Looking to empower your chatbot with comprehensive knowledge from a specific document? The Document Scraper is here to assist! In this article, we'll explain how to use the Document Scraper effectively.
In addition to adding domain knowledge, you may want to incorporate much more information into your chatbot. By using the Document Scraper, all relevant information from specific documents is 'scraped' and integrated into your chatbot's knowledge! This eliminates the need to manually add all data, simplifying the maintenance of your chatbot.
Check out this video:
1. Accessing the Document Scraper
To get started, create a new chatbot or open an existing one where you want to include information from a specific document Go to 'Sources' to find the Document Scraper.
2. Adding the document
Once in the Document Scraper environment, you can easily add and manage your documents. Enter the file which you want to extract information from and the scraping will begin immediately.
The status of the scraping process and the last time the document was scraped will be displayed. For larger documents, it may take some time to complete the entire scraping process.
3. Editing, downloading or deleting a scraped document
If you want to edit, download or delete a specific document from the Document Scraper, simply click on the designated button next to the document.
Note: Removing a document will also erase all the knowledge that the chatbot gained from that particular document.
4. Testing the chatbot with document knowledge
Once the scraping process is complete, you can test your chatbot using the knowledge acquired from the scraped document. This can be done through the Interactive tester.
Important: If the information on your document contradicts the manually added prompts, the chatbot will always prioritize the instructions from the prompts and use that information to generate answers, regardless of the scraped data.