Repo · Search & RAG

llama-index-jev

Add Jev judgments at two points in a LlamaIndex workflow: ranking retrieved passages and selecting the query engine that should handle a question.

Open github.com ↗

How builders describe it

LlamaIndex reranker + router powered by TypeSafe Jev — typed scores/choices, cheaper than LLM-as-judge.

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 56 search & rag projects →

Related projects