Step-by-Step: PDF Analyzer Workflow in n8n

Step 1: Create a New Workflow

• Log in to n8n.io.
• Click “Create Workflow”.
• This opens your workspace to build the automation.

Step 2: Add a Form Trigger

• Use a Form Trigger Node to allow users to upload a PDF file.
• Configure the form:
  • Form Name: PDF Analyzer
  • Form Element: pdf_file
  • Element Type: File Upload

Step 3: Add OCR Node (Optional)

• If the PDF is scanned or image-based, add an OCR node to extract text.
• Use a third-party OCR service (e.g., Tesseract, Google Vision, or custom HTTP request).
• If the PDF is text-based, skip this step.

Step 4: Add LLM Node (e.g., Mistral)

• Add a Large Language Model (LLM) node to analyze the extracted text.
• Recommended model: Mistral (European model optimized for PDFs).
• Configure the node:
  • Prompt: "Extract structured financial data from this PDF."
  • Input: Connect to the OCR output or directly to the uploaded file if text-based.

Step 5: Process and Format Output

• Use a Markdown Viewer Node or Text Formatter Node to clean and format the output.
• This helps visualize structured data like:
  • Company name and address
  • Nature of business
  • Financial highlights
  • Shareholder and director info

Step 6: Export to Excel or Database

• Add a Google Sheets or Excel Node to store the extracted data.
• Alternatively, connect to a database node (e.g., MySQL, PostgreSQL) for structured storage.

Step 7: Optional Enhancements

• Add multiple LLM agents (e.g., Gemini, ChatGPT) for cross-validation.
• Include error handling and retry logic for failed extractions.
• Use conditional logic to handle different PDF formats.

@lerlerchan by LerLer Chan

|


|


|


|

Ler Travel Diary is using
Web Hosting and n8n on Hostinger

To be a smart saver, check out
ShopBack for more information.

Enjoy SGD5 discount voucher on
Klook with code 53E7UD

Need discount for your travels? Check out our travel deals page.