Skip to main content
Integrations are a core component of LangChain. LangChain provides standard interfaces for several different components (language models, vector stores, etc) that are crucial when building LLM applications. Implementing a new integration helps expand LangChain’s ecosystem and makes your service discoverable to millions of developers.
New integrations are not accepted as PRs to any langchain-ai repository. All new integrations must be published as independent packages to PyPI (e.g., langchain-yourprovider). The only PR you should open to a langchain-ai repo is to list your published package in the docs: either a YAML row for the download table, or a hosted guide if you meet the eligibility criteria.

​
Why implement a LangChain integration?

Discoverability

LangChain is the most used framework for building LLM applications, with over 200 million monthly downloads.

Interoperability

LangChain components expose a standard interface, allowing developers to easily swap them for each other. If you implement a LangChain integration, any developer using a different component will easily be able to swap yours in.

Best Practices

Through their standard interface, LangChain components encourage and facilitate best practices (streaming, async, etc.) that improve developer experience and application performance.

​
Components to integrate

While any component can be integrated into LangChain, there are specific types of integrations we encourage more: Integrate these ✅: Not these ❌:
  • LLMs (Text-Completion Models): Deprecated in favor of Chat Models
  • Document Loaders: High maintenance burden
  • Key-Value Stores: Limited usage
  • Document Transformers: Niche use cases
  • Model Caches: Infrastructure concerns
  • Graphs: Complex abstractions
  • Message Histories: Storage abstractions
  • Callbacks: System-level components
  • Chat Loaders: Limited demand
  • Adapters: Edge case utilities

​
How to contribute an integration

1

Implement your package

How to implement a LangChain integration

2

Pass standard tests

If applicable, implement support for LangChain’s standard test suite for your integration and successfully run them.
3

Publish integration

How to publish an integration

4

List your integration

Open a PR in the LangChain docs repo so users can find your package. Hosted guides are limited; most integrations are listed via YAML.
Default (under 50,000 monthly downloads, not featured): Add a row to scripts/data/integration_external_docs.yaml. The name column links to your docs_url (partner docs preferred, then GitHub, then PyPI or npm). Do not add a new MDX page.Hosted guide (50,000+ monthly downloads, or featured by maintainers): Create a page under src/oss/python/integrations/<component_type>/ from a template:For full steps, eligibility details, and rejection criteria, see Publish an integration.

Co-marketing

(Optional) Engage with the LangChain team for joint co-marketing.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.
Edit this page on GitHub or file an issue.