Semantic Image Search CLI

 Like

Enhance your image searching with a command-line tool enabling semantic search locally via node-mlx. Utilizing CLIP model embeddings stored as binary JSON for indexing serves rapid queries without any reliance on third parties, ensuring efficiency even with extensive image collections.

Semantic Image Search CLI screenshot 1

License model

  • Free • Open Source

Platforms

  • Mac
  • Linux
  • npm
Semantic Image Search CLI screenshot 1
Semantic Image Search CLI screenshot 2
Alternatives  
  No rating
0likes
0comments
18alternatives
0news articles

Features

Suggest and vote on features

Properties

  1.  Privacy focused

Features

  1.  No registration required
  2.  Ad-free
  3.  Works Offline
  4.  No Tracking
  5.  Command line interface
  6.  Semantic Search
  7.  AI-Powered
  8.  Local Search

 Tags

Semantic Image Search CLI News & Activities

Highlights • All activities

Recent activities

Show all activities

Semantic Image Search CLI information

  • Developed by

    Frost Beta

  • Licensing

    Open Source (MIT) and Free product.

  • Written in

  • Alternatives

    18 alternatives listed

  • Supported Languages

    • English

AlternativeTo Categories

Development, OS & Utilities, Online Services

GitHub repository

  •  550 Stars
  •  20 Forks
  •  2 Open Issues
  •   Updated Sep 16, 2024 
View on GitHub

Popular alternatives

View all

Our users have written 0 comments and reviews about Semantic Image Search CLI, and it has gotten 0 likes

Semantic Image Search CLI was added to AlternativeTo by Paul on Sep 21, 2024 and this page was last updated Sep 21, 2024. Semantic Image Search CLI is sometimes referred to as sisi.
No comments or reviews, maybe you want to be first?
Post comment/review

What is Semantic Image Search CLI?

CLI tool for semantic image search, locally without using third party APIs. Powered by node-mlx, a machine learning framework for Node.js.

The index is built by computing the embeddings of images using the CLIP model, and then stored in a binary JSON file.

Searching the images is computing cosine similarities between the query string and the indexed embeddings. There is no database involved here, everytime you do a search the computation is done for all the embeddings stored, which is very fast even when you have tens of thousands of pictures.

The JavaScript implementation of the CLIP model is in a separate module.

Official Links

AppStores & Other Links