jev-reranker
Jev-powered relevance filtering and reranking for RAG in Python.
How it uses Jev
jev-reranker: Relevance Filtering & Reranking for RAG
Highlights
- Relevance filtering scores documents for their contribution to an answer,
- A configurable threshold determines which documents to keep. Results are sorted
- Prompts are Python dictionaries. You can change the instructions and criteria
- Long candidate lists are split automatically. Document limits and split budgets
- Sync and async methods share request handling, concurrency limits, retries,
- Optional details record all scores, including excluded documents, along with
Getting started
Requires Python 3.11+ and a TypeSafe API key. Jev API usage is billed by the service.
- Language
- Python 100%
- License
- MIT
- Latest release
- v0.1.2
- Last activity
- Sep 2026
- Added
- 2026-09-21
- Stars at snapshot
- 6
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.