Happy New Year everyone! I’m pretty excited about this. Like every other tech geek out there, I was experimenting with ChatGPT when it was announced in December of 2022.
Initially I was amazed at how well the AI appeared to work, and somewhat terrified with what people could actually do with it. I teach a database class at the University of Maryland Baltimore County (UMBC) and I was really worried that students could use ChatGPT to generate answers to essay questions on my exams. I wanted to see if there were ways of phrasing questions that would make it obvious that a person did not write them. After using ChatGPT for a while, I do think it would be possible to detect if a student was using AI to write their papers, as the quality and style are fairly distinct.
But I digress…
What really intrigued me was that these models can write SQL queries using natural language. Of course the fact that you can write a SQL query isn’t necessarily useful unless you understand the schema of the underlying data and you have a query engine or database capable of executing that query.
Well… guess what…
My team and I have been hard at work at incorporating this powerful feature into our DataDistillr. Today, I am happy to announce that we’ve added natural language AI capability to DataDistillr!
Wait, You Can Just Ask a Question???
Let’s see how this works. We have some databases with notional data connected to DataDistillr. I asked DataDistillr the question below:
Armed only with that question, DataDistillr generated the following query:
SELECT
`city`.`city`,
COUNT(`store`.`store_id`) AS `store_count`
FROM `jacob_jacob_mysql`.`sakila`.`store`
JOIN `jacob_jacob_mysql`.`sakila`.`address`
ON `store`.`address_id` = `address`.`address_id`
JOIN `jacob_jacob_mysql`.`sakila`.`city`
ON `address`.`city_id` = `city`.`city_id`
GROUP BY
`city`.`city`
ORDER BY
`store_count` DESC
With no additional data catalog products, DataDistillr was able to generate a query which joins three tables together and performs an aggregation. What’s most impressive is that this query actually runs in DataDistillr and returns the correct results. So that you don’t think this is vaporware, here is a brief video of the whole process.
What Does This Mean?
ChatGPT and all the Large Language Models (LLM) can do some amazing things using generative AI technology, but at the end of the day, you still need to be able to translate that into action. Much like Google was able to transform internet search, I believe that our decision to combine Generative AI with DataDistillr has potential to radically change business intelligence for companies of all sizes.
Armed with this new feature, DataDistillr enables users to access their data, but until today, required that a user have a fundamental knowledge of SQL.
With the AI Integration, users can literally ask simple, plain language questions of their data and get answers immediately, without coding. What’s more is that it doesn’t matter where their data is. If you want to query Splunk, or ElasticSearch or a bunch of Excel files, you can do that in exactly the same way, by simply ask a question. So I have a question for you. What are you waiting for? Try it for yourself: https://app.datadistillr.io.