HackerTrans
TopNewTrendsCommentsPastAskShowJobs

saigal

no profile record

Submissions

Show HN: Natural Language to SQL "Text-to-SQL" API

dataherald.com
62 points·by saigal·2 lata temu·40 comments

[untitled]

1 points·by saigal·2 lata temu·0 comments

Fine-tuning GPT-3.5-turbo for natural language to SQL

medium.com
208 points·by saigal·3 lata temu·75 comments

Show HN: Data content creation tool using OpenAI+LangChain(lessons learned)

app.dataherald.ai
3 points·by saigal·3 lata temu·1 comments

comments

saigal
·2 lata temu·discuss
we intend to
saigal
·2 lata temu·discuss
The autonomous car analogy is a good one. The technology is overall so far superior to a human (probably scrolling TikTok) driving but the moment it makes a mistake we remove the AEV which would be to to higher societal benefit.

Decisions should be made against an alternative, not against some fictitious perfect solution.
saigal
·2 lata temu·discuss
Couldn’t agree with this more. Exactly.
saigal
·2 lata temu·discuss
For companies that are willing to put in some effort, the self hosting option is a great one. There are certain use cases where this works now, and is already in production. These tend to be use cases with some constraints and don’t deal with very sensitive data.
saigal
·2 lata temu·discuss
we've encountered a lot of instances when people know SQL but just want a first draft of SQL to expedite the process. we see this a lot from data analysts too.
saigal
·2 lata temu·discuss
yes. some want BYOC solutions. others don't want to even be perceived as being used to train an LLM. not to mention CCPA, GDPR, etc etc etc.

lots of questions around what data is being sent to the LLM, or just schema.
saigal
·2 lata temu·discuss
The question was around row level security
saigal
·2 lata temu·discuss
Yes totally agree. You can easily sniff out products that are simple wrap of GPT
saigal
·2 lata temu·discuss
Search bar within the SaaS interface that allows user to ask data questions and returns back NL answer or specific cut of data
saigal
·2 lata temu·discuss
Yes. Correct.
saigal
·2 lata temu·discuss
We also encounter a lot of build vs buy conversations with businesses.
saigal
·2 lata temu·discuss
Enterprises are spending lots of time and money on this. The biggest issue that has slowed down sales cycle at this stage has been data governance. Most folks think it’s about accuracy or latency (which of course is an issue) but data governance can make this whole thing a non starter.
saigal
·2 lata temu·discuss
https://discord.com/invite/A59Uxyy2k9

discord invite in case anything comes up
saigal
·2 lata temu·discuss
there is a middle ground here. the most complicated queries will need the intel and business context of a smart data scientist. there are however so many types of queries where automation would make the world so much easier and allow more self-serve type data inquiries. too often the rhetoric around these topics is binary as in "it works" or "it doesn't work." in reality, there are certain use cases that work now and others that don't yet.
saigal
·2 lata temu·discuss
fantastic. let us know how it goes :-)
saigal
·2 lata temu·discuss
is there an easier way?
saigal
·2 lata temu·discuss
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
saigal
·2 lata temu·discuss
"...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.
saigal
·2 lata temu·discuss
I agree with you. The larger point with text to SQL, however, is that it will not work if it is a simple wrap of an LLM (GPT or otherwise). Text to SQL will only work if there is a sufficient understanding of the business context required. To do this is hard, but with tools such as Dataherald a dev's life gets a whole lot easier.
saigal
·2 lata temu·discuss
Yes please do. We’d love your feedback and or to hear whether you see material improvement over what you have now