SqlToolkit

This will help you getting started with the SqlToolkit. For detailed documentation of all SqlToolkit features and configurations head to the API reference. You can also find the documentation for the Python equivalent here.

This toolkit contains a the following tools:

Name	Description
query-sql	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.
info-sql	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 list-tables-sql first! Example Input: “table1, table2, table3”.
list-tables-sql	Input is an empty string, output is a comma-separated list of tables in the database.
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 query-sql!

This toolkit is useful for asking questions, performing queries, validating queries and more on a SQL database.

Setup

This example uses Chinook database, which is a sample database available for SQL Server, Oracle, MySQL, etc. To set it up, follow these instructions, placing the .db file in the directory where your code lives.

If you want to get automated tracing from runs of individual tools, you can also set your LangSmith API key by uncommenting below:

process.env.LANGSMITH_TRACING="true"
process.env.LANGSMITH_API_KEY="your-api-key"

Installation

This toolkit lives in the langchain package. You’ll also need to install the typeorm peer dependency.

import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
<IntegrationInstallTooltip></IntegrationInstallTooltip>

<Npm2Yarn>
  langchain @langchain/core typeorm
</Npm2Yarn>

Instantiation

First, we need to define our LLM to be used in the toolkit.

<ChatModelTabs customVarName="llm" />

// @lc-docs-hide-cell

import { ChatOpenAI } from "@langchain/openai";

const llm = new ChatOpenAI({
  model: "gpt-4o-mini",
  temperature: 0,
})

import { SqlToolkit } from "langchain/agents/toolkits/sql"
import { DataSource } from "typeorm";
import { SqlDatabase } from "langchain/sql_db";

const datasource = new DataSource({
  type: "sqlite",
  database: "../../../../../../Chinook.db", // Replace with the link to your database
});
const db = await SqlDatabase.fromDataSourceParams({
  appDataSource: datasource,
});

const toolkit = new SqlToolkit(db, llm);

Tools

View available tools:

const tools = toolkit.getTools();

console.log(tools.map((tool) => ({
  name: tool.name,
  description: tool.description,
})))

[
  {
    name: 'query-sql',
    description: 'Input to this tool is a detailed and correct SQL query, output is a result from the database.\n' +
      '  If the query is not correct, an error message will be returned.\n' +
      '  If an error is returned, rewrite the query, check the query, and try again.'
  },
  {
    name: 'info-sql',
    description: 'Input to this tool is a comma-separated list of tables, output is the schema and sample rows for those tables.\n' +
      '    Be sure that the tables actually exist by calling list-tables-sql first!\n' +
      '\n' +
      '    Example Input: "table1, table2, table3.'
  },
  {
    name: 'list-tables-sql',
    description: 'Input is an empty string, output is a comma-separated list of tables in the database.'
  },
  {
    name: 'query-checker',
    description: 'Use this tool to double check if your query is correct before executing it.\n' +
      '    Always use this tool before executing a query with query-sql!'
  }
]

Use within an agent

First, ensure you have LangGraph installed:

<Npm2Yarn>
  @langchain/langgraph
</Npm2Yarn>

import { createAgent } from "langchain"

const agentExecutor = createAgent({ llm, tools });

const exampleQuery = "Can you list 10 artists from my database?"

const events = await agentExecutor.stream(
  { messages: [["user", exampleQuery]]},
  { streamMode: "values", }
)

for await (const event of events) {
  const lastMsg = event.messages[event.messages.length - 1];
  if (lastMsg.tool_calls?.length) {
    console.dir(lastMsg.tool_calls, { depth: null });
  } else if (lastMsg.content) {
    console.log(lastMsg.content);
  }
}

[
  {
    name: 'list-tables-sql',
    args: {},
    type: 'tool_call',
    id: 'call_LqsRA86SsKmzhRfSRekIQtff'
  }
]
Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track
[
  {
    name: 'query-checker',
    args: { input: 'SELECT * FROM Artist LIMIT 10;' },
    type: 'tool_call',
    id: 'call_MKBCjt4gKhl5UpnjsMHmDrBH'
  }
]
The SQL query you provided is:

\`\`\`sql
SELECT * FROM Artist LIMIT 10;
\`\`\`

This query is straightforward and does not contain any of the common mistakes listed. It simply selects all columns from the `Artist` table and limits the result to 10 rows.

Therefore, there are no mistakes to correct, and the original query can be reproduced as is:

\`\`\`sql
SELECT * FROM Artist LIMIT 10;
\`\`\`
[
  {
    name: 'query-sql',
    args: { input: 'SELECT * FROM Artist LIMIT 10;' },
    type: 'tool_call',
    id: 'call_a8MPiqXPMaN6yjN9i7rJctJo'
  }
]
[{"ArtistId":1,"Name":"AC/DC"},{"ArtistId":2,"Name":"Accept"},{"ArtistId":3,"Name":"Aerosmith"},{"ArtistId":4,"Name":"Alanis Morissette"},{"ArtistId":5,"Name":"Alice In Chains"},{"ArtistId":6,"Name":"Antônio Carlos Jobim"},{"ArtistId":7,"Name":"Apocalyptica"},{"ArtistId":8,"Name":"Audioslave"},{"ArtistId":9,"Name":"BackBeat"},{"ArtistId":10,"Name":"Billy Cobham"}]
Here are 10 artists from your database:

1. AC/DC
2. Accept
3. Aerosmith
4. Alanis Morissette
5. Alice In Chains
6. Antônio Carlos Jobim
7. Apocalyptica
8. Audioslave
9. BackBeat
10. Billy Cobham

API reference

For detailed documentation of all SqlToolkit features and configurations head to the API reference.