Support for Namespaces in Vector Search

[anupriya17]

Proposal:

Thank you for your amazing product in the open-source world with enterprise features. Does ManticoreSearch supports namespaces in vector search similar to how Cloudflare VectorDB or Qdrant VectorDB support them.

Namespaces provide a way to segment the vectors within your index. For example, by customer, merchant, or store ID. When a namespace is provided, only vectors within that namespace are used for the search. Namespace filtering is applied before vector search, not after.

This feature would be highly beneficial for organizing and efficiently querying vectors in various segments in single collection or table

https://developers.cloudflare.com/vectorize/best-practices/insert-vectors/#namespaces https://qdrant.tech/documentation/guides/multiple-partitions/

Checklist:

^{To be completed by the assignee. Check off tasks that have been completed or are not applicable.}

- [ ] Implementation completed - [ ] Tests developed - [ ] Documentation updated - [ ] Documentation reviewed - [ ] Changelog updated - [x] OpenAPI YAML updated and issue created to rebuild clients

[sanikolaev]

Thanks for the feature request. Manticore doesn't support it now and you have to create a separate table for each tenant, but we'll discuss if we can add easier support for it.

[anupriya17]

Thanks and looking forward to it.

[sanikolaev]

@anupriya17

This feature would be highly beneficial for organizing and efficiently querying vectors in various segments in single collection or table

Can you provide any benchmarks, studies or smth on when segmenting vectors into namespaces helps in terms of performance / accuracy?