Re:Vanna.ai: Chat with your SQL database
by kleiba on Sunday January 14, 2024 @03:34PM
(#38994184)
Sorry, maybe I'm just too tired to see it, but how much control do you have over the SQL query that is generated by the AI? Is there a risk that it could access unwanted portions or, worse, delete parts of your data? (the AI equivalent of Bobby Tables, so to speak)
[ Parent
| on HN ]
In some SQL providers, your can define rules that dynamically mask fields, suppress rows, etc. based upon connection-specific details (e.g. user or tenant ID).
So, you could have all connections from the LLM-enabled systems enforce masking of PII, whereas any back-office connections get to see unmasked data. Doing things at this level makes it very difficult to break out of the intended policy framework.
Why not give it access to relevant parts of the database only? And read only access too?
Re:Vanna.ai: Chat with your SQL database
by 8organicbits on Monday January 15, 2024 @10:31AM
(#39002046)
Access management can be harder than building queries if you start getting fine grained.
Yes. Then again, in a project where queries are simpler than granting relevant access to a third party, I guess the AI chat product is just not a good fit.
I guess you could limit that with the correct user permissions.
Guessing its intended use case is business analytic queries without write permissions —- particularly for non-programmers. I don’t think it’d be advisable to use something like this for app logic
Re:Vanna.ai: Chat with your SQL database
by zainhoda on Sunday January 14, 2024 @07:02PM
(#38995783)
100% -- in fact originally the package used to parse out SELECT statements and only execute SELECT statements. After some feedback, we decided that the permissions on the user should handle that level of detail.