Repo · Search & RAG

Jevflix

Hybrid movie recommender: FAISS + BM25 narrow ~4,800 films to a shortlist, then TypeSafe Jev parses constraints and picks one title with a confidence…

Open github.com ↗

From the repository

Jev picks, you watch. A hybrid movie recommender: fast semantic + keyword search narrows 4,800 films to a shortlist, then TypeSafe Jev reads your constraints and picks the one film that fits - with a confidence score that decides whether to answer instantly or ask a follow-up.

How builders describe it

Hybrid movie recommender: FAISS + BM25 narrow ~4,800 films to a shortlist, then TypeSafe Jev parses constraints and picks one title with a confidence gate that either answers or asks a follow-up.

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