PgAdmin 4 9.13 with AI Assistant Panel
pgadmin.orgWhen 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.
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#...
Note: AI features must be enabled in the server configuration
in config.py for these preferences to be available.LLM_ENABLED = TrueI did not enable this and yet I got the panel in the UI.
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.
Worth pointing out that Postgres is perfectly usable without an admin dashboard at all
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.
There is no need of potential dangers to not want to have non-deterministic features in an application.
> 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.
just don't accept bogus changes it suggests? this is why having a human in the loop is a very good idea
Yep, I fully agree. It'd be awesome if all (or even most?) of the users were immune to automation bias though. :)
https://en.wikipedia.org/wiki/Automation_bias
And hopefully the users who are using this aren't YOLO-ing it. Though I'm pretty sure we're all expecting there will be a sizeable percentage who are.
It's there on the UI, but it doesn't do anything if it's not enabled.
If you arent using it is it even a danger?
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!
When I open a new query window, the AI tab is selected by default which is annoying. I just want to write SQL without having to switch tabs like I could before. Not only has it ruined my muscle memory, it's also more inefficient.
You can use it with Ollama rubbing a local model.
Why do you do in production?
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).
I run pgAdmin with docker and there's almost nothing to it.
When a new version comes out, I just update the image version on the stack yml.
The fact that you need Docker to make it easy is already a mayor failure. What happened to single binary programs that you can just run? I don't want a whole virtualized OS installation just to get a desktop application to work.
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.
Switched from DBeaver to DataGrip and I couldn't be happier.
i want to love datagrip but it big, slow, memory-hungry, and presents an unfamiliar paradigm to me over against most tools i've used for admin tasks. other than this last issue, do you have any suggestions for streamlining the experience?
I already use several development tools from JetBrains, so it made sense to streamline everything since I'm familiar with their terminology and UI.
I recommend going with DBeaver if you're only using it for admin tasks and small queries. It's probably your best option for a free, lightweight client. Another strong alternative I keep reading about is TablePlus, but I don't have any personal experience with it.
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.
I was on the prowl for a new DB Management tool, after pgAdmin 4 shifted to their web based client crap.
I never came across this. Found DBeaver and using it since then.
I found DBGate to be a pretty good cross platform FOSS option
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.
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.
I've used similar with SQL Server Management Studio (GH copilot) and it's pretty useful for database work and gnarly queries.
This is great, but I'd prefer to see a refit of their UI first, it's currently a bit slow and looks prehistoric.
If I can use this with a local LLM it could be useful.
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.
In ollama is included default add the endpoint URL yourself
No thank you. One of the worst ads for python that exists. The only one worse than pgAdmin is Windows 11.
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.
postico is really nice on macos
Now I don’t need to copy, paste, take screenshots or use Claude? This will save me minutes per year.