> For the complete documentation index, see [llms.txt](https://docs.xtreme1.io/xtreme1-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.xtreme1.io/xtreme1-docs/changelog/v-0.7.md).
# V 0.7
New LLM Text Annotation
## Release v0.7.2
Release v0.7.2 (Oct 09 2023)
1. Fixed the issue of missing Class in image object detection model;
2. Fixed the abnormal login status issue of the point cloud tool;
3. Optimized document.
## Release v0.7.1
Release v0.7.2 (May 05 2023)
1. Fixed the problem of exporting no class after importing class;
2. Fixed the problem that the MinIO pre-signed address check fails;
3. Fixed the problem that Chinese characters appear in the url;
4. Fixed data result and add classID;
5. Fixed text-dataset load bug;
6. Fixed upload by url.
## Release v0.7.0
Release v0.7.0 (April 28 2023)
## What's new?
Multiple rounds of dialogues annotation refer to the process of annotating a conversation between two or more parties through multiple iterations or rounds of annotation. In this process, after annotating each round of dialogue, the annotations are reviewed and corrected if necessary before proceeding to the next round of annotation.
### **Text annotation for LLM**
* Add new data category - Text is support;
* Allow user to upload text datasets;
* New thumbnails and UI styles;
* Support to import and export data in the required format
Text annotation interface with Xtreme1 v0.7.0
* Sample dataset:
```json
[
{ "id": "6f1d0711", "parentId": null, "text": "Hi!", "role": "prompter" }
,js
{ "id": "4a24530b", "parentId": "6f1d0711", "text": "Hello! How can I help you?", "role": "assistant" }
,
{ "id": "a8c01c04", "parentId": "4a24530b", "text": "Do you have a recipe for potato soup?", "role": "prompter" }
,
{ "id": "f43a93b7", "parentId": "4a24530b", "text": "Who were the 8 presidents before George Washington?", "role": "prompter" }
,
{ "id": "c886920", "parentId": "6f1d0711", "text": "Hey buddy! How can I serve you?", "role": "assistant" }
,
{ "id": "cec432cf", "parentId": null, "text": "euirdteunvglfe23908230892309832098 AAAAAAAA", "role": "prompter" }
,
{ "id": "4f85f637", "parentId": "cec432cf", "text": "Sorry, I did not understand your request and it is unclear to me what you want me to do. Could you describe it in a different way?", "role": "assistant" }
,
{ "id": "0e276b98", "parentId": "cec432cf", "text": "I'm unsure how to interpret this. Is it a riddle?", "role": "assistant" }
,
{ "id": "89384709", "parentId": "0e276b98", "text": "No, I just wanted to see how you reply when I type random characters. Can you tell me who invented Wikipedia?", "role": "prompter" }
,
{ "id": "6d452c57", "parentId": "0e276b98", "text": "Sorry, my cat sat on my keyboard. Can you print a cat in ASCII art?", "role": "prompter" }
]
```
```
LLM text annotation dataset structure
├── test
│ ├── 00.json
```
This is still an early version of text annotation for LLM.
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.xtreme1.io/xtreme1-docs/changelog/v-0.7.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
