Top AI Repos — open-source AI, indexed and scored

Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.

frutik/awesome-search

Awesome Search - this is all about the (e-commerce, but not only) search and its awesomeness

64No licencePython

View on GitHub Website

Stars: 1,552
Forks: 140
Watchers: 63
Open issues: 10
Contributors: 30

Star history, last 90 days— over 5 snapshots

2026-07-24 · 1,5522026-08-06 · 1,552

Star history, last 90 days
Date	Stars
2026-07-24	1552
2026-07-25	1552
2026-07-28	1552
2026-07-30	1552
2026-08-06	1552

Today

— stars today

This week

— stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.00%/day

From the README

# Awesome Search

<p align="center"> <a href="https://savelife.in.ua/en/about-foundation-en/" target="_blank">Support Ukrainian fight for the freedom</a> 
  
I've been building e-commerce search applications for 15+ years. Below is a list of some publications, conferences, and books that have inspired me, grouped by topic. If an item fits into multiple topics, it appears in multiple sections.

:star: Star us on GitHub — it helps!

Also you can explore this information as a [Knowledge Graph](https://frutik.github.io/awesome-search/)

*Topics*

<!-- START doctoc generated TOC please keep comment here to allow auto update -->
<!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->

- [General, fun, philosophy](#general-fun-philosophy)
- [Types of search](#types-of-search)
  - [Classic/Lexical Search](#classiclexical-search)
  - [Vectors/Semantic search](#vectorssemantic-search)
    - [Symmetric and Asymmetric semantic search](#symmetric-and-asymmetric-semantic-search)
    - [Embeddings](#embeddings)
      - [Encoder architecture](#encoder-architecture)
        - [Bi-encoders / Two towers (no interaction)](#bi-encoders--two-towers-no-interaction)
        - [Cross-encoders (early interaction)](#cross-encoders-early-interaction)
        - [ColBERT (late interaction)](#colbert-late-interaction)
      - [Vector types](#vector-types)
        - [Dense vectors](#dense-vectors)
        - [Sparse vectors](#sparse-vectors)
        - [Constructed query vectors](#constructed-query-vectors)
      - [Dimensionality handling](#dimensionality-handling)
        - [Dimensionality reduction](#dimensionality-reduction)
        - [Quantization](#quantization)
      - [Finetuning](#finetuning)
        - [Supervised finetuning](#supervised-finetuning)
        - [Knowledge distillation](#knowledge-distillation)
        - [Multimodal finetuning](#multimodal-finetuning)
    - [Vector retrieval](#vector-retrieval)
  - [Hybrid search](#hybrid-search)
    - [Reciprocal rank fusion (RRF)](#reciprocal-rank-fusion-rrf)
    - [Linear Score Combination](#linear-score-combination)
  - [Multimodal search](#multimodal-search)
    - [Multimodality Problems](#multimodality-problems)
      - [Modality Gap](#modality-gap)
      - [Contrastive Gap](#contrastive-gap)
  - [Agentic search](#agentic-search)
- [Search Quality Assurance](#search-quality-assurance)
  - [Evaluation Paradigms](#evaluation-paradigms)
    - [Session-based Evaluation](#session-based-evaluation)
    - [Query-based Evaluation](#query-based-evaluation)
      - [Random sampling](#random-sampling)
      - [Stratified sampling](#stratified-sampling)
      - [Probability-proportional-to-size sampling](#probability-proportional-to-size-sampling)
  - [Metrics](#metrics)
    - [Focused on ranking quality](#focused-on-ranking-quality)
    - [Focused on diversity of results](#focused-on-diversity-of-results)
      - [MMR](#mmr)
      - [Average Pairwise Distance, APD](#average-pairwise-distance-apd)
      - [Entropy](#entropy)
    - [Behavioral / Product / Performance](#behavioral--product--performance)
      - [Clicks](#clicks)
        - [Zero clicks](#zero-clicks)
        - [Clicks residual](#clicks-residual)
      - [Zero results](#zero-results)
  - [Evaluation Modes](#evaluation-modes)
    - [Offline](#offline)
      - [Judgements](#judgements)
        - [HUman judgements](#human-judgements)
        - [Implicite judgements](#implicite-judgements)
        - [Using LLM as judge](#using-llm-as-judge)
    - [Online](#online)
- [Areas of application](#areas-of-application)
  - [Enterprise search](#enterprise-search)
  - [e-Commerce search](#e-commerce-search)
  - [Conversational search](#conversational-search)
- [Search Results](#search-results)
  - [Retrieval](#retrieval)
    - [Relevance](#relevance)
      - [Relevance Algorithms](#relevance-algorithms)
        - [BM25](#bm25)
        - [Bayesian BM25 (BB25)](#bayesian-bm25-bb25)
  - [Ranking](#ranking)
    - [Multi-stage ranking](#multi-stage-ranking

Excerpt of 77,215 characters

Read on GitHub

Top contributors20 shown

frutik
616
github-actions[bot]
15
AdamDubnytskyy
8
tpayet
Thomas Payet · @meilisearch · France
4
Blankll
2
kacperlukawski
Kacper Łukawski · Poland
2
nikhilgarg28
2
gitcommitshow
2
epugh
1
otrosien
1
codebrain
1
otisg
1
softwaredoug
1
prakash-in21
1
marekdlugos
1
radu-gheorghe
1
AiDinho
1
mincong-h
1
akurilov
1
AaronWGoh
1

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

64/10064

Maintenance: 90%; How recently the default branch was pushed to
Releases: 25%; Recency and cadence of tagged releases
Community: 45%; Contributor breadth and bus factor
Issue backlog: 100%; Open issues measured against the size of the audience
Documentation: 100%; README depth, plus a homepage and topics
Licensing: 0%; How freely the code can be adopted

What to know before adopting

No tagged releases
Bus factor of 1 — one contributor dominates
No license — all rights reserved by default, not safe to reuse
No licence file — default copyright applies, all rights reserved.

Details

Created: 7 years ago
Last push: 18 days ago
Last release: none
Release tag: —
Releases in the last year: 0
Default branch: master
Size: 85k KB
Owner type: User
Owner location: Amsterdam area
Discovered via: topic:semantic-search
First indexed: 13 days ago
Last synced: 12 days ago

frutik/awesome-search

Awesome Search - this is all about the (e-commerce, but not only) search and its awesomeness

64No licencePython

View on GitHub Website

Stars: 1,552
Forks: 140
Watchers: 63
Open issues: 10
Contributors: 30

Star history, last 90 days— over 5 snapshots

2026-07-24 · 1,5522026-08-06 · 1,552

Star history, last 90 days
Date	Stars
2026-07-24	1552
2026-07-25	1552
2026-07-28	1552
2026-07-30	1552
2026-08-06	1552

Today

— stars today

This week

— stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.00%/day

From the README

# Awesome Search

<p align="center"> <a href="https://savelife.in.ua/en/about-foundation-en/" target="_blank">Support Ukrainian fight for the freedom</a> 
  
I've been building e-commerce search applications for 15+ years. Below is a list of some publications, conferences, and books that have inspired me, grouped by topic. If an item fits into multiple topics, it appears in multiple sections.

:star: Star us on GitHub — it helps!

Also you can explore this information as a [Knowledge Graph](https://frutik.github.io/awesome-search/)

*Topics*

<!-- START doctoc generated TOC please keep comment here to allow auto update -->
<!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->

- [General, fun, philosophy](#general-fun-philosophy)
- [Types of search](#types-of-search)
  - [Classic/Lexical Search](#classiclexical-search)
  - [Vectors/Semantic search](#vectorssemantic-search)
    - [Symmetric and Asymmetric semantic search](#symmetric-and-asymmetric-semantic-search)
    - [Embeddings](#embeddings)
      - [Encoder architecture](#encoder-architecture)
        - [Bi-encoders / Two towers (no interaction)](#bi-encoders--two-towers-no-interaction)
        - [Cross-encoders (early interaction)](#cross-encoders-early-interaction)
        - [ColBERT (late interaction)](#colbert-late-interaction)
      - [Vector types](#vector-types)
        - [Dense vectors](#dense-vectors)
        - [Sparse vectors](#sparse-vectors)
        - [Constructed query vectors](#constructed-query-vectors)
      - [Dimensionality handling](#dimensionality-handling)
        - [Dimensionality reduction](#dimensionality-reduction)
        - [Quantization](#quantization)
      - [Finetuning](#finetuning)
        - [Supervised finetuning](#supervised-finetuning)
        - [Knowledge distillation](#knowledge-distillation)
        - [Multimodal finetuning](#multimodal-finetuning)
    - [Vector retrieval](#vector-retrieval)
  - [Hybrid search](#hybrid-search)
    - [Reciprocal rank fusion (RRF)](#reciprocal-rank-fusion-rrf)
    - [Linear Score Combination](#linear-score-combination)
  - [Multimodal search](#multimodal-search)
    - [Multimodality Problems](#multimodality-problems)
      - [Modality Gap](#modality-gap)
      - [Contrastive Gap](#contrastive-gap)
  - [Agentic search](#agentic-search)
- [Search Quality Assurance](#search-quality-assurance)
  - [Evaluation Paradigms](#evaluation-paradigms)
    - [Session-based Evaluation](#session-based-evaluation)
    - [Query-based Evaluation](#query-based-evaluation)
      - [Random sampling](#random-sampling)
      - [Stratified sampling](#stratified-sampling)
      - [Probability-proportional-to-size sampling](#probability-proportional-to-size-sampling)
  - [Metrics](#metrics)
    - [Focused on ranking quality](#focused-on-ranking-quality)
    - [Focused on diversity of results](#focused-on-diversity-of-results)
      - [MMR](#mmr)
      - [Average Pairwise Distance, APD](#average-pairwise-distance-apd)
      - [Entropy](#entropy)
    - [Behavioral / Product / Performance](#behavioral--product--performance)
      - [Clicks](#clicks)
        - [Zero clicks](#zero-clicks)
        - [Clicks residual](#clicks-residual)
      - [Zero results](#zero-results)
  - [Evaluation Modes](#evaluation-modes)
    - [Offline](#offline)
      - [Judgements](#judgements)
        - [HUman judgements](#human-judgements)
        - [Implicite judgements](#implicite-judgements)
        - [Using LLM as judge](#using-llm-as-judge)
    - [Online](#online)
- [Areas of application](#areas-of-application)
  - [Enterprise search](#enterprise-search)
  - [e-Commerce search](#e-commerce-search)
  - [Conversational search](#conversational-search)
- [Search Results](#search-results)
  - [Retrieval](#retrieval)
    - [Relevance](#relevance)
      - [Relevance Algorithms](#relevance-algorithms)
        - [BM25](#bm25)
        - [Bayesian BM25 (BB25)](#bayesian-bm25-bb25)
  - [Ranking](#ranking)
    - [Multi-stage ranking](#multi-stage-ranking

Excerpt of 77,215 characters

Read on GitHub

Top contributors20 shown

frutik
616
github-actions[bot]
15
AdamDubnytskyy
8
tpayet
Thomas Payet · @meilisearch · France
4
Blankll
2
kacperlukawski
Kacper Łukawski · Poland
2
nikhilgarg28
2
gitcommitshow
2
epugh
1
otrosien
1
codebrain
1
otisg
1
softwaredoug
1
prakash-in21
1
marekdlugos
1
radu-gheorghe
1
AiDinho
1
mincong-h
1
akurilov
1
AaronWGoh
1

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

64/10064

Maintenance: 90%; How recently the default branch was pushed to
Releases: 25%; Recency and cadence of tagged releases
Community: 45%; Contributor breadth and bus factor
Issue backlog: 100%; Open issues measured against the size of the audience
Documentation: 100%; README depth, plus a homepage and topics
Licensing: 0%; How freely the code can be adopted

What to know before adopting

No tagged releases
Bus factor of 1 — one contributor dominates

Details

Created: 7 years ago
Last push: 18 days ago
Last release: none
Release tag: —
Releases in the last year: 0
Default branch: master
Size: 85k KB
Owner type: User
Owner location: Amsterdam area
Discovered via: topic:semantic-search
First indexed: 13 days ago
Last synced: 12 days ago

Top AI Repos — open-source AI, indexed and scored

frutik/awesome-search

From the README

Top contributors20 shown

Quality score

What to know before adopting

Categories

Details

frutik/awesome-search

From the README

Top contributors20 shown

Quality score

What to know before adopting

Categories

Details

Top AI Repos — open-source AI, indexed and scored

Trend

From the README

Top contributors20 shown

Quality score

What to know before adopting

Categories

Details

Trend

From the README

Top contributors20 shown

Quality score

What to know before adopting

Categories

Details