Dockerfile

FROM python:3.10

# Minimal system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    git \
    && rm -rf /var/lib/apt/lists/*

RUN pip install --no-cache-dir --upgrade pip

# Install regular dependencies
RUN pip install --no-cache-dir \
    fastapi \
    uvicorn \
    huggingface_hub \
    pydantic

# Install PRE-COMPILED llama-cpp-python for CPU
# This prevents the "Job timeout" by skipping the build phase
RUN pip install llama-cpp-python \
    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu

# Set working directory
WORKDIR /app

# Copy your application code
COPY app.py .

# Run the API
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]