Overview

The Smart FAQ Model is the centerpiece for creating Generative AI-powered FAQ bots. This feature allows the user to upload content of multiple file types, like- Documents, Knowledge Base articles and Question and Answer Pairs. The bot then uses content present in these files to answer user queries, using a technique called Retrieval-Augmented Generation (RAG).

Navigating to Smart FAQ Models

1. Hover over your Conversational AI Application and click Manage.

2. Select ML Models within the AI Tools section.

   ​

3. On the ML Models window, click Add ML Model in the top right corner.

4. On the Create New Model window, add the desired Name of the model and select the Model Type as Smart FAQ. Click Create at the bottom.

   

5. Now, click on the created model, and you will be directed to the Training Content window.

   

Capabilities under Smart FAQ Model

Within the Content Sources feature, you have access to a wide range of capabilities aimed at managing and optimizing your content sources effectively.

1. Create, update, and delete content sources.

2. Sync data from the Sprinklr Knowledge Base utilizing filters, upload files of various types and custom question-answer pairs, and import assets from Digital Asset Manager.

3. Generate reports detailing similarity and ambiguity in content across different sources.

4. Upvote and downvote content types based on relevance.

5. Other capabilities include discovering content through FAQs, creating and managing a Golden Test Set for performance evaluation, and triggering and downloading bulk predictions from an Excel format for further analysis and insights.

What's Next?

Learn how to add content and use it to run Generative AI bots.