Delecte README.md

README.md

@@ -1,42 +0,0 @@
----
-title: VisualRAG
-emoji: 🔍
-colorFrom: purple
-colorTo: green
-sdk: gradio
-sdk_version: 4.44.1
-python_version: "3.10"
-app_file: app.py
-pinned: false
-license: mit
----
-
-# 🔍 VisualRAG — Multi-Modal AI System
-
-A production-grade **Retrieval-Augmented Generation (RAG)** system that combines computer vision and natural language understanding in a single pipeline.
-
-## 🧠 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`
-
-## 🛠 Tech Stack
-
-| Component | Technology |
-|---|---|
-| Object Detection | YOLOv8n (Ultralytics) |
-| Visual Embedding | CLIP ViT-B/32 (OpenAI) |
-| Vector Index | FAISS IndexFlatIP |
-| LLM | Zephyr-7B-β (HF Serverless API) |
-| UI | Gradio 4.44.1 |
-
-## 🚀 How to Use
-
-1. **Detect & Index tab** — Upload images. YOLOv8 detects objects and CLIP stores 512-d embeddings in FAISS
-2. **Query (RAG) tab** — Ask any natural language question; CLIP retrieves relevant images, Zephyr-7B answers
-3. **How it works tab** — Full system architecture and changelog
-
-## 🔑 Optional: HF Token
-
-Add a `HF_TOKEN` Space secret for higher LLM API rate limits  
-(Settings → Variables and secrets → New secret → Name: `HF_TOKEN`)