July 28: Support for indexing workflow stage, Azure AI language detection, bug fixes

New Features

• Added indexing workflow stage. This provides for configuration of indexing services, which may infer metadata from the content.

• Added AZURE_AI_LANGUAGE content indexing service, which supports inferring the language of extracted text or transcript.

• Added support for language content metadata. This returns a list of languages in ISO 639-1 format, which may have been inferred from the extracted text or transcript.

• Added support for MODEL_IMAGE extraction service. This provides integration with vision models beyond those provided by OpenAI. You can assign a custom specification and bring-your-own API key for image extraction models.

• ⚡ We have deprecated the OPENAI_IMAGE service type, and developers should now use the LLM image service instead.

• ⚡ We have removed the language field from AudioMetadata type, which has been replaced by the new LanguageMetadata type.

Bugs Fixed

• GPLA-2987: Extracting text with Azure Doc Intelligence does not extract hyperlinks