Manage PDFs in Your Chatbot

Control how PDFs are crawled and which files your chatbot can access.

In this article

• Enable or Disable PDF Crawling

• Show or Hide Specific PDF Files After a Crawl

Enable or Disable PDF Crawling

Choose whether your chatbot includes PDFs during the crawl process.

When you start a new crawl, you can decide if PDFs should be part of your chatbot’s knowledge base or left out to keep things more focused.

How to enable or disable PDF crawling

1. Open the Knowledge tab.

2. In the upper right corner, click New Crawl.

3. Under Site Crawl, enter the URL of the website you want to crawl.

4. At the bottom of the setup options, look for Crawl PDFs Found on Pages.

5. Toggle this option off if you want to exclude PDFs. Leave it on to include them.
   

Note: PDF crawling is turned on by default.

Show or Hide Specific PDF Files After a Crawl

Fine-tune exactly which PDFs your chatbot can reference.

Once your crawl is complete, you can review all detected files and decide which PDFs should be included or excluded from the chatbot’s responses.

How to show or hide PDF files

1. Open the Knowledge tab.

2. Click into the crawl where you want to manage PDF visibility.

3. Click the Files tab.

4. In the upper right corner, click Show/Hide Files.
   

5. Use the search bar or scroll through the list to find the PDF files you want to blacklist.

6. Select the files you want to remove from being included. This will restart the crawl and exclude those files.