-
Notifications
You must be signed in to change notification settings - Fork 91
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.
Already on GitHub? Sign in to your account
馃巸[Provider Request]: Implement Vespa as an Vector DB #1084
Labels
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Description
A Vector Database provider is designed to facilitate nearest-neighbor lookups.
Vespa is a popular open-source vector database that stores, indexes, and manages vector embeddings.
Featureform supports vector databases like Pinecone, Redis, and Weaviate.
In Featureform, Vector DBs share several similarities with an inference store but are distinguished by their support for the client.nearest API. Configuration is typically done when registering an embedding associated with an entity. This setup enables efficient retrieval of nearest neighbors based on feature vectors.
Current Behavior
No response
Desired Behavior
Implement Vespa as a vector database so that it can be registered as a provider in Featureform.
Benefits
With Vespa provider support, users can manage and version their ML embeddings with Featureform while leveraging Vespa's indexing, storage, and nearest-neighbor lookups.
Possible Implementation
It should implement the https://github.com/featureform/featureform/blob/main/provider/online.go#L36 interface.
Look at https://github.com/featureform/featureform/blob/main/provider/pinecone.go for inspiration
Additional Context
No response
The text was updated successfully, but these errors were encountered: