> 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/june-2025/june-10-support-for-reducto-pdf-preparation-text-geotagging-bug-fixes.md).

# June 10: Support for Reducto PDF preparation, text geotagging, bug fixes

### New Features

* :bulb: Graphlit now supports [Reducto](https://reducto.ai/) as a preparation service for PDF text extraction.
* We have added support for geotagging as a summarization type. We will use an LLM to infer one or more geolocated features from the text or transcript, and return the data in GeoJSON format.
* ⚠️ We have removed support for Azure OpenAI built-in model deployments.  You can still provide your own custom deployments of Azure OpenAI models, from your own Azure subscription, but we no longer support GPT-4 and other legacy models with Azure OpenAI.

### Bugs Fixed

* GPLA-4306: Uppy handler not parsing 'userId' from JWT
* GPLA-3720: Failing to process Spreadsheet leaves content in Indexed state.
* GPLA-4316: Failing to filter content with empty string on 'boundaries'
* GPLA-4279: Google Drive feed still says 'Running' but it's read all 100 files