N8N Tools - Document Processor icon

N8N Tools - Document Processor

Process documents with OCR, text extraction and AI analysis using N8N Tools platform
Join our community

Actions6

Overview

The N8N Tools - Document Processor node enables automated processing of documents using OCR (Optical Character Recognition), text extraction, and AI-powered analysis. It supports multiple input sources including binary files, URLs, and Base64-encoded content. The node sends documents to an external API service for processing and can return results in various formats.

This node is beneficial in scenarios such as:

  • Extracting searchable text from scanned PDFs or images.
  • Analyzing document content with AI to classify or summarize.
  • Converting documents into structured data including tables and metadata.
  • Automating workflows that require document ingestion and processing without manual intervention.

Practical examples:

  • Automatically extracting invoice data from PDF attachments in emails.
  • Processing scanned contracts to extract key clauses and metadata.
  • Performing OCR on images uploaded by users to convert them into editable text.
  • Using AI analysis to categorize large batches of documents by topic or type.

Properties

Name Meaning
Operation The action to perform on the document. Options: Process Document, Process from URL, Extract Text Only, OCR Document, Analyze Document, Process Sync.
Input Source Source of the document input. Options: Binary File (from workflow binary data), URL (publicly accessible document URL), Base64 (Base64 encoded document content).
Binary Property Name of the binary property containing the file when Input Source is Binary File. Default is "data".
Document URL Publicly accessible URL of the document when Input Source is URL or operation is Process from URL.
Document (Base64) Base64 encoded document content when Input Source is Base64.
Processing Options Collection of options controlling processing details:
• Output Format: JSON, Text, Markdown, HTML
• Language: OCR language code (auto, en, pt, es, fr, de, etc.)
• Include Images: whether to extract images
• Include Tables: preserve table structures
• AI Analysis: enable AI-powered content analysis
• Extract Metadata: extract document metadata like author, creation date
Output How to return processed results. Options: JSON Response (default), Binary File (processed document as binary), Both (JSON data and binary file).

Output

The node outputs data in one of three ways depending on the selected Output property:

  • JSON Response: Returns a JSON object containing extracted text, metadata, AI analysis results, and other structured information about the document. This includes fields like extractedText, content, metadata, jobId, and processing timestamps.

  • Binary File: Returns the processed document as a binary file attached to the output item. The binary data is prepared with appropriate filename and MIME type (usually PDF).

  • Both: Returns both the JSON data and the binary file together in the output item.

If asynchronous processing is used, the node polls the job status up to 3 times with 10-second intervals. If the job does not complete in time, it falls back to synchronous processing to ensure results are returned.

Dependencies

  • Requires an API key credential for authenticating with the external N8N Tools API service.
  • The node makes HTTP requests to the configured API URL endpoint.
  • The external service must be reachable and the API key valid.
  • The workflow environment should allow outgoing HTTPS requests.
  • No additional local dependencies are required.

Troubleshooting

  • Invalid subscription or API key: Error messages indicating 401 or 403 status codes mean the API key is invalid or subscription expired. Verify and update credentials.

  • No binary data found under property: When using binary input source, ensure the specified binary property exists and contains valid file data.

  • Unknown operation or input source: Check that the selected operation and input source values are supported and correctly spelled.

  • Document processing timeout: If the async job does not complete within ~30 seconds, the node attempts synchronous fallback. Persistent timeouts may indicate issues with the external processing queue or Redis service connectivity.

  • Document processing failed: Generic failure messages may include error details from the API. Review document format compatibility and API service status.

  • Missing or malformed document URL/Base64: Ensure URLs are publicly accessible and Base64 strings are properly encoded.

Links and References

This summary is based solely on static analysis of the provided source code and property definitions.

Discussion