Endpoint to upload documents.
Documents are saved to the persistent storage, parsed, chunked and embedded.
The file is indexed as a document in the SQL database, with its chunks, and related to its owner, company and collection for permission application.
To specify a workspace, set collection_type to one of the following:
private for a personal workspacecompany for a company workspaceworkspace for other workspacesIf workspace is specified, workspace_id must be provided.
If collection_type is not specified, it defaults to company.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Request serializer for file upload.
255512Owner of the file (optional)
Company to associate the file with (optional)
30Type of collection to store the file in (private, company, or workspace)
private - privatecompany - companyworkspace - workspaceprivate, company, workspace Workspace ID when collection_type is 'workspace'
Size of chunks for document processing (optional)
Overlap between chunks (optional)
OCR agent to use for processing (optional)
Enable complete document table extraction (optional)
High resolution OCR model name (optional)
OCR processing strategy (optional)
OCR processing timeout in seconds (optional)
OCR service URL (optional)
Enable visual ingestion processing (optional)
Default processing pipeline to use (optional)
Response serializer for file upload results.
Unique identifier for the uploaded file
Object type, always 'file'
Size of the file in bytes
Unix timestamp of when the file was created
Original filename of the uploaded file
Purpose of the file, always 'documents'
Processing status of the file