Encerramento

Databricks com o SDK em Python

Avi Steinberg

Senior Software Engineer

Consultar modelos de IA no Databricks

WorkspaceClient.serving_endpoints.query()

Usar modelos de IA para executar SQL em dados do Databricks

SQLDatabase.from_databricks(catalog, schema, warehouse_id)
SQLDatabaseToolkit(db, llm)
create_sql_agent(llm, toolkit, verbose)
agent.run("your question..")

Criar e gerenciar clusters

w.clusters.create(spark_version, cluster_name)
w.clusters.delete(cluster_id)
w.clusters.start(cluster_id)
w.clusters.get(cluster_id)

Criar e gerenciar jobs

w.jobs.create(
    name, 
    tasks=[
      jobs.Task(
          description,
          notebook_task=jobs.NotebookTask(notebook_path),
          task_key
          )
    ],
    schedule=jobs.CronSchedule(quartz_cron_expression,timezone_id),
    timeout_seconds, 
)

Juntando tudo

Job do Databricks e Modelo de IA

Parabéns!

Databricks com o SDK em Python