Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / Documents, PDF & OCR

Documents, PDF & OCR

Parse PDF Documents with Nanonets via Webhook

When a document is uploaded to the webhook, it sends the PDF to Nanonets for parsing and returns the extracted data.

Import it free Sign in to open it

What it does

Workflow Overview This workflow automates PDF document parsing with Nanonets. Upload a document (via form or webhook), and get structured data—including line items—returned as an Excel file. Use the Form Trigger node for user-uploaded files, or Use the Webhook node for programmatic POST/file uploads. 3. Before The Nanonets API Call Setup Required Add your Nanonets API credentials in n8n’s credentials manager (HTTP Basic Auth). Insert your Nanonets Workflow ID in the HTTP Request nodes as needed.

The steps

  1. HTTP Request
  2. HTTP Request2
  3. Convert to File
  4. Code
  5. Code1
  6. Wait
  7. Webhook
  8. Respond to Webhook

Similar automations

Documents, PDF & OCRParse Documents with LlamaParse and OpenAI from Gmail77 stepsDocuments, PDF & OCRParse Documents with LlamaParse and GPT-4o-mini36 stepsRAG & Knowledge BasesParse Invoice Emails with Claude RAG and Weaviate11 stepsBuilding Blocks & UtilitiesParse and Format Dates with the Date and Time Node2 steps