Show HN: We open sourced our entire text-to-SQL product • Hacker News Board

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

#31

Post by numlocked » Fri, May 24, 2024, 9:16 PM UTC

saigal wrote: post #27

numlocked wrote: post #25

Earlier quoted context omitted.

Is that documented somewhere? The "contributing" link in the readme also 404s. I would definitely need to understand the licensing and how contributing works before I could consider integrating this (and I would definitely consider it!). Cool stuff.

We'll make the licensing more visible. Stay tuned in a few minutes.

thanks much!

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

#32

Post by tootie » Fri, May 24, 2024, 9:27 PM UTC

Is the only LLM support OpenAI?

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

#33

Post by TheRealPomax » Fri, May 24, 2024, 9:35 PM UTC

saigal wrote: post #20

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…

the target audience is developers who wish to embed text to SQL functionality into their own products. the target audience is less the 'internal use case' (i.e. a data analyst) and more about letting external users do things they couldn't do before. a good example is payroll software where this type of technology can allow users to pull reports.

With what level of accuracy? And what guarantee of correctness? Because a report that happens to get the joins wrong once every 1000 reports is going to lead to fun legal problems.

You still need someone who understands why you should use which approach to get the data you need without getting completely wrong numbers back that _look_ perfectly fine but reflect fantasy, not reality.

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

#34

Post by boredemployee » Fri, May 24, 2024, 9:42 PM UTC

greenavocado wrote: post #28

saigal wrote: post #20

Earlier quoted context omitted.

the target audience is developers who wish to embed text to SQL functionality into their own products. the target audience is less the 'internal use case' (i.e. a data analyst) and more about letting external users do things they couldn't do before. a good example is payroll software where this type of technology can allow users to pull reports.

> the target audience is developers who wish to embed text to SQL functionality into their own products Who is asking?

you wouldnt believe the amount of developers that don't know how to write sql

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

#35

Post by saigal » Fri, May 24, 2024, 9:44 PM UTC

tootie wrote: post #32

Is the only LLM support OpenAI?

"The agent is LLM agnostic and you can use it with OpenAI or self-hosted LLMs."

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

#36

Post by vlovich123 » Fri, May 24, 2024, 9:50 PM UTC

aazo11 wrote: post #10

vlovich123 wrote: post #4

Are there strategic parts of the stack you haven’t open-sourced?

The entirety of the codebase is now open source.

It’s sometimes hard to understand how you keep a business running when you’ve open-sourced your entire stack, both consumers self-hosting but even worse would be a competitor just taking what you spend R&D budget on & rehosting it with a cheaper price since they don’t need to pay for that R&D. From a business perspective, do you see the operational challenge of running your stack at scale as the differentiator?

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

#37

Post by saigal » Fri, May 24, 2024, 9:50 PM UTC

arrosenberg wrote: post #23

saigal wrote: post #20

Earlier quoted context omitted.

the target audience is developers who wish to embed text to SQL functionality into their own products. the target audience is less the 'internal use case' (i.e. a data analyst) and more about letting external users do things they couldn't do before. a good example is payroll software where this type of technology can allow users to pull reports.

I agree that is a more reasonable use-case. The readme for this tool seems geared toward the business of answering business questions.

Tbh the original intention was to be the "data analyst" but we found over time (and with literally 100s of user conversations at small cos and enterprises) the embedded use case was more interesting and made for a better business, which was not at all what we expected.

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

#38

Post by totalhack » Fri, May 24, 2024, 9:52 PM UTC

Is this more like text-to-semantic layer or does it throw the schema in the prompt and generate SQL with the llm?

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

#39

Post by saigal » Fri, May 24, 2024, 9:56 PM UTC

greenavocado wrote: post #28

saigal wrote: post #20

Earlier quoted context omitted.

the target audience is developers who wish to embed text to SQL functionality into their own products. the target audience is less the 'internal use case' (i.e. a data analyst) and more about letting external users do things they couldn't do before. a good example is payroll software where this type of technology can allow users to pull reports.

> the target audience is developers who wish to embed text to SQL functionality into their own products Who is asking?

hmm not sure I understand the question

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

#40

Post by winphone1974 » Fri, May 24, 2024, 9:58 PM UTC

SQL is really close to a natural language that's unambiguous, there's a few rough edges but it's not bad. Anything more natural requires a lot of context and needs to solve ambiguity.