SEARCHSearch & retrieval
Jev for Document Retrieval and Content Similarity
Vasily Betin / ajasra.eth / vasily.xtz@Vasily_onl
This project explores replacing black-box embeddings with content-relevant structural vectors for document retrieval and content similarity, using the Jev mechanism.
sympoietic.substack.com/p/protocol-entry-0
Can we replace the black-box embeddings with content-relevant structural vectors for document retrieval and content similarity? The first experiment with @typesafeai's Jev shows a good starting point.
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.
