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

Show HN: Describe SQL using natural language, and execute against real data

news.ycombinator.com

Post reply on HN
Print view View original

31–37 of 37 posts

Re: Show HN: Describe SQL using natural language, and execute against real data

#31

Post by lswainemoore »

/* When it rains does it pour? */

SELECT date, wban, stn, year, mo, da, temp, count_temp, dewp, count_dewp, slp, count_slp, stp, count_stp, visib, count_visib, wdsp, count_wdsp, mxpsd, gust, max, flag_max, min, flag_min, prcp, flag_prcp, sndp, fog, rain_drizzle, snow_ice_pellets, hail, thunder, tornado_funnel_cloud, usaf, name, country, state, call, lat, lon, elev, begin, end, point_gis, fake_date FROM `fh-bigquery.weather_gsod.all_geoclustered` WHERE lat IS NOT NULL AND lon IS NOT NULL AND lat != 0 AND lon != 0 AND lat != 1 AND lon != 1 AND lat != -1 AND lon != -1 AND lat != 2 AND lon != 2 AND lat != -2 AND lon != -2 AND lat != 3 AND lon != 3 AND lat != -3 AND lon != -3 AND lat != 4 AND lon != 4 AND lat != -4 AND lon != -4 AND lat != 5 AND lon != 5 AND lat != -5 AND lon != -5 AND lat != 6 AND lon != 6 AND lat != -6 AND lon != -6 AND lat != 7 AND lon != 7 AND lat != -7 AND lon != -7 AND lat != 8 AND lon != 8 AND lat != -8 AND lon

Re: Show HN: Describe SQL using natural language, and execute against real data

#32

Post by atom_arranger »

bob1029 wrote: post #22

This demo sent us on a warpath today. We have a fairly clean SQL schema for which we need to craft a lot of queries that handle things like business logic, reporting and configuration. If we could get even 50% success rate on a reasonable starting point for the generated SQL each time, that would be the biggest value-add our organization has ever seen. I think our use case is compelling because we have to implement t…

There are projects out there that do this.

Possibly relevant: https://yale-lily.github.io/spider

I briefly worked on a startup to commercialize this tech, but we decided it wasn't accurate enough to be useful. It was very cool when it actually worked. If you can only produce what you want half the time on simple queries, that doesn't seem very useful to me though.

Re: Show HN: Describe SQL using natural language, and execute against real data

#33

Post by newusertoday »

bob1029 wrote: post #22

This demo sent us on a warpath today. We have a fairly clean SQL schema for which we need to craft a lot of queries that handle things like business logic, reporting and configuration. If we could get even 50% success rate on a reasonable starting point for the generated SQL each time, that would be the biggest value-add our organization has ever seen. I think our use case is compelling because we have to implement t…

Have you considered using templates? can you elaborate more on why they can't be used (I guess there is no way to cleanly separate parameters but i may be wrong)

Re: Show HN: Describe SQL using natural language, and execute against real data

#34

Post by easylearnai »

Nice idea, but the default natural language query generated a query that didn't run. Perhaps turn down the temperature or tune other parameters. This could be better if you fine-tune it such that anyone could bring their own dataset, with GPT3 just making it available recently. My favorite recent app for no code sql query is trevor.io that has allowed me to build a dashboard so easily. I only knew basic sql query and didn't have to tamper with the actual SQL code; it was all interactive and the results is always in the correct format. Comparing to the GPT3 approach, I would say I prefer trevor over using natural language for the precision. The appeal of using GPT3 exists only if it gets high enough accuracy, imo.

Re: Show HN: Describe SQL using natural language, and execute against real data

#35

Post by weepa »

atom_arranger wrote: post #32
bob1029 wrote: post #22

This demo sent us on a warpath today. We have a fairly clean SQL schema for which we need to craft a lot of queries that handle things like business logic, reporting and configuration. If we could get even 50% success rate on a reasonable starting point for the generated SQL each time, that would be the biggest value-add our organization has ever seen. I think our use case is compelling because we have to implement t…

There are projects out there that do this. Possibly relevant: https://yale-lily.github.io/spider I briefly worked on a startup to commercialize this tech, but we decided it wasn't accurate enough to be useful. It was very cool when it actually worked. If you can only produce what you want half the time on simple queries, that doesn't seem very useful to me though.

Can you elaborate on what kind of use cases you were trying to tackle using NL2SQL in that startup? Who was the target audience/persona?

Re: Show HN: Describe SQL using natural language, and execute against real data

#36

Post by atom_arranger »

weepa wrote: post #35
atom_arranger wrote: post #32

Earlier quoted context omitted.

There are projects out there that do this. Possibly relevant: https://yale-lily.github.io/spider I briefly worked on a startup to commercialize this tech, but we decided it wasn't accurate enough to be useful. It was very cool when it actually worked. If you can only produce what you want half the time on simple queries, that doesn't seem very useful to me though.

Can you elaborate on what kind of use cases you were trying to tackle using NL2SQL in that startup? Who was the target audience/persona?

Any company that has a lot of data in an SQL system that they want to make sense of. The idea would be that business intelligence people, analysts, the CEO, anyone who needed answers could ask a question in plain english and hopefully get a response.

The success rate was just not good enough, even for relatively simple queries. You'd probably need to adjust the query 90% of the time, and the other 10% you couldn't even really trust that the answer was correct.

Post reply on HN