Use Extend to parse a document supplied as a file or file reference. The result includes structured chunks and block-level elements, the page count, and credits consumed. Pass those outputs to later steps for extraction or document review.
Parse and extract structured content from documents or file references.
Parse and extract content from documents using Extend AI
| Parameter | Type | Required | Description |
|---|
file | file | Yes | Document to be processed |
outputFormat | string | No | Target output format (markdown or spatial). Defaults to markdown. |
chunking | string | No | Chunking strategy (page, document, or section). Defaults to page. |
engine | string | No | Parsing engine (parse_performance or parse_light). Defaults to parse_performance. |
apiKey | string | Yes | Extend API key |
| Parameter | Type | Description |
|---|
id | string | Unique identifier for the parser run |
status | string | Processing status |
chunks | json | Parsed document content chunks |
blocks | json | Block-level document elements with type and content |
pageCount | number | Number of pages processed |
creditsUsed | number | API credits consumed |
