Fix README metadata for Hugging Face Spaces

README.md

@@ -1,4 +1,13 @@
-<<<<<<< HEAD
+---
+title: CSFAQ Project
+emoji: 💻
+colorFrom: purple
+colorTo: red
+sdk: docker
+app_file: app.py
+pinned: false
+---
+
 # FAQ RAG Chatbot
 
 RAG chatbot for a FAQ knowledge base. Uses FAISS for vector search with dense embeddings and a BM25 hybrid retriever.
@@ -8,7 +17,11 @@ RAG chatbot for a FAQ knowledge base. Uses FAISS for vector search with dense em
 - Virtualenv with dependencies in `requirements.txt`
 
 ## Quick setup
-1. Activate virtualenv 
+1. Activate virtualenv:
+```powershell
+cd C:\Users\gupta\Desktop\faq-ai-chatbot
+myenv\Scripts\Activate.ps1
+```
 2. Install packages:
 ```powershell
 pip install -r requirements.txt
@@ -22,30 +35,31 @@ copy .env.example .env
 - `GOOGLE_GENAI_API_KEY` — API key for the Google GenAI LLM
 - `HF_TOKEN` — Hugging Face token to avoid unauthenticated download slowdowns
 
-## Building the vectorstore (recommended before first run)
-Run the one-shot builder to compute embeddings and persist the FAISS index. This avoids the expensive first-request work during normal usage.
+## Build the vectorstore
+Run once to compute embeddings and persist the FAISS index:
 
 ```powershell
 myenv\Scripts\python.exe build_index.py
 ```
 
-On first run this can take ~15–25s depending on hardware and network (model download).
+On first run this can take ~15–25s depending on hardware and network.
 
 ## Run CLI
 ```powershell
-myenv\Scripts\python.exe cli.py "What is the Vicharanashala internship?"
+myenv\Scripts\python.exe cli.py
 ```
 
 ## Run API
 ```powershell
 myenv\Scripts\python.exe -m uvicorn app:app --reload
 ```
+
 Then POST JSON to `http://127.0.0.1:8000/chat`:
 ```json
 { "question": "What is VINS?" }
 ```
 
-## Notes & guidance
+## Notes
 - The first run must compute embeddings if the index does not exist.
-- To avoid repeated downloads and speed up startup: set `HF_TOKEN` and run `build_index.py` once on the host machine.
-- If you need smaller cold-start times, consider precomputing embeddings offline or using an even smaller embedding model.
+- To avoid repeated downloads and speed up startup: set `HF_TOKEN` and run `build_index.py` once.
+- Do not commit `vectorstore/`, `myenv/`, or `.env`.