Skip to main content

OCR (Optical Character Recognition)

The OCR API allows you to extract text from images, enabling powerful search capabilities for your applications. This feature is particularly useful for searching parts with printed text, labels, or documentation.

Overview​

The OCR module enables you to:

  • Extract text from images in multiple languages
  • Support various text formats (single line, multi-line, digits, special characters)
  • Integrate with Partium's search capabilities
  • Process images from different sources (camera, file upload)

Prerequisites​

Before using the OCR API, ensure you have:

  • A valid API key or access token
  • Images in supported formats (PNG, JPEG, BMP, ...)
  • Proper authorization for the organization you're working with

Getting Started​

For a practical example of OCR implementation, visit the Partium Help Center.

Integration Guide​

The OCR API is designed to work seamlessly with Partium's search capabilities. You can use the extracted text for:

  • Text-based searches
  • Attribute filtering
  • Hierarchy filtering
  • Custom search implementations