Use Pulse to extract text and structured content from PDFs, images, and Office files with optical character recognition (OCR). Supply a file URL or upload, select pages when needed, and choose the supported Markdown, text, or JSON output options.
Optional figure and table extraction returns captions and descriptions. The result also includes processing metadata such as file type, page count, and processing time. Pass the extracted content to later steps for review or summarization.
Use the block
Extract text from PDF documents, images, and Office files via upload or file references.
Actions
Pulse Document Parser
Parse documents (PDF, images, Office docs) using Pulse OCR API
Input
| Parameter | Type | Required | Description |
|---|---|---|---|
file | file | Yes | Document to be processed |
pages | string | No | Page range to process (1-indexed, e.g., "1-2,5") |
chunking | string | No | Chunking strategies (comma-separated: semantic, header, page, recursive) |
chunkSize | number | No | Maximum characters per chunk when chunking is enabled |
apiKey | string | Yes | Pulse API key |
Output
| Parameter | Type | Description |
|---|---|---|
markdown | string | Extracted content in markdown format |
page_count | number | Number of pages in the document |
job_id | string | Unique job identifier |
bounding_boxes | json | Bounding box layout information |
extraction_url | string | URL for extraction results (for large documents) |
html | string | HTML content; returned only when the hidden returnHtml input is enabled |
structured_output | json | Structured output; Sim exposes no input for supplying a schema, so this is always null |
chunks | json | Chunked content if chunking was enabled |
figures | json | Extracted figures; returned only when the hidden extractFigure input is enabled |