# haltakov/natural-language-image-search

Search photos on Unsplash using natural language

Repository: https://github.com/haltakov/natural-language-image-search
Canonical: https://ross.abutalabs.com/products/natural-language-image-search
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: unsplash, clip, machine-learning, computer-vision, image-search, photos
Last push: 2022-10-13T21:20:00+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2055, "days_push": 1420, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1042, forks 103 (observed 2026-08-28T04:03:20.869729+00:00)

## What it is
A demo application that searches Unsplash photos using natural language descriptions, powered by OpenAI's CLIP model over the ~2M photo Unsplash Dataset. It is provided primarily as Jupyter/Colab notebooks.

## Use cases
- search photos by describing them in plain English
- find images matching a text query without keywords
- demo CLIP zero-shot image retrieval
- build a natural language image search prototype
- explore the Unsplash dataset with semantic search

## When to choose
- you want a ready-made CLIP-based semantic photo search demo
- you want to learn how CLIP enables text-to-image retrieval
- you want to run it quickly in Colab without setup

## When to avoid
- you need a production search service with an API
- you want to search your own image collection rather than Unsplash
- you need actively maintained code with recent updates

## Facets
- artifact type: application
- maturity: maintenance
- function: search-engine, machine-learning, computer-vision, nlp
- domain: machine-learning, image-processing, computer-vision
- platform: python
- tags: clip, unsplash, semantic-image-search, jupyter-notebook, colab, search, web-server

## Member repositories
- haltakov/natural-language-image-search (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.869729+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 2026-08-30T07:02:39.968099+00:00, confidence not recorded.
  - readme: https://github.com/haltakov/natural-language-image-search (fetched 2026-08-28T04:03:20.869729+00:00, sha 077598b98a02)
- Data as of 2026-08-30T08:39:29.467469+00:00.