# 6.100.0

February 13, 2025

## **What's new** 💡

### **Data Studio**

* Activity — A more granular tracking for Row and Document Labeling, capturing each answer for every submission.
* Bounding Box Labeling — Tesseract OCR is now enabled by default during project creation for automatic caption generation.
* Completed Project — Retained label colors based on status, consistent with the "In Review" project status, to provide clarity and improve the review process by making label statuses easily identifiable.
* Project Creation Wizard — Improved the layout of the Members table in Step 4 (Assignment Step) to enhance visibility and usability.
* Row / Document Labeling Extension — Improved dialog wording when replacing question sets for better clarity.
* Yes/No renamed to [True/False](https://docs.datasaur.ai/nlp-projects/lets-get-labeling/label-sets#id-5.-true-false) — To better align with the resulting value.

### **LLM Labs**

* Azure OpenAI — Supported Azure OpenAI integration connection via certificate.
* Evaluation — Improved our manual evaluation flow to let users create fine-tuning projects using Rating evaluation results.
* Free trial — Added dynamic rate limit configuration for free trial users.
* Knowledge base — Integrated docling in our knowledge base; users can now upload CSV and XLSX files in our knowledge base.
* Models catalog — Added an onboarding tutorial for the models catalog page.
* PAYGO — Added spending limiter for paying customers to prevent fraudulent cards.

## **Bug fixes** 🐞

### **Data Studio**

* Fixed an issue in Conversational Labeling where inactive labels were not visually indicated as inactive in message labels when “Show Labels from Inactive Label Set” was enabled.

### **LLM Labs**

* Fixed an issue where custom models could not be deleted.
* Fixed an issue where deploying a SageMaker JumpStart model caused a blank page.
* Fixed an issue where the Bedrock RAG runner tool call was implemented incorrectly.
* Fixed an issue where the Initial Prompt checkbox was not consistently checked.
* Fixed an issue where the total cost and total number of tokens used in the deployment page remained 0 after usage.


---

# 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://docs.datasaur.ai/compatibility-and-updates/release-notes/version-6/6.100.0.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.