Extracta.ai
DashboardJoin Discord
  • extracta.ai
    • Introduction
    • Overview
  • API Reference
    • 🔓Authentication
    • 📁Supported File Types
  • Data Extraction - API
    • đŸ’ģAPI Endpoints - Data Extraction
      • 1. Create extraction
      • 2. View extraction
      • 3. Update extraction
      • 4. Delete extraction
      • 5. Upload Files
      • 6. Get results
    • Extraction Details
      • 🌎Supported Languages
      • âš™ī¸Options
      • 📋Fields
    • Receiving Batch Results
      • Polling vs Webhook
      • How to use the Webhook
    • đŸ•šī¸Postman Integration
  • Document Classification - API
    • đŸ’ģAPI Endpoints - Document Classification
      • 1. Create classification
      • 2. View classification
      • 3. Update classification
      • 4. Delete data
        • 4.1 Delete classification
        • 4.2 Delete batch
        • 4.3 Delete files
      • 5. Upload Files
      • 6. Get results
    • Classification Details
      • 📄Document Types
  • Documents
    • Custom Document
    • Resume / CV
    • Contract
    • Business Card
    • Email
    • Invoice
    • Receipt
    • Bank Statement
  • Support
    • 💁Tutorials
    • đŸŸĸAPI Status
  • Contact
    • 📧Contact Us
    • ❓FAQ
Powered by GitBook
On this page
  • Comprehensive Format Support
  • Currently Supported Formats:
  • Processing Capabilities
  • Getting Started

Was this helpful?

  1. API Reference

Supported File Types

At Extracta.ai, we understand the importance of versatility in document extraction processes. Our platform is engineered to accommodate a broad spectrum of document types, ensuring that you can seamlessly integrate our solutions into your workflow, regardless of the document formats you work with.

Comprehensive Format Support

Our AI-powered extraction technology is designed to handle documents in various formats, including image files, PDFs, and Microsoft Word documents. This capability ensures that Extracta.ai can meet your needs, whether you're processing scanned documents, digital files, or editable documents.

Currently Supported Formats:

  • Image Files: Ideal for scanned documents, photographs of documents, and screenshots (.jpeg, .jpg, .png, .tiff, .bmp).

    • image/jpeg
    • image/jpg
    • image/png
    • image/tiff
    • image/bmp
  • PDF: Suitable for digital documents that maintain their formatting across different platforms (.pdf).

    • application/pdf
  • Microsoft Word Document: Perfect for editable text documents created in Microsoft Word (.docx, .doc)

    • application/msword
    • application/vnd.openxmlformats-officedocument.wordprocessingml.document
  • Text Files: Essential for parsing data from plain text files, facilitating straightforward text extraction without formatting complexities (.txt)

    • text/plain

Processing Capabilities

Extracta.ai's sophisticated document parsing technology not only supports a wide range of file types but also ensures high accuracy in data extraction. Our platform leverages advanced Optical Character Recognition (OCR) techniques to extract text and data efficiently, even from complex document layouts.

Getting Started

To begin extracting data from your documents, simply upload your files in one of the supported formats via our API. For detailed instructions on how to upload your documents and create extraction requests, please refer to our API documentation.

By supporting multiple document formats, Extracta.ai aims to provide a flexible and comprehensive solution for your document extraction needs. Whether you're working with printed material, digital documents, or editable files, our platform is equipped to deliver precise and reliable extraction results.

PreviousAuthenticationNextAPI Endpoints - Data Extraction

Last updated 1 month ago

Was this helpful?

📁
1. Create extraction