# Website

Website sources help you use data from web-based platforms to train our AI Models. You can either enter the website URL (<https://your-website.com>) or the sitemap URL(<https://your-website.com/sitemap.xml>) to train our models.&#x20;

As of now, data from the following web-based platform can be used out of the box.&#x20;

* Regular websites
* WordPress
* Shopify
* Wix
* Zendesk
* GitBook
* Sitemaps
* Magento 2

### Add a new website

To add a new website source, navigate to the "Data Sources" sidebar and Click on "Add Source". Choose "Website" as the source and click on it

On the next form, add a name for your website and the link to your website or sitemap. If everything is in order, you can click on the "Add Source" button.

Once you save it, you will be able to see the links we can find on your website.&#x20;

<figure><img src="/files/7lgOFvZHf57kgmjkY4sz" alt=""><figcaption><p>Add a new website as source to bodt training data</p></figcaption></figure>

### Train Model

To train a model chose the links you want to use to train our AI models and click on "Train Selected".&#x20;

In case you want to use all the URLs, click on "Train All" and the system will use all website links to train the bot.&#x20;

<figure><img src="/files/LOumdjP0420JR1jh66BJ" alt=""><figcaption></figcaption></figure>

### Remove a link

In case you want to remove the URLs used earlier as part of the training data, simply click on the "Delete" link next to it. It will remove the URL from the system and will not be used further to answer any queries.&#x20;

### Delete the website as a source

If you would like to remove the entire website as the source for bodt, simply navigate to the required source and click on the "Delete Source" button to remove it from the system.&#x20;

### Tutorial

{% embed url="<https://www.loom.com/share/c8a2cdb79ccd4072af4f511cafaa6b52?sid=5cf9d9d1-e386-45b6-83c5-19774afa3441>" %}
How to add a website to bodt.io sources
{% endembed %}


---

# 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.bodt.io/data-source/website.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.