Faraz618/VisualRAG

🔍 VisualRAG — Multi-Modal AI System

A production-grade Retrieval-Augmented Generation (RAG) system combining computer vision and natural language understanding.

🧠 Pipeline

Index: Image → YOLOv8 detection → CLIP ViT-B/32 embedding → FAISS vector store Query: Text → CLIP text embedding → cosine k-NN → Zephyr-7B answer generation

🛠 Stack

🚀 How to use

1. 1.Detect & Index — upload images; YOLOv8 detects objects, CLIP stores 512-d embeddings in FAISS
2. 2.Query (RAG) — ask a question; CLIP retrieves relevant images, Zephyr-7B answers
3. 3.How it works — full architecture overview

🔑 Optional: HF token

Settings → Variables and secrets → New secret → Name: HF_TOKEN