RRepoGEO

REPOGEO REPORT · LITE

castorini/pyserini

Default branch master · commit e5d3a4ae · scanned 5/15/2026, 10:51:51 PM

GitHub: 2,050 stars · 514 forks

AI VISIBILITY SCORE
83 /100
Healthy
Category recall
2 / 2
Avg rank #4.0 when recommended
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface castorini/pyserini, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • hightopics#1
    Expand GitHub topics for better categorization

    Why:

    CURRENT
    information-retrieval
    COPY-PASTE FIX
    information-retrieval, ir-toolkit, python, reproducible-research, sparse-retrieval, dense-retrieval, anserini, lucene, faiss, nlp, search-engine
  • mediumreadme#2
    Strengthen README opening to highlight unique value proposition

    Why:

    CURRENT
    Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations. Retrieval using sparse representations is provided via integration with our group's Anserini IR toolkit, which is built on Lucene. Retrieval using dense representations is provided via integration with Facebook's Faiss library.
    COPY-PASTE FIX
    Pyserini is a Python toolkit for **reproducible information retrieval research**, offering a unified interface for **first-stage retrieval** with both **sparse (via Anserini/Lucene) and dense (via Faiss) representations**. It provides a self-contained, easy-to-use environment for experimenting with and evaluating IR systems on standard test collections.
  • lowcomparison#3
    Add a 'Why Pyserini?' or 'Comparison' section to the README

    Why:

    COPY-PASTE FIX
    ## ✨ Why Pyserini?
Pyserini stands out as a **unified Python toolkit** specifically designed for **reproducible information retrieval research**. Unlike general machine learning libraries, Pyserini integrates powerful sparse (Anserini/Lucene) and dense (Faiss) retrieval methods into a single, easy-to-use package. It provides prebuilt indexes, queries, and evaluation scripts for many standard IR test collections, making it ideal for researchers and practitioners focused on robust, verifiable IR experiments.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
2 / 2
100% of queries surface castorini/pyserini
Avg rank
#4.0
Lower is better. #1 = top recommendation.
Share of voice
11%
Of all named tools, what % are you?
Top rival
PyTerrier
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. PyTerrier · recommended 1×
  2. IR_datasets · recommended 1×
  3. scikit-learn · recommended 1×
  4. LightGBM · recommended 1×
  5. XGBoost · recommended 1×
  • CATEGORY QUERY
    How can I set up a reproducible information retrieval research pipeline in Python?
    you: #2
    AI recommended (in order):
    1. PyTerrier
    2. Pyserini ← you
    3. IR_datasets
    4. scikit-learn
    5. LightGBM
    6. XGBoost
    7. Pandas
    8. Polars
    9. MLflow
    10. Poetry
    11. Rye
    Show full AI answer
  • CATEGORY QUERY
    Looking for a Python library to perform first-stage retrieval using sparse and dense embeddings.
    you: #6
    AI recommended (in order):
    1. Haystack (deepset/haystack)
    2. Sentence Transformers
    3. Faiss
    4. Annoy
    5. Elasticsearch
    6. Pyserini ← you
    7. Hugging Face `transformers`
    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of castorini/pyserini?
    pass
    AI named castorini/pyserini explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts castorini/pyserini in production, what risks or prerequisites should they evaluate first?
    pass
    AI named castorini/pyserini explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo castorini/pyserini solve, and who is the primary audience?
    pass
    AI named castorini/pyserini explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of castorini/pyserini. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/castorini/pyserini.svg)](https://repogeo.com/en/r/castorini/pyserini)
HTML
<a href="https://repogeo.com/en/r/castorini/pyserini"><img src="https://repogeo.com/badge/castorini/pyserini.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

castorini/pyserini — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite