Add Hugging Face deployment configuration

DEPLOY_HUGGINGFACE.md

@@ -0,0 +1,143 @@
+# Deploying to Hugging Face Spaces
+
+This guide will help you deploy the Analytical Finance Chatbot to Hugging Face Spaces.
+
+## Prerequisites
+
+1. **Hugging Face Account**: Sign up at [huggingface.co](https://huggingface.co)
+2. **Groq API Key**: Get one from [console.groq.com](https://console.groq.com)
+
+## Step 1: Create a New Space
+
+1. Go to [huggingface.co/spaces](https://huggingface.co/spaces)
+2. Click **"Create new Space"**
+3. Fill in the details:
+   - **Space name**: `analytical-finance-chatbot` (or your choice)
+   - **License**: MIT
+   - **SDK**: Docker
+   - **Hardware**: CPU basic (free tier)
+4. Click **"Create Space"**
+
+## Step 2: Push Your Code
+
+### Option A: Using Git (Recommended)
+
+```bash
+# Add Hugging Face remote
+git remote add hf https://huggingface.co/spaces/YOUR_USERNAME/analytical-finance-chatbot
+
+# Rename README for Hugging Face
+mv README.md README_GITHUB.md
+mv README_HF.md README.md
+
+# Commit the Hugging Face config
+git add README.md Dockerfile backend/requirements.txt backend/.env.example
+git commit -m "Add Hugging Face deployment configuration"
+
+# Push to Hugging Face
+git push hf main
+```
+
+### Option B: Using Hugging Face Web Interface
+
+1. Go to your Space's **"Files"** tab
+2. Click **"Add file"** → **"Upload files"**
+3. Upload these files:
+   - `README.md` (rename README_HF.md to README.md)
+   - `Dockerfile`
+   - All `backend/` files
+   - All `frontend-next/` files
+4. Commit the changes
+
+## Step 3: Configure Secrets
+
+1. In your Space, go to **"Settings"** tab
+2. Scroll to **"Repository secrets"**
+3. Add a new secret:
+   - **Name**: `GROQ_API_KEY`
+   - **Value**: Your Groq API key
+4. Click **"Add secret"**
+
+## Step 4: Update API URL in Frontend
+
+Before deploying, update the API URL in `frontend-next/src/lib/api.js`:
+
+```javascript
+// Change from:
+const API_BASE_URL = 'http://localhost:8000';
+
+// To:
+const API_BASE_URL = process.env.NEXT_PUBLIC_API_URL || 'http://localhost:8000';
+```
+
+Then set the environment variable in Hugging Face:
+- **Name**: `NEXT_PUBLIC_API_URL`
+- **Value**: `http://localhost:8000` (backend runs on same container)
+
+## Step 5: Wait for Build
+
+1. Hugging Face will automatically build your Docker image
+2. This may take 5-10 minutes
+3. Watch the build logs in the **"Logs"** tab
+4. Once complete, your app will be live!
+
+## Step 6: Access Your App
+
+Your app will be available at:
+```
+https://huggingface.co/spaces/YOUR_USERNAME/analytical-finance-chatbot
+```
+
+## Troubleshooting
+
+### Build Fails
+
+**Check logs** in the "Logs" tab. Common issues:
+- Missing dependencies in `requirements.txt`
+- Incorrect Dockerfile syntax
+- Port conflicts (ensure using 7860)
+
+### App Doesn't Load
+
+1. Check if both services started (backend + frontend)
+2. Verify `GROQ_API_KEY` is set in secrets
+3. Check browser console for errors
+
+### API Errors
+
+1. Ensure backend is running on port 8000
+2. Verify frontend is connecting to correct API URL
+3. Check CORS settings in `backend/main.py`
+
+## Updating Your Space
+
+To update your deployed app:
+
+```bash
+# Make changes locally
+git add .
+git commit -m "Update: description of changes"
+
+# Push to Hugging Face
+git push hf main
+```
+
+Hugging Face will automatically rebuild and redeploy.
+
+## Cost & Limits
+
+- **Free tier**: CPU basic (sufficient for demo)
+- **Upgrade**: For production, consider upgrading to GPU or better CPU
+- **Persistent storage**: Conversations are stored in memory (lost on restart)
+
+## Next Steps
+
+Consider adding:
+- Persistent database (PostgreSQL on external service)
+- Authentication
+- Rate limiting
+- Analytics
+
+---
+
+**Need help?** Check [Hugging Face Spaces documentation](https://huggingface.co/docs/hub/spaces)

Dockerfile

@@ -0,0 +1,51 @@
+# Multi-stage build for production
+
+# Stage 1: Build Frontend
+FROM node:18-alpine AS frontend-builder
+
+WORKDIR /app/frontend
+
+# Copy frontend files
+COPY frontend-next/package*.json ./
+RUN npm ci
+
+COPY frontend-next/ ./
+RUN npm run build
+
+# Stage 2: Backend + Serve Frontend
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy backend files
+COPY backend/requirements.txt ./backend/
+RUN pip install --no-cache-dir -r backend/requirements.txt
+
+COPY backend/ ./backend/
+
+# Copy built frontend from previous stage
+COPY --from=frontend-builder /app/frontend/.next ./frontend/.next
+COPY --from=frontend-builder /app/frontend/public ./frontend/public
+COPY --from=frontend-builder /app/frontend/package*.json ./frontend/
+COPY --from=frontend-builder /app/frontend/node_modules ./frontend/node_modules
+
+# Create startup script
+RUN echo '#!/bin/bash\n\
+cd /app/backend && uvicorn main:app --host 0.0.0.0 --port 8000 &\n\
+cd /app/frontend && npm start -- -p 7860\n\
+wait' > /app/start.sh && chmod +x /app/start.sh
+
+# Expose port
+EXPOSE 7860
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+ENV NODE_ENV=production
+
+# Start both services
+CMD ["/app/start.sh"]

README_HF.md

@@ -0,0 +1,27 @@
+---
+title: Analytical Finance Chatbot
+emoji: 💹
+colorFrom: black
+colorTo: gray
+sdk: docker
+pinned: false
+license: mit
+app_port: 7860
+---
+
+# Analytical Finance Chatbot
+
+An AI-powered financial data analysis chatbot with an OpenAI-inspired interface.
+
+## Features
+- Real-time streaming responses
+- Financial data analysis (holdings & trades)
+- Clean, modern UI with dark mode
+- Markdown table rendering
+
+## Tech Stack
+- Backend: FastAPI + Groq AI
+- Frontend: Next.js + Tailwind CSS
+- Deployment: Docker
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

backend/.env.example

@@ -0,0 +1,2 @@
+GROQ_API_KEY=your_groq_api_key_here
+DATA_DIR=data

backend/requirements.txt

@@ -0,0 +1,5 @@
+fastapi==0.115.0
+uvicorn[standard]==0.32.0
+pandas==2.2.3
+groq==0.11.0
+python-dotenv==1.0.1

frontend-next/src/lib/api.js

@@ -1,6 +1,7 @@
 // Basic API client for the analytical backend
-
-const API_BASE_URL = 'http://localhost:8000'; // Make this configurable via env
+const API_BASE_URL = typeof window !== 'undefined' && window.location.hostname !== 'localhost'
+    ? `${window.location.protocol}//${window.location.hostname}:8000`
+    : 'http://localhost:8000';
 
 export const api = {
     // Get all conversations