Databricks
Connect Databricks to AI to review failed job runs, inspect error output, and launch existing workloads.
Inspect job definitions, run states, and available output, or start an existing workload with supplied parameters.
Cosa può fare il tuo agente in Databricks
Azioni raggruppate per attività. Ogni gruppo elenca le azioni che chiama.
Job and run inspection
Read workload definitions, execution states and run output.
- Get Job
- List Runs
- Get Run By Id
- Get Run Output
Existing job execution
Start a job with its identifier and optional workload parameters.
- Run Now Job
Attività da affidare al tuo agente
Compila le parti tra parentesi e collega l'eventuale seconda app indicata dall'attività.
Explain recent job failures
Summarize execution states and useful error details for a selected job.
Review job [job ID] during [time range]. Inspect failed runs and summarize affected tasks, errors, and follow-up checks.
Start a specified existing job
Run the chosen workload with the supplied parameters and report its run identifier.
Start existing job [job ID] with [parameters] for [purpose]. Check its current progress and tell me whether it has finished.
Azioni36
Tutte le azioni offerte dal connettore Databricks, con nome e id.
- Get Current User
get_current_userGet the current Databricks workspace principal profile for the connected personal access token. - List Jobs
list_jobsList Databricks jobs in the connected workspace with optional pagination, name filtering, and task expansion. - Get Job
get_jobGet one Databricks job, including its current settings and optional continuation page token. - Create Job
create_jobCreate a Databricks job from a raw official Jobs API settings object and return the new job ID. - Update Job By Id
update_job_by_idUpdate an existing Databricks job by ID using the official partial-update payload fields. - Delete Job
delete_jobDelete a Databricks job by ID. - Run Now Job
run_now_jobTrigger an immediate run for a Databricks job with optional parameter maps and idempotency token. - List Runs
list_runsList Databricks job runs with optional job, state, time-range, and pagination filters. - Get Run By Id
get_run_by_idGet one Databricks job run by run ID. - Get Run Output
get_run_outputGet the output payload for one Databricks run, including notebook output or error details when available. - Cancel Run
cancel_runCancel a Databricks job run by run ID. - Submit Run
submit_runSubmit a one-time Databricks run from a raw official Jobs API submit payload and return the run ID. - List Clusters
list_clustersList Databricks clusters with optional paging, filtering, and sorting controls from the official clusters API. - Get Cluster
get_clusterGet one Databricks cluster by cluster ID. - Create Cluster
create_clusterCreate a Databricks cluster from a raw official clusters create payload and return the new cluster ID. - Edit Cluster
edit_clusterEdit an existing Databricks cluster by cluster ID using a raw official clusters edit payload. - Start Cluster
start_clusterStart a terminated Databricks cluster by cluster ID. - Permanent Delete Cluster
permanent_delete_clusterPermanently delete a Databricks cluster by cluster ID. - List Cluster Node Types
list_cluster_node_typesList Databricks cluster node types that are available in the connected workspace region. - List Cluster Zones
list_cluster_zonesList Databricks cluster availability zones for the connected workspace when the API is supported.
Come si accede a Databricks
- Metodo di accesso
- Chiave APIConnect with a Databricks personal access token and workspace URL.
- Ti serve
- The token needs access to the jobs and runs you want to inspect.
- Note
- Starting a job executes its workload and may incur compute costs. Run output depends on the workload and may be limited.