Skip to main content
Last updated on

Ingest data from Anthropic

Beta

This feature is in Beta. Workspace admins can control access to this feature from the Previews page. See Manage Databricks previews.

This page shows how to create a managed Anthropic ingestion pipeline using Lakeflow Connect.

Requirements​

  • To create an ingestion pipeline, you must first meet the following requirements:

    • Your workspace must be enabled for Unity Catalog.

    • Serverless compute must be enabled for your workspace. See Serverless compute requirements.

    • To create a new connection, you must have CREATE CONNECTION privileges on the metastore. See Manage privileges in Unity Catalog.

      If the connector supports UI-based pipeline authoring, an admin can create the connection and the pipeline at the same time by completing the steps on this page. However, if the users who create pipelines use API-based pipeline authoring or are non-admin users, an admin must first create the connection in Catalog Explorer. See Connect to managed ingestion sources.

    • To use an existing connection, you must have USE CONNECTION privileges or ALL PRIVILEGES on the connection object.

    • You must have USE CATALOG privileges on the target catalog.

    • You must have USE SCHEMA and CREATE TABLE privileges on an existing schema or CREATE SCHEMA privileges on the target catalog.

  • To ingest from Anthropic, you must first configure authentication from Databricks. See Configure authentication to Anthropic.

Create an ingestion pipeline​

  1. In the sidebar of the Databricks workspace, click Data Ingestion.
  2. On the Add data page, under Databricks connectors, click Anthropic.
  3. On the Connection page of the ingestion wizard, select the connection that stores your Anthropic access credentials. If you have the CREATE CONNECTION privilege on the metastore, you can click Plus icon. Create connection to create a new connection with the authentication details in Create an Anthropic connection.
  4. Click Next.
  5. On the Ingestion setup page, enter a unique name for the pipeline.
  6. Select a catalog and a schema to write event logs to. If you have USE CATALOG and CREATE SCHEMA privileges on the catalog, you can click Plus icon. Create schema in the drop-down menu to create a new schema.
  7. Click Create pipeline and continue.
  8. On the Source page, select the tables to ingest.
  9. Click Save and continue.
  10. On the Destination page, select a catalog and a schema to load data into. If you have USE CATALOG and CREATE SCHEMA privileges on the catalog, you can click Plus icon. Create schema in the drop-down menu to create a new schema.
  11. Click Save and continue.
  12. (Optional) On the Schedules and notifications page, click Plus icon. Create schedule. Set the frequency to refresh the destination tables.
  13. (Optional) Click Plus icon. Add notification to set email notifications for pipeline operation success or failure, then click Save and run pipeline.

Examples​

Use these examples to configure your pipeline.

Ingest the entire schema​

The following pipeline definition file ingests all supported Anthropic tables into a destination schema:

YAML
resources:
  pipelines:
    anthropic_pipeline:
      name: anthropic_pipeline
      catalog: 'main'
      target: 'anthropic_data'
      ingestion_definition:
        connection_name: anthropic_connection
        objects:
          - schema:
              source_schema: 'default'
              destination_catalog: 'main'
              destination_schema: 'anthropic_data'

Ingest specific tables​

Ingest individual Anthropic tables. For a full list of supported tables, see Supported source tables.

The following pipeline definition file ingests individual Anthropic tables:

YAML
resources:
  pipelines:
    anthropic_pipeline:
      name: anthropic_pipeline
      catalog: 'main'
      target: 'anthropic_data'
      ingestion_definition:
        connection_name: anthropic_connection
        objects:
          - table:
              source_schema: 'default'
              source_table: 'audit_log_activities'
              destination_catalog: 'main'
              destination_schema: 'anthropic_data'
              destination_table: 'audit_log_activities'
          - table:
              source_schema: 'default'
              source_table: 'organizations'
              destination_catalog: 'main'
              destination_schema: 'anthropic_data'
              destination_table: 'organizations'
          - table:
              source_schema: 'default'
              source_table: 'users'
              destination_catalog: 'main'
              destination_schema: 'anthropic_data'
              destination_table: 'users'
          - table:
              source_schema: 'default'
              source_table: 'chats'
              destination_catalog: 'main'
              destination_schema: 'anthropic_data'
              destination_table: 'chats'

Declarative Automation Bundles job definition file​

YAML
resources:
  jobs:
    anthropic_job:
      name: anthropic_job
      schedule:
        quartz_cron_expression: '0 0 0 * * ?'
        timezone_id: 'UTC'
      tasks:
        - task_key: anthropic_ingestion
          pipeline_task:
            pipeline_id: ${resources.pipelines.anthropic_pipeline.id}

Common patterns​

For advanced pipeline configurations, see Common patterns for managed ingestion pipelines.

Next steps​

Start, schedule, and set alerts on your pipeline. See Common pipeline maintenance tasks.

Additional resources​

On this page