Ingest a file into a chunked document

POST 
/api/v1/documents/ingest

Parses an already-uploaded file and creates one Document split into one or more embedded chunks. The source format is detected from the file's content type: PDFs are parsed page-by-page; text/plain and text/markdown files are read as a single source. How the source is chunked is controlled by chunk_strategy.

Request

Responses

201

Ingestion completed synchronously (only when ?async=false). The document is fully indexed and ready for search.

202

Ingestion accepted. The document record has been created with status=pending and processing runs in the background. Poll GET /api/v1/documents/{document_id} until status is ready or failed.

400

Invalid request, file not found, or unsupported content type

401

Unauthorized

403

Forbidden

413

The file is too large to ingest synchronously (?async=false). Retry in async mode and poll the document status.