In this example we ask a simple question that gives counts of data from a table.
Video of VerbaGPT in action:
User question: Give me the counts of the different types of iris flower.
VerbaGPT response: 
Cost of query: $0.00
Answer:
Type: 0, Count: 50
Type: 1, Count: 50
Type: 2, Count: 50
VerbaGPT answered the question correctly. Since VerbaGPT comes with an embedding framework, it did not have to be told where to look, only pointed to a SQL server instance that contains many different databases including one [Db_Test_01] that has the [iris] table. This is the famous small dataset that is used to illustrate classification algorithms in predictive modeling.
Leave a Reply