Dockerfile

FROM nvidia/cuda:12.1.1-base-ubuntu22.04

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE 1
ENV PYTHONUNBUFFERED 1
ENV HF_HOME=/data/hf_cache
ENV TRANSFORMERS_CACHE=/data/hf_cache/txagent_models
ENV MPLCONFIGDIR=/tmp/matplotlib

# Install system dependencies
RUN apt-get update && apt-get install -y \
    python3 \
    python3-pip \
    python3-dev \
    build-essential \
    libpoppler-cpp-dev \
    && rm -rf /var/lib/apt/lists/*

# Create and set working directory
WORKDIR /app

# Install specific versions of PyTorch and vLLM with CUDA 12.1 support
RUN pip install --no-cache-dir \
    torch==2.1.2+cu121 \
    --extra-index-url https://download.pytorch.org/whl/cu121
RUN pip install --no-cache-dir vllm==0.3.0

# Create necessary directories
RUN mkdir -p /data/hf_cache/txagent_models \
    /data/hf_cache/tool_cache \
    /data/hf_cache/cache \
    /data/hf_cache/reports \
    /tmp/matplotlib

# Copy requirements first to leverage Docker cache
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Expose port
EXPOSE 7860

# Command to run the application
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]