CADDI Chat (Talk to your Data)

Introduction

Artificial Intelligence (AI) plays a crucial role in data analysis by providing a simple interface to extract insights from large and complex data sets. With its ability to process natural language quickly, AI helps people make better-informed decisions, identify patterns and trends, and uncover hidden insights that might otherwise go unnoticed. In DvSum users have the ability to talk to their data using Conversational AI for Data-Driven Insights (CADDI). DvSum CADDI is a user-friendly platform where users can ask different questions from their datasets and extract useful insights. The following article explains how CAADI chat can be used. 

This article is linked to Chat bots. The link to the article of Chat Bots is attached here

Here is the video tutorial explaining CAADI chat in detail:

/*                                                               Tutorial Video to be attached here                                           /*

How to talk to the data in DvSum Data Catalog:

Before we start chatting with data, first, we need to create a chatbot and share it with some users.  Here I have a chatbot shown below, which I have shared with the user. On the Chat bot go to "Manage Access" and share the chatbot with any user.

Once the chatbot is shared, click on "Talk to Your Data" from the left Nav. It will open the Conversational page on a new tab. 

Now in the Conversational tab, all the chatbots that are shared with some users will appear as bots. So we need to select some bot in order to start the conversation. I'm selecting the bot which I shared above.

Once the bot is selected, an About section of that chat will appear on the new chat, which will contain details of the bot i.e. the tables that were added to the chatbot.

On clicking the book icon located on the top right of the chat bar, some sample questions show up. Users can use these questions for analysis:

On the CADDI, there are three types of questions that can be asked which are:

1. Sample Question
2. Typed Question
3. Detailed Question

1- Sample Question

Click on the "Sample Data" button, and it will show the sample data of that data set. The Sample question will not have any SQL code generated, and there will be no visualized charts for it. The Sample Data will have the Pivot View.

From the sample data, users can have some basic insights into what data is about and what it looks like. Users can select different columns and apply filters to check the results. 

Users can see the profiling of the sample questions by clicking on the profiling icon:

Users can apply some filters and set up that question as a context also by clicking on the context icon:

Note: For Sample Questions, context can only be set up when some filter is selected

The Concept of Profiling and Context will be explained further in this article.

2- Typed Question 

A typed question is one for which the answer is only in textual form. There is no SQL code generated for this question, and there will be no visualized grid or charts for these types of questions. 

3- Detailed Question

A detailed question is one for which:

1.  SQL Code is generated
2.  Visualized Grid, Charts and Pivot Information is generated
3.  Context can be set up, and Profiling Information is provided

3.1-  SQL Query

When the question is asked about any dataset, then for that question, SQL code is generated, but it can be seen only when users select the "Show Code" option on the three dots on the top right.

3.2- Different Generated Views

For the question that is not typed, there are 3 different views that are generated which are:

1. Chart View (located next to Chart Settings)
2. Grid View
3. Pivot View

The Chart View, Chart Settings, and Pivot View are separate detailed topics, and they are not included in the scope of this article. For Information regarding charts and their settings, click here. For Information regarding the Pivot View, click here

The Grid View shows the data in tabular form of the columns that are fetched from the SQL query:

3.3- Profiling

The Profiling Icon can be seen on the top right of the question. Profiling can be opened from there, or if any column is clicked on the Grid, then profiling of the column is opened. The profiling basically shows the distribution of different values of a column. Users can apply filters on the Grid by selecting particular values:

3.4- Saving the Question as Context

The question that is asked that can be added as context or any specific filter applied on the grid can also be added from the Context icon on the top right of the question:

The added context can be seen on the top left of the chat bar below. Users can add more than one context from different datasets. If the context is no longer needed, then it can be removed from Clear Context.

Next Time when any question related to the dataset is added as context this context will be incorporated into the questions also:

4- Basic CRUD Operations

On the top left of the Chat, where the name is written, there are some basic crud operations that can be performed:

1. Update Chat Name & Objective
2. Refresh Insights
3. Delete Chat 
4. Collapse All/Expand All Questions

The Chat Name can be updated by clicking on the "Edit" icon. Users can update the chat name as well as the objective for that chat:

The "Refresh Insights" button will refresh all the questions present in the chat:

The "Delete" button will delete the Chat and all the questions that are asked in it:

The "Expand All/Collapse All" will expand and collapse all the questions present on the chat:

On the top left of the chat bar, the bot that is opened will be shown. When a user clicks on it the view is expanded, and all the chatbots that are shared are shown here. Users can switch from one bot to another:

5- Left Navigation Bar

When any bot is opened, if "New Chat" is clicked, then it takes to the Default CADDI window. Users can also scroll around the bots that were created:

The "Find Data" tab opens up the Home page of the Application on a new tab, and the "Logout" tab logs out of the Application: