Dockerfile.gpu

# GPU-enabled Dockerfile для использования CUDA
# Использование: docker build -f Dockerfile.gpu -t insightaudio:gpu .
# Используем образ с cuDNN9 runtime (совместим с cu12)
FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04

# Python 3.10
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.10 \
    python3.10-dev \
    python3-pip \
    ffmpeg \
    git \
    wget \
    unzip \
    build-essential \
    gcc \
    g++ \
    libsndfile1 \
    libgomp1 \
    tesseract-ocr \
    gosu \
    && rm -rf /var/lib/apt/lists/* \
    && ln -s /usr/bin/python3.10 /usr/bin/python

WORKDIR /app

# Copy only requirements first (better layer caching)
COPY requirements.txt .

# Install Python dependencies
RUN pip3 install --no-cache-dir --upgrade pip setuptools wheel \
    && pip3 install --no-cache-dir -r requirements.txt \
    && pip3 install --no-cache-dir torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

# Workaround for this package
RUN pip3 install --no-cache-dir --no-build-isolation "nemo-toolkit[asr]==1.23.0"

# Prepare writable dirs for non-root user
RUN mkdir -p /app/logs /app/results /tmp/mplcache && \
    mkdir -p /models /config && \
    chown -R 1000:1000 /app /models /config /tmp

# Copy application code and default configs
COPY app/ ./app/
COPY config/default_settings.json ./config/default_settings.json
COPY config/prompt_templates.json ./config/prompt_templates.json
RUN cp ./config/default_settings.json ./config/config.json

# Create directories
RUN mkdir -p /models /config /tmp

EXPOSE 55667

COPY entrypoint.sh /app/entrypoint.sh
RUN chmod +x /app/entrypoint.sh

ENTRYPOINT ["/app/entrypoint.sh"]
CMD ["python3", "-m", "uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "55667"]