> For the complete documentation index, see [llms.txt](https://changelog.graphlit.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://changelog.graphlit.dev/july-2024/july-28-support-for-indexing-workflow-stage-azure-ai-language-detection-bug-fixes.md).

# 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.
* :zap: We have deprecated the `OPENAI_IMAGE` service type, and developers should now use the LLM image service instead.
* :zap: We have removed the `language` field from `AudioMetadata` type, which has been replaced by the new `LanguageMetadata` type.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