Overview
Connect Docling to your data sources and destinations
Connectors
Connectors allow you to read documents from and write converted outputs to various storage systems and databases. Use connectors with the Batch API to process documents at scale.
Available Connectors
Vector databases
File and object storage
Amazon S3
Read and write S3-compatible storage, including IBM Cloud Object Storage.
Azure Blob Storage
Read and write Azure Blob containers.
Google Cloud Storage
Read and write GCS buckets.
Google Drive
Read and write Google Drive folders.
Databricks Volumes
Read and write Unity Catalog volumes.
Enterprise content management
SharePoint and OneDrive
Read and write SharePoint sites and OneDrive.
Box
Read and write Box folders.
IBM FileNet
Read documents from FileNet Content Manager.
Streaming
Connector Types
Source Connectors
Source connectors read documents for conversion. Multiple source connectors can be specified in a single batch job.
Target Connectors
Target connectors write converted document outputs.
Using Connectors
Connectors are configured as part of the sources and target fields in the Batch API request. See Batch API documentation. Chunk targets (Kafka, OpenSearch, AstraDB) also need chunking_options. See Chunking.
Each connector has specific authentication requirements and configuration parameters. See the individual connector pages for complete setup instructions.