PgAdmin 4 9.13 with AI Assistant Panel

Posted by __natty__ 10 hours ago

Counter82Comment27OpenOriginal

Comments

Comment by chaz6 8 hours ago

When I got the update I looked through the settings and there appears to be no way to disable it. I do not want AI anywhere near my database. I only use it for testing/staging at least so I should hopefully not have to worry about it wrecking production.

Comment by ziml77 7 hours ago

What's the danger? It can see the schemas to help it generate the queries but it can't run anything on its own. Also you have to give the application credentials to an AI provider for the feature to work. So, you can just not do that.

Comment by adamas 7 hours ago

There is no need of potential dangers to not want to have non-deterministic features in an application.

Comment by justinclift 47 minutes ago

> What's the danger?

Hallucinated ideas about what needs doing, what commands to run, etc.

So, data that's no longer reliable (ie could be subtly changed), or even outright data loss.

Comment by giancarlostoro 15 minutes ago

If you arent using it is it even a danger?

Comment by imjared 8 hours ago

The docs suggest that you can set the default provider to "None" to disable AI features: https://www.pgadmin.org/docs/pgadmin4/9.13/preferences.html#...

Comment by zenmac 7 hours ago

It is nice that they have the default set to "None". However to have this feature in pgAmdin is as distraction from the project.

If it is just calling API anyway, then I don't want to have this in my db admin tool. It also expose surface area of potential data leakage.

Comment by bensyverson 7 hours ago

Worth pointing out that Postgres is perfectly usable without an admin dashboard at all

Comment by smartbit 7 hours ago

Note: AI features must be enabled in the server configuration

  LLM_ENABLED = True
in config.py for these preferences to be available.

Comment by OptionOfT 6 hours ago

I did not enable this and yet I got the panel in the UI.

Comment by 7 hours ago

Comment by 8 hours ago

Comment by lateforwork 5 hours ago

Did you miss this:

"This feature requires an AI provider to be configured in Preferences > AI."

And then you have to supply an API key (see here https://www.pgedge.com/blog/ai-features-in-pgadmin-configura... )

You don't get AI for free!

Comment by rubicon33 7 hours ago

Why do you do in production?

Comment by panzi 6 hours ago

Yeah, no thanks. I switched to dbeaver already anyway, because pgadmin was annoying about to which postgres versions it could connect. Too much of a hassle to setup a new version from source back when I tried. With dbeaver I just run ./dbeaver from the extracted .tag.gz. dbeaver is also not a web interface, but a real desktop application (Java, though).

Comment by david_iqlabs 41 minutes ago

The interesting challenge with AI assistants inside technical tools is grounding the responses in real system signals. If the model is just interpreting natural language prompts, it tends to produce generic advice. But if the assistant is tied directly to system telemetry or query results, it becomes much more useful.

In experiments I’ve been running, the pattern that seems to work best is deterministic signals first, then a constrained AI layer that interprets those signals rather than inventing analysis.

Comment by david_iqlabs 43 minutes ago

One thing I’ve learned building AI-assisted tooling is that the usefulness depends heavily on how constrained the AI layer is. If the AI is generating suggestions without grounding in deterministic signals from the system, it tends to produce very confident but generic output.

What ended up working better in my own experiments was system signals,structured scoring, AI narrative on top of the signals.

Comment by Fuzzwah 1 hour ago

While everyone else is posting top level comments about which tools they're using rather than PgAdmin; I've been a huge fan of Beekeeper Studio since I tried out a range of postgresql db apps such as DBeaver, Postico, etc a few years ago.

https://www.beekeeperstudio.io

Comment by SOLAR_FIELDS 23 minutes ago

I found DBGate to be a pretty good cross platform FOSS option

Comment by vavkamil 7 hours ago

Quick fix based on https://github.com/pgadmin-org/pgadmin4/issues/9696#issuecom...

Click on the "Reset layout" button in the query tool (located in the top right corner), and it will move the "AI Assistant" tab to the right. Now, when you query a table, it will default to the Query tab as always.

Comment by jplaz 4 hours ago

Switched from DBeaver to DataGrip and I couldn't be happier.

Comment by aitchnyu 7 hours ago

Might as well choose our AI subscription for our tools. I always hated the sparkle icons in Mongodb Compass (db browsing tool), Cloudwatch (logs) etc which is wired to a useless model. So I always chose to write Python scripts to query Postgres and other DBs and render pretty tables to CLI.

Comment by zbentley 7 hours ago

Eh, as someone generally on the skeptical end of the spectrum for a lot of AI-assisted ops tasks, exploratory query generation is a great use case for it.

I’m highly proficient in code, only average at SQL, and am routinely tasked to answer one-off questions or prototype reporting queries against highly complex schemas of thousands of tables (owned by multiple teams and changing all the time, with wildly insufficient shared DAO libraries or code APIs for constructing novel queries). My skill breakdown and situation aren’t optimal, certainly, but they aren’t uncommon either.

In that context, being able to ask “write a query that returns the last ten addresses of each of the the highest-spending customers, but only if those addresses are in rhetorical shipment system and are residences, not businesses”. Like, I could figure out the schemas of the ten tables involved in those queries and write those joins by hand, slowly. That would take time and, depending on data queries, the approach might get stale fast.

Comment by stuaxo 7 hours ago

If I can use this with a local LLM it could be useful.

Comment by kay_o 4 hours ago

In ollama is included default add the endpoint URL yourself

Comment by zbentley 7 hours ago

Yeah. This seems like an area where a “tiny” (2-4GB) local model would be more than sufficient to generate very high quality queries and schema answers to the vast majority of questions. To the point that it feels outright wasteful to pay a frontier model for it.

Comment by 7 hours ago

Comment by msavara 6 hours ago

No thank you. One of the worst ads for python that exists. The only one worse than pgAdmin is Windows 11.

Comment by allthetime 3 hours ago

postico is really nice on macos

Comment by naranha 7 hours ago

The only interface that works for me efficiently with LLMs is the chatbot interface. I rather copy and paste snippets into the chat box than have IDEs and other tools guess what I might want to ask AI.

The first thing I do with these integration is look how I can remove them.