Imagine if you have many datasets available and want to extract useful information for business use. Now, a person who is an expert in SQL can efficiently extract useful information from any dataset by using the relevant commands, but for a business person, it might be a little challenging to know about all the SQL commands. Conversational AI for Data-Driven Insights or CADDI provides business users to extract useful information from any dataset by using plain English. The useful information or insights help business users to make well-informed decisions. Other than this, the concept of Chat Bots is introduced by DvSum. Chat Bots provide users with the ability to create Chat Bots and Train it accordingly. The following article will explain the different functionalities and capabilities of CAADI.
Here is the Video about how chatbots are created and how they can be used:
/* Video to be attached here /*
1. Creating a Chat Bot
Chat Bots can be found on the Sources Detail page. Any Source that will have Chat Enabled will have the Chat Bot Tab. Chat Access can be given to any source through the Module Settings. For more information, click here.
Chat Bot Tab can be found on the detail page of the source for which Chat is enabled.
The "Chat Bots" tab can be seen next to the "Settings" Tab. On clicking on Chat bots, a new Chat bot can be created:
When a new Chat Bot is created, the user is landed on the Definition Tab of Chat bot. In a Data source, there can be a number of Tables. Users can either use all the tables in the Chat Bot or user can limit the chat bot to some specific sources by adding tables from the Available Tables.
Any added table shows up in "Tables For Chat". Users can also preview the Table to see the data inside it:
User can also see individual columns and their profiling by clicking on the "Manage Fields" option. Here Users can select or unselect columns of any Table:
After Adding the necessary Tables, the user can click on the "Done" and "Save" button to save the changes:
2- Train Bot
After the user has selected specific tables and saved the changes, along with the "Definition" Tab, the "Train Bot" tab can be seen. On clicking the "Train Bot," user can see the "Generate Questions" button up front and the Chat bar below that where questions can be typed:
On clicking Generate Questions, some sample questions show up. Users can use these questions for analysis:
On the Chat Bot, there are two types of questions that can be asked which are:
1- Typed Question
2- Detailed Question
3- 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.
4- Detailed Question
A detailed question is one for which:
- SQL Code and Logs are generated
- Visualized Grid, Charts and Pivot Information is generated
- Context can be set up and Profiling Information is provided
- Positive or Negative feedback can be given for further improvement (Training)
4.1- Logs Generation & SQL Query
The Logs, in simpler words, are the information related to when a question is asked and what goes to the Backend in textual form. By default, the logs are not turned on. To turn the logs on, the user will have to enable them from three dots at the top right:
Once the logs are turned on any question is asked the Logs will be printed, and SQL query generated for that question will be printed below the Logs:
The Log details and the SQL code can be hidden from the three dots located on the top right of the question:
4.2- Different Generated Views
For the question that is not typed, there are 3 different views that are generated which are:
- Chart View (located next to Chart Settings)
- Grid View
- 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:
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:
4.4- 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:
4.5- Giving Feedback
Often times there will be some questions that may not get answered, or the answer was not according to the user expectations. To tackle this problem, the concept of giving Feedback is introduced. The feedback can be positive if the user is satisfied with the answer:
But there will be times when the user will not be satisfied with the answer or the query generated for that question is wrong, due to which the question may give an error. In this case, the user can give negative feedback:
In the negative feedback, the user can select an option like whether the Query was wrong or the calculation was wrong, and in addition, the user can explain in plain English about how the question should be approached, or the user can write the correct SQL query which should have been generated:
When the feedback is submitted, this feedback is taken into consideration when the next question will be asked. This is the kind of training that we are doing, so the accuracy of results can be improved over time.
5- Share a Concept
Just like the feedback, the user can share any concept of a particular thing that he wants to incorporate in the coming questions. "Share a Concept" can be found at the plus button with the chat bar:
The next time the question is asked related to this table this added concept is incorporated in the response if necessary:
6- Basic CRUD Operations
On the top right of the Chat Bot, there are some basic operations that can be quite handy for the users. There are 4 toggle buttons that can be seen:
- Not Responded
The Questions can be filtered according to these toggle buttons:
With the toggle buttons on the three dots, users have the option of "Refresh All", which refreshes all the questions and Expand/Collapse All, which will expand or collapse all the questions present in the chatbot.
The user has the option of Duplicating & Deleting the Chat bot. If the user wants to work on the same chatbot, but the user does not want to affect the original chatbot so the chatbot can be duplicated. If the user wants to delete the chatbot, then the option is available along with the duplicate button.
Some more basic information about the Source and Chat bot can be found below the Chat bot name, like questions asked, tables and Chat exclusion criteria, which are mentioned in the Module Settings for this source. The link to the Module settings article can be found here
7- Manage Access
By default, when any chatbot is created, then it is private, and it is indicated by a "lock" icon present in front of the name of chatbot. Users have the option of sharing the Chat bots with other users or user groups through Manage Access:
On clicking Manage Access, a modal opens up where the user can enter any user group or users with whom he wants to share the chatbot. There are 2 types of Access that can be given which are:
- Chat Only
"Chat Only" access means that the user will only have access to CAADI chat (Talk to your Data). In "Chat Only", the user will not have any access to the chatbot, which is present on the Sources Detail page. Once the user shares the chatbot and gives "Chat Only" Access, another user will receive an email, and a link will be provided.
The Link provided in the email takes the user to CAADI chat (Talk to your Data). For more information about CAADI chat (Talk to your Data), go through the article here
When the chatbot is shared with Access as "Edit," then the other user will have edit access to the Chat bot that is present on the source detail page. When the chatbot is shared with other users with access as "Edit", then user will receive an email with a link.
The above link takes the user to the "Definition" Tab of the Chat bot. This user can also make changes in the original chatbot since he has edit access:
Once the user has given "Chat Only" access or "Edit" access, then on Manage access, there is another option of "Remove Access", which basically will remove the Chat and Edit access to the other user: