# Use Hugging Face TGI as the base image
FROM ghcr.io/huggingface/text-generation-inference:3.0.2

# Set working directory
WORKDIR /app

# Create and set permissions for cache directories
RUN mkdir -p /data && chmod 777 /data
RUN mkdir -p /.cache && chmod 777 /.cache
RUN mkdir -p /.triton && chmod 777 /.triton

# Expose the model API on port 8080
EXPOSE 8080

# Set Hugging Face token for private models
ARG HF_TOKEN
ENV HF_TOKEN=${HF_TOKEN}

# Run the TGI server with Mistral 7B
CMD ["--model-id", "mistralai/Mistral-7B-v0.3", "--port", "8080"]