# What Plugin Do I Need?

{% hint style="info" %}
This page only mentions first-party plugins, that is, plugins officially created and supported by the Ango Hub development team.

For very specialized needs, you may create your own plugin. See: [Plugin Developer Documentation](/plugins/plugin-developer-documentation.md).
{% endhint %}

This quick guide helps you find the right plugin for common workflows. If you’re not sure which plugin to use, start here. Each question maps to the recommended plugin so you can move from setup to results faster.

<details>

<summary>1. How do I export my annotations to another format?</summary>

Use export plugins to download your annotations in the format needed for your training pipeline or external tools. The following plugins are available for this purpose:

* [Ango to COCO Converter](/plugins/first-party-ango-plugins/ango-export-converter-plugins.md)
* [Ango to YOLO Converter](/plugins/first-party-ango-plugins/ango-export-converter-plugins.md)
* [Ango to Mask Converter](/plugins/first-party-ango-plugins/ango-to-mask-converter.md)
* [CSV Export for Classification](/plugins/first-party-ango-plugins/csv-export-for-classification.md)

</details>

<details>

<summary>2. I have annotations in another tool. How do I import them?</summary>

If you already labeled data elsewhere and want to bring it into your workspace, use [Import Labels](/plugins/first-party-ango-plugins/import-labels.md) to ingest existing annotations.

</details>

<details>

<summary>3. How can I convert segmentation annotations to masks images?</summary>

Use [Ango to Mask Converter](/plugins/first-party-ango-plugins/ango-to-mask-converter.md) to export annotations as mask images.

</details>

<details>

<summary>4. How can I compare annotators or stages of labeling?</summary>

* Use [Stage Comparison](/plugins/first-party-ango-plugins/stage-comparison.md) to compare different labeling stages
* Use [Calculate Consensus Score](/plugins/first-party-ango-plugins/calculate-consensus-score.md) to measure agreement between annotators in consensus stage
* Export results for reporting with [Benchmark & Consensus Export](/plugins/first-party-ango-plugins/benchmark-and-consensus-export.md)

</details>

<details>

<summary>5. How can I retrieve how many annotations were created for each asset?</summary>

* Use [Statistics Export](/plugins/first-party-ango-plugins/statistics-export.md) to extract fine-grained counts from your projects.
* Use [TPT Export](/plugins/first-party-ango-plugins/tpt-export.md) to get basic counts for each asset & stage.

</details>

<details>

<summary>6. Can I use AI to help with labeling?</summary>

Use model plugins to produce preliminary labels. The following plugins are available for this purpose:

* [ChatGPT](/plugins/first-party-ango-plugins/chatgpt-deprecated.md)
* [YOLO | Object Detection](/plugins/first-party-ango-plugins/yolo-or-object-detection.md)
* [YOLO | Instance Segmentation](/plugins/first-party-ango-plugins/yolo-or-instance-segmentation.md)
* [Open World Object Detection](/plugins/first-party-ango-plugins/open-world-object-detection.md)
* [YOLO | Pose Estimation](/plugins/first-party-ango-plugins/yolo-or-pose-estimation.md)
* [YOLO | Image Classification](/plugins/first-party-ango-plugins/yolo-or-image-classification.md)
* [Optical Character Recognition](/plugins/first-party-ango-plugins/optical-character-recognition.md)

</details>

<details>

<summary>7. How can I see how long labeling takes and how each annotator is performing?</summary>

Use the [TPT Export](/plugins/first-party-ango-plugins/tpt-export.md) to export labeling duration and annotator performance metrics for analysis and reporting.

</details>


---

# 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.imerit.net/plugins/what-plugin-do-i-need.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.