Databricks Jobs

databricks bundle init default-python --config-file <(echo '{"project_name": "my_job", "include_job": "yes", "include_pipeline": "no", "include_python": "yes", "serverless": "yes"}') --profile <PROFILE> < /dev/null

# Declarative Automation Bundles Project

This project uses Declarative Automation Bundles (formerly Databricks Asset Bundles) for deployment.

## Prerequisites

Install the Databricks CLI (>= v0.288.0) if not already installed:
- macOS: `brew tap databricks/tap && brew install databricks`
- Linux: `curl -fsSL https://raw.githubusercontent.com/databricks/setup-cli/main/install.sh | sh`
- Windows: `winget install Databricks.DatabricksCLI`

Verify: `databricks -v`

## For AI Agents

Read the `databricks-core` skill for CLI basics, authentication, and deployment workflow.
Read the `databricks-jobs` skill for job-specific guidance.

If skills are not available, install them: `databricks aitools install`

my-job-project/
├── databricks.yml              # Bundle configuration
├── resources/
│   └── my_job.job.yml          # Job definition
├── src/
│   ├── my_notebook.ipynb       # Notebook tasks
│   └── my_module/              # Python wheel package
│       ├── __init__.py
│       └── main.py
├── tests/
│   └── test_main.py
└── pyproject.toml              # Python project config (if using wheels)

# resources/jobs.yml
resources:
  jobs:
    my_etl_job:
      name: "[${bundle.target}] My ETL Job"
      tasks:
        - task_key: extract
          notebook_task:
            notebook_path: ../src/notebooks/extract.py

from databricks.sdk import WorkspaceClient
from databricks.sdk.service.jobs import Task, NotebookTask, Source

w = WorkspaceClient()

job = w.jobs.create(
    name="my-etl-job",
    tasks=[
        Task(
            task_key="extract",
            notebook_task=NotebookTask(
                notebook_path="/Workspace/Shared/etl/extract",
                source=Source.WORKSPACE,
            ),
        ),
    ],
)
print(f"Created job: {job.job_id}")

databricks jobs create --json '{
  "name": "my-etl-job",
  "tasks": [{
    "task_key": "extract",
    "notebook_task": {
      "notebook_path": "/Workspace/Shared/etl/extract",
      "source": "WORKSPACE"
    }
  }]
}'

tasks:
  - task_key: extract
    notebook_task:
      notebook_path: ../src/extract.py

  - task_key: transform
    depends_on:
      - task_key: extract
    notebook_task:
      notebook_path: ../src/transform.py

  - task_key: load
    depends_on:
      - task_key: transform
    run_if: ALL_SUCCESS  # Only run if all dependencies succeed
    notebook_task:
      notebook_path: ../src/load.py

job_clusters:
  - job_cluster_key: shared_cluster
    new_cluster:
      spark_version: "15.4.x-scala2.12"
      node_type_id: "i3.xlarge"
      num_workers: 2
      spark_conf:
        spark.speculation: "true"

tasks:
  - task_key: my_task
    job_cluster_key: shared_cluster
    notebook_task:
      notebook_path: ../src/notebook.py

new_cluster:
  spark_version: "15.4.x-scala2.12"
  node_type_id: "i3.xlarge"
  autoscale:
    min_workers: 2
    max_workers: 8

tasks:
  - task_key: my_task
    existing_cluster_id: "0123-456789-abcdef12"
    notebook_task:
      notebook_path: ../src/notebook.py

tasks:
  - task_key: serverless_task
    notebook_task:
      notebook_path: ../src/notebook.py
    # No cluster config = serverless

parameters:
  - name: env
    default: "dev"
  - name: date
    default: "{{start_date}}"  # Dynamic value reference

catalog = dbutils.widgets.get("env")
load_date = dbutils.widgets.get("date")

tasks:
  - task_key: my_task
    notebook_task:
      notebook_path: ../src/notebook.py
      base_parameters:
        env: "{{job.parameters.env}}"
        custom_param: "value"

from databricks.sdk import WorkspaceClient

w = WorkspaceClient()

# List jobs
jobs = w.jobs.list()

# Get job details
job = w.jobs.get(job_id=12345)

# Run job now
run = w.jobs.run_now(job_id=12345)

# Run with parameters
run = w.jobs.run_now(
    job_id=12345,
    job_parameters={"env": "prod", "date": "2024-01-15"},
)

# Cancel run
w.jobs.cancel_run(run_id=run.run_id)

# Delete job
w.jobs.delete(job_id=12345)

# List jobs
databricks jobs list

# Get job details
databricks jobs get 12345

# Run job
databricks jobs run-now 12345

# Run with parameters (must use --json with job_id inside)
databricks jobs run-now --json '{"job_id": 12345, "job_parameters": {"env": "prod"}}'

# Cancel run
databricks jobs cancel-run 67890

# Delete job
databricks jobs delete 12345

# Validate configuration
databricks bundle validate --profile <profile>

# Deploy to a target
databricks bundle deploy -t dev --profile <profile>

# Run a job
databricks bundle run <job_name> -t dev --profile <profile>

# Check run status
databricks jobs get-run --run-id <id> --profile <profile>

# Destroy resources
databricks bundle destroy --auto-approve

resources:
  jobs:
    my_job:
      name: "My Job"
      permissions:
        - level: CAN_VIEW
          group_name: "data-analysts"
        - level: CAN_MANAGE_RUN
          group_name: "data-engineers"
        - level: CAN_MANAGE
          user_name: "[email protected]"

uv run pytest