Pulse
Extract text from documents using Pulse OCR
Overview
Integrate Pulse into your workflow to extract text from PDF documents, images, and Office files. Supports URL-based or uploaded documents with optional chunking and layout analysis.
Setup
- Add the Pulse block to your workflow
- Enter your Pulse API key
- Upload a document or provide a URL
Configuration
| Parameter | Type | Required | Description |
|---|---|---|---|
apiKey | string | Yes | Pulse API key |
document | file/URL | Yes | Document to extract (PDF, images, DOCX, PPTX, XLSX; max 50MB) |
pages | string | No | Page range (e.g., 1-3,5) |
chunking | string | No | Chunking strategy: semantic, header, page, or recursive |
chunkSize | number | No | Max characters per chunk |
Tools
pulse_parser
Extracts text and structure from documents using Pulse OCR.
Output
| Parameter | Type | Description |
|---|---|---|
markdown | string | Extracted content in markdown format |
page_count | number | Number of pages |
job_id | string | Unique job identifier |
bounding_boxes | json | Bounding box layout information |
html | string | HTML content if requested |
structured_output | json | Structured output if schema provided |
chunks | json | Chunked content if chunking enabled |
figures | json | Extracted figures if enabled |
Supported Formats
- PDF documents
- Images (JPEG, PNG)
- Microsoft Office files (DOCX, PPTX, XLSX)
Notes
- Category:
tools - Type:
pulse - Maximum file size: 50MB