I played around with GPT-3 to build this demo. Select a public BigQuery dataset and describe your query in natural English, then edit the generated SQL as needed and execute it.
https://app.tabbydata.com/sql-assistant-demo
Show HN: Describe SQL using natural language, and execute against real data
1–10 of 37 posts
Re: Show HN: Describe SQL using natural language, and execute against real data
#2Clickable link: https://app.tabbydata.com/sql-assistant-demo
Re: Show HN: Describe SQL using natural language, and execute against real data
#3We did a similar analysis a while back, works surprisingly well! I OpenAI increases the amount of "training data" you can send in, I think it could get really good at generating SQL.
Re: Show HN: Describe SQL using natural language, and execute against real data
#4Very nice! I’ve been working on something similar recently: https://acolytehq.com.
Would be happy to chat and compare notes if you'd like!
Re: Show HN: Describe SQL using natural language, and execute against real data
#5This is pretty cool.
I thought it was funny in that in the weather dataset that "NULL" comes in first for the win for some questions:
> what is the all time rainiest city? > what are the top 5 most dry states?
The query conversion is impressive!
Re: Show HN: Describe SQL using natural language, and execute against real data
#6Hey that's very cool and works surprisingly well!
At Veezoo (http://www.veezoo.com) we have been tackling this problem for over 5 years now.
Under the hood we are using our own models. With GPT-3 we're a bit worried about the lack of fine-grained control needed for productive use-cases and obv. also lock in.
Will try out against the same dataset and see how it compares!
Re: Show HN: Describe SQL using natural language, and execute against real data
#7We did a similar analysis a while back, works surprisingly well! I OpenAI increases the amount of "training data" you can send in, I think it could get really good at generating SQL. https://blog.seekwell.io/gpt3
Cool! Yes, the ability to customize the model (https://openai.com/blog/customized-gpt3/) also seems like it could be really useful for this.
Re: Show HN: Describe SQL using natural language, and execute against real data
#8Very nice! I’ve been working on something similar recently: https://acolytehq.com . Would be happy to chat and compare notes if you'd like!
Awesome! Always happy to chat; my contact info is in my profile (and also at the bottom of the linked demo).
Re: Show HN: Describe SQL using natural language, and execute against real data
#9May be some rough edges - or I have unreasonable expecations.
The weather data set has 'begin' and 'end' columns which generates bad sql.
ie, "ERROR: Syntax error: Expected end of input but got keyword END at [49:3]"
Re: Show HN: Describe SQL using natural language, and execute against real data
#10May be some rough edges - or I have unreasonable expecations. The weather data set has 'begin' and 'end' columns which generates bad sql. ie, "ERROR: Syntax error: Expected end of input but got keyword END at [49:3]"
Yeah many rough edges indeed. The generated SQL is the plain output from GPT-3; I have not done anything to customize the model or validate syntax outside it, so the roughness is expected. No idea if folks will find value in this despite that, hence the demo.