local-inference / Dockerfile
ButterM40's picture
Restore full ML server (Space is working, just need real models)
9bb8348
raw
history blame
932 Bytes
# Use Python 3.11 slim image
FROM python:3.11-slim
# Set working directory
WORKDIR /code
# Set environment variables
ENV PORT=7860
ENV TRANSFORMERS_CACHE=/code/.cache/transformers
# Install system dependencies
RUN apt-get update && \
apt-get install -y --no-install-recommends \
build-essential \
git \
&& rm -rf /var/lib/apt/lists/*
# Copy requirements first for better caching
COPY requirements.txt .
# Install dependencies (add back torch and transformers)
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir torch==2.1.0 transformers==4.46.3 && \
pip install --no-cache-dir -r requirements.txt
# Copy the rest of the application
COPY . .
# Create cache directory for transformers
RUN mkdir -p /code/.cache/transformers
# Make port 7860 available
EXPOSE 7860
# Run the main FastAPI server (not minimal)
CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "7860"]