SEARCHSearch & retrieval
Jev for Knowledge Graph Retrieval
Mike Lembo@mike_lembo
Jev enhances knowledge graph retrieval by improving accuracy and reducing the need for follow-up searches, with a minimal latency increase.
The best use of @typesafeai 's Jev so far is knowledge graph retrieval. By adding ~100ms of latency to my searches Jev was able to improve retrieval accuracy by more than 2x. Most searches are a one-shot now. x.com/mike_lembo/status/210212435793401493
Related builds
Vectorless RAG with Jev
This project introduces a novel approach to Retrieval Augmented Generation (RAG) that replaces traditional embedding methods with a structured, table-of-contents-based navigation system, significantly improving speed and reducing costs by offloading non-generative tasks to Jev.
