Adding README

README.md

@@ -1,27 +1,29 @@
-# 🚀 Text-to-SQL RAG with CodeLlama - HF Deployment
+---
+# Required metadata for Hugging Face Spaces
+# Replace with your details if desired
+title: Text-to-SQL RAG with CodeLlama
+colorFrom: indigo
+colorTo: cyan
+sdk: gradio
+app_file: app.py
+python_version: "3.10"
+pinned: false
+---
 
-## 📁 **Files for Hugging Face Spaces**
+# Text-to-SQL RAG with CodeLlama
 
-This folder contains only the essential files needed for deployment to Hugging Face Spaces.
+This Space runs a Retrieval-Augmented Generation (RAG) system that converts natural language questions into SQL.
 
-### **Core Files:**
-- **`app.py`** - Main Gradio application (renamed from app_gradio.py)
-- **`requirements.txt`** - Python dependencies (renamed from requirements_hf.txt)
-- **`rag_system/`** - Complete RAG system implementation
-- **`data/`** - Vector database and sample data
-- **`prompts/`** - Prompt templates for SQL generation
+- Primary LLM: CodeLlama (via ctransformers)
+- Vector store: ChromaDB (recreated on first run if empty)
+- UI: Gradio (`app.py`)
 
-### **Deployment Steps:**
-1. Create a new HF Space with **Gradio** SDK
-2. Clone the space to your local machine
-3. Copy all files from this `hf_deployment` folder to the cloned space
-4. Push to deploy
+## Files
+- `app.py`: Gradio app entrypoint
+- `requirements.txt`: Dependencies
+- `rag_system/`: Core RAG components
+- `data/`, `prompts/`: Runtime data and prompt templates
 
-### **What's NOT Included:**
-- Test files (test_*.py)
-- Installation scripts
-- Documentation files
-- Log files
-- Development-only files
-
-Your RAG system is ready for production deployment! 🎉
+## Notes
+- SQLite databases are not committed; they are generated at runtime.
+- If the Space fails to start, check the Logs tab for missing packages and update `requirements.txt` accordingly.