Common text processing parameters

Lanuage restrictions with the text processing APIs

Text classification

You can use the classification API with English language documents only.

Text extraction

You cannot use the extraction API with a mixed-language document when the languages do not share a common script. However, you can use documents with a mix of English and one other language in any script. For example, you can extract text from images in a document with a mix of English and French text because both languages are Latin-based. However, you cannot extract text from images in a document with a mix of Japanese and French text.

You can use the text extraction API to extract key-value pair data from English language documents only.

Supported handwritten languages

If your document contains text in English handwriting, use the en_hw language code in your API request body.

Supported machine-printed languages

The following table provides details about the languages supported by the text extraction API for printed text recognition:

Defining schemas with the schemas field

Based on the layout, documents can be broadly classified into the following types:

Variable layout documents

Documents without a consistent structure, such as invoices, purchase orders, or passports, where the structure spans multiple pages.

Fixed layout documents

Structured documents where each page follows a pre-defined format such as a tax form where each page has a specific layout.

"semantic_config": {
  "schemas": [ {
      "document_type": "Receipt",
      "document_description": "A receipt issued for a purchase at ABC store.",
      "fields": {
        "receipt_number": {
          "default": "",
          "example": "R-20241027-ABC",
          "description": "Unique identifier on the receipt."
        },
        "customer_name": {
          "default": "",
          "example": "John Smith",
          "description": "Full name of the customer or payee."
        },
        "date_of_transaction": {
          "default": "",
          "example": "2023-01-01",
          "description": "Date when the purchase or payment occurred."
        },
        "total_paid": {
          "default": "",
          "example": "8.64",
          "description": "Final amount paid by the customer."
        },
        "payment_method": {
          "default": "",
          "example": "Credit Card",
          "description": "How payment was made, such as cash, card, check, etc.)."
        },
      }
  } ]
}

Controlling how pre-defined and custom schemas interact with the schemas_merge_strategy field

You can define how custom schemas you create interact with the pre-defined schemas supported by the text processing API.

The following table provides details about the different ways pre-defined and custom schemas are processed when you configure the schemas_merge_strategy setting in the semantic_config parameter:

By default, if you create a custom schema for a document type that matches a supported pre-defined schema, both schemas are merged before being used to process key-value pair data in your document.