 API reference.

---

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

Edit this page on GitHub or file an issue.