Vespa
A search platform with tensor fields, lexical retrieval, and configurable multi-stage ranking.
Published by Vespa
How to use it
Define a document schema with the original text and its vector representation. A rank profile can combine ranking signals and reserve heavier model inference for a smaller candidate set.
Test candidate coverage and final ranking separately. Run Vespa locally using its documented container setup and record the ranking profile used for each comparison.
- Compatibility
- Docker, REST, Vespa schemas
- Components
- Search engine, Tensor ranking, Hybrid retrieval
- Access
- Local deployment or managed service.