langchain-ai/langchain

Support for Sarvam Chat Model Integration

Closed this issue · 3 comments

Nightwing-77 commented

Checked other resources

  • This is a feature request, not a bug report or usage question.
  • I added a clear and descriptive title that summarizes the feature request.
  • I used the GitHub search to find a similar feature request and didn't find it.
  • I checked the LangChain documentation and API reference to see if this feature already exists.
  • This is not related to the langchain-community package.

Feature Description

It would be great if LangChain could add support for Sarvam AI
chat models. Sarvam provides LLMs optimized for Indian Languages understanding and efficiency, which could be valuable for a wide range of LangChain applications.

Use Case

Sarvam offers strong multilingual capabilities (especially for Indic and low-resource languages).

Having it as a first-class ChatModel in LangChain would enable developers to use it seamlessly within chains, agents, and RAG pipelines.

This would expand the ecosystem’s coverage of open/accessible models.

Proposed Solution

Add a new integration in langchain/chat_models similar to existing providers.

Implement SarvamChat class following the BaseChatModel interface.

Support configuration via API key and model parameters (temperature, max tokens, etc.).

Also, if this feature would be appreciated, I’d be happy to work on the implementation and open a PR.

Alternatives Considered

Right now, developers would need to write custom wrappers outside LangChain. An official integration would standardize usage and improve developer experience

Additional Context

No response

parth1609 commented

I Will be!!!