Skip to content
@castorini

Castorini

Jimmy Lin's research group at the University of Waterloo

Pinned Loading

  1. anserini anserini Public

    Anserini is a Lucene toolkit for reproducible information retrieval research

    Java 1.1k 572

  2. pyserini pyserini Public

    Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

    Python 2k 489

  3. onboarding onboarding Public

    Onboarding guide to Jimmy Lin's research group at the University of Waterloo

    41 29

  4. rank_llm rank_llm Public

    RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.

    Python 578 85

  5. umbrela umbrela Public

    Python 53 8

  6. nuggetizer nuggetizer Public

    Python 23 3

Repositories

Showing 10 of 113 repositories
  • pyserini Public

    Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

    castorini/pyserini’s past year of commit activity
    Python 2,024 Apache-2.0 489 61 16 Updated Feb 27, 2026
  • rosaos Public
    castorini/rosaos’s past year of commit activity
    Python 1 0 0 1 Updated Feb 27, 2026
  • anserini Public

    Anserini is a Lucene toolkit for reproducible information retrieval research

    castorini/anserini’s past year of commit activity
    Java 1,098 Apache-2.0 572 24 14 Updated Feb 27, 2026
  • NanoKnow Public
    castorini/NanoKnow’s past year of commit activity
    Python 7 Apache-2.0 0 1 0 Updated Feb 27, 2026
  • UniIR-for-Pyserini Public Forked from TIGER-AI-Lab/UniIR

    Creates a wrapper around the original UniIR and releases a PyPI package for Pyserini integration

    castorini/UniIR-for-Pyserini’s past year of commit activity
    Python 0 MIT 18 0 3 Updated Feb 27, 2026
  • anserini-tools Public

    Evaluation tools shared across anserini, pyserini, and pygaggle

    castorini/anserini-tools’s past year of commit activity
    Python 35 30 0 0 Updated Feb 26, 2026
  • rank_llm Public

    RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.

    castorini/rank_llm’s past year of commit activity
    Python 578 Apache-2.0 85 23 (2 issues need help) 11 Updated Feb 24, 2026
  • anserini-data Public
    castorini/anserini-data’s past year of commit activity
    HTML 1 5 0 1 Updated Feb 15, 2026
  • VLM2Vec-for-Pyserini Public Forked from TIGER-AI-Lab/VLM2Vec

    This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR 2025]

    castorini/VLM2Vec-for-Pyserini’s past year of commit activity
    Python 0 Apache-2.0 52 0 0 Updated Feb 12, 2026
  • nuggetizer Public
    castorini/nuggetizer’s past year of commit activity
    Python 23 Apache-2.0 3 0 1 Updated Feb 2, 2026