CalibratedDecisions.

Repo · Search & RAG

JevEmbed

Turn embeddings into choices, scores and judgments.

Open github.com ↗

From the repository

Meet JevEmbed — turn embeddings into decisions. Choose, score, and judge with your choice of embedding model.

How builders describe it

Meet JevEmbed — turn embeddings into decisions. Choose, score, and judge with your choice of embedding model.
Independent Python framework that turns embedding models into Choice, Score, and Noul decisions with Jev-style request/response schemas (API, CLI, optional HTTP server).
Research toolkit that turns embedding models into Choice, Score and Noul decision models, covering data synthesis, LoRA fine-tuning, serving, benchmarking and a playground.

The decision Jev makes

Rank candidates against a query, or answer whether a passage is relevant.

Where it fits

Search pipelines retrieve too much. These projects use Jev as a reranker or relevance check after the first search, so only useful results reach the user or the model. All 108 search & rag projects →

Related projects