Skip to main content

Contribute Integrations

To begin, make sure you have all the dependencies outlined in guide on Contributing Code.

There are a few different places you can contribute integrations for LangChain:

  • Community: For lighter-weight integrations that are primarily maintained by LangChain and the Open Source Community.
  • Partner Packages: For independent packages that are co-maintained by LangChain and a partner.

For the most part, new integrations should be added to the Community package. Partner packages require more maintenance as separate packages, so please confirm with the LangChain team before creating a new partner package.

In the following sections, we'll walk through how to contribute to each of these packages from a fake company, Parrot Link AI.

Community package​

The @langchain/community package is in libs/langchain-community and contains most integrations.

It can be installed with e.g. npm install @langchain/community, and exported members can be imported with code like

import { ChatParrotLink } from "@langchain/community/chat_models/parrot_link";
import { ParrotLinkLLM } from "@langchain/community/llms/parrot_link";
import { ParrotLinkVectorStore } from "@langchain/community/vectorstores/parrot_link";

The @langchain/community package relies on manually-installed dependent packages, so you will see errors if you try to import a package that is not installed. In our fake example, if you tried to import ParrotLinkLLM without installing parrot-link-sdk, you would see an error telling you that the package failed to import.

Let's say we wanted to implement a chat model for Parrot Link AI. We would create a new file in libs/langchain-community/src/chat_models/parrot_link.ts with something like the following code:

import {
  SimpleChatModel,
} from "@langchain/core/language_models/chat_models";

export class ChatParrotLink extends SimpleChatModel {

  ...

Tests are colocated in the src/ directory, so you could write them in files like the below:

  • Unit tests: libs/langchain-community/src/chat_models/tests/parrot_link.test.ts
  • Integration tests: libs/langchain-community/src/chat_models/tests/parrot_link.int.test.ts

Unit tests should not have any external API calls or require any environment variables.

You should add documentation to:

  • docs/core_docs/docs/integrations/chat/parrot_link.mdx

Partner package in LangChain repo​

Partner packages can be hosted in the LangChain monorepo.

Partner packages in the LangChain repo should be placed under libs/langchain-{partner}

A package is installed by users with npm install @langchain/{partner}, and the package members can be imported with code like:

import { X } from "@langchain/{partner}";

Set up a new package​

To set up a new partner package, you can use create-langchain-integration, a utility that will automatically scaffold a repo with support for both ESM + CJS entrypoints. You can run it like this within the libs/ folder:

cd libs/
npx create-langchain-integration

Then, follow the prompts to name your package. The default package will include stubs for a Chat Model, an LLM, and/or a Vector Store. You should delete any of the files you won't use and remove them from index.ts.

Dependencies​

If your package needs dependencies, such as your company's SDK, you can add them to your package's package.json file as normal:

npm install parrot-link-sdk

Write Unit and Integration Tests​

Some basic tests are presented in the src/tests/ directory. You should add more tests to cover your package's functionality.

For information on running and implementing tests, see the Testing guide.

Write documentation​

Please copy and use the appropriate template from here:

https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-scripts/src/cli/docs/templates

You should place the notebooks with examples in the relevant docs/core_docs/docs/integrations directory in the monorepo root.

(If Necessary) Deprecate community integration​

Note: this is only necessary if you're migrating an existing community integration into a partner package. If the component you're integrating is net-new to LangChain (i.e. not already in the community package), you can skip this step.

Let's pretend we migrated our ChatParrotLink chat model from the community package to the partner package. We would need to deprecate the old model in the community package. We can do this using a @deprecated TSDoc comment.

Before our change, our chat model might look like this:

class ChatParrotLink extends SimpleChatModel {
  ...

After our change, it would look like this:

/** @deprecated Install and import from `@langchain/parrot-link` instead. */
class ChatParrotLink extends SimpleChatModel {
  ...

You should do this for each component that you're migrating to the partner package.

Was this page helpful?


You can also leave detailed feedback on GitHub.