Building a well-structured knowledge base is essential for your chatbot, as it serves as the central repository of information for your company or organization. Ensure that all content is clear, readable, and comprehensive so the chatbot can accurately understand user inquiries and provide relevant responses. Our platform supports data indexing from websites, PDFs, text snippets, and Q&A to enhance your chatbot’s intelligence.
Your website is often the primary source of information for making your chatbot smarter. To add a website:
Toggle “Sync Subpages” to automatically sync all pages under the same domain (if needed).
In Advanced Settings, you can:
Add specific URLs to be included in addition to the main URL.
Use glob expressions (e.g., /*) to exclude all pages that begin with a certain prefix.
The Last Synced At column indicates when the website was last updated in the chatbot’s database.
Once a website is added, the system will process the data. The status may show:
By integrating website content, you can ensure your chatbot remains up-to-date with the latest company information, FAQs, and product details.
My sub-pages are not crawled
If you’re crawling subpages on a website but only one page is being crawled despite expecting multiple under the URL path, check the following:
The bot is not responding with knowledge from crawled pages
Your webpage’s content may not be set up correctly for crawling.
You can upload this content as documents or text snippets.
Do I need to crawl pages that are localised to different languages?
Our bot does not require the same knowledge in different languages, as we can translate it into the customer’s language. However, if the content differs by language, please crawl the specific pages so our bot can recognize the differences. You can exclude localized pages using the ‘Exclude’ feature under Advanced Settings.
The Documents feature allows you to upload and extract content from files, helping the chatbot respond accurately based on structured knowledge. This is useful for handling FAQs, policy documents, product manuals, and other reference materials.
Once a document is uploaded, the system will extract and index the content. The status may show:
By integrating document-based knowledge, you ensure that your chatbot provides accurate and well-structured responses based on official company materials.
Text snippets allow you to add or update chatbot content instantly. They are useful for last-minute updates, time-sensitive announcements, or temporary information that may need quick modifications. Follow these steps to create a text snippet in AiChat:
Once saved, the text snippet will be indexed and available for the chatbot to retrieve when responding to relevant user queries. Always review the indexing status to ensure it is successfully processed.
The Q&A section allows you to define specific question-answer pairs that improve your chatbot’s response accuracy. This feature is useful for providing direct answers to user queries instead of relying solely on data crawling from websites, documents, or text snippets.
There are two ways to add Q&A pairs:
A. Manually Add Q&A
B. Bulk Upload via CSV
Once added, the Q&A entries will undergo processing. The status may show:
Processing – The system is indexing the Q&A.
Indexed – Successfully added and ready for chatbot use.
Failed – An issue occurred; check and re-upload if necessary.
By effectively managing your knowledge base, you can optimize your chatbot’s performance and ensure users receive accurate, helpful responses.