Snehil-Shah/Multimodal-Image-Search-Engine
Text to Image & Reverse Image Search Engine built upon Vector Similarity Search utilizing CLIP VL-Transformer for Semantic Embeddings & Qdrant as the Vector-Store
This tool helps you find images based on their content and context, not just keywords. You provide either a text description or an example image, and it returns visually similar images from a large collection. It's ideal for anyone who needs to quickly locate specific images without having to precisely tag or keyword every single one.
Use this if you need to search a large image collection using natural language descriptions or by providing a reference image.
Not ideal if you need to search for images based on exact metadata like filenames, dates, or specific categories.
Stars
17
Forks
4
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Snehil-Shah/Multimodal-Image-Search-Engine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
comptech-winter-school/image-finder
Search relevant images by text query, using CLIP/ruCLIP embedder and HNSW index
rkouye/es-clip-image-search
Sample implementation of natural language image search with OpenAI's CLIP and Elasticsearch or...
R0GUE-A5H/CLIP-Style-Multimodal
A Multimodal AI Search Engine built from scratch using CLIP-style architecture (ViT + MPNet)....