> For the complete documentation index, see [llms.txt](https://docs.datasaur.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasaur.ai/compatibility-and-updates/release-notes/version-6/6.93.0.md).

# 6.93.0

December 19, 2024

## **What's new** 💡

### **Data Studio**

* Bounding Box Labeling — Updated tooltip copy for the hide/unhide icon in the Bounding Box Labels extension to enhance clarity.
* Self-Assignment — Improved handling of available documents in cases where consensus has not been reached.

### **LLM Labs**

* API Key — Improved API key generation in LLM Labs; API keys will now start with "ds-".
* Automated Evaluation — Added a "Use in Sandbox" button in automated evaluation test reports for users to improve their prompts.
* Automated Evaluation — Added a new feature to use "Custom Metrics" in automated evaluation.
* Direct Access LLMs — Added Gemini 2.0 Flash from the Vertex AI provider.
* Free Trial — LLM Evaluation free trial quota has been upgraded to 5.
* Model Catalog — The "Try in Sandbox" button will automatically generate a prompt once it is clicked.

## **Bug fixes** 🐞

### **Data Studio**

* Fixed an issue in Bounding Box Labeling where Bounding Box selection was cleared when opening the context menu.
* Fixed an issue in Bounding Box Labeling where overlapping bounding boxes disappeared after resizing stacked boxes.
* Fixed an issue where the "Label All" button in the Search extension was squeezed.
* Fixed an issue where the "Upgrade My Plan" button in expired workspaces was squeezed.

### **LLM Labs**

* Fixed an issue where the "Use in Sandbox" behavior in automated evaluation test reports was inconsistent.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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://docs.datasaur.ai/compatibility-and-updates/release-notes/version-6/6.93.0.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.