←back to thread

Show HN: SnapQL – Desktop app to query Postgres with AI

(github.com)
103 points nicktikhonov | 4 comments | 20 Jun 25 11:08 UTC | HN request time: 1.036s | source

SnapQL is an open-source desktop app (built with Electron) that lets you query your Postgres database using natural language. It’s schema-aware, so you don’t need to copy-paste your schema or write complex SQL by hand.

Everything runs locally — your OpenAI API key, your data, and your queries — so it's secure and private. Just connect your DB, describe what you want, and SnapQL writes and runs the SQL for you.

Show context
joshstrange ◴[21 Jun 25 11:46 UTC] No.44336777[source]▶
I might test this out, but I worry that it suffers from the same problems that I ran into the last time I played with LLMs writing queries. Specifically not understanding your schema. It might understand relations but most production tables have oddly named columns, potentially columns that changed function overtime, potentially deprecated columns, internal-lingo columns, and the list goes on.

Granted, I was using 3.5 at the time, but even with heavy prompting and trying to explain what certain tables/columns are used for, feeding it the schema, and feeding it sample rows, more often than not it produced garbage. Maybe 4o/o3/Claude4/etc can do better now, but I’m still skeptical.

replies(4): >>44336911 #>>44337293 #>>44337492 #>>44339085 #
1. pu_pu ◴[21 Jun 25 13:35 UTC] No.44337492[source]▶
This is not a difficult problem to solve. We can add the schema, columns and column descriptions in the system prompt. It can significantly improve performance.

All it will take is a form where the user supplies details about each column and relation. For some reason, most LLM based apps don't add this simple feature.

replies(1): >>44337511 #
2. joshstrange ◴[21 Jun 25 13:38 UTC] No.44337511[source]▶
It’s not a difficult problem to solve, I did it, last year, with 3.5, it didn’t help. That’s not to say that newer models wouldn’t do better, but I have tried this approach. It is a difficult problem to actually get working.
replies(1): >>44337595 #
3. pu_pu ◴[21 Jun 25 13:49 UTC] No.44337595[source]▶
So, I have not tried it on a very complex database myself so I can't comment how well it will work in production systems I have tried this approach with a single Big Query table and it worked pretty well for my toy example.

If by 3.5 you mean ChatGPT 3.5 you should absolutely try it with newer models, there is a huge difference in capabilities.

replies(1): >>44337629 #
4. joshstrange ◴[21 Jun 25 13:53 UTC] No.44337629{3}[source]▶
Yes, ChatGPT 3.5, this testing was a while back. I’m sure it has improved but I doubt it’s solid enough for me to trust.

Example/clean/demo datasets it does very well on. Incredibly impressive even. But on real world schema/data for an app developed over many years, it struggled. Even when I could finally prompt my way into getting it to work for 1 type of query, my others would randomly break.

It would have been easier to just provide tools for hard-coded queries if I wanted to expose a chat interface to the data.

replies(1): >>44337707 #