Get Document
Returns detailed information for a single document.
Authorizations
Every request authenticates with an API key: Authorization: Bearer {API_KEY}. App endpoints take an app API key; knowledge endpoints take a knowledge base API key (Get Started).
Keep keys server-side; never embed them in client code. Requests with a missing or invalid key fail with HTTP 401 (unauthorized).
Query Parameters
all returns all fields including metadata. only returns only id, doc_type, and doc_metadata. without returns all fields except doc_metadata.
all, only, without Response
Document details. The returned fields depend on the metadata query parameter.
Document identifier.
Position index within the knowledge base.
How the document was uploaded. upload_file for file uploads, notion_import for Notion imports.
Data source details. For file uploads, this detail endpoint returns the full file object under upload_file (the list endpoint returns only upload_file_id).
ID of the processing rule applied to this document.
Knowledge-base-level processing rule configuration.
Document-level processing rule configuration.
Document name.
Origin of the document. api for API creation, web for UI creation.
ID of the user who created the document.
Unix timestamp of document creation.
Number of tokens in the document.
Current indexing status, e.g. waiting, parsing, cleaning, splitting, indexing, completed, error, paused.
Error message if indexing failed, null otherwise.
Whether the document is enabled for retrieval.
Unix timestamp when the document was disabled, null if enabled.
ID of the user who disabled the document, null if enabled.
Whether the document is archived.
Display-friendly indexing status for the UI.
Number of times this document has been retrieved.
Document chunking mode. text_model for standard text, hierarchical_model for parent-child, qa_model for QA pairs.
Language of the document content.
Document type classification, null if not set.
Custom metadata key-value pairs for this document.
Unix timestamp when processing completed, null if not yet completed.
Unix timestamp of last update, null if never updated.
Time taken for indexing in seconds, null if not completed.
Number of chunks in the document.
Average character length of chunks.
Status of summary indexing, null if summary index is not enabled.
Whether the document needs summary generation.