Dockerfile

# Base image
FROM python:3.10-slim

# Install system dependencies
RUN apt-get update && apt-get install -y \
    git \
    wget \
    build-essential \
    cmake \
    libopenblas-dev \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

# Copy app code
COPY . .

# Download TinyLlama GGUF model from Hugging Face
RUN mkdir -p /app/models && \
    wget -O /app/models/TinyLlama.gguf \
    https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf

# Clone and build llama.cpp
RUN git clone https://github.com/ggerganov/llama.cpp.git /app/llama.cpp && \
    cd /app/llama.cpp && \
    mkdir -p build && cd build && \
    cmake .. -DLLAMA_BUILD_EXAMPLES=ON -DLLAMA_BUILD_SERVER=OFF && \
    cmake --build . --config Release

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Expose the port
EXPOSE 7860

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