Refactor Dockerfile and requirements.txt for improved dependency management; update README.md with clearer installation options and instructions for prebuilt images.

.github/workflows/docker-build.yml

@@ -0,0 +1,73 @@
+name: Build and Push Docker Images
+
+on:
+  push:
+    branches: [ main, develop ]
+    tags: [ 'v*' ]
+  pull_request:
+    branches: [ main ]
+  release:
+    types: [published]
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
+
+    - name: Log in to Container Registry
+      uses: docker/login-action@v3
+      with:
+        registry: ${{ env.REGISTRY }}
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Extract metadata
+      id: meta
+      uses: docker/metadata-action@v5
+      with:
+        images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+        tags: |
+          type=ref,event=branch
+          type=ref,event=pr
+          type=semver,pattern={{version}}
+          type=semver,pattern={{major}}.{{minor}}
+          type=semver,pattern={{major}}
+          type=raw,value=latest,enable={{is_default_branch}}
+
+    - name: Build and push Docker image
+      uses: docker/build-push-action@v5
+      with:
+        context: .
+        platforms: linux/amd64,linux/arm64
+        push: true
+        tags: ${{ steps.meta.outputs.tags }}
+        labels: ${{ steps.meta.outputs.labels }}
+        cache-from: type=gha
+        cache-to: type=gha,mode=max
+
+    - name: Build and push GPU-enabled image
+      uses: docker/build-push-action@v5
+      with:
+        context: .
+        file: Dockerfile.gpu
+        platforms: linux/amd64
+        push: true
+        tags: |
+          ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:latest-gpu
+          ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ github.sha }}-gpu
+        labels: ${{ steps.meta.outputs.labels }}
+        cache-from: type=gha
+        cache-to: type=gha,mode=max 

Dockerfile

@@ -15,11 +15,12 @@ RUN apt-get update && apt-get install -y \
 # Copy requirements first for better Docker layer caching
 COPY requirements.txt .
 
-# Install Python dependencies
+# Install Python dependencies with pinned versions
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Install PyTorch with CUDA support (adjust based on your needs)
+# Optional: Install CUDA-specific PyTorch if GPU support needed
-RUN pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+# Uncomment and modify for your CUDA version:
+# RUN pip install --force-reinstall torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
 
 # Copy application code
 COPY . .

Dockerfile.gpu

@@ -0,0 +1,53 @@
+FROM python:3.11-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies including CUDA-related packages
+RUN apt-get update && apt-get install -y \
+    ffmpeg \
+    git \
+    wget \
+    curl \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first for better Docker layer caching
+COPY requirements.txt .
+
+# Install CPU versions from requirements.txt first
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Install CUDA-optimized PyTorch (overwrites CPU versions)
+RUN pip install --force-reinstall \
+    torch==2.0.1+cu118 \
+    torchvision==0.15.2+cu118 \
+    torchaudio==2.0.2+cu118 \
+    --index-url https://download.pytorch.org/whl/cu118
+
+# Copy application code
+COPY . .
+
+# Create directories for mounted volumes
+RUN mkdir -p /app/data/videos /app/data/outputs /app/data/cache
+
+# Set environment variables
+ENV STREAMLIT_SERVER_PORT=8501
+ENV STREAMLIT_SERVER_ADDRESS=0.0.0.0
+ENV STREAMLIT_SERVER_HEADLESS=true
+ENV STREAMLIT_BROWSER_GATHER_USAGE_STATS=false
+
+# GPU-specific environment variables
+ENV CUDA_VISIBLE_DEVICES=0
+ENV NVIDIA_VISIBLE_DEVICES=all
+ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
+
+# Expose Streamlit port
+EXPOSE 8501
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+    CMD curl -f http://localhost:8501/_stcore/health || exit 1
+
+# Start the application
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"] 

QUICK-FIX.md

@@ -0,0 +1,60 @@
+# 🚨 Quick Fix for PyTorch Compatibility Error
+
+If you're seeing the `torch.compiler.disable` error, here's how to fix it:
+
+## Immediate Fix
+
+```bash
+# Stop the current container
+docker-compose down
+
+# Remove the old image to force rebuild with fixed versions
+docker rmi $(docker images | grep videotranscriber | awk '{print $3}')
+
+# Rebuild with fixed dependencies
+docker-compose up -d --build
+```
+
+## Better Solution: Use Prebuilt Images
+
+Once available, use the prebuilt images instead:
+
+```bash
+# Stop current container
+docker-compose down
+
+# Use prebuilt image (no build required)
+docker-compose -f docker-compose.prebuilt.yml up -d
+```
+
+## What Was Fixed
+
+1. **Version Pinning**: Updated `requirements.txt` with compatible versions:
+   - `torch==2.0.1` (was `>=1.7.0`)
+   - `pytorch-lightning==2.0.6` (compatible with torch 2.0.1)
+   - `pyannote.audio==3.1.1` (updated to compatible version)
+
+2. **Build Process**: Removed duplicate PyTorch installation that could cause conflicts
+
+3. **Prebuilt Images**: Created GitHub Actions to build reliable, tested images
+
+## Verification
+
+After fixing, you should see the Streamlit app load without errors at `http://localhost:8501`
+
+## If Still Having Issues
+
+1. **Clear Docker cache**:
+   ```bash
+   docker system prune -a
+   ```
+
+2. **Check logs**:
+   ```bash
+   docker-compose logs -f
+   ```
+
+3. **Manual rebuild**:
+   ```bash
+   docker build --no-cache -t videotranscriber .
+   ``` 

README.md

@@ -17,8 +17,9 @@ https://github.com/user-attachments/assets/990e63fc-232e-46a0-afdf-ca8836d46a13
 
 **Benefits**: Isolated environment, no dependency conflicts, easy deployment
 
+#### Option A: Prebuilt Images (Fastest & Most Reliable)
 ```bash
-# 1. Clone repository
+# 1. Clone repository for config files
 git clone https://github.com/DataAnts-AI/VideoTranscriber.git
 cd VideoTranscriber
 
@@ -30,13 +31,19 @@ cp docker.env.example .env
 ollama serve  # In separate terminal
 ollama pull llama3
 
-# 4. Start with Docker Compose
+# 4. Start with prebuilt image
-docker-compose up -d
+docker-compose -f docker-compose.prebuilt.yml up -d
 
 # 5. Access application
 # Open browser to: http://localhost:8501
 ```
 
+#### Option B: Build from Source (Development)
+```bash
+# Use the local build approach
+docker-compose up -d
+```
+
 See [DOCKER.md](DOCKER.md) for complete Docker setup guide.
 
 ### Easy Installation (Recommended)

docker-compose.prebuilt.yml

@@ -0,0 +1,70 @@
+version: '3.8'
+
+services:
+  videotranscriber:
+    # Use prebuilt image from GitHub Container Registry
+    image: ghcr.io/dataants-ai/videotranscriber:latest
+    container_name: videotranscriber
+    ports:
+      - "8501:8501"
+    volumes:
+      # Mount your video files directory (change the left path to your actual videos folder)
+      - "${VIDEO_PATH:-./videos}:/app/data/videos"
+      # Mount output directory for transcripts and summaries
+      - "${OUTPUT_PATH:-./outputs}:/app/data/outputs" 
+      # Mount cache directory for model caching (optional, improves performance)
+      - "${CACHE_PATH:-./cache}:/app/data/cache"
+      # Mount a config directory if needed
+      - "${CONFIG_PATH:-./config}:/app/config"
+    environment:
+      # Ollama configuration for host access
+      - OLLAMA_API_URL=${OLLAMA_API_URL:-http://host.docker.internal:11434/api}
+      # Optional: HuggingFace token for advanced features
+      - HF_TOKEN=${HF_TOKEN:-}
+      # GPU configuration
+      - CUDA_VISIBLE_DEVICES=${CUDA_VISIBLE_DEVICES:-}
+      # Cache settings
+      - TRANSFORMERS_CACHE=/app/data/cache/transformers
+      - WHISPER_CACHE=/app/data/cache/whisper
+    restart: unless-stopped
+    # Use bridge networking for Windows/Mac with host.docker.internal
+    networks:
+      - videotranscriber-network
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8501/_stcore/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+
+  # Alternative GPU-enabled service (uncomment to use)
+  # videotranscriber-gpu:
+  #   image: ghcr.io/dataants-ai/videotranscriber:latest-gpu
+  #   container_name: videotranscriber-gpu
+  #   ports:
+  #     - "8501:8501"
+  #   volumes:
+  #     - "${VIDEO_PATH:-./videos}:/app/data/videos"
+  #     - "${OUTPUT_PATH:-./outputs}:/app/data/outputs" 
+  #     - "${CACHE_PATH:-./cache}:/app/data/cache"
+  #     - "${CONFIG_PATH:-./config}:/app/config"
+  #   environment:
+  #     - OLLAMA_API_URL=${OLLAMA_API_URL:-http://host.docker.internal:11434/api}
+  #     - HF_TOKEN=${HF_TOKEN:-}
+  #     - CUDA_VISIBLE_DEVICES=${CUDA_VISIBLE_DEVICES:-0}
+  #     - TRANSFORMERS_CACHE=/app/data/cache/transformers
+  #     - WHISPER_CACHE=/app/data/cache/whisper
+  #   deploy:
+  #     resources:
+  #       reservations:
+  #         devices:
+  #           - driver: nvidia
+  #             count: 1
+  #             capabilities: [gpu]
+  #   restart: unless-stopped
+  #   networks:
+  #     - videotranscriber-network
+
+networks:
+  videotranscriber-network:
+    driver: bridge 

requirements.txt

@@ -1,24 +1,32 @@
 # OBS Recording Transcriber Dependencies
-# Core dependencies
+# Core dependencies with pinned compatible versions
 streamlit==1.26.0
 moviepy==1.0.3
 openai-whisper==20231117
-transformers>=4.21.1
-torch>=1.7.0
-torchaudio>=0.7.0
 requests>=2.28.0
 humanize>=4.6.0
 
-# Phase 2 dependencies
+# PyTorch ecosystem - pinned for compatibility
-scikit-learn>=1.0.0
+torch==2.0.1
-numpy>=1.20.0
+torchaudio==2.0.2
+torchvision==0.15.2
 
-# Phase 3 dependencies
+# Transformers ecosystem - compatible versions
-pyannote.audio>=2.1.1
+transformers==4.30.2
+tokenizers==0.13.3
+
+# ML dependencies with compatible versions
+numpy==1.24.3
+scipy==1.10.1
+scikit-learn==1.3.0
+
+# Audio processing and ML models
+pyannote.audio==3.1.1
+pytorch-lightning==2.0.6
+
+# Other dependencies
 iso639>=0.1.4
 protobuf>=3.20.0,<4.0.0
-tokenizers>=0.13.2
-scipy>=1.7.0
 matplotlib>=3.5.0
 soundfile>=0.10.3
 ffmpeg-python>=0.2.0