Skip to content

@castorini Castorini

Change the repository type filter

All

    Repositories list

    116 repositories

    • anserini

      Public
      Anserini is a Lucene toolkit for reproducible information retrieval research
      information-retrievallucene
      information-retrievallucene
      Java
      •
      Apache License 2.0
      •602•1.1k•30•8•Updated May 28, 2026May 28, 2026

    • pyserini

      Public
      Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
      information-retrieval
      information-retrieval
      Python
      •
      Apache License 2.0
      •522•2.1k•65•18•Updated May 28, 2026May 28, 2026

    • quackir

      Public
      QuackIR is an IR toolkit built on DuckDB
      Python
      •2•13•1•3•Updated May 28, 2026May 28, 2026

    • rank_llm

      Public
      RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.
      Python
      •
      Apache License 2.0
      •92•598•19•22•Updated May 24, 2026May 24, 2026

    • anserini-tools

      Public
      Evaluation tools shared across anserini, pyserini, and pygaggle
      Python
      •31•36•0•0•Updated May 16, 2026May 16, 2026

    • UniIR-for-Pyserini

      Public
      Creates a wrapper around the original UniIR and releases a PyPI package for Pyserini integration
      Python
      •
      MIT License
      •17•0•1•1•Updated May 6, 2026May 6, 2026

    • ura-projects

      Public
      JavaScript
      •1•0•35•0•Updated Apr 27, 2026Apr 27, 2026

    • orbit

      Public
      Open Web-Reasoning for Information Retrieval Tasks
      Python
      •
      Apache License 2.0
      •0•12•0•0•Updated Apr 24, 2026Apr 24, 2026

    • nuggetizer

      Public
      Python
      •
      Apache License 2.0
      •4•27•0•0•Updated Apr 19, 2026Apr 19, 2026

    • llm-relevance-feedback

      Public
      0•4•0•0•Updated Apr 19, 2026Apr 19, 2026

    • ragnarok

      Public
      Retrieval-Augmented Generation battle!
      Python
      •
      Apache License 2.0
      •10•67•2•1•Updated Apr 18, 2026Apr 18, 2026

    • umbrela

      Public
      Python
      •
      Apache License 2.0
      •8•56•4•3•Updated Apr 18, 2026Apr 18, 2026

    • castorini-skills

      Public
      Claude Code skills for cross-repo Castorini workflows
      Python
      •
      Apache License 2.0
      •2•2•0•0•Updated Apr 2, 2026Apr 2, 2026

    • VLM2Vec-for-Pyserini

      Public
      This repo is a fork of the original VLM2Vec repo, modified for easy Pyserini integration and released as a PyPI package.
      Python
      •
      Apache License 2.0
      •61•0•1•1•Updated Mar 18, 2026Mar 18, 2026

    • NanoKnow

      Public
      Python
      •
      Apache License 2.0
      •1•14•0•0•Updated Mar 1, 2026Mar 1, 2026

    • rosaos

      Public
      Python
      •0•4•0•1•Updated Feb 27, 2026Feb 27, 2026

    • anserini-data

      Public
      HTML
      •5•1•0•1•Updated Feb 15, 2026Feb 15, 2026

    • onboarding

      Public
      Onboarding guide to Jimmy Lin's research group at the University of Waterloo
      29•43•1•0•Updated Nov 1, 2025Nov 1, 2025

    • lmsys_nuggetize

      Public
      Python
      •
      Apache License 2.0
      •0•1•0•2•Updated Oct 9, 2025Oct 9, 2025

    • ragnarok_data

      Public
      1•6•0•0•Updated Jul 24, 2025Jul 24, 2025

    • visa

      Public
      Python
      •0•4•0•0•Updated Jun 2, 2025Jun 2, 2025

    • rlhn

      Public
      Identifying and relabeling false negatives in IR training datasets
      Apache License 2.0
      •0•10•2•0•Updated May 22, 2025May 22, 2025

    • UniRAG

      Public
      Python
      •0•13•0•0•Updated Mar 17, 2025Mar 17, 2025

    • chatserini

      Public
      TypeScript
      •
      Other
      •0•0•0•0•Updated Feb 9, 2025Feb 9, 2025

    • UniIR

      Public
      Official code for paper "UniIR: Training and Benchmarking Universal Multimodal Information Retrievers"
      Python
      •
      MIT License
      •17•1•0•1•Updated Feb 4, 2025Feb 4, 2025

    • w1kp

      Public
      w1kp: Toolkit for analyzing perceptual variability in text-to-image generation.
      aimldiffusion
      aimldiffusiont2ifoundation-modelsgenai
      Python
      •
      MIT License
      •0•2•0•0•Updated Nov 14, 2024Nov 14, 2024

    • AfriTeVa-keji

      Public
      Python
      •8•11•0•0•Updated Oct 15, 2024Oct 15, 2024

    • ragamuffin

      Public
      An in-memory, everything-on-GPU retrieval system.
      C++
      •
      MIT License
      •0•0•0•0•Updated Oct 14, 2024Oct 14, 2024

    • LiT5

      Public
      Python
      •
      Apache License 2.0
      •3•19•0•0•Updated Aug 9, 2024Aug 9, 2024

    • howl

      Public
      Wake word detection modeling toolkit for Firefox Voice, supporting open datasets like Speech Commands and Common Voice.
      wake-word-detection
      wake-word-detection
      Python
      •
      Mozilla Public License 2.0
      •31•214•29•3•Updated Jul 25, 2024Jul 25, 2024
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.