> For the complete documentation index, see [llms.txt](https://docs.imerit.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.imerit.net/core-concepts/workflow/plugin.md).

# Plugin

If you have any Single Model plugins active in your project, tasks passed as input will be sent to be processed by the plugin. The processed task, if the plugin returned no errors, will be returned as output.

<figure><img src="https://3895963154-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FTcOUG6rfWxqGM0N4db2P%2Fuploads%2F1R4ADA9m7SfD9ht7kFvk%2Fimage.png?alt=media&amp;token=130ca8a2-bd1b-4f33-b1bb-5cb65dd34f27" alt="" width="440"><figcaption></figcaption></figure>

The green or red dot next to the chosen plugin's name indicates its liveness. Red means the plugin is down, and green means the plugin is up.

{% hint style="warning" %}
If you re-queue tasks to a *Plugin* stage, Hub will not automatically send them to be processed by the plugin. They will instead be shown as being in the *Plugin* stage unprocessed.

To have the tasks be processed by the plugin, from the *Plugin* stage's settings, click on the three dots and then on *Re-Run*. The plugin will be run on all tasks currently in the *Plugin* stage.

<img src="https://3895963154-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FTcOUG6rfWxqGM0N4db2P%2Fuploads%2F57vjOrJGEYMh4adL1suL%2Fimage.png?alt=media&amp;token=fed4c2ce-2845-4909-a4a9-145a7c559eac" alt="" data-size="original">
{% endhint %}

#### Setup

<figure><img src="https://3895963154-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FTcOUG6rfWxqGM0N4db2P%2Fuploads%2FxzolHa15MzX0q7ejtkyD%2Fimage.png?alt=media&amp;token=d1ebf93e-51da-457e-b244-390cda26fb71" alt=""><figcaption></figcaption></figure>

In the first dropdown, select the *Model* plugin to use in this stage. Tasks passed as input to this stage will be sent to the *Model* plugin you choose here.

In the *Load Preset* dropdown, you can select a plugin setting preset which has been saved earlier for the current project and selected plugin. [See here for more information on setting and loading presets](/plugins/introduction-to-plugins/plugin-configuration-and-preset-management.md).

If you disable **overwrite existing annotations**, the plugin will not overwrite annotations existing on the asset – it will instead append to them.

In the dropdowns below, pair the plugin's classes with classes in your project. For example, if your plugin is a detector, detecting various types of objects, it may have classes such as `car`, `traffic_light`, etc. Here, you would match them with your project's own "Car" and "Traffic Light" classes.

You may additionally pass configuration as JSON in the text field.


---

# 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.imerit.net/core-concepts/workflow/plugin.md?ask=<question>&goal=<user_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.
