# AnswerDotAI/rerankers

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

Repository: https://github.com/AnswerDotAI/rerankers
Canonical: https://ross.abutalabs.com/products/rerankers
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-12-20T13:10:13+00:00

## Health v2 (maintenance only)
Score: 42/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 58, release rhythm 8, longevity 65
- inputs: {"age_days": 910, "days_push": 256, "days_rel": 659, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1629, forks 104 (observed 2026-08-28T04:05:13.899330+00:00)

## What it is
A lightweight, dependency-free Python library providing a unified API for using all common reranking and cross-encoder models. It lets developers swap between different reranking architectures (cross-encoders, LLM-based rankers, ColBERT, API rerankers) with a single handful of calls.

## Use cases
- rerank search results with a cross-encoder
- add a reranker to my RAG pipeline
- compare different reranking models with one API
- use RankGPT or ColBERT rerankers in Python
- reorder retrieved documents by relevance to a query
- unified interface for reranking models

## When to choose
- you want to experiment with or swap reranking models without rewriting pipeline code
- you need a minimal-dependency library that fits into existing retrieval pipelines
- you want support for many reranker architectures including LLM-based, late-interaction, and API rerankers

## When to avoid
- you need a single highly-optimized reranker with advanced tuning options specific to one architecture
- you need production-grade guarantees - the project describes itself as beta
- your stack is not Python

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, nlp, search-engine, rag
- domain: machine-learning
- platform: python, cross-platform
- tags: reranking, cross-encoder, unified-api, information-retrieval, lightweight, natural-language-processing, search, retrieval-augmented-generation

## Member repositories
- AnswerDotAI/rerankers (main) score 42

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:13.899330+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:48:16.005339+00:00, confidence not recorded.
  - readme: https://github.com/AnswerDotAI/rerankers (fetched 2026-08-28T04:05:13.899330+00:00, sha 9b3945d6e822)
  - registry_pypi: https://pypi.org/pypi/rerankers/json (fetched 2026-08-29T11:20:42.732682+00:00, sha 55af5321fa1d)
- Data as of 2026-08-30T08:39:29.467469+00:00.