johntash

I have a similar goal/desire as you. My current project is ingesting this type of data into Elasticsearch with vector embeddings and using a normal search+knn to generate some context when creating a prompt.

This works reasonably well with gpt4, but my context is almost always too large for self-hosted models so far.

Would this work for having proxmox modes across multiple datacenters? IIRC it was sensitive to latency

I don't really use the HA features of proxmox that often, mostly just for migrating vms across hosts. But I had been thinking of re-installing some of my remote servers with proxmox and hooking them up to the same cluster so that I could potentially shut off all of the servers in my basement and run everything from a remote location, then migrate the vms back later.

If you're already familiar with Ansible, what about doing some stuff with cloud-init and then having cloud-init trigger a local ansible run? Then you don't have to worry about running into the limit.

This looks pretty great! I used to use beancount + fava a lot, but have been slacking lately because it just feels like work to input everything and catch up.

I might give this a try and then see if I can convert my beancount files to ledger.

hurl is great, glad to see it's being improved on. I wrote a small wrapper around it a while back to be able to re-use some auth stuff in different requests, but a simple "include <file.hurl>" would be an awesome addition in a future release.

Getting started with it was way easier than figuring out postman or any of the many other http testing frameworks with their own languages/dsls

Will the server-side option still be included in the open source version? I have almost the same use-case. I want to run devpod (or something) in my homelab and sometimes access it from my ipad.

Is there a list of changes compared to searxng somewhere? I'd recommend adding something to the readme about the reason for forking the project as well. As far as I know, searxng is still maintained and accepting PRs?

Also, the readme says:

> In short, we just don't log nothing which means you don't really have anything to hide.

Double negatives like "don't log nothing" really bother me. You'd probably inspire more confidence simply changing it to "We don't log anything".

YaCy always seemed like it'd be much more popular if it had a UI/UX overhaul. Once I figured out how to have it auto-index feeds from certain sites, recent linkding saved links, etc, it became a lot more useful to me. I also have SearXNG include results from yacy automatically so I basically never interact with yacy directly anymore.

Another thread mentioned something like a 30day unlimited trial. That could be a good way to gather metrics on how many searches/day to expect from users, and should help with pricing.

Which part of the service actually costs you more money? Is it the cpu/bandwidth of returning search results, or is it the indexing that happens before then, or the storage/memory?

Maybe instead of charging per # of queries, you could charge per number of sites the user follows/searches? You could always leave something in the ToS about abuse to have an option to stop users who are making an excessive number of searches.

I've been using a self-hosted instance of SearXNG (a meta search engine) to exclude a lot of spammy sites from search results. I'm not sure if you can force it to only search a list of domains, but might be worth looking into.

Thanks! I have something similar that I've been using and struggling to keep consistent. I like that this is a relatively small package, I'll probably end up using it to play around with.

I've only skimmed through the docs so far, and it sounds interesting, but..

> The Mojo standard library, compiler, and runtime are not available for local development yet, so we created a hosted development environment where you can try it out. We call it the Mojo Playground!

Is this going to be a SaaS-style programming language, or will it be open source and local later? I'm not sure I understand why a new programming language wouldn't start off as open source, or at least able to be used locally?

I'm not super impressed yet either, but I do think there's a lot of value. I tried a few times to get it to write some simple python scripts, and usually it'd get some things wrong. But it did help to get the basics of the script started.

If you haven't already, look into trying out Copilot (I don't think there's a free version anymore?) or Codeium (free and has extensions for a lot of editors, just be careful with what code you're okay sending to a third party). Using AI prompts as a fancy auto complete is what has been giving me the most benefit. Something simple like a comment "# Test the empty_bank_account method" in an existing file using pytest, I go to the next line and then hit tab to auto-complete a 10-15 line unit test. It's not always right, but it definitely helps speed things up compared to either typing it all out or copy/pasting.

My biggest annoyance so far, at least with Codeium, is that sometimes it guesses wrong. With LSP-based auto-complete, it only gives me options for real existing functions/variables/etc. But Codeium/copilot like to "guess" what exists and can get it wrong.

> Like a buddy who sits nearby with a beer, sees what you do and is seasoned enough to drop a comment or a story about what’s on your screen any time.

I agree with you, this is probably where it would be most useful (to me). I don't need someone to write the code for me, but I'd love an automated pair-programming buddy that doesn't require human interaction.

This looks great so far, thanks for sharing!

I'll probably give it a try this weekend, but I'm curious - does the @ai_fn decorator ask the llm to write python code and then runs that python code in place of the function? Or does it basically send that prompt to the llm and return the results from the llm? I'm assuming it's the latter, but I didn't see it mentioned at first glance.

When I had multiple billable clients, I used to use org-mode and org-clock. It was really nice because I could keep really detailed track of which projects I was working on throughout the day.

I've changed jobs since then though and don't really need to know more than the total number of hours for a day, but I've been using Obsidian for that. In the yaml frontmatter, I have a 'clocks' array similar to what the clock-in/clock-out looks like from org-clock.

I recently imported my bookmarks into a linkding instance, and use the firefox extension to add new ones to it.

It's slightly better than the browser bookmark manager.

https://github.com/sissbruecker/linkding

Thanks for writing this up. I read through it the other day and it was a lot simpler to get through than digging through Langchain for the first time.

I took your example and added a couple other "actions" like searching a searxng instance and returning the markdown version of a certain url. It's surprising how much more useful it can be when it has the ability to look stuff up on the internet.

Can this be run locally without beefy GPUs by any chance?

If this is true, could he get in legal trouble and be required to pay everything back?

Thanks, the nreal air are the ones I had seen a few videos about. I'm not sure if they're worth the current price to me yet, but I might think about it if it comes down in price or a newer version comes out

What glasses are you trying? I've seen a few videos of people using their steamdeck with AR glasses, and it seems kind of neat.

Having them on a plane could be interesting. What resolution is the display equivalent to?

I was tempted to do something like this but couldn't get over the idea of sending a bunch of personal data off to openai (or any 3rd party really)

Do you know if the Aranet4 can be used over bluetooth/wifi without internet access? I've been looking at a bunch of devices and haven't seen aranet yet.

Also, have you ever put all of your devices near each other to compare the variance between them all?

There was a video I watched years ago where someone was on an airplane and basically tested how they'd react with a lack of oxygen. It was pretty crazy. He knew he needed oxygen, but didn't feel like he needed to do anything about it.

I think it was this one: https://www.youtube.com/watch?v=kUfF2MTnqAw

I don't know much about Nix, but I'm planning on reading more about it.

Since you mentioned packer/proxmox/nixos-generators - am I understanding correctly that nix could be used instead of packer to generate a vm image/template for proxmox(or whatever hypervisor)? Is it limited to NixOS or could it create a centos image as an example?

I've used a combination of packer+ansible/chef/salt to create images, but it's always felt a little clunky.

I never heard of either of these, but Neon does look pretty cool. I might try it for some homelab type stuff that doesn't need a database running 24/7.

https://github.com/neondatabase/neon

This sounds pretty interesting to me, what exactly is the flow like?

I thought about making a google chat (or some other chat) bot message me every few hours and basically ask what I'm doing. That combined with some fancy logic like detecting when I'm not home/sleep/etc, could probably come up with a good personal timeline.

Looks pretty interesting. Can you log and track more than just mood? I used to use Nomie, and now use Bearable for something similar. Having an open source alternative would be really awesome.

Also, small feedback - it took a while to find the link to the projects github. It should probably be on the main page somewhere?

Do you tile your windows as well, or just keep one-ish app in each desktop? I.e. do you switch between desktops and windows all the time, or only between desktops usually?

This looks pretty neat so far, and I'll probably try it out. What I really liked from the demo was that the queries get rendered into the actual markdown file.

I've been using Obsidian a lot lately, and one of the downsides to something like the dataview plugin is that the results of the queries are only available within the app. I can't open up the .md file in vim/emacs/vscode and see the same results.

With emacs, I relied quite a bit on this sort of functionality too so it's been annoying me lately to not have it.