Multimodal RAG Systems RAG Tools

Tools and frameworks for retrieval-augmented generation systems that process and integrate multiple data modalities (images, text, video, audio, tables) together. Does NOT include single-modality RAG, domain-specific RAG applications, or general multimodal AI without retrieval components.

There are 105 multimodal rag systems tools tracked. 4 score above 50 (established tier). The highest-rated is illuin-tech/colpali at 59/100 with 2,555 stars. 1 of the top 10 are actively maintained.

Get all 105 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=rag&subcategory=multimodal-rag-systems&limit=20"

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

#	Tool	Score	Tier	Stars	Language
1	illuin-tech/colpali The code used to train and run inference with the ColVision models, e.g....	59	Established	2,555	Python
2	AnswerDotAI/byaldi Use late-interaction multi-modal models such as ColPali in just a few lines of code.	55	Established	844	Python
3	jolibrain/colette Multimodal RAG to search and interact locally with technical documents of any kind	51	Established	284	HTML
4	nannib/nbmultirag Un framework in Italiano ed Inglese, che permette di chattare con i propri...	50	Established	29	Python
5	OpenBMB/VisRAG Parsing-free RAG supported by VLMs	49	Emerging	932	Python
6	chiang-yuan/llamp [EMNLP '25] A web app and Python API for multi-modal RAG framework to ground...	47	Emerging	89	Jupyter Notebook
7	Leon1207/Video-RAG-master ✨✨[NeurIPS 2025] This is the official implementation of our paper...	44	Emerging	404	Python
8	cilabuniba/artseek ArtSeek: Deep artwork understanding via multimodal in-context reasoning and...	43	Emerging	10	Jupyter Notebook
9	tonywu71/colpali-cookbooks Recipes for learning, fine-tuning, and adapting ColPali to your multimodal...	42	Emerging	355	—
10	llm-lab-org/Multimodal-RAG-Survey A Survey on Multimodal Retrieval-Augmented Generation	41	Emerging	487	—
11	JuliaGenAI/ColBERT.jl Efficient late-interaction retrieval systems in Julia!	41	Emerging	18	Julia
12	deep-div/Multimodel-RAG Multimodal RAG ingests PDFs and generates combined text and image outputs by...	39	Emerging	20	Jupyter Notebook
13	ACMarcone86/artseek ArtSeek combines late-interaction retrieval over a 5M+ multimodal corpus...	38	Emerging	1	Jupyter Notebook
14	adithya-s-k/VARAG Vision-Augmented Retrieval and Generation (VARAG) - Vision first RAG Engine	37	Emerging	497	Python
15	wgcyeo/UniversalRAG UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse...	37	Emerging	161	Python
16	chg0901/Honor_of_Kings_Multi-modal_Dataset A Multi-modal RAG Project with Dataset from Honor of Kings, one of the most...	35	Emerging	73	Python
17	the-bird-F/GLM-Voice-RAG [EMNLP 2025 Findings] A complete cross-modal RAG system for end-to-end...	34	Emerging	28	Python
18	Ahmed-AI-01/Multimodal-RAG An AI-powered chat application using text, audio, and images for...	34	Emerging	2	Python
19	richard-peng-xia/RULE [EMNLP'24] RULE: Reliable Multimodal RAG for Factuality in Medical Vision...	33	Emerging	98	Python
20	joohyung00/lilac This is the public repository for "LILaC: Late Interacting in Layered...	32	Emerging	17	Python
21	MohamedMostafa259/pif-multimodal-rag A modular, multilingual, and multimodal Retrieval-Augmented Generation (RAG)...	32	Emerging	14	Python
22	zhaosuifeng/FinRAGBench-V FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the...	30	Emerging	12	Python
23	Hoar012/RAP-MLLM [CVPR 2025] RAP: Retrieval-Augmented Personalization	30	Emerging	81	Python
24	AhmedAl93/multimodal-semantic-RAG A RAG system designed to process documents with multimodal content. It can...	30	Emerging	26	Python
25	dame-cell/VisionRAG A new novel multi-modality (Vision) RAG architecture	29	Experimental	40	Jupyter Notebook
26	DataFog/vlm-api REST API for computing cross-modal similarity between images and text using...	29	Experimental	7	Python
27	ChaoLinAViy/OMGM OMGM: Orchestrate Multiple Granularities and Modalities for Efficient...	29	Experimental	13	Python
28	RodneyFinkel/groq_deepgram_agent Multi Modal Agent using Deepgram and Groq LPU's and Sentence Transformers...	28	Experimental	2	HTML
29	santiago68310/RAG-based-multimodal-agent A sophisticated Retrieval-Augmented Generation (RAG) system that combines...	27	Experimental	24	Python
30	kyopark2014/llm-multimodal-and-rag It shows how to use mutimodal and RAG based on multi-region LLM.	27	Experimental	27	Python
31	aimagelab/ReT-2 Recurrence Meets Transformers for Universal Multimodal Retrieval	27	Experimental	15	Python
32	SnowNation101/Nyx Code for the paper “Towards Mixed-Modal Retrieval for Universal...	27	Experimental	15	Python
33	Azure-Samples/multimodal_rag_python Python notebook for solving overlapping tables problem with Azure document...	27	Experimental	9	Jupyter Notebook
34	DuhanJishnu/NeuraNexus Offline Multimodal RAG System for Unified Retrieval from Text, Image, and Audio Data	26	Experimental	1	TypeScript
35	cany7/LumiCite LumiCite is a multimodal RAG system for academic papers, designed for...	26	Experimental	2	Python
36	naimkatiman/Multi-Modal-RAG-Pipeline-on-Images-and-Text-Locally My first Multi-Modal RAG pipeline....Dummy version	25	Experimental	5	Jupyter Notebook
37	RecSys-lab/RAG-VisualRec 🧠 A Resource for Multi-Modal Learning in Visual RAGs	25	Experimental	3	Jupyter Notebook
38	MMDocRAG/MMDocRAG The code used to train and run inference with MMDocRAG	24	Experimental	15	JavaScript
39	seth-woo/mkrs-optional-memory Multimodal Knowledge Retrieval System with Optional Memory (MKRS)	24	Experimental	1	Python
40	Alijanloo/MultiModalRag A Multi-Modal Agentic RAG pipeline designed to handle unstructured documents...	24	Experimental	4	Python
41	Rayen-Hamza/Klippy A text-centric multimodal local first RAG system with knowledge graph...	23	Experimental	2	Python
42	starsuzi/VideoRAG VideoRAG: Retrieval-Augmented Generation over Video Corpus	23	Experimental	77	Python
43	jiangnanboy/pdf_multimodal_rag pdf multimodal rag 【pdf多模态rag问答】	22	Experimental	27	Python
44	THE-S0HAM/OmniWhale-RAG Generalized, Offline-First Multimodal AI System	22	Experimental	4	Python
45	GenCEO/mm-rag-playbook Lightweight multimodal RAG patterns for PDF-like documents	22	Experimental	1	Python
46	CKeibel/FHSWF-deep-learning Multimodal RAG and comparisons between language models. (Project for Deep...	21	Experimental	1	Jupyter Notebook
47	connectpool/multimodal-rag-lab Compact multimodal RAG baseline with chunking, BM25 retrieval and prompt assembly.	21	Experimental	—	Python
48	medazizsaaadallah/Knowledge-Infused-Multimodal-Retrieval-A-RAG-Based-Approach-for-Context-Aware-Image-Understanding 🌟 Enhance image understanding through a RAG-based approach, combining...	21	Experimental	—	Jupyter Notebook
49	SainathPattipati/multi-modal-rag RAG over images, PDFs, tables, and structured data — unified retrieval...	21	Experimental	—	Python
50	alilooop/AssetRetrieval3D 🌐 Retrieve 3D assets effortlessly using text or images with this multi-modal...	21	Experimental	—	Python
51	ResearchAgents/multimodal-doc-rag A lightweight pipeline for multimodal document retrieval and QA using...	21	Experimental	—	Python
52	aniketpoojari/Enterprise-AI-Assistant-MCP Production-grade Multi-Modal RAG system for intelligent document Q&A with...	21	Experimental	—	Python
53	nicolas-len/gcp-multimodal-ai-rag Multimodal AI knowledge base, RAG on GCP with Gemini parsing, BigQuery...	21	Experimental	—	Jupyter Notebook
54	id4thomas/psi-king Framework for building Multimodal Document Retrievers	21	Experimental	3	Jupyter Notebook
55	forfrt/vgsg_rag Visual Grounded Story Generation with RAG	20	Experimental	2	Jupyter Notebook
56	RazerArdi/Knowledge-Infused-Multimodal-Retrieval-A-RAG-Based-Approach-for-Context-Aware-Image-Understanding A modular RAG-based framework for image retrieval and context-aware...	20	Experimental	1	Jupyter Notebook
57	Bhavik-Ardeshna/Multimodal-VideoRAG Multimodal-VideoRAG: Using BridgeTower Embeddings and Large Vision Language Models	20	Experimental	5	Jupyter Notebook
58	tph-kds/TriModalRAG_System *Built upon the integration of text, image, and audio modalities, this...	19	Experimental	4	Python
59	SubhamIO/Multimodal-RAG-System Handle mixture of content types, including text, tables and images using...	19	Experimental	2	Jupyter Notebook
60	simoncampos1022/RAG-System-arXivRAG-Multimodal-Conversational A practical, multimodal-multilingual RAG chatbot application powered by...	19	Experimental	2	Python
61	TioeAre/BayesRAG BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal...	19	Experimental	5	Python
62	DngBack/HPC-ColPali Implementation of Hierarchical Patch Compression for ColPali: Efficient...	19	Experimental	2	Python
63	adam-aimoscloud/MoleSearch Multimodal data Retriever, including text, image, video, audio	18	Experimental	1	Python
64	neha-nambiar/Retrieval-Augmented-Multimodal-AI-for-Engineering-Homework-Solving Engineering Homework solver using ColPali PDF retrieval, Qwen2.5-VL...	18	Experimental	1	Python
65	selvatharrun/Multimodal-RAG-Application A comprehensive Multimodal Retrieval-Augmented Generation (RAG) application...	18	Experimental	1	Jupyter Notebook
66	WizKnight/MultimodalMovieRAG A multimodal movie search engine using RAG techniques. It allows users to...	17	Experimental	1	Python
67	AliHamzaAzam/multimodal-rag Multimodal RAG system with CLIP embeddings, FAISS search, and MLX-powered Mistral LLM	17	Experimental	—	Python
68	Ghost-141/Multi-Modal-Local-RAG A Multi-Modal RAG Pipeline with Local LLMs	17	Experimental	—	Python
69	SungJuyeon/multimodal_RAG_System 이미지, 영상을 업로드하여 질의응답하는 시스템	17	Experimental	—	Jupyter Notebook
70	muthusamir/GraphMultimodalRAG Enhancing Vision-Language Retrieval with Graph-Based and Multimodal RAG Integration	17	Experimental	—	Python
71	sakshamVerma08/MultiModal-RAG-Practice- Multi-Modal RAG: Retrieval-Augmented Generation over Text and Visual PDFs A...	17	Experimental	—	—
72	Koushiki-Chakraborty/Multimodal-Question-Answering Collaborative research exploring multimodal question answering using OCR,...	16	Experimental	1	—
73	MMDocRAG/MMDocIR The code used to train and run inference with MMDocIR	16	Experimental	32	JavaScript
74	Ashutosh-AIBOT/multimodal-rag-research-assistant Multi-source RAG assistant — chat with PDFs, research YouTube channels,...	16	Experimental	2	Python
75	Nir0g0/Multimodal-RAG This project is a multimodal Retrieval-Augmented Generation (RAG) system...	15	Experimental	2	Python
76	winstonbartlegod/enhanced-multimodal-rag Advanced document analysis and chat app with Mistral OCR, Marker (Gemini 2.5...	15	Experimental	2	Python
77	RS2002/Image2Music Official Repository for The Paper, Zero-Effort Image-to-Music Generation: An...	15	Experimental	2	Python
78	Arnav000/Multimodal-RAG This repository contains a full-stack Multimodal Retrieval-Augmented...	15	Experimental	1	Python
79	AnithaKarre/multimodel_RAG Multimodal RAG pipeline that ingests PDFs, Word docs, CSVs, Excel files, and...	14	Experimental	—	Python
80	RitamPatra/rag-project Multimodal RAG chatbot	14	Experimental	—	Jupyter Notebook
81	jthiruveedula/multimodal-rag-pipeline End-to-end Multimodal RAG pipeline ingesting PDFs, images, and audio using...	14	Experimental	—	Python
82	rutvik29/multimodal-rag Production multimodal RAG pipeline: ingests PDFs, images, and tables with...	14	Experimental	—	Python
83	robustvisrag/RobustVisRAG CVPR26 - RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented...	14	Experimental	1	—
84	Sreyan88/RECAP Code for ICASSP 2024 Paper: RECAP: Retrieval-Augmented Audio Captioning	14	Experimental	15	Python
85	emrekuruu/local-multimodal-personal-knowledge-base A multi-hop multimodal RAG system to chat with your PDFs locally, using...	14	Experimental	1	Python
86	Schinkenwurst/lightmrag Lightweight multimodal RAG baseline with late-fusion retrieval	13	Experimental	—	Python
87	isatyamks/multimodal-rag Multimodal RAG system for generating test cases and use cases from documents...	13	Experimental	—	Python
88	sgxs2014/mmrag-toolkit A minimal toolkit for Multimodal RAG — retrieve images and text, ground...	13	Experimental	—	Python
89	prakhar175/multimodal-RAG-application Multimodal pdf based RAG application where it scans the pdf for text and...	13	Experimental	—	Jupyter Notebook
90	easy1ive/modality-router-kit Lightweight modality-aware query router for multimodal RAG experiments	13	Experimental	—	Python
91	Moncef-Bj/cv-papers-rag Multimodal RAG system for Computer Vision research papers with intelligent...	13	Experimental	—	Python
92	Shubin-vadim/Arxplover Comprehensive multimodal system for analyzing documents with support for...	13	Experimental	—	HTML
93	amitkumarj441/mRAG-gim Code for CIKM'25 paper - Multimodal RAG Enhanced Visual Description	13	Experimental	—	Python
94	suncatchin/visual-rag Lightweight multimodal RAG pipeline for image-and-text understanding — CLIP...	13	Experimental	—	Python
95	thomaskty/HybridRag Multi-modal RAG system with vector embeddings for text retrieval, GPT-4V for...	12	Experimental	1	Python
96	montoyitadevelp/multi-vector-image-retrieval Multimodal approach with memory and speed optimization for RAG systems	12	Experimental	1	Jupyter Notebook
97	Cyangen/RAG Multimodal RAG	11	Experimental	4	Jupyter Notebook
98	Gabya06/cat_breeds A multimodal RAG system powered by Gemini and ChromaDB that lets you explore...	11	Experimental	1	Jupyter Notebook
99	anusha-chebolu/multimodal-rag A multimodal RAG application using Qwen 2.5 VL, ColPali, and QdrantDB for...	11	Experimental	3	Jupyter Notebook
100	YeonwooSung/vision-rag Vision-based RAG	11	Experimental	2	Python
101	dongxuecheng/SafetyVision-RAG AI-Powered Safety Hazard Detection System using VLM and...	10	Experimental	1	Python
102	SJ9VRF/Multimodal-RAG Multimodal RAG using LangChain and Vertex AI for advanced document search...	10	Experimental	2	Python
103	K0EKJE/VLM-Based-Retrieval-Augmented-Generation Stanford NLP course group project repo. RAG based on VLM retriever for...	10	Experimental	2	Python
104	Lizhecheng02/MultiModal Basic implementation code for multimodal models and some applications or...	10	Experimental	2	Jupyter Notebook
105	pynterest83/VDT-UniversalRAG Multimodal RAG for Vietnamese	10	Experimental	1	Jupyter Notebook

Comparisons in this category

VisRAG and VARAG (49 vs 37) Multimodal-RAG-Survey and UniversalRAG (41 vs 37)