Update README.md

README.md

@@ -1,44 +1,50 @@
 ---
-title: Study RAG Assistant UI Mock
+title: Study RAG Assistant
 emoji: 📚
 colorFrom: blue
 colorTo: indigo
 sdk: gradio
+app_file: app.py
 pinned: false
 ---
 
-# Study RAG Assistant (UI Mock)
+# 📚 Study RAG Assistant (Functional RAG)
 
-This Space hosts a **frontend UI mock** for a "Study RAG Assistant" that supports:
-- Uploading up to **10 Jupyter notebooks (.ipynb)** and **5 PDFs**
-- Browsing sources
-- Chat / Notes / Quiz tabs
-- Citation-style UI components
-- Preview modal (mock)
+This Hugging Face Space runs a **fully functional Retrieval-Augmented Generation (RAG)** system built with:
 
-✅ **Note:** This Space is a **static UI only** (no backend connected yet).  
-It is meant to help decide the interface before wiring the real RAG pipeline.
+- Gradio (UI)
+- FAISS (vector search)
+- Sentence Transformers (embeddings)
+- Transformers (LLM generation)
+- PDF + Jupyter Notebook parsing
 
 ---
 
-## ✅ How to Deploy (Hugging Face Spaces)
+## 🚀 What It Does
 
-### 1) Create a new Space
-- Go to **Hugging Face → Spaces → Create new Space**
-- Choose **SDK: Static**
-- Name it anything (e.g., `study-rag-ui`)
+You can:
 
-### 2) Upload these files into the Space repo
-Required:
-- `index.html`  ← (your UI HTML file)
+- Upload up to 10 `.ipynb` notebooks
+- Upload up to 5 `.pdf` files
+- Index them into vector embeddings
+- Chat grounded strictly in your documents
+- Generate structured Notes
+- Generate tricky Quiz questions (10–50)
+- See citations from retrieved chunks
 
-Optional:
-- `README.md` (this file)
+---
+
+## ⚙️ How It Works
 
-### 3) Done
-Hugging Face will automatically serve `index.html`.
+1. Files are parsed and chunked
+2. Chunks are embedded using `all-MiniLM-L6-v2`
+3. FAISS stores embeddings for fast retrieval
+4. Top-k chunks are retrieved per query
+5. The LLM generates grounded responses
 
 ---
 
-## 📁 Expected Repo Structure
+## 📁 Required Files
+
+This Space must contain: