Repo · Search & RAG

Siftrank

Go CLI that ranks large text collections by having a model compare small randomized batches across repeated trials until the order converges; with…

Open github.com ↗

From the repository

Use LLMs to find the needles in your haystack

How builders describe it

Go CLI that ranks large text collections by having a model compare small randomized batches across repeated trials until the order converges; with Jev it combines returned pairwise probabilities.

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