Dockerfile

FROM python:3.12-slim

# Install system dependencies
RUN apt-get update && apt-get install -y \

    gcc g++ cmake build-essential curl git \
    && apt-get clean && rm -rf /var/lib/apt/lists/*
    
# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    PYTHON_VERSION=3.12.4 \
    HF_HOME=/data/.cache/huggingface \
    PATH="/root/.local/bin:$PATH"

# Set working directory
WORKDIR /app

# Ensure Hugging Face cache is writable
RUN mkdir -p /data/.cache/huggingface && \

    chmod -R 777 /data

# Copy requirements and install them
COPY requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \

    pip install llama-cpp-python==0.2.72 && \
    pip install --no-cache-dir -r requirements.txt

# Copy the rest of the application
COPY . .

# Expose FastAPI port
EXPOSE 7860

# Run FastAPI app using uvicorn
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]