Ask Document

Ask Document node
Ask Document: ask questions about a document

Upload a document and ask it a question in natural language. The AI reads the document and generates an answer based on its content.

Type: TINYVISION_DOC_ASK Color: Purple (#8B5CF6) Credits: 10 per run Test: Required (cannot skip)

Configure fields

FieldTypeRequiredDescription
File URLFX formulaYesURL of the document (PDF, image, DOCX)
PromptFX formulaYesThe question to ask about the document
Output formatSelectNotext (default)

Example questions

DocumentPromptAnswer
Invoice PDF"What is the total amount and due date?""The total is $1,250.00, due by March 15, 2026."
Contract PDF"Who are the parties and what is the term?""The agreement is between Acme Corp and Globex Inc for a 24-month term."
Product spec"What are the key features?"Bullet list of features from the document
Meeting notes"What were the action items?"List of action items assigned to team members

vs other Vision nodes

NodeWhat it doesWhen to use
Read PDFExtracts ALL textWhen you need the full document text
Extract TextOCR on imagesWhen the document is an image/scan
Ask DocumentAnswers a QUESTIONWhen you need a specific answer, not all the text
Extract FieldsKey-value pairsWhen the document has labeled fields (invoices, forms)
Tip

Ask Document is the most flexible Vision node: you can ask anything. But it's also the most expensive (10 credits). Use Read PDF or Extract Text when you just need the raw text.

File URL sources

The file URL can come from:

  • Webhook payload: {{trigger.body.file_url}}
  • Form submission: {{trigger.file_upload.url}}
  • HTTP Request: {{http.body.download_url}}
  • Static URL: a direct link to a file hosted anywhere

Error handling

If the file can't be processed (corrupt, unsupported format, too large):

  • The node fails with an error message
  • Use Continue on error + If-Else to handle gracefully
  • Check file type before processing with an If-Else on the URL extension

Credits

This node consumes credits per execution. Monitor usage in Monitor → Credit Usage.