update ignore

.github/workflows/deploy-hf.yml

@@ -0,0 +1,22 @@
+name: Deploy to Hugging Face Spaces
+
+on:
+  push:
+    branches: [ main, master ]
+  pull_request:
+    branches: [ main, master ]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - uses: actions/checkout@v3
+    
+    - name: Deploy to Hugging Face Spaces
+      uses: huggingface/huggingface_hub@main
+      with:
+        token: ${{ secrets.HF_TOKEN }}
+        repo_id: ${{ secrets.HF_REPO_ID }}
+        space_sdk: docker
+        space_hardware: cpu-basic 

.gitignore

@@ -49,3 +49,20 @@ huggingface/
 *.csv
 *.tsv
 *.js*
+
+# Vector stores and binary data
+vector_store/
+*.faiss
+*.index
+*.bin
+
+# Database files
+*.db
+*.sqlite
+*.sqlite3
+
+# Temporary files and caches
+temp/
+tmp/
+.cache/
+cache/

.huggingface.yaml

@@ -1,2 +1,10 @@
-# .huggingface.yaml
+# Hugging Face Spaces Configuration
 sdk: docker
+title: Dubsway Video AI
+emoji: 🎥
+colorFrom: blue
+colorTo: purple
+sdk_version: 0.0.20
+app_file: app/main.py
+pinned: false
+license: mit

DEPLOYMENT_SUMMARY.md

@@ -0,0 +1,58 @@
+# 🚀 Quick Deployment Summary
+
+## ✅ Files Created/Updated for Hugging Face Deployment
+
+1. **`.huggingface.yaml`** - Hugging Face Spaces configuration
+2. **`Dockerfile`** - Optimized for HF Spaces with CPU-only PyTorch
+3. **`requirements-hf.txt`** - Lightweight dependencies for deployment
+4. **`app/main.py`** - Added health checks and root endpoints
+5. **`.github/workflows/deploy-hf.yml`** - GitHub Actions workflow
+6. **`deploy-to-hf.bat`** - Windows deployment helper script
+7. **`HUGGINGFACE_DEPLOYMENT.md`** - Complete deployment guide
+
+## 🎯 Quick Deployment Steps
+
+### 1. Push to GitHub
+```bash
+git add .
+git commit -m "Deploy to Hugging Face Spaces"
+git push origin main
+```
+
+### 2. Create Hugging Face Space
+1. Go to [huggingface.co/spaces](https://huggingface.co/spaces)
+2. Click "Create new Space"
+3. Settings:
+   - **SDK**: Docker
+   - **License**: MIT
+   - **Connect to your GitHub repo**
+
+### 3. Set Environment Variables
+In your Space settings, add:
+```
+GROQ_API_KEY=your_groq_api_key
+DATABASE_URL=sqlite+aiosqlite:///./dubsway_hf.db
+SECRET_KEY=your_secret_key
+ENVIRONMENT=production
+```
+
+### 4. Deploy
+- Hugging Face will automatically build and deploy
+- Monitor build logs in your Space
+- Your API will be available at: `https://your-username-dubsway-video-ai.hf.space/`
+
+## 🔍 Test Your Deployment
+
+1. **Health Check**: `GET /health`
+2. **API Docs**: `GET /docs`
+3. **Root Endpoint**: `GET /`
+
+## 📞 Need Help?
+
+- Run `deploy-to-hf.bat` for step-by-step guidance
+- Check `HUGGINGFACE_DEPLOYMENT.md` for detailed instructions
+- Monitor build logs in your Hugging Face Space
+
+---
+
+**Your Dubsway Video AI is ready for deployment! 🎉** 

Dockerfile

@@ -1,33 +1,47 @@
-# Use a lightweight Python image
+# Use a lightweight Python image optimized for ML workloads
 FROM python:3.10-slim
 
 # Set working directory
 WORKDIR /app
 
-RUN git config user.email "[email protected]" && \
-    git config user.name "peace2024"
+# Set environment variables for better performance
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV DEBIAN_FRONTEND=noninteractive
 
 # Install system-level dependencies
 RUN apt-get update && \
-    apt-get install -y ffmpeg libsndfile1 wget curl git && \
-    rm -rf /var/lib/apt/lists/*
+    apt-get install -y \
+    ffmpeg \
+    libsndfile1 \
+    wget \
+    curl \
+    git \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
 
 # Copy requirements first to leverage Docker layer caching
-COPY requirements.txt .
+COPY requirements-hf.txt .
 
-# Upgrade pip and install dependencies
+# Upgrade pip and install Python dependencies
 RUN pip install --no-cache-dir --upgrade pip && \
-    pip install --no-cache-dir -r requirements.txt
-    pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
+    pip install --no-cache-dir -r requirements-hf.txt
+
+# Install PyTorch with CUDA support (will fall back to CPU if no GPU)
+RUN pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
 
 # Copy the entire app source code
 COPY . .
 
+# Create necessary directories
+RUN mkdir -p vector_store logs
+
 # Expose port 7860 (used by Hugging Face Spaces)
 EXPOSE 7860
 
-# Set environment variables (if needed)
-ENV PYTHONUNBUFFERED=1
+# Health check
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:7860/docs || exit 1
 
-# Run the FastAPI app via Uvicorn
-CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]
+# Run the FastAPI app via Uvicorn with optimized settings
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]

HUGGINGFACE_DEPLOYMENT.md

@@ -0,0 +1,162 @@
+# 🚀 Hugging Face Spaces Deployment Guide
+
+This guide will help you deploy your Dubsway Video AI system to Hugging Face Spaces via GitHub.
+
+## 📋 Prerequisites
+
+1. **GitHub Repository**: Your code should be pushed to a GitHub repository
+2. **Hugging Face Account**: Create an account at [huggingface.co](https://huggingface.co)
+3. **Environment Variables**: Set up your API keys and configuration
+
+## 🔧 Step-by-Step Deployment
+
+### 1. Prepare Your Repository
+
+Your repository should already have the necessary files:
+- `.huggingface.yaml` - Hugging Face Spaces configuration
+- `Dockerfile` - Container configuration
+- `requirements-hf.txt` - Optimized dependencies
+- `app/main.py` - FastAPI application
+
+### 2. Set Up Environment Variables
+
+In your Hugging Face Space settings, add these environment variables:
+
+```bash
+# Required for Groq LLM
+GROQ_API_KEY=your_groq_api_key_here
+
+# Database (use SQLite for simplicity)
+DATABASE_URL=sqlite+aiosqlite:///./dubsway_hf.db
+
+# AWS S3 (optional - for file storage)
+AWS_ACCESS_KEY_ID=your_aws_access_key
+AWS_SECRET_ACCESS_KEY=your_aws_secret_key
+AWS_REGION=us-east-1
+S3_BUCKET_NAME=your_s3_bucket_name
+
+# Application
+SECRET_KEY=your_secret_key_here
+ALGORITHM=HS256
+ACCESS_TOKEN_EXPIRE_MINUTES=30
+
+# Environment
+ENVIRONMENT=production
+```
+
+### 3. Create Hugging Face Space
+
+1. Go to [huggingface.co/spaces](https://huggingface.co/spaces)
+2. Click "Create new Space"
+3. Choose settings:
+   - **Owner**: Your username
+   - **Space name**: `dubsway-video-ai` (or your preferred name)
+   - **License**: MIT
+   - **SDK**: Docker
+   - **Visibility**: Public or Private
+
+### 4. Connect GitHub Repository
+
+1. In your Space settings, go to "Repository" tab
+2. Select "Connect to existing repository"
+3. Choose your GitHub repository
+4. Set the branch (usually `main` or `master`)
+
+### 5. Configure Build Settings
+
+The Space will automatically use:
+- `.huggingface.yaml` for configuration
+- `Dockerfile` for container build
+- `requirements-hf.txt` for dependencies
+
+### 6. Deploy
+
+1. Push your changes to GitHub
+2. Hugging Face will automatically build and deploy
+3. Monitor the build logs in your Space
+
+## 🔍 Verification
+
+Once deployed, you can:
+
+1. **Check the API**: Visit `https://your-username-dubsway-video-ai.hf.space/`
+2. **View Documentation**: Visit `https://your-username-dubsway-video-ai.hf.space/docs`
+3. **Health Check**: Visit `https://your-username-dubsway-video-ai.hf.space/health`
+
+## 🛠️ API Endpoints
+
+Your deployed API will have these endpoints:
+
+- `GET /` - Root endpoint with API info
+- `GET /health` - Health check
+- `GET /docs` - Interactive API documentation
+- `POST /api/auth/register` - User registration
+- `POST /api/auth/login` - User login
+- `POST /api/upload/video` - Video upload and analysis
+- `GET /api/dashboard/videos` - Get user videos
+- `POST /api/custom-chatbot/chat` - Chat with video content
+
+## 🔧 Troubleshooting
+
+### Common Issues
+
+1. **Build Failures**:
+   - Check the build logs in your Space
+   - Ensure all dependencies are in `requirements-hf.txt`
+   - Verify Dockerfile syntax
+
+2. **Environment Variables**:
+   - Make sure all required env vars are set in Space settings
+   - Check for typos in variable names
+
+3. **Memory Issues**:
+   - The Space uses CPU-only PyTorch to save memory
+   - Consider using smaller models for production
+
+4. **Database Issues**:
+   - Use SQLite for simplicity in Spaces
+   - Ensure database directory is writable
+
+### Monitoring
+
+- Check Space logs for errors
+- Monitor resource usage
+- Test API endpoints regularly
+
+## 🔄 Continuous Deployment
+
+Once connected to GitHub:
+1. Push changes to your repository
+2. Hugging Face automatically rebuilds and deploys
+3. Monitor deployment status in your Space
+
+## 📊 Performance Optimization
+
+For better performance in Hugging Face Spaces:
+
+1. **Use CPU-only PyTorch**: Already configured in Dockerfile
+2. **Optimize model loading**: Models are loaded on first request
+3. **Use SQLite**: Lighter than PostgreSQL for Spaces
+4. **Cache results**: Implement caching for repeated requests
+
+## 🔐 Security Considerations
+
+1. **API Keys**: Store sensitive keys in Space environment variables
+2. **CORS**: Configure allowed origins for production
+3. **Rate Limiting**: Implement rate limiting for public APIs
+4. **Input Validation**: Validate all user inputs
+
+## 📞 Support
+
+If you encounter issues:
+1. Check the build logs in your Space
+2. Review the troubleshooting section
+3. Check Hugging Face Spaces documentation
+4. Monitor your application logs
+
+---
+
+**Happy Deploying! 🎉**
+
+Your Dubsway Video AI system will be accessible at:
+`https://your-username-dubsway-video-ai.hf.space/` 

app/main.py

@@ -1,19 +1,25 @@
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 import logging
+import os
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
 
 from app.auth import router as auth_router
 from app.upload import router as upload_router
 from app.dashboard import router as dashboard_router
 from app.agent.custom_chatbot import router as custom_chatbot_router
 # from app.routes import pdf_ingestion
+
 # Initialize logger
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
 app = FastAPI(
     title="Dubsway Video AI",
-    description="Production-ready API for auth, video upload, and analysis",
+    description="Production-ready API for auth, video upload, and analysis with Groq LLM integration",
     version="1.0.0",
     docs_url="/docs",  # Optional: secure this in prod
     redoc_url=None,
@@ -35,10 +41,26 @@ app.include_router(dashboard_router, prefix="/api", tags=["Dashboard"])
 app.include_router(custom_chatbot_router, prefix="/api", tags=["Custom Chatbot"])
 # app.include_router(pdf_ingestion.router, prefix="/api", tags=["PDF Ingestion"])
 
+@app.get("/")
+async def root():
+    """Root endpoint for Hugging Face Spaces"""
+    return {
+        "message": "🎥 Dubsway Video AI API",
+        "version": "1.0.0",
+        "docs": "/docs",
+        "status": "running"
+    }
+
+@app.get("/health")
+async def health_check():
+    """Health check endpoint for Hugging Face Spaces"""
+    return {"status": "healthy", "service": "dubsway-video-ai"}
+
 @app.on_event("startup")
 async def startup_event():
     logger.info("✅ FastAPI app started")
-
+    logger.info(f"Environment: {os.getenv('ENVIRONMENT', 'development')}")
+    logger.info(f"Database URL configured: {'DATABASE_URL' in os.environ}")
 
 @app.on_event("shutdown")
 async def shutdown_event():

clean-for-deployment.bat

@@ -0,0 +1,69 @@
+@echo off
+echo 🧹 Cleaning repository for Hugging Face deployment...
+
+echo.
+echo 📋 Removing binary files and vector stores...
+
+REM Remove vector store directory
+if exist "vector_store" (
+    echo Removing vector_store directory...
+    rmdir /s /q "vector_store"
+    echo ✅ vector_store removed
+) else (
+    echo ℹ️ vector_store directory not found
+)
+
+REM Remove database files
+for %%f in (*.db *.sqlite *.sqlite3) do (
+    if exist "%%f" (
+        echo Removing %%f...
+        del "%%f"
+        echo ✅ %%f removed
+    )
+)
+
+REM Remove FAISS files
+for %%f in (*.faiss *.index *.bin) do (
+    if exist "%%f" (
+        echo Removing %%f...
+        del "%%f"
+        echo ✅ %%f removed
+    )
+)
+
+REM Remove log files
+for %%f in (*.log) do (
+    if exist "%%f" (
+        echo Removing %%f...
+        del "%%f"
+        echo ✅ %%f removed
+    )
+)
+
+echo.
+echo 🔄 Updating git...
+
+REM Remove tracked files that should be ignored
+git rm -r --cached vector_store/ 2>nul
+git rm --cached *.db 2>nul
+git rm --cached *.sqlite 2>nul
+git rm --cached *.sqlite3 2>nul
+git rm --cached *.faiss 2>nul
+git rm --cached *.log 2>nul
+
+echo.
+echo 📝 Committing changes...
+git add .
+git commit -m "Clean repository for Hugging Face deployment - remove binary files"
+
+echo.
+echo ✅ Repository cleaned! You can now push to Hugging Face:
+echo.
+echo git push space develop
+echo.
+echo Or create a new branch:
+echo git checkout -b main
+echo git push space main
+echo.
+
+pause 

deploy-to-hf.bat

@@ -0,0 +1,82 @@
+@echo off
+echo 🚀 Preparing Dubsway Video AI for Hugging Face Deployment...
+
+echo.
+echo 📋 Checking prerequisites...
+
+REM Check if git is available
+git --version >nul 2>&1
+if errorlevel 1 (
+    echo ❌ Git is not installed or not in PATH
+    pause
+    exit /b 1
+)
+
+REM Check if we're in a git repository
+git status >nul 2>&1
+if errorlevel 1 (
+    echo ❌ Not in a git repository. Please run this from your project root.
+    pause
+    exit /b 1
+)
+
+echo ✅ Git repository found
+
+REM Check for required files
+if not exist ".huggingface.yaml" (
+    echo ❌ .huggingface.yaml not found
+    pause
+    exit /b 1
+)
+
+if not exist "Dockerfile" (
+    echo ❌ Dockerfile not found
+    pause
+    exit /b 1
+)
+
+if not exist "requirements-hf.txt" (
+    echo ❌ requirements-hf.txt not found
+    pause
+    exit /b 1
+)
+
+echo ✅ All required files found
+
+echo.
+echo 🔄 Checking git status...
+git status --porcelain
+
+echo.
+echo 📝 Current branch: 
+git branch --show-current
+
+echo.
+echo 🚀 Ready to deploy! Follow these steps:
+echo.
+echo 1. Push your changes to GitHub:
+echo    git add .
+echo    git commit -m "Deploy to Hugging Face Spaces"
+echo    git push origin main
+echo.
+echo 2. Go to https://huggingface.co/spaces
+echo.
+echo 3. Create a new Space with these settings:
+echo    - SDK: Docker
+echo    - License: MIT
+echo    - Connect to your GitHub repository
+echo.
+echo 4. Set environment variables in your Space settings:
+echo    - GROQ_API_KEY
+echo    - DATABASE_URL=sqlite+aiosqlite:///./dubsway_hf.db
+echo    - SECRET_KEY
+echo    - AWS_ACCESS_KEY_ID (if using S3)
+echo    - AWS_SECRET_ACCESS_KEY (if using S3)
+echo    - S3_BUCKET_NAME (if using S3)
+echo.
+echo 5. Monitor deployment in your Space
+echo.
+echo 📖 See HUGGINGFACE_DEPLOYMENT.md for detailed instructions
+echo.
+
+pause 

push-to-hf.bat

@@ -0,0 +1,49 @@
+@echo off
+echo 🚀 Pushing to Hugging Face Spaces...
+
+echo.
+echo 🧹 Cleaning binary files...
+
+REM Remove vector store from git tracking
+git rm -r --cached vector_store/ 2>nul
+git rm --cached *.db 2>nul
+git rm --cached *.log 2>nul
+
+echo.
+echo 📝 Committing changes...
+git add .
+git commit -m "Clean repository for Hugging Face deployment"
+
+echo.
+echo 🔄 Pushing to Hugging Face...
+echo Choose your branch:
+echo 1. Push to develop branch
+echo 2. Create and push to main branch
+echo 3. Cancel
+echo.
+set /p choice="Enter choice (1-3): "
+
+if "%choice%"=="1" (
+    echo Pushing to develop branch...
+    git push space develop
+) else if "%choice%"=="2" (
+    echo Creating main branch...
+    git checkout -b main
+    echo Pushing to main branch...
+    git push space main
+) else (
+    echo Cancelled.
+    pause
+    exit /b 0
+)
+
+echo.
+echo ✅ Push completed!
+echo.
+echo 📍 Your Space URL will be:
+echo https://huggingface.co/spaces/peace2024/DubswayAgenticAI
+echo.
+echo 🔍 Monitor the build logs in your Space settings.
+echo.
+
+pause 

requirements-hf.txt

@@ -0,0 +1,47 @@
+# Core FastAPI dependencies
+fastapi==0.104.1
+uvicorn[standard]==0.24.0
+python-dotenv==1.0.0
+python-multipart==0.0.6
+pydantic[email]==1.10.13
+
+# Database
+asyncpg==0.29.0
+sqlalchemy==2.0.23
+aiosqlite==0.19.0
+
+# Auth
+passlib[bcrypt]==1.7.4
+python-jose[cryptography]==3.3.0
+
+# LLM & RAG
+langchain==0.1.13
+langchain-openai==0.1.7
+langchain-community==0.0.38
+langchain-core==0.1.53
+langchain-groq==0.0.1
+
+# Embedding & vector DB
+sentence-transformers==2.2.2
+faiss-cpu==1.7.4
+
+# Transcription
+faster-whisper==1.0.1
+ctranslate2==4.0.0
+
+# Enhanced Analysis
+transformers==4.35.2
+duckduckgo-search==4.1.1
+wikipedia-api==0.6.0
+timm==0.9.12
+
+# PDF & Reports
+PyPDF2==3.0.1
+reportlab==4.0.7
+beautifulsoup4==4.12.2
+
+# AWS
+boto3==1.34.0
+
+# Utilities
+requests==2.31.0