Setup Dify for HF Spaces deployment with optimized Docker configuration

Dockerfile

@@ -3,133 +3,34 @@
 # ============================================
 FROM python:3.10-slim-bookworm AS base
 
-# Force package update and installation at build time
-ARG CACHEBUST=1
-ARG DEBIAN_FRONTEND=noninteractive
-
-# Create directory for Node.js setup
-RUN mkdir -p /etc/apt/keyrings
-
-# Install Node.js and npm with all dependencies
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends \
-        curl \
-        gnupg \
-        ca-certificates \
-    && curl -fsSL https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key | gpg --dearmor -o /etc/apt/keyrings/nodesource.gpg \
-    && echo "deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_20.x nodistro main" | tee /etc/apt/sources.list.d/nodesource.list \
-    && apt-get update \
-    && apt-get install -y --no-install-recommends \
-        nodejs \
-        build-essential \
-        python3-dev \
-    && npm install -g npm@latest \
-    && npm install -g yarn \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install system dependencies
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends \
-        build-essential \
-        gcc \
-        g++ \
-        libc6-dev \
-        libffi-dev \
-        libgmp-dev \
-        libmpfr-dev \
-        libmpc-dev \
-        libssl-dev \
-        postgresql-client \
-        redis-tools \
-        make \
-        pkg-config \
-    && apt-get clean \
+# Reduce layer size and memory usage
+ENV DEBIAN_FRONTEND=noninteractive \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    POETRY_VERSION=1.8.3 \
+    POETRY_VIRTUALENVS_CREATE=false \
+    POETRY_CACHE_DIR=/tmp/poetry_cache
+
+# Install only essential build dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    curl \
+    gnupg \
+    libgmp-dev \
+    libmpfr-dev \
+    libmpc-dev \
+    libssl-dev \
+    postgresql-client \
+    redis-tools \
     && rm -rf /var/lib/apt/lists/*
 
-# Install Python packages in smaller groups to better handle dependencies
-RUN pip install --no-cache-dir \
-    gunicorn \
-    gevent \
-    grpcio \
-    pydantic-settings \
-    protobuf \
-    grpcio-tools
-
-RUN pip install --no-cache-dir \
-    flask \
-    flask-cors \
-    Flask-SQLAlchemy==3.1.1 \
-    Flask-Migrate==4.0.7 \
-    flask-login \
-    flask-restful \
-    flask-limiter \
-    flask-caching \
-    flask-jwt-extended \
-    flask-socketio
-
-RUN pip install --no-cache-dir \
-    PyYAML \
-    celery \
-    redis \
-    psycopg2-binary \
-    sqlalchemy \
-    alembic \
-    pyjwt \
-    requests
-
-# Install ML and AI packages separately
-RUN pip install --no-cache-dir \
-    numpy \
-    pandas \
-    python-dotenv \
-    pycryptodome \
-    cryptography \
-    bcrypt \
-    python-jose[cryptography] \
-    passlib \
-    python-multipart \
-    gmpy2
-
-RUN pip install --no-cache-dir \
-    transformers \
-    torch \
-    tensorflow \
-    sentencepiece \
-    tokenizers \
-    nltk
-
-# Install remaining packages
-RUN pip install --no-cache-dir \
-    openai==1.14.0 \
-    anthropic==0.23.1 \
-    Pillow \
-    opencv-python-headless \
-    scikit-learn \
-    scipy \
-    google-cloud-aiplatform \
-    google-generativeai \
-    vertexai \
-    google-cloud-core \
-    google-api-core \
-    yarl \
-    aiohttp \
-    "tritonclient[all]" \
-    cohere==4.43 \
-    replicate \
-    aleph-alpha-client \
-    stability-sdk \
-    huggingface_hub \
-    langchain \
-    langchain-community \
-    langchain-core \
-    langchain-openai
-
-# Install NLTK data
-RUN python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger')"
-
-# Verify installations
-RUN node --version && npm --version && yarn --version
+# Install Node.js efficiently
+RUN curl -fsSL https://deb.nodesource.com/setup_20.x | bash - && \
+    apt-get install -y nodejs && \
+    npm install -g npm@latest && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
 
 # ============================================
 # Web builder stage - optimized
@@ -159,16 +60,29 @@ FROM base AS python-builder
 
 WORKDIR /app
 
-# Copy api directory
-COPY api/ api/
-
-WORKDIR /app/api
-
-# Install core dependencies first
+COPY api/pyproject.toml api/poetry.lock ./
 RUN pip install --no-cache-dir poetry==1.8.3 && \
     poetry config virtualenvs.create false && \
     poetry install --no-dev --no-interaction --no-ansi
 
+# Install core dependencies first
+RUN pip install --no-cache-dir \
+    gunicorn \
+    gevent \
+    flask \
+    flask-cors \
+    Flask-SQLAlchemy==3.1.1 \
+    Flask-Migrate==4.0.7 \
+    redis \
+    psycopg2-binary
+
+# Install ML dependencies separately with --no-deps
+RUN pip install --no-cache-dir --no-deps \
+    numpy \
+    pandas \
+    torch \
+    transformers
+
 # ============================================
 # Final stage - minimal runtime
 # ============================================
@@ -186,86 +100,22 @@ RUN apt-get update && \
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
         build-essential \
-        nodejs \
-        npm \
+        curl \
+        gnupg \
         libgmp-dev \
         libmpfr-dev \
         libmpc-dev \
         libssl-dev \
         postgresql-client \
         redis-tools && \
+    # Install Node.js from NodeSource
+    curl -fsSL https://deb.nodesource.com/setup_20.x | bash - && \
+    apt-get install -y nodejs && \
+    # Install npm separately
+    npm install -g npm@latest && \
+    # Cleanup
     apt-get clean && \
-    rm -rf /var/lib/apt/lists/* && \
-    pip install --no-cache-dir \
-        gunicorn \
-        gevent \
-        grpcio \
-        pydantic-settings \
-        protobuf \
-        grpcio-tools \
-        flask \
-        flask-cors \
-        Flask-SQLAlchemy==3.1.1 \
-        Flask-Migrate==4.0.7 \
-        flask-login \
-        flask-restful \
-        flask-limiter \
-        flask-caching \
-        flask-jwt-extended \
-        flask-socketio \
-        PyYAML \
-        celery \
-        redis \
-        psycopg2-binary \
-        sqlalchemy \
-        alembic \
-        pyjwt \
-        requests \
-        numpy \
-        pandas \
-        python-dotenv \
-        pycryptodome \
-        cryptography \
-        bcrypt \
-        python-jose[cryptography] \
-        passlib \
-        python-multipart \
-        gmpy2 \
-        transformers \
-        torch \
-        tensorflow \
-        sentencepiece \
-        tokenizers \
-        nltk \
-        openai==1.14.0 \
-        anthropic==0.23.1 \
-        flask-migrate==4.0.5 \
-        Pillow \
-        opencv-python-headless \
-        scikit-learn \
-        scipy \
-        google-cloud-aiplatform \
-        google-generativeai \
-        vertexai \
-        google-cloud-core \
-        google-api-core \
-        yarl \
-        aiohttp \
-        tritonclient[all] \
-        cohere==4.43 \
-        anthropic \
-        replicate \
-        aleph-alpha-client \
-        stability-sdk \
-        huggingface_hub \
-        langchain \
-        langchain-community \
-        langchain-core \
-        langchain-openai \
-        openai==1.14.0 \
-        Flask-Migrate==4.0.7 \
-        Flask-SQLAlchemy==3.1.1 && \
-    python -m nltk.downloader punkt averaged_perceptron_tagger
+    rm -rf /var/lib/apt/lists/*
 
 # Set up directory structure
 WORKDIR /app

docker/docker-compose.yaml

@@ -276,26 +276,34 @@ services:
     image: langgenius/dify-api:0.11.0
     restart: always
     environment:
-      # Use the shared environment variables.
+      # Use the shared environment variables
       <<: *shared-api-worker-env
-      # Startup mode, 'api' starts the API server.
+      # Startup mode, 'api' starts the API server
       MODE: api
+      MALLOC_ARENA_MAX: 2
+      NODE_OPTIONS: "--max-old-space-size=2048"
     depends_on:
       db:
         condition: service_healthy
       redis:
         condition: service_healthy
     volumes:
-      # Mount the storage directory to the container, for storing user files.
+      # Mount the storage directory to the container
       - ./volumes/app/storage:/app/api/storage
     networks:
       - ssrf_proxy_network
       - default
+    deploy:
+      resources:
+        limits:
+          memory: 6G
+        reservations:
+          memory: 2G
 
   # worker service
   # The Celery worker for processing the queue.
   worker:
-    image: langgenius/dify-api:0.11.0
+    image: langgenius/dify-api
     restart: always
     environment:
       # Use the shared environment variables.

docker/entrypoint.sh

@@ -155,4 +155,8 @@ NEXT_TELEMETRY_DISABLED=1 \
 node server.js &
 
 # Wait for both processes
-wait
+wait
+
+# Add to entrypoint.sh
+export MALLOC_ARENA_MAX=2
+export NODE_OPTIONS="--max-old-space-size=2048"