# Tagging

This guide provides an overview and step-by-step instructions for using the **Manual Tagging for Embedding Analysis** feature in Catalyst. This powerful tool allows users to create, manage, and analyze tags for data points in their embeddings visualizations, enhancing dataset organization and analysis.

***

#### **1. Overview**

The tagging feature enables users to:

* Create tags for individual data points or clusters.
* Filter and analyze data efficiently based on meaningful tags.
* Integrate tags into the dataset for improved data exploration and insights generation.

***

**2. User Flow**

**Adding Tags**

1. Navigate to the embeddings visualization screen.
2. Use the **lasso tool** to select clusters or individual points.
3. Click the **Tag** button in the header (enabled after selection).

<figure><img src="/files/zcLcgQcpQiPgk4wfKmY0" alt=""><figcaption></figcaption></figure>

4. A modal appears prompting you to **Add Tags**.
5. Enter the desired tags and press **Enter** to add.
6. The modal dynamically adjusts as you add new tags.
7. Tags are appended to the **Tags** column in the dataset.

**Filtering by Tags**

1. Open the **Filter** menu in the embeddings view or dataset tab.
2. Select the tags to filter by; multiple tags can be combined using **AND logic**.
3. View the filtered data in the visualization or dataset table.

**Editing and Deleting Tags**

* Tags can be modified or removed directly from the dataset or the **Prediction Details** screen.
* Hover over a tag to view its full name and the **Delete** button.
* Click the **Delete** button to remove the tag from the data point.

***

#### **4. Tagging Workflow in Evaluations > Dataset Tab**

1. Navigate to the **Dataset** tab under **Evaluations**.
2. Locate the **Tags** column in the dataset table.
3. Click **+Add** to enter cursor mode for adding tags.
4. After entering a tag, press **Enter** to save it.
5. A new line appears to add additional tags (no limit).
6. The **+Add Tag** button reappears after 1 second to enable further additions.


---

# 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.raga.ai/ragaai-catalyst/human-feedback-and-annotations/tagging.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.