> For the complete documentation index, see [llms.txt](https://docs.unitlab.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.unitlab.ai/ai-models/how-to-use.md).

# How To Use?

In the previous sections on [Model Integration](/ai-models/model-integration.md) and [Model Management](/ai-models/model-management.md), we explored Built-in AI Models and the integration of your own AI models. In this section, we will discuss how to effectively use both types of models within your project. 

{% hint style="info" %}
Learn how to integrate your own models into Unitlab Annotate on the [Model Integration](/ai-models/model-integration.md) page.
{% endhint %}

{% content-ref url="/pages/osazGEvd7j9p7nTnrOyM" %}
[Model Integration](/ai-models/model-integration.md)
{% endcontent-ref %}

If you have already integrated your own AI models into Unitlab Annotate, they appear on the AI Models page alongside other built-in models.

<figure><img src="/files/yPgZM6fXhPo5skmP2Gd6" alt=""><figcaption><p>Unitlab Annotate: AI Models Page</p></figcaption></figure>

### Create a New Project

You can start annotating your data by creating a project with your integrated AI model. Learn how to create a project on the "[Setup a Project](/project-management/setup-a-project.md)" page.

{% content-ref url="/pages/ra37iaceX75ulYimZO2l" %}
[Setup a Project](/project-management/setup-a-project.md)
{% endcontent-ref %}

When creating a new project, you can select your own AI model that has been integrated into Unitlab Annotate. On the [Model Integration](/ai-models/model-integration.md) page, we have experimentally integrated a demo AI model called **YOLOv8 - Vehicle Segmentation** into Unitlab Annotate. Let's use this integrated AI model in this demo project.

<figure><img src="/files/S5MlMcldw3lLHiXUjKRZ" alt=""><figcaption><p>Unitlab Annotate: Creating a Project for a Demo of the Integrated AI Model</p></figcaption></figure>

### How to Use?

After successfully creating the project by following the steps on the [Setup a Project](/project-management/setup-a-project.md) page, you can find the project on the list of Projects page of Unitlab Annotate.

<figure><img src="/files/zILUvxVGyV0fohvznOsG" alt=""><figcaption><p>Unitlab Annotate: A Demo Project Featuring the Integrated AI Model</p></figcaption></figure>

Your integrated AI models can be used by the following auto-annotation tools of Unitlab Annotate.

1. [Batch Auto-Annotation](/auto-labeling/batch-auto-annotation.md)&#x20;
2. [Crop Auto-Annotation ](/auto-labeling/crop-auto-annotation.md)

Let's annotate images using [Batch Auto-Annotation](/auto-labeling/batch-auto-annotation.md) with our own integrated AI models, as shown in the demo video below.

{% embed url="<https://homepage-files.s3.us-east-2.amazonaws.com/docs-contents/docs-ai-usecase-batch.mp4>" %}
Unitlab Annotate: Batch Auto-Annotation using the Integrated AI Model
{% endembed %}

In the second option, you can use your integrated AI models with the [Crop Auto-Annotation](/auto-labeling/crop-auto-annotation.md) tool, as demonstrated in the following video.

{% embed url="<https://homepage-files.s3.us-east-2.amazonaws.com/docs-contents/docs-ai-usecase-crop.mp4>" %}
Unitlab Annotate: Crop Auto-Annotation using the Integrated AI Model
{% endembed %}

Discover how to use the [Batch Auto-Annotation](/auto-labeling/batch-auto-annotation.md) and [Crop Auto-Annotation](/auto-labeling/crop-auto-annotation.md) tools with the built-in AI models of Unitlab Annotate.

{% content-ref url="/pages/b13vbkFvSTBRG75cE4Q7" %}
[Batch Auto-Annotation](/auto-labeling/batch-auto-annotation.md)
{% endcontent-ref %}

{% content-ref url="/pages/M5WwRUBn54zG141bDr4O" %}
[Crop Auto-Annotation](/auto-labeling/crop-auto-annotation.md)
{% endcontent-ref %}


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.unitlab.ai/ai-models/how-to-use.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.