Multimodal Search Engines ML Frameworks

Tools and applications for searching across image and text modalities using vision-language models like CLIP. Includes text-to-image search, image-to-image search, and video content search. Does NOT include general recommendation systems, dataset creation/filtering tools, or single-modality search applications.

There are 42 multimodal search engines frameworks tracked. 1 score above 50 (established tier). The highest-rated is rom1504/img2dataset at 61/100 with 4,380 stars.

Get all 42 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=multimodal-search-engines&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Framework	Score	Tier	Stars	Language
1	rom1504/img2dataset Easily turn large sets of image urls to an image dataset. Can download,...	61	Established	4,380	Python
2	devrimcavusoglu/pybboxes Light weight toolkit for bounding boxes providing conversion between...	49	Emerging	154	Python
3	PyRetri/PyRetri Open source deep learning based unsupervised image retrieval toolbox built...	49	Emerging	1,183	Python
4	Particle1904/DatasetHelpers Dataset Helper program to automatically select, re scale and tag Datasets...	47	Emerging	224	C#
5	salesforce/LAVIS LAVIS - A One-stop Library for Language-Vision Intelligence	46	Emerging	11,183	Jupyter Notebook
6	haltakov/natural-language-image-search Search photos on Unsplash using natural language	45	Emerging	1,036	Jupyter Notebook
7	haltakov/natural-language-youtube-search Search inside YouTube videos using natural language	43	Emerging	934	Jupyter Notebook
8	jina-ai/example-multimodal-fashion-search Input text or image, get back matching image fashion results, using Jina,...	42	Emerging	49	Python
9	RAHUL-KAD/Reverse-Image-Search-Engine With the help of this repo you can build image search algorithm on your...	39	Emerging	30	Python
10	TheoCoombes/crawlingathome A client library for LAION's effort to filter CommonCrawl with CLIP,...	39	Emerging	32	Python
11	lucko515/image-search-engine End-to-end image search engine based on the Deep learning techniques.	38	Emerging	49	Jupyter Notebook
12	masesk/process-google-dataset Process Google Dataset is a tool to download and process images for neural...	38	Emerging	33	JavaScript
13	bwconrad/video-content-search Search the content of a video with a text or image query	37	Emerging	16	Jupyter Notebook
14	zabir-nabil/bangla-image-search A dead-simple image search / retrieval and image-text matching system for...	36	Emerging	13	Python
15	huggingface/OBELICS Code used for the creation of OBELICS, an open, massive and curated...	36	Emerging	211	Python
16	TAU-VAILab/Vox-E This repo contains the python code as well as the webpage html files for the...	35	Emerging	78	Python
17	sayannath/Identical-Image-Retrieval Identical-Image-Retrieval using Deep Learning	32	Emerging	12	Jupyter Notebook
18	Zeeshier/VistAI VistAI is an AI-powered visual search for e-commerce, enabling users to...	32	Emerging	3	Python
19	thatgeeman/pybx A simple python module to generate anchor (aka default/prior) boxes for...	31	Emerging	5	Jupyter Notebook
20	Sagykri/NOVA The official repository for NOVA, a deep learning framework designed for...	31	Emerging	7	HTML
21	woctezuma/steam-image-search Search for images on Steam using natural language queries.	28	Experimental	11	Jupyter Notebook
22	Ivan-Zhou/image-search Simple Image Search powered by Multimodal Foundation Models (OpenAI Clip and...	27	Experimental	18	Python
23	Rishabh1925/scene-localization-system Powerful CLIP-based computer vision system for natural language-driven...	26	Experimental	10	HTML
24	masa-57/PIC Hierarchical image clustering API for product catalog images. Two-level...	25	Experimental	1	Python
25	santoshlite/ByteDetective The easiest way to search for images on your desktop 🔎	24	Experimental	32	Rust
26	snehilhbtu/vectalab 📊 Evaluate image quality and performance with Vectalab's vectorization tools...	23	Experimental	1	Python
27	ItzCrazyKns/Dataset-Converter A Python script for converting URL-based datasets into image datasets.	23	Experimental	4	Python
28	Subhasri-Babu/AI-Scene-Safety-Analyzer-Project AI-powered image safety analyzer using BLIP + LLaMA 3.3 via Groq API	22	Experimental	—	Jupyter Notebook
29	CN-Scars/picture_sherlock A local image search tool based on pre-trained deep learning models	22	Experimental	14	Python
30	kyegomez/VisionDatasets Open source scripts to create large scale datasets with rich detail for...	21	Experimental	11	Python
31	koushikvikram/multimodal-image-retrieval 📝🔍🖼️ A deep learning application for retrieving images by searching with text.	21	Experimental	7	Jupyter Notebook
32	TunggTungg/image_retrieval An image retrieval system that utilizes deep learning ResNet for feature...	19	Experimental	3	Jupyter Notebook
33	heydido/VisualSearchEngine This is the methodology I worked on while developing Visual Search Engine...	17	Experimental	1	—
34	MarceAriel99/simil-photo Software to detect and delete similar images in a directory	14	Experimental	20	Python
35	ajaysawandkar05/spare-part-recognition Spare part recognition system using CLIP + DINOv2 with hybrid re-ranking...	14	Experimental	—	Python
36	RishabThapliyal/Video-Scene-Classification-System AI-powered video analysis tool with natural language search inside video...	13	Experimental	—	JavaScript
37	kaeldrin-gh/image-similarity-search Image similarity search system using deep learning embeddings and FAISS indexing	13	Experimental	—	Jupyter Notebook
38	NavdeepSinghNegi999/DeepVisionIntelligence 🧠 DeepVisionIntelligence — An end-to-end multimodal AI system that...	13	Experimental	—	Python
39	raj-pulapakura/Image-Search-Engine Upload an image and find similar images easily!	12	Experimental	6	Jupyter Notebook
40	sebastiantramontana/DatasetBuilder A simple dataset builder .Net library to generate automatically random...	11	Experimental	—	C#
41	AI-technologies-for-IR-system/image-search-engine This project is about creating image search engine for the discipline...	11	Experimental	—	Jupyter Notebook
42	mrgehlot/object_detection_using_vllm Real-time vision demo using SmolVLM with llama.cpp backend	10	Experimental	1	HTML