Repo · Search & RAG

Search with Jev and Milvus

Nine runnable notebooks combine Gemini embeddings and Milvus retrieval with Jev judgments for reranking, filtering, search stopping, routing, cache…

Open github.com ↗

How builders describe it

Nine runnable notebooks combine Gemini embeddings and Milvus retrieval with Jev judgments for reranking, filtering, search stopping, routing, cache reuse, curation, guardrails, and evaluation.

Milvus bootcamp notebooks pairing vector retrieval with typesafe judgments across nine search scenarios: reranking, context filtering, stopping criteria, routing, cache reuse, guardrails, curation and evaluation.

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