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

Show HN: Dataherald AI – Natural Language to SQL Engine

github.com

Post reply on HN
Print view View original

61–70 of 108 posts

Re: Show HN: Dataherald AI – Natural Language to SQL Engine

#61

Post by DaiPlusPlus »

cpursley wrote: post #26
aazo11 wrote: post #23

Earlier quoted context omitted.

Interesting. So far we have been focused on allowing non-technical users to self-serve from enterprise data warehouses. It might be possible to enable this scenario with a simple addition to the NL-2-SQL engine to translate the generated SQL to API calls. If that does not work, a custom imeplementation of the NL-2-SQL module would def solve this. Do you have a specific use-case in mind? Would love to collaborate on a…

Mostly my concerns are around authorization (who can access what) and those two tools handle that before generating a database query. So maybe the approach would be to go from natural lang -> SQL (as you do now) then to Hasura's or PostgREST's specific query syntax (which are already pretty SQL like). And specifically with Hasura, since it's GraphQL - you can get all the available types. But that might all be to far…

Re: security - assuming your RDBMS supports row-level security then you should be fine as-is - otherwise let users only query VIEW objects with security filters baked-in to them.

Re: Show HN: Dataherald AI – Natural Language to SQL Engine

#62

Post by DaiPlusPlus »

canvascritic wrote: post #45
i_have_an_idea wrote: post #41

Earlier quoted context omitted.

This is a rather superficial take that seems to only consider the aspect of querying a database, but, nevertheless, I'll jot down a few quick counterpoints: 1) A middle layer, such as SQL, offers a vital introspection point to understand and fix LLM mistakes. Without it, we will end up with a "black box" that could lead to errors in data queries and manipulations, making debugging and correction much more challenging…

Appreciate your insights. A few comments/responses 1. Agree on the introspection point, but it's worth noting that the future of LLMs might involve self-awareness capabilities, which could provide an introspective mechanism similar to SQL's transparency. the aim would be to build upon this middle layer, not blindly supplant it. 2. While 3NF, BCNF, and other normalization forms have served us well, they are essentiall…

Your answer to question 2 tells me that you haven’t read Codd’s seminal paper.

Re: Show HN: Dataherald AI – Natural Language to SQL Engine

#64

Post by sandGorgon »

this is very interesting. just curious - is the context store specific to the table structure of the target database ? or is it a very generic one. im asking this cos the DIN-SQL algorithm seems to be a chain-of-thought kind of algorithm (with query decomposition). I'm wondering where do u plug-in the context store ? in DIN-SQL the schema linking module is random samples from Spider. Is that whats in the context store ?

Re: Show HN: Dataherald AI – Natural Language to SQL Engine

#65

Post by calcsam »

DaiPlusPlus wrote: post #60
p1necone wrote: post #59

Earlier quoted context omitted.

Yeah, I hope this is paired with something that actually stops those statements from running otherwise this is a pretty naive way to do this.

SQL injection meets prompt-injection…

Couldn’t you solve this simply by executing from a user without these permissions?

Re: Show HN: Dataherald AI – Natural Language to SQL Engine

#68

Post by newaccount74 »

calcsam wrote: post #65
DaiPlusPlus wrote: post #60

Earlier quoted context omitted.

SQL injection meets prompt-injection…

Couldn’t you solve this simply by executing from a user without these permissions?

Sure, but it's something that the customer has to do. I wouldn't rely on customers to configure everything correctly, especially if there is no way to discover the configuration error before the damage has been done.

Re: Show HN: Dataherald AI – Natural Language to SQL Engine

#69

Post by l5870uoo9y »

> select price from rent_prices where city=”Los Angeles” AND month=”05” AND year=”2023”

I have to say the best implementations out there are already far ahead. Naturally there are some context limitations with large database schema but those can be handled:

- having an easy way to include/exclude tables ad hoc

- importing database schema in multiple different data sources that you can switch between depending on usage

And of course if AI isn't using the correct tables or columns, simple prime the prompt using autosuggest feature containing the tables and columns.

Generating JOINS isn't really a hurdle if you have a good prompt template:

- https://aihelperbot.com/snippets/cllovmlat000kmj0fedssj8c5 (notice it even uses the correct "film" tables even-thought it was instructed to find "movies" and naturaly category and category bridges table)

- https://aihelperbot.com/snippets/cllnztzky0002mj0fa78hw0o2 (it can also find lat/lng for Boston for AWS Athena, was demonstrating this for a Boston company)

- https://aihelperbot.com/snippets/cllo1vwl6000wlb0fj5669zt4 (It can generate in Mandarin as well, but less capable than English. Same goes for German, French, Spanish and so)

You can also have AI generate advanced SWOT analysis based on your database schema: https://i.imgur.com/JTv4QmX.png

Re: Show HN: Dataherald AI – Natural Language to SQL Engine

#70

Post by tillvz »

aazo11 wrote: post #25
tillvz wrote: post #15

"So is enterprise conversational BI impossible in 2023? Will there be a few more years of academic papers and company AI hackathon projects before a solution can be deployed in production? We don’t think so." -- from the medium article. Want to put your attention to https://www.veezoo.com as well. A conversational self-service analytics solution that's been around since 2016 and productively deployed in fortune 500 c…

Amazing! Feel free to shoot me a line at amir at dataherald

done :)! Looking forward
Post reply on HN