# Extracting Insights

### <mark style="background-color:purple;">Get Insights From Your Data</mark>&#x20;

Once you have completed your data setup, you can extract insights from your data by detecting outliers and edge cases.

This code snippet below generates Manot's insights on outliers that your model will perform poorly on. Once it has completed processing, Manot will return an ID value which we will use in the next step to visualize the insights Manot has identified.&#x20;

```
insight = manot.insight(
    name="insight_example",
    setup_id=setup["id"],
    data_path="/path/to/data",
    data_provider="local",  # it can be "s3", "local" or "deeplake"
    percentage="percentage" # percentage of images to be considered insight should be larger than 0 and less or equal than 100
)
```

## <mark style="background-color:purple;">Visualize Your Data</mark>

Finally, we will use the ID generated in the previous step to visualize the outliers that Manot has identified.&#x20;

```
insight_info = manot.get_insight(insight["id"])
manot.visualize_data_set(insight_info['data_set']['id'], deeplake_token)
```

*Note: Providing a Deep Lake token in the line of code below is only required if you used* [*Deep Lake*](/manot/product-guide/using-manot-with-activeloop.md) *as the data storage*

Example of output:

<figure><img src="/files/3IvLgYiM6deXcFMpyJGo" alt=""><figcaption></figcaption></figure>

To see a full end-to-end example, visit our [Colab notebook](https://colab.research.google.com/drive/1QQ-xnShfpQx9skpzlT3u80n3lw_gM7Y-?usp=sharing#scrollTo=eab35eb2-5bdd-4715-a721-23fb188ca1ed).


---

# 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://manot.gitbook.io/manot/product-guide/extracting-insights.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.