Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: We open sourced our entire text-to-SQL product

github.com

Post reply on HN
Print view View original

71–80 of 147 posts

Re: Show HN: We open sourced our entire text-to-SQL product

#71

Post by e1g »

robertlagrant wrote: post #22
bobismyuncle wrote: post #5

Curious why you decided to open source your entire product. Are you moving to an open core model? I’d expect in that case that much of 2, 3 & 4 would have stayed closed. Would be grateful if you can share your reasoning

This is often the move when the team's spent the money developing something and now the end's in sight, so they want the chance to leave and take the code with them. Don't know if this is that at all, but it's always worth considering.

That is almost certainly what’s happening here. They raised $3M three years ago, at the peak of evaluations, and don’t have the metrics to raise a Series A in the current climate. Running out of money and want to leave some artifact behind. A very difficult and emotional transition.

Re: Show HN: We open sourced our entire text-to-SQL product

#73

Post by aazo11 »

iandanforth wrote: post #72

Am I misreading this code? It looks like you don't have precomputed table representations and search, instead you scan, embed, and compare on each run? https://github.com/Dataherald/dataherald/blob/main/services/...

Tables, columns and views are scanned at configuration time (or based on an API trigger) and stored in the data store and a vector store, not on every run.

They are then retrieved and injected based on relevance to the query.

Re: Show HN: We open sourced our entire text-to-SQL product

#74

Post by hackernewds »

robertlagrant wrote: post #22
bobismyuncle wrote: post #5

Curious why you decided to open source your entire product. Are you moving to an open core model? I’d expect in that case that much of 2, 3 & 4 would have stayed closed. Would be grateful if you can share your reasoning

This is often the move when the team's spent the money developing something and now the end's in sight, so they want the chance to leave and take the code with them. Don't know if this is that at all, but it's always worth considering.

I don't understand the "leave the code with them" part

Re: Show HN: We open sourced our entire text-to-SQL product

#75

Post by hackernewds »

arrosenberg wrote: post #18

I still wonder who the audience is for tools like this. The website posits you can answer data questions without going through an analyst, but the role of the analyst is not to be a SQL whisperer for PMs and Executives - it is to be an expert in the model and the data. A data warehouse of any real scale is going to have some amount of issues - anomalous data, different interpretations of the same numbers - how does t…

This is the grievance I have as a data scientist. It is one of the fields where things are technical, while meanwhile everyone thinks they could do the job and provide excessive input and exact direction.

Re: Show HN: We open sourced our entire text-to-SQL product

#76

Post by learnedbytes »

hackernewds wrote: post #74
robertlagrant wrote: post #22

Earlier quoted context omitted.

This is often the move when the team's spent the money developing something and now the end's in sight, so they want the chance to leave and take the code with them. Don't know if this is that at all, but it's always worth considering.

I don't understand the "leave the code with them" part

I think they mean by open sourcing, they can take the code to a new startup without having IP legality issues.

Re: Show HN: We open sourced our entire text-to-SQL product

#77

Post by aazo11 »

nicoburns wrote: post #70
saigal wrote: post #54

Earlier quoted context omitted.

allow me to clarify.. Dataherald isn't intended for developers because they don't know SQL, it's intended for developers who want to build text to SQL into their products

But who wants text-to-sql in products that they use? You wouldn't be able to trust the results. So what is it useful for? Of course you could learn to check the output. But then you could just learn SQL. I know dozens of not particularly technical people (certainly not software developers) who have learnt enough SQL to be useful over a couple of days.

While the engine response is not accurate all the time, the engine returns a confidence score. We have never encountered cases where a deployment with necessary training data indicates a .9 confidence score on an incorrectly generated SQL.

Re: Show HN: We open sourced our entire text-to-SQL product

#79

Post by saigal »

altdataseller wrote: post #67
saigal wrote: post #41

Earlier quoted context omitted.

i agree that there will be "early adopter" type use cases and others that might take a while (e.g. healthcare with hipaa compliance) it is still the early days. goal is to give the developer tools to do this easier.

Its not the early days in terms of expecting digital tools to be correct 99% of the time. Early adoption age was back in 2000-2009. Now everyone expects polished tools that does what it expects them to do

"...what it expects them to do"

therein lies the nuance. some people expect to get a natural language answer back. others expect to get a data table back. others expect to get correct SQL back. this is why it's so important to understand the use case and not bucket everything together.

Re: Show HN: We open sourced our entire text-to-SQL product

#80

Post by saigal »

altdataseller wrote: post #67
saigal wrote: post #41

Earlier quoted context omitted.

i agree that there will be "early adopter" type use cases and others that might take a while (e.g. healthcare with hipaa compliance) it is still the early days. goal is to give the developer tools to do this easier.

Its not the early days in terms of expecting digital tools to be correct 99% of the time. Early adoption age was back in 2000-2009. Now everyone expects polished tools that does what it expects them to do

if you expect correct 99% of the time, you will be waiting for a very very very long time for most, except for the most constrained, use cases
Post reply on HN