website / Dockerfile
Tim Luka Horstmann
remove manual llama build
47d79de
raw
history blame
1.03 kB
# Use an official Python runtime as a base image
FROM python:3.10-slim
# Set environment variables
ENV TRANSFORMERS_CACHE=/app/cache \
HF_HOME=/app/cache \
DEBIAN_FRONTEND=noninteractive
# Set working directory
WORKDIR /app
# Install minimal system dependencies for running the app
RUN apt-get update && apt-get install -y --no-install-recommends \
libgomp1 \
&& rm -rf /var/lib/apt/lists/*
# Prepare cache directory
RUN mkdir -p /app/cache && chmod -R 777 /app/cache
# Copy requirements and install Python packages
COPY requirements.txt .
# Install most packages from requirements.txt, then llama-cpp-python with binary-only
RUN grep -v "llama-cpp-python" requirements.txt | pip install --no-cache-dir -r /dev/stdin \
&& pip install --no-cache-dir --only-binary=all llama-cpp-python==0.3.14
# Copy application code and data
COPY app.py cv_embeddings.json cv_text.txt ./
# Expose the port your FastAPI app runs on
EXPOSE 7860
# Launch
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]