tcarambat1010

For ternary mlx, size on disk is 3.8GB. 512x512 peak memory use is ~3.7

We will have plugins for: - Auth - Agent skills - Data connectors

soon, agent skills are first and this should help plug the gaps between offerings since we can't build everything for everyone

That's the point! Shouldn't have to know and naturally over time you'll learn more and the controls are there when you feel comfortable tuning them

We actually are planning to really lean into the "Desktop assistant" style of things, so yes absolutely. Like how on Mac you can cmd+space to launch spotlight, we can offer the same functionality alongside everything else.

WIP!

Depends on the model you want to run! That is the beauty of it. If you can muster that ability to run a Q4 Llama3.1 8B - great, if your specs are really low end you can always outsource to a cloud provider.

Maybe you want to run privately, but can only manage a Gemma-2B - then great, you can use that also.

This is a connection issue for your docker cli - we have seen this issue before and it had to do with client proxy.

https://stackoverflow.com/a/48066666

It's not my position to "impose" a preference on a user for an LLM.

Privacy by default means "if you use the defaults, it's private".

Obviously, if your computer is low-end or you really have been loving GPT-4o or Claude you _can_ use just that external component while still using a local vector db, document storage, etc.

So its basically like opt-in for external usage of any particular part of the app, whether that be an LLM, embedder model, vector db, or otherwise.

You can use LiteLLM _as the LLM provider_ which is just a relay to a ton of other models. For people who already have it set up connecting to x,y,z providers can keep that work and use it for inferencing as well

It was indeed a brainfart on my end that has then been in there since the dawn of time. Pretty funny honestly

It was a typo haha, someone just PR'd the fix for it. God knows how long it has been there - whoops

In a world of AI Agents/Assistants now is the best time to easily experiment with scope-focused agents that do a handful of specific tasks very well instead of one agent doing them all well.

We were working with many assistants and found that the task of delegating work to known agents via a single "head" assistant automatically selecting the best assistant(s) was working really well for us! So we built a library around it with some other convenience functions for assistants for OpenAI.

With parallel function calling you can have a single complex user query be automatically split and delegated to many assistants at once via a single library.

From a developer perspective, it simply extends the OpenAI SDK making a new `swarm` method available so code lift is minimal.

Other helper methods like grabbing all your assistants that are available in a single call with pagination handled exist - checkout the docs on the Github or NPM package.

NPM: https://www.npmjs.com/package/@mintplex-labs/openai-assistan...

Im not surprised Azure would add something like this to the stack. We build AnythingLLM (https://github.com/Mintplex-Labs/anything-llm) back in June due to some enterprise customers wanting something isolated they could run on premises with Azure OpenAI support + any vector DB they want.

With Azure's move to try to internalize any enterprise integration for AI it makes sense to make a chatbot wrapper because its a no-moat move. I think a lot of the "moat" if one can exist in the "chat with your docs" vertical is just integrations into flows and data sources SMB/Enterprises are already using.

For businesses, in my experience, the on-prem thing has been the first decision point - without question. Azure wrapper could be nice to have for those who cannot use chatGPT on the work comp but have access to this instead.

I wonder what kind of hypervisor view it gives to Azure admins for those who use it - it any. Multi-tenant instances was the second highest demand from SMB/Enterprise customers for AnythingLLM.

Hey everyone,

My name is Timothy Carambat and as a side project a while back I built senatestockwatcher.com and housestockwatcher.com which track congressional stock trades since the STOCK act was passed.

Since I've made those sites the data from transcriptions has been used anywhere and everywhere for people looking for "insider" information or just to see who is in violation of the act (over 60 congressional members are).

I figured with the rise of AI and the sheer amount and complexity of this information it would be WAY nicer for someone to just ask "How much volume did Nancy Pelosi trade in Q12022" and get an exact answer.

Other popular questions: "Who trades more? Republicans or Democrats" "Who is the top trading Senator?"

You can also ask any question you wants. I took heavy inspiration from ChatGPT's UI because...why not?

Its free to use, just signup with an email and its 5 custom queries every 24 hours!

Hope everyone enjoys it! You can also download all the raw information directly on the respective websites!

The site has been hammered down by google now and will be unranked since this story broke.

https://html-online.com/editor/

In case you cannot view it the banner across the site says now "Goodbye!

This site has been penalized for unnatural link building and will be removed from Google Search

Please bookmark if you wish to continue use of the site.

We are sorry and are working on fixing the problem to recover from the penalty. "

They are only sorry they got caught

Hey everyone, I'm the creator of this. I'm listening to everyone's comments about new features and expect them shortly!

Thanks for everyone's support and appreciation.

I am, I keep a local copy because this is not an API service. So i have to collect the data and retain it.

that being said I am developing some trending graphs to see trends on a time axis. I think some of that may be useful as you can correlate trades with news for that day.

The data comes directly from https://efdsearch.senate.gov/search/home/, which is where the senators must file their trades.

So it is as accurate as legally permissible. The tool only shows reports for the day, currently, there is no time-based analysis.