@basetenlabs/client - v0.2.0
    Preparing search index...

    Interface DockerServer

    Deploy a custom Docker image that has its own HTTP server, without writing a Model class.

    interface DockerServer {
        liveness_endpoint: string;
        no_build?: boolean | null;
        predict_endpoint: string;
        readiness_endpoint: string;
        run_as_user_id?: number | null;
        server_port: number;
        start_command?: string | null;
        [k: string]: unknown;
    }

    Indexable

    • [k: string]: unknown
    Index
    liveness_endpoint no_build? predict_endpoint readiness_endpoint run_as_user_id? server_port start_command?
    liveness_endpoint: string

    The endpoint for liveness probes. Determines if the container needs to be restarted.

    no_build?: boolean | null

    Skip the build step and deploy the base image as-is. Baseten copies the image to its container registry without running docker build or modifying the image in any way.

    predict_endpoint: string

    The endpoint for inference requests. This is mapped to Baseten's /predict route.

    readiness_endpoint: string

    The endpoint for readiness probes. Determines when the container can accept traffic.

    run_as_user_id?: number | null

    The Linux UID to run the server process as inside the container. Use this when your base image expects a specific non-root user (for example, NVIDIA NIM containers).

    server_port: number

    The port where the server runs. Port 8080 is reserved by Baseten's internal reverse proxy and cannot be used.

    start_command?: string | null

    The command to start the server. Required when no_build is not true.

    Settings
    Member Visibility

    On This Page
    Properties