Skip to main content
Version: 0.4.x

Docker Deployment

Running Denkflow in Docker requires careful handling of the data directory for persistence, especially with OneTimeLicenseSource or TensorRT caching.

Sample Dockerfile (TensorRT Jetson)​

FROM nvcr.io/nvidia/l4t-jetpack:r36.4.0

WORKDIR /denkflow

# uv for python management
ADD https://astral.sh/uv/install.sh /uv-installer.sh
RUN sh /uv-installer.sh && rm /uv-installer.sh
ENV PATH="/root/.local/bin/:$PATH"
RUN uv venv -p 3.10.12
RUN . .venv/bin/activate

# install denkflow
RUN uv pip install --upgrade denkflow[tensorrt] \
    --index-url https://__token__:glpat-8ZB7unxdFxiTGdW-BBzA@\
    gitlab.com/api/v4/projects/69262737/packages/pypi/simple

# Set up entrypoint to activate virtual environment and start bash
ENTRYPOINT ["/bin/bash", "-c", \
    "source .venv/bin/activate && exec /bin/bash"]

Build the Docker image​

docker build -t denkflow:latest .

Run the container​

Mount a host directory to the container and set DENKFLOW_DATA_DIRECTORY to point to a path inside the mounted volume. Pass the PAT securely.

# Create a directory on the host for persistent data
mkdir -p ./denkflow_persistent_data

# Run the container
docker run --runtime nvidia -it -v \
  -v ./denkflow_persistent_data:/app/persistent_data \ # Mount host dir
  -e DENKFLOW_DATA_DIRECTORY=/app/persistent_data \ # Set env var inside container
  denkflow:latest

This setup ensures that license state (OneTimeLicenseSource) and caches (TensorRT) are saved in ./denkflow_persistent_data on the host machine and persist across container restarts.