APIs

  1. Form Recognizer API (v2.1-preview.1)

    Form Recognizer extracts information from forms and images into structured data. It includes the following options:

    • Form - Extracts information from forms (PDFs and images) into structured data based on a model created from a set of representative training forms. Form Recognizer learns the structure of your forms to intelligently extract text and data. It ingests text from forms, applies machine learning technology to identify keys, tables, and fields, and then outputs structured data that includes the relationships within the original file.
    • Receipt - Detects and extracts data from receipts using optical character recognition (OCR) and our receipt model, enabling you to easily extract structured data from receipts such as merchant name, merchant phone number, transaction date, transaction total, and more.
    • Business Card - Detects and extracts data from business cards using optical character recognition (OCR) and our business card model, enabling you to easily extract structured data from business cards such as contact names, company names, phone numbers, emails, and more.
    • Layout - Extracts text and table structure from documents using optical character recognition (OCR).
  2. Form Recognizer API (v2.1-preview.2)

    Form Recognizer extracts information from forms and images into structured data. It includes the following options:

    • Form - Extracts information from forms (PDFs and images) into structured data based on a model created from a set of representative training forms. Form Recognizer learns the structure of your forms to intelligently extract text and data. It ingests text from forms, applies machine learning technology to identify keys, tables, and fields, and then outputs structured data that includes the relationships within the original file.
    • Receipt - Detects and extracts data from receipts using optical character recognition (OCR) and our receipt model, enabling you to easily extract structured data from receipts such as merchant name, merchant phone number, transaction date, transaction total, and more.
    • Business Card - Detects and extracts data from business cards using optical character recognition (OCR) and our business card model, enabling you to easily extract structured data from business cards such as contact names, company names, phone numbers, emails, and more.
    • Layout - Extracts text and table structure from documents using optical character recognition (OCR).
  3. Image Search API - v7

    The Image Search API lets partners send a search query to Bing and get back a list of relevant images. Note you should call the Image API if you need image content only. If you need other content such as news and webpages in addition to images, you must call the Search API which includes images in the response. You must display the images in the order provided in the response.

  4. LUIS API

  5. LUIS Endpoint API v2.0

    This API is currently available in:

    • China East2 - chinaeast2.api.cognitive.azure.cn
    • China North - chinanorth.api.cognitive.azure.cn
  6. LUIS Endpoint API v3.0

    This API is currently available in:

    • China East2 - chinaeast2.api.cognitive.azure.cn
    • China North - chinanorth.api.cognitive.azure.cn
  7. LUIS Endpoint API v3.0-preview

    This API is currently available in:

    • China East2 - chinaeast2.api.cognitive.azure.cn
    • China North - chinanorth.api.cognitive.azure.cn
  8. LUIS Programmatic API

  9. LUIS Programmatic APIs v2.0

    This API is currently available in:

    • China East2 - chinaeast2.api.cognitive.azure.cn
    • China North - chinanorth.api.cognitive.azure.cn
  10. LUIS Programmatic APIs v3.0-preview

    This API is currently available in:

    • Australia East - australiaeast.api.cognitive.microsoft.com
    • West Europe - westeurope.api.cognitive.microsoft.com
    • West US - westus.api.cognitive.microsoft.com