Skip to main content

Train on your website

Website URL Training

 

Connect your AI agent to web-based content:

  • Enter URLs of websites that contain relevant information. Make sure the URLs are accessible and up-to-date.

  • Specify Crawl Depth to control how many linked pages will be processed. A deeper crawl may uncover additional relevant content.

  • Set Exclusion Patterns to filter out irrelevant content. This helps streamline the training process and improve the quality of the data collected.

This feature allows your AI agent to learn from diverse sources, enhancing its knowledge and capabilities. Take advantage of the flexibility in adjusting crawl depth and exclusion patterns to tailor the training experience to your specific needs.

Please enter a valid URL starting with "https://" to proceed. Ensure that you review the URLs for accuracy before submitting.

 

 

 

Now you have two options:  

  1. Start Training Immediately:
    If you're ready to begin, you can initiate the training process right away. This option allows your AI agent to begin learning from the available data without any further setup. In this case, Chatislav will automatically find all web pages for the root website.
    (Step 1 -Start training)

  2. Focus on the Details:
    Alternatively, you can take some time to refine the process. If you do not provide a sitemap URL, we will attempt to guess it. This may include enabling website crawling, allowing your AI agent to gather information from linked pages on the specified websites.
    (Step 2 - Website Crawler - Start training)

 

image2.webp

Note: Please adjust the "Max Pages" setting according to your preferences.

 

After the crawler is finished, select or deselect the URLs you want to include or exclude, and then click the "Add" button.

 

 

Now, your URLs are ready for training: