Extract Data from Documents with AI
Transform your PDF documents and images into structured JSON data instantly. Support for invoices, bank statements, GRN, expenses, GST certificates, and Aadhar cards.
Upload Your Document
Select your PDF file and document type to extract structured data
Error
Success
Extraction Results
Powerful Features
Everything you need for efficient document processing
AI-Powered Extraction
Advanced AI technology ensures accurate data extraction from PDF documents and images with complex layouts.
Multiple Document Types
Support for 6 different document types with specialized extraction algorithms.
Structured JSON Output
Get clean, structured JSON data that's ready for integration with your applications.
Supported Document Types
Extract data from various business and personal documents
Invoice
Extract vendor details, line items, amounts, and payment terms from business invoices.
GRN
Process Goods Received Notes with supplier details, received items, and delivery information.
Expenses
Extract employee expense reports with categories, amounts, and approval details.
GST Certificate
Extract business registration details, GST numbers, and validity information.
Bank Statement
Extract account details, transaction history, and balance information.
Aadhar Card
Extract personal details, address, and verification information from Aadhar cards.
API Integration
Integrate our powerful extraction API into your applications
REST API Endpoint
POST /api/extract-document/{document_type}
Upload PDF files or multiple images and get structured JSON responses instantly.
URL Parameter:
- •
document_type- Type of document (invoice, grn, expenses, gst_certificate, bank_statement, aadhar_card)
Request Body:
- •
files[]- Document files (max 20MB each) - •
extract_mode- Optional: detailed, summary, items_only
File Rules:
- • PDF: Single file only
- • Images: 1-10 files (JPG, PNG, GIF, BMP, WEBP)
- • No mixing: Cannot upload PDF + images together
Example Requests:
# Single PDF
POST /api/extract-document/invoice
files[]: invoice.pdf
# Multiple Images
POST /api/extract-document/invoice
files[]: page1.jpg, page2.jpg, page3.jpg
Example Response
{
"success": true,
"message": "Document data extracted successfully for invoice",
"data": {
"document_type": "invoice",
"summary": {
"invoice_number": "INV-001",
"total_amount": 1250.00,
"currency": "USD"
},
"items": [...]
},
"extraction_metadata": {
"document_type": "invoice",
"file_count": 1,
"file_type": "pdf",
"extraction_method": "Gemini Flash 2.5",
"model_used": "gemini-2.0-flash-exp",
"processing_time_ms": 2341.5,
"extract_mode": "detailed"
}
}