Dockerfile

FROM node:22

SHELL ["/bin/bash", "-c"]

# Install build dependencies and wget for model downloading
RUN apt-get update && \
    apt-get install -y --no-install-recommends git cmake clang libgomp1 wget ca-certificates && \
    rm -rf /var/lib/apt/lists/*

WORKDIR /opt/app

# Create necessary directories
RUN mkdir -p models public

# Download the model directly from Hugging Face during the Docker build
# Use /resolve/ to get the actual file stream
RUN wget -qO models/model.gguf "https://huggingface.co/unsloth/gemma-3-1b-it-GGUF/resolve/main/gemma-3-1b-it-UD-IQ1_S.gguf?download=true"
# RUN wget -qO models/model.gguf "https://huggingface.co/msievers/gemma-4-E2B-it-qat-q4_0-assistant-GGUF/resolve/main/gemma-4-E2B-it-qat-assistant-q4_0.gguf?download=true"

# Copy package files and install dependencies
COPY package*.json ./
RUN npm install

# # Download latest llama.cpp source, then compile it
# RUN npx --yes node-llama-cpp source download
# RUN npx --yes node-llama-cpp source build

# Copy the rest of the application code (including server.js and the public folder)
COPY . .

# Expose the standard Hugging Face Spaces port
EXPOSE 7860

# Start the server
CMD ["npm", "start"]