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

# Databricks Asset Bundles Project

This project uses 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` 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 experimental aitools skills 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:
    my_job:
      name: my_job

      tasks:
        - task_key: my_notebook
          notebook_task:
            notebook_path: ../src/my_notebook.ipynb

        - task_key: my_python
          depends_on:
            - task_key: my_notebook
          python_wheel_task:
            package_name: my_package
            entry_point: main

resources:
  jobs:
    my_job:
      parameters:
        - name: catalog
          default: ${var.catalog}
        - name: schema
          default: ${var.schema}

# Read parameters
catalog = dbutils.widgets.get("catalog")
schema = dbutils.widgets.get("schema")

# Read tables
df = spark.read.table(f"{catalog}.{schema}.my_table")

# SQL queries
result = spark.sql(f"SELECT * FROM {catalog}.{schema}.my_table LIMIT 10")

# Write output
df.write.mode("overwrite").saveAsTable(f"{catalog}.{schema}.output_table")

resources:
  jobs:
    my_job:
      trigger:
        periodic:
          interval: 1
          unit: DAYS

      schedule:
        quartz_cron_expression: "0 0 2 * * ?"
        timezone_id: "UTC"

resources:
  jobs:
    my_pipeline_job:
      tasks:
        - task_key: extract
          notebook_task:
            notebook_path: ../src/extract.ipynb

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

        - task_key: load
          depends_on:
            - task_key: transform
          notebook_task:
            notebook_path: ../src/load.ipynb

uv run pytest