Managed Data Sink

Use LlamaCloud managed index as data sink.

Configure via UI

Configure via API / Client

Simply set data_sink_id to None when creating a pipeline

Python Client

pipeline = {
  'name': 'test-pipeline',
  'transform_config': {...},
  'embedding_config': {...},
  'data_sink_id': None
}

pipeline = client.pipelines.upsert_pipeline(request=pipeline)

TypeScript Client

const pipeline = {
  'name': 'test-pipeline',
  'transform_config': {...},
  'embedding_config': {...},
  'dataSinkId': null
}

pipeline = await client.pipelines.upsertPipeline(pipeline)