Feature request: Native Qdrant support for vector stores and reranking in the AI SDK

AI SDK
,
1

Summary

Would love to see official Qdrant support in the AI SDK, both for vector store integration and reranking.

Current Situation

Using Qdrant with AI SDK today means manually wiring embed() with @qdrant/js-client-rest. For reranking, there’s no option — you have to fall back to Cohere or Together.ai even though Qdrant has its own native reranker.

What Would Be Useful

  • A @ai-sdk/qdrant provider or a vectorstores adapter for Qdrant
  • rerank() support using Qdrant’s native reranker

Qdrant is one of the most widely adopted open-source vector databases. Upstash already has a community integration — would be great to see the same for Qdrant. Happy to help build this out if there’s interest.

References

5

Hey @yusuf-eren. I’m from the Qdrant team (anush.shetty@qdrant.com).

We’d be happy to help build/maintain this integration for the community.

Looking forward to hearing from the Vercel AI SDK team.

1 Like
6

@anush a community plugin would be great, we will be happy to add it to the list of AI SDK community providers: Community Providers. The AI SDK does support reranking and embedding, but we do not have a store abstraction built into the AI SDK, that’s currently out of scope. Maybe you can add a guide on how to use Qdrant with AI SDK using your community provider and vector store?

8

Hey @gr2m
I’m a fan of your work on Octokit.js and Semantic Release. Thank you.

but we do not have a store abstraction built into the AI SDK, that’s currently out of scope.

I see. Building a plugin without a common abstraction means users won’t have the ability to swap the vector store providers. Like with other components.

How about we have examples/guides on how to use the AI SDK with the Qdrant client instead?