Document lookup aims to provide bot builder’s ability to make the bot training effort more seamless, an option to combine answers to user queries from multiple sources widens the capability of the bot to provide more appropriate responses. Minimizing the format reduces effort and time consumed leading to a more intelligent bot with lesser efforts.
This feature is available in beta for Enterprise plan customers. Please reach out to [email protected] to enable this feature.
Steps to Use
Step 1 – Go to Build and select Smart Response
For our existing users on their first visit, the following wizard will be shown.
For the new users, the following wizard will be shown, you can check ‘Don’t show me again’ which would ensure this wizard is not displayed in the future.
Step 2 – Select the Document Lookup tab from the mode of response.
Step 3 – Click on ‘Upload Document’ button from this tab and upload the reference document.
Prioritize Document Lookup
Default behavior of the bot is set to search in FAQs for a user query and then in document lookup before displaying the default response.
Once ‘Prioritize Document Lookup Response’ setting has been enabled and a user asks a query, the bot will first search through the documents uploaded into it and provide the response from them if there is no response matching up to the Threshold ratio defined then the bot will look up into the FAQ section of the bot.
When the user asks a query the system finds a corresponding response from the document and displays it to the user. The maximum characters which will be displayed from the document will be 255 characters.
Fig1.1 An excerpt from the document.
Fig 1.2 Uploading the Document into the Portal.
Fig 1.3 User asking a query whose response is being fetched from the Document fed.
To enable the debug mode you can navigate to the Configure -> Conversations -> Debug Mode.
Response found from: This will show the source of the file from which the response has been fetched.
Document Name: This would display the PDF file through which the system is getting the response.
Page No: This represents the page number in which the response is present.
Format Supported and limitations.
- At present, we support documents only in PDF format and should not exceed 5MB.
- Documents having content in the column format are not processed.
- Documents having more than 200 pages are not allowed at the moment.