Toolkits are sets of tools that can be used to interact with various services and APIs.
Construct a json agent from an LLM and tools.
Construct an OpenAPI agent from an LLM and tools.
Security Note: When creating an OpenAPI agent, check the permissions and capabilities of the underlying toolkit.
For example, if the default implementation of OpenAPIToolkit
uses the RequestsToolkit which contains tools to make arbitrary
network requests against any URL (e.g., GET, POST, PATCH, PUT, DELETE),
Control access to who can submit issue requests using this toolkit and
what network access it has.
See https://python.langchain.com/docs/security for more information.
Construct a Power BI agent from an LLM and tools.
Construct a Power BI agent from a Chat LLM and tools.
If you supply only a toolkit and no Power BI dataset, the same LLM is used for both.
Construct a Spark SQL agent from an LLM and tools.
This agent can execute arbitrary SQL against your Spark environment.
By default, the agent is allowed to generate SQL strings and run them via the underlying connection. This is powerful, but it also means the agent can generate expensive or dangerous queries (e.g., long-running queries, large scans/joins, or locking queries depending on your environment and permissions).
create_spark_sql_agent returns a langchain_classic AgentExecutor.
AgentExecutor is an agent abstraction that has long been considered legacy
and is not actively supported as the recommended foundation for new production
applications.
For production-grade agent development, prefer building with Deep Agents: https://github.com/langchain-ai/deepagents
If you use this in production, coordinate with your security/DB teams and apply server-side controls:
Client-side timeouts do not always guarantee that a running statement is cancelled on the server.
Construct a SQL agent from an LLM and toolkit or database.
This agent can execute arbitrary SQL against your database.
By default, the agent is allowed to generate SQL strings and run them via the database connection. This is powerful, but it also means the agent can generate expensive or dangerous queries (e.g., long-running queries, large scans/joins, locking queries, or unintended writes depending on your database permissions).
create_sql_agent returns a langchain_classic AgentExecutor.
AgentExecutor is an agent abstraction that has long been considered legacy
and is not actively supported as the recommended foundation for new production
applications.
For production-grade agent development, prefer building with Deep Agents: https://github.com/langchain-ai/deepagents
If you use this in production, coordinate with your security/DB teams and apply server-side controls:
Client-side timeouts do not always guarantee that a running statement is cancelled on the database server.
Toolkit for interacting with AINetwork Blockchain.
Security Note: This toolkit contains tools that can read and modify the state of a service; e.g., by reading, creating, updating, deleting data associated with this service.
See https://python.langchain.com/docs/security for more information.
Toolkit for interacting with Amadeus which offers APIs for travel.
Toolkit for Azure AI Services.
Toolkit for Azure Cognitive Services.
Toolkit for interacting with an Apache Cassandra database.
Toolkit for CogniSwitch.
Use the toolkit to get all the tools present in the Cogniswitch and use them to interact with your knowledge.
Toolkit with a list of Connery Actions as tools.
Toolkit for interacting with local files.
Security Notice: This toolkit provides methods to interact with local files. If providing this toolkit to an agent on an LLM, ensure you scope the agent's permissions to only include the necessary permissions to perform the desired operations.
By **default** the agent will have access to all files within
the root dir and will be able to Copy, Delete, Move, Read, Write
and List files in that directory.
Consider the following:
- Limit access to particular directories using `root_dir`.
- Use filesystem permissions to restrict access and permissions to only
the files and directories required by the agent.
- Limit the tools available to the agent to only the file operations
necessary for the agent's intended use.
- Sandbox the agent by running it in a container.
See https://python.langchain.com/docs/security for more information.
Toolkit for interacting with Gmail.
Security Note: This toolkit contains tools that can read and modify the state of a service; e.g., by reading, creating, updating, deleting data associated with this service.
For example, this toolkit can be used to send emails on behalf of the
associated account.
See https://python.langchain.com/docs/security for more information.
Jira Toolkit.
Security Note: This toolkit contains tools that can read and modify the state of a service; e.g., by creating, deleting, or updating, reading underlying data.
See https://python.langchain.com/docs/security for more information.
Toolkit for interacting with a JSON spec.
Toolkit for interacting with the Browser Agent.
Security Note: This toolkit contains tools that interact with the user's browser via the multion API which grants an agent access to the user's browser.
Please review the documentation for the multion API to understand
the security implications of using this toolkit.
See https://python.langchain.com/docs/security for more information.
Nasa Toolkit.
Natural Language API Toolkit.
Security Note: This toolkit creates tools that enable making calls to an Open API compliant API.
The tools created by this toolkit may be able to make GET, POST,
PATCH, PUT, DELETE requests to any of the exposed endpoints on
the API.
Control access to who can use this toolkit.
See https://python.langchain.com/docs/security for more information.
Toolkit for interacting with Office 365.
Security Note: This toolkit contains tools that can read and modify the state of a service; e.g., by reading, creating, updating, deleting data associated with this service.
For example, this toolkit can be used search through emails and events,
send messages and event invites, and create draft messages.
Please make sure that the permissions given by this toolkit
are appropriate for your use case.
See https://python.langchain.com/docs/security for more information.
Toolkit for interacting with an OpenAPI API.
Security Note: This toolkit contains tools that can read and modify the state of a service; e.g., by creating, deleting, or updating, reading underlying data.
For example, this toolkit can be used to delete data exposed via
an OpenAPI compliant API.
Toolkit for PlayWright browser tools.
Security Note: This toolkit provides code to control a web-browser.
Careful if exposing this toolkit to end-users. The tools in the toolkit
are capable of navigating to arbitrary webpages, clicking on arbitrary
elements, and extracting arbitrary text and hyperlinks from webpages.
Specifically, by default this toolkit allows navigating to:
- Any URL (including any internal network URLs)
- And local files
If exposing to end-users, consider limiting network access to the
server that hosts the agent; in addition, consider it is advised
to create a custom NavigationTool wht an args_schema that limits the URLs
that can be navigated to (e.g., only allow navigating to URLs that
start with a particular prefix).
Remember to scope permissions to the minimal permissions necessary for
the application. If the default tool selection is not appropriate for
the application, consider creating a custom toolkit with the appropriate
tools.
See https://python.langchain.com/docs/security for more information.
Polygon Toolkit.
Toolkit for interacting with Power BI dataset.
Security Note: This toolkit interacts with an external service.
Control access to who can use this toolkit.
Make sure that the capabilities given by this toolkit to the calling
code are appropriately scoped to the application.
See https://python.langchain.com/docs/security for more information.
Toolkit for interacting with Slack.
Toolkit for interacting with Spark SQL.
SQLDatabaseToolkit for interacting with SQL databases.
Steam Toolkit.
Zapier Toolkit.
Tools provide access to various resources and services.
LangChain has a large ecosystem of integrations with various external resources like local and remote file systems, APIs and databases.
These integrations allow developers to create versatile applications that combine the power of LLMs with the ability to access, interact with and manipulate external resources.
When developing an application, developers should inspect the capabilities and permissions of the tools that underlie the given agent toolkit, and determine whether permissions of the given toolkit are appropriate for the application.
See Security for more information.
Toolkits for agents.
CogniSwitch Toolkit
Jira Toolkit.
Apache Cassandra Toolkit.
Json agent.
Zapier Toolkit.
Spark SQL agent.
This module contains the ConneryToolkit.
financial datasets toolkit.
Slack toolkit.
SQL agent.
Office365 toolkit.
Gmail toolkit.
AINetwork toolkit.
Local file management toolkit.
GitLab Toolkit.
Steam Toolkit.
NASA Toolkit
Playwright browser toolkit.
GitHub Toolkit.
Polygon Toolkit
MultiOn Toolkit.
OpenAPI spec agent.
Power BI agent.