Merge pull request #63 from rishikanthc/fix/docker-arm64-build

feat: Update Dockerfiles and move dependency installations to deployment

Author: BarbellDwarf

.dockerignore

@@ -1,11 +1,14 @@
 .dockerdata
 docker-compose.ollama.yaml
 Dockerfile
+Dockerfile-gpu
 install_audiowaveform.sh
 samples
 scriberr_files
 scriberr
 install_aw.sh
 .prettier*
 venv
+node_modules
+
 

Dockerfile

@@ -1,69 +1,50 @@
 # Use a specific version of Ubuntu as the base image
 FROM ubuntu:24.04
 
-# Set environment variables to make installation non-interactive and set timezone
+# Set environment variables
 ENV DEBIAN_FRONTEND=noninteractive \
     TZ="Etc/UTC" \
     PATH="/root/.local/bin/:$PATH"
 
-# Combine all apt-get related commands to reduce layers and avoid multiple updates
+# Install minimal runtime dependencies
 RUN apt-get update && \
-    apt-get upgrade -y && \
     apt-get install -y \
         python3 \
-        python3-dev \
         python3-pip \
+        python3-venv \
         postgresql-client \
-        software-properties-common \
-        build-essential \
-        cmake \
-        tzdata \
         ffmpeg \
         curl \
-        unzip \
         git && \
-    # Add the PPA and install audiowaveform
-    add-apt-repository ppa:chris-needham/ppa && \
-    apt-get update && \
-    apt-get install -y audiowaveform && \
     # Install UV
     curl -sSL https://astral.sh/uv/install.sh -o /uv-installer.sh && \
     sh /uv-installer.sh && \
     rm /uv-installer.sh && \
     # Install Node.js
     curl -fsSL https://deb.nodesource.com/setup_23.x | bash - && \
     apt-get install -y nodejs && \
-    # Clean up to reduce image size
+    # Clean up
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
-# Set the working directory
+# Set working directory
 WORKDIR /app
 
-# Copy and install Python dependencies first to leverage caching
-COPY requirements.txt .
-RUN uv venv && \
-    uv pip install -r requirements.txt
+# Create deps directory
+RUN mkdir -p /app/deps
 
-# Copy package.json and package-lock.json separately to cache npm install
-COPY package*.json ./
-RUN npm ci
-
-# Now copy the rest of the application code
+# Copy only the files needed for dependency installation and runtime
 COPY . .
 
-# Build the frontend application
-RUN npm run build
-
-# Copy the entrypoint script and ensure it has execute permissions
-COPY docker-entrypoint.sh /usr/local/bin/
-RUN chmod +x /usr/local/bin/docker-entrypoint.sh
+# Install node dependencies and build frontend
+RUN npm install && \
+    npm run build
 
-# Set NODE_ENV to production after building to avoid installing dev dependencies
-ENV NODE_ENV=production
+# Ensure entrypoint script is executable
+RUN chmod +x docker-entrypoint.sh
 
-# Expose the desired port
+# Expose port
 EXPOSE 3000
 
-# Define the default command
-CMD ["/usr/local/bin/docker-entrypoint.sh"]
+# Define default command
+CMD ["./docker-entrypoint.sh"]

Dockerfile-gpu

@@ -1,69 +1,49 @@
-# Use NVIDIA CUDA development image as the base for GPU acceleration
-FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04
+FROM nvidia/cuda:12.8.0-cudnn-runtime-ubuntu24.04
 
-# Set environment variables to make installation non-interactive and set timezone
+# Set environment variables
 ENV DEBIAN_FRONTEND=noninteractive \
     TZ="Etc/UTC" \
     PATH="/root/.local/bin/:$PATH"
 
-# Combine all apt-get related commands to reduce layers and avoid multiple updates
+# Install minimal runtime dependencies
 RUN apt-get update && \
-    apt-get upgrade -y && \
     apt-get install -y \
         python3 \
-        python3-dev \
         python3-pip \
+        python3-venv \
         postgresql-client \
-        software-properties-common \
-        build-essential \
-        cmake \
-        tzdata \
         ffmpeg \
         curl \
-        unzip \
         git && \
-    # Add the PPA and install audiowaveform
-    add-apt-repository ppa:chris-needham/ppa && \
-    apt-get update && \
-    apt-get install -y audiowaveform && \
     # Install UV
     curl -sSL https://astral.sh/uv/install.sh -o /uv-installer.sh && \
     sh /uv-installer.sh && \
     rm /uv-installer.sh && \
     # Install Node.js
     curl -fsSL https://deb.nodesource.com/setup_23.x | bash - && \
     apt-get install -y nodejs && \
-    # Clean up to reduce image size
+    # Clean up
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
-# Set the working directory
+# Set working directory
 WORKDIR /app
 
-# Copy and install Python dependencies first to leverage caching
-COPY requirements.txt .
-RUN uv venv && \
-    uv pip install -r requirements.txt
+# Create deps directory
+RUN mkdir -p /app/deps
 
-# Copy package.json and package-lock.json separately to cache npm install
-COPY package*.json ./
-RUN npm ci
-
-# Now copy the rest of the application code
+# Copy files to container
 COPY . .
 
-# Build the frontend application
-RUN npm run build
-
-# Copy the entrypoint script and ensure it has execute permissions
-COPY docker-entrypoint.sh /usr/local/bin/
-RUN chmod +x /usr/local/bin/docker-entrypoint.sh
+# Install node dependencies and build frontend
+RUN npm install && \
+    npm run build
 
-# Set NODE_ENV to production after building to avoid installing dev dependencies
-ENV NODE_ENV=production
+# Ensure entrypoint script is executable
+RUN chmod +x docker-entrypoint.sh
 
-# Expose the desired port
+# Expose port
 EXPOSE 3000
 
-# Define the default command
-CMD ["/usr/local/bin/docker-entrypoint.sh"]
+# Define default command
+CMD ["./docker-entrypoint.sh"]

docker-compose.yml

@@ -1,6 +1,3 @@
-# Docker Compose file for deploying Scriberr with a PostgreSQL database
-# Make sure a .env file is present in the same directory that this is being run from:
-
 services:
   app:
     image: ghcr.io/rishikanthc/scriberr:${IMAGE_TAG:-main}
@@ -9,7 +6,7 @@ services:
       platforms:
         - linux/arm64
         - linux/amd64
-      args: # Build-time variables
+      args:
         - DATABASE_URL=postgres://root:mysecretpassword@db:5432/local
         - ADMIN_USERNAME=admin
         - ADMIN_PASSWORD=password
@@ -21,15 +18,12 @@ services:
         - OPENAI_API_KEY=""
         - BODY_SIZE_LIMIT=100M
     env_file:
-      # Specify your .env file here
       - .env
     ports:
       - "${PORT:-3000}:3000"
     volumes:
-      # Comment out the following line if you want to use a local directory for Scriberr data storage
       - scriberr_data:/scriberr
-      # Uncomment the following line if you want to use a local directory for data storage
-      #- /path/to/scriberr_data:/scriberr
+      - scriberr_deps:/app/deps  # For marker files like requirements_installed
     networks:
       - app-network
     depends_on:
@@ -43,14 +37,10 @@ services:
       POSTGRES_USER: ${POSTGRES_USER}
       POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
       POSTGRES_DB: ${POSTGRES_DB}
-    # Uncomment the following lines if you want to access PostgreSQL from outside the container
     #ports:
-      #- "${POSTGRES_PORT:-5432}:5432"
+     # - "${POSTGRES_PORT:-5432}:5432"
     volumes:
-      # Comment out the following line if you want to use a local directory for PostgreSQL data storage
       - postgres_data:/var/lib/postgresql/data
-      # Uncomment the following line if you want to use a local directory for data storage
-      #- /path/to/postgres_data:/var/lib/postgresql/data
     healthcheck:
       test: ["CMD-SHELL", "pg_isready -U root -d local"]
       interval: 5s
@@ -64,8 +54,7 @@ networks:
   app-network:
     driver: bridge
 
-# Comment out the following lines if you want to use a local directory for data storage
 volumes:
   postgres_data:
   scriberr_data:
-
+  scriberr_deps:

docker-entrypoint.sh

@@ -1,53 +1,110 @@
 #!/bin/bash
 set -e
 
-# If the HARDWARE_ACCEL environment variable is not set, default to 'cpu', if set to GPU, use 'cuda'
+# Set HARDWARE_ACCEL: 'cuda' for GPU, 'cpu' otherwise
 if [ "$HARDWARE_ACCEL" = "gpu" ]; then
   export HARDWARE_ACCEL='cuda'
+else
+  export HARDWARE_ACCEL='cpu'
 fi
 
-# Active the python virtual environment
-source /app/.venv/bin/activate
-
-# Function to wait for database to be ready
+# Function to wait for the database to be ready
 wait_for_db() {
   echo "Waiting for database to be ready..."
-  
-  # For debugging
   echo "Current DATABASE_URL: $DATABASE_URL"
-  
+
   until PGPASSWORD="$POSTGRES_PASSWORD" pg_isready -h db -p 5432 -U "$POSTGRES_USER" -d "$POSTGRES_DB"
   do
     echo "Database connection attempt failed. Retrying in 2 seconds..."
     sleep 2
   done
-  
+
   echo "Database is ready!"
 }
 
-# Wait for database
+# Function to install dependencies based on hardware type
+install_dependencies() {
+  echo "Checking and installing dependencies..."
+
+  VENV_LOCATION_DIR="/app/deps/"
+  VENV_DIR="/app/deps/.venv"
+  MARKER_FILE="/app/deps/requirements_installed"
+
+  # Create venv if it doesn't exist
+  if [ ! -d "$VENV_DIR" ]; then
+    echo "Creating virtual environment..."
+    uv venv --directory "$VENV_LOCATION_DIR"
+     echo "Virtual environment created."
+  else
+    echo "Virtual environment already exists."
+  fi
+
+  # Activate venv
+  source "$VENV_DIR/bin/activate"
+
+  # Install Python dependencies if not already installed
+  if [ ! -f "$MARKER_FILE" ]; then
+    echo "Installing Python dependencies..."
+
+    # Install PyTorch based on hardware
+    if [ "$HARDWARE_ACCEL" = "cuda" ]; then
+      uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
+      uv pip install nvidia-cudnn-cu11==8.9.6.50
+      echo "PyTorch with CUDA installed."
+    else
+      uv pip install torch==2.0.0 torchvision==0.15.1 torchaudio==2.0.1 --index-url https://download.pytorch.org/whl/cpu
+    fi
+
+    # Install remaining dependencies from requirements.txt
+    uv pip install -r requirements.txt
+
+    # Create marker file
+    touch "$MARKER_FILE"
+  else
+    echo "Python dependencies already installed."
+  fi
+  # Note: Venv remains activated so PATH is set for the Node.js application
+
+  # Install Node.js dependencies if directory is empty
+  echo "Checking for Node.js dependencies..."
+ if [ ! "$(ls -A /app/node_modules)" ]; then
+    echo "Installing Node.js dependencies..."
+  else
+    echo "Node.js dependencies already installed."
+  fi
+
+  # Build the application
+  if [ ! "$(ls -A /app/build)" ]; then
+    echo "Building the application..."
+    NODE_ENV=development npm run build
+  else
+    echo "Application already built."
+  fi
+}
+export VENV_DIR="/app/deps/.venv"
+export LD_LIBRARY_PATH=$VENV_DIR/lib/python3.12/site-packages/nvidia/cudnn/lib
+export NODE_ENV=production
+
+# Execute the setup steps
+install_dependencies
 wait_for_db
 
+
 # Run database migrations
-echo "Creating database ..."
+echo "Creating database..."
 if ! npx drizzle-kit generate; then
-    echo "Migration generation failed, but continuing..."
+  echo "Migration generation failed, but continuing..."
 fi
 
 if ! npx drizzle-kit migrate; then
-    echo "Migration generation failed, but continuing..."
+  echo "Migration failed, but continuing..."
 fi
 
-# Run database push
 echo "Running database push..."
 if ! npx drizzle-kit push; then
-    echo "Database push failed, but continuing..."
+  echo "Database push failed, but continuing..."
 fi
 
 # Start the application
-echo "Building the application..."
-exec "$@"
-
 echo "Starting the application..."
-node build
-
+node build