40 lines
1.2 KiB
Docker
40 lines
1.2 KiB
Docker
|
# Use a lightweight official Python base image
|
||
|
|
FROM python:3.10-slim
|
||
|
|
|
||
|
|
# Set system environment variables
|
||
|
|
ENV PYTHONUNBUFFERED=1 \
|
||
|
|
PYTHONDONTWRITEBYTECODE=1
|
||
|
|
|
||
|
|
# Set workspace directory
|
||
|
|
WORKDIR /app
|
||
|
|
|
||
|
|
# Install system utility for container health checks
|
||
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||
|
|
curl \
|
||
|
|
&& rm -rf /var/lib/apt/lists/*
|
||
|
|
|
||
|
|
# Copy python dependencies and install them
|
||
|
|
COPY requirements.txt .
|
||
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
||
|
|
|
||
|
|
# Copy RAG engine source code and pre-computed database
|
||
|
|
COPY app.py search_kb.py embed_docs.py .
|
||
|
|
COPY knowledge_base.db .
|
||
|
|
|
||
|
|
# Configure default environment variables
|
||
|
|
# Note: 'host.docker.internal' makes it easy to communicate with Ollama running on the host machine
|
||
|
|
ENV OLLAMA_URL=http://host.docker.internal:11434/api/embed
|
||
|
|
ENV OLLAMA_GENERATE_URL=http://host.docker.internal:11434/api/generate
|
||
|
|
ENV EMBEDDING_MODEL=qwen3-embedding:0.6b
|
||
|
|
ENV DB_PATH=/app/knowledge_base.db
|
||
|
|
|
||
|
|
# Expose port for the FastAPI REST API
|
||
|
|
EXPOSE 8000
|
||
|
|
|
||
|
|
# Container healthcheck
|
||
|
|
HEALTHCHECK --interval=30s --timeout=5s --start-period=5s --retries=3 \
|
||
|
|
CMD curl -f http://localhost:8000/health || exit 1
|
||
|
|
|
||
|
|
# Start the RAG Engine FastAPI server by default
|
||
|
|
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]
|