# 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


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://changelog.graphlit.dev/june-2025/june-10-support-for-reducto-pdf-preparation-text-geotagging-bug-fixes.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.