วีดีโอ

What agents do you have planned for future?

There were some concepts I didn't quite understand; for example, tunneling from the Windows PC to the Mac (if it's on your local network, why work with VPN protocols rather than client/server - due to needing a stateful connection vs. 200 response code or something?). But the interface itself is brilliant! And I think that when it becomes agent-swarm-capable it's going to be a much better option for me than Crew AI, as it feels more intuitive, I am just going to need multiple agents working together. I have never installed a local LLM, but you have inspired me to give it a try. Thanks!

Funny ! I heard yesterday for the first time about AnythingLLM during an AI-info event.... and discarded the idea of giving it more attention because it was presented as "just another local RAG support". And now I stumble across this video by chance - and the additional agent functionality changes everything ! BTW, very well presented , this feature ! My immediate idea & feedback: if there was ANY chance to model custom agents in Flowise and re-import the JSON exports of this Flowise flow as input for an AnythingLLM custom agent, you'd save yourself the trouble of designing your own agent editor AND would start with a comparably large installed base. OK, maybe that's just wishful thinking..... but maybe I'm also not the only one with this wish to facilitate local agent building ;-)

is there an option to utilize GPU? is this an advantage of something like openwebui? Still learning and barely getting into understanding local llms

Tried running AnythingLLM Desktop v1.5.5 on my MacBook. Seemed to install without errors. Unfortunately, the Document import feature didn't work, which meant I couldn't import local files or websites. Fortunately, the AnythingLLM Docker image worked. It allowed me to import local documents for analysis. EZ loading of local documents is wonderful.

Can it also use dalle but unrestricted?

Hi Tim, thank you very much for the great video showcasing open source llms, and tools like anythingllm to create agents. I followed your video and successfully was able to do everything in your video. Are there other agentic videos for other usecases you made, look forward to see them. Cheers

Can't wait to use this. Thank you!

The rothschild/descartes scarred western mind believes so deeply in a stupid mechanistic universe that its surprising when being polite to an intelligence is beneficial for this cuckold

@Tim: I am a professional translator (English to French), and I've just discovered AnythingLLM. Sometimes I have to translate confidential documents that cannot be shared on the cloud. They need to remain locally on my own computer. Once the translation is done, they have to be encrypted to be sent to clients. Could I use AnythingLLM to help me with the translation process? Could I use it with my actual Lexicum, glossaries and personal dictionaries? Most are PDF or DOCX files. How would I do that? What are the first steps? Many thanks if you can give me some hints on how to proceed. I'm now a new subscriber! 😊

i tried anything LLM and RAG sort of works but I can never pull anything factually from my uploaded text files which are configuration files. Is this a model issue? I was using Llama3 Q8 via ollama and llm studio.

When I try to run the Agent I get "Could not respond to message. No provider found to power agent cluster."

Good stuff, will try it out. Subscribed. Looking forwards to seeing how this develops.

Great job! This is wonderful! I will be responding after using to let you know my thoughts if you care to see them :)

How do you connect it with sqlite3 locally? Can you make a video how to connect to database?

Great info. Need a detailed tutorial. You skip over so many important things on the setup process. Nothing works when I tried to follow your steps. It’s too fast. Please put out an updated video with in detail steps on how to make all of this work. Thank you. 😊

You skip over this part. From creating a google search engine. Copy the following code and paste it into your site's <body> section, where you want the search box and the search results to render. I pasted the google provided infomation into AnythingLLM, when queried AnythingLLM returns Could not respond to message. No provider found to power agent cluster. I tried breaking the google provided code to fill Search engine ID and Programmatic Access APIKey boxes provided in AnythingLLM still no luck. Everything else has been easypeasy. Thanks for your efforts.

Looking forward to release for Linux

Is this tool capable of multimodality?

I can see the hunter2 password

Thank

Why do LLMs "hallucinate?" Why can't they just say, "I don't know. Never heard of it. You tell me?"

A fantastic beginning! When do you think we willbe able to create our own agents?

Hey, thank you for putting out anytingllm. I have two questions: 1. When I ask the llm to remember something, is that long term memory stored on my pc on a server? 2. is the summary part of the long term memory necessary? And I have a feature request for an automatic long term memory. Meaning that I don't have to say specifically what to remember but that the llm will be able to recall the entire chat history - eveything i have ever said in that thread. Is that in the picture?

Live web search and browsing. Can anyone help me. When I click and create API from google, I get: <script async src="cse.google.com/cse.js?cx=CUSTOMNUMBER"> What do I write in Search Engine ID and Programmatic Access API Key? Search Engine ID is probably just an internal name, which I can write anything? What about API? Do I insert just a CUSTOMNUMBER, or "cse.google.com/cse.js?cx=CUSTOMNUMBER" (Without ""), or what? It seems I don't understanding something... Thanks...

Great video! however, i followed every step you described in every detail, but i could not make the agents communicate with outside world. in any ''search'' or 'webscrape'' request, the model is hallusinating, and presents data that are already to its knowledge insted of real time data (i.e. current gold price ). i used llama3 Q8, i inserted google api and id code, i also tried the other search engine.. nothing. the logs show that it really creates json commands, but nothing comes in from the internet.... any help ?

Im a chronic video skipper but watched this back to back. Great explanations and can't wait to try this out! Would love to see more videos, tutorials or even lectures from you. You really have a knack for explaining things!😊

Really impressive, I obviously lost my time with privateGPT before knowing anythingllm. I connected it to 2 x self hosted ollama dockers for agents, which are on another server and plus LMStudio, which runs on my workstation for faster instances and testing new models/embeddings etc. This piece of software is really the beast. I would really appreciate if we could see more improvement on agents, where we can use them in more flexible way

it would be nice if the desktop version could have a web server integrated into it so you do not have to mess around with Docker which I found to be slower

Weel Done. A sugestion is how to conect AnythingLLM with Grafana Dashboards and Node Red to give voice comands to switch on machines and ask for telemetry of then. Rafael from Brazil. Sorry about my English. My mother language is Portuguese.

Do not make stupid. You cannot replace ChatGPT with only the tools you mention.

Hi, how to see if this LLM is using my GPU as well? I have a nvidia 3060 laptop gpu. Don't have the cuda installed.

I tried uploading a few PDFs to VectorAdmin, but after finishing processing, it shows "no text found" in all the chunks. There is no problem with the PDFs. I uploaded the same files to AnythingLLM, and they work fine and display correctly inside VectorAdmin. The issue occurs when uploading the PDFs through VectorAdmin. Can you please check?

Absolutely great!! thank you!!!

Hi this is awesome and am newbie.. does this bot have voice to text functionality? Will it also help integrating streaming avatars such as heygen api?

WOW! Mindblown! The RAG is fantastic! I uploaded a 'Davidson's textbook of medicine' and was able to ask questions and what not out of it! Thank you for the AnythingLLM Desktop. Thank you! Thank you! I have no more words!

any chance that this can work with PgVector?

Brilliant! Could it use my own computer as a data source for the agents? Can I scrape my mac?

This is impossible...

and fortunately, I don't feel like you covered the material properly. For the most part, you effectively dragged every. dragged everybody the same exact spots that everybody else has been doing for the last two years. So you don't actually have anything really new. You talked about the quantization as though you were going to show how to do some extra manipulations, but didn't go. There. overall in getting to the points of the main meat, you took far too long, I'd say. effectively you had three minutes worth of material that you turned into over 14 minutes. Sorry, but I can't recommend you because 6 months ago we had people doing far better breakdowns showing how to work multi agent systems. You do have a really decent radio style voice. If you work with that that'll make you successful alone. That a lot of the guys who are really learned will get bored. in seconds listening to the way you talk and go. Nope, you're not the guy. Sorry to bring the criticism out there, but I'm a big believer of somebody doesn't mention something. Then people cannot improve upon what it is they're doing I would tie to basically reedit the entire 14 minutes and see. if you could get it under three minutes.

I had no idea you had a channel talking about your software. Im a big fan of your work!

This is so dope. Great no-code solution and it's awesome that it's open source.

thanks a lot for your video, this the first video that i see and it's really simple to understand, i have a question, if for example the model that i use know that the capital of france is paris, how can i change that information and make the answer different from paris? best regards

This dude is the coolest underrated person imo

You downloaded 8b-instruct-q8_0 but selected the latest version why? 6:42

Fantastic video but i dont understand how to get the google api, can anyone help point me the the right direction? thanks

I know it's a huge ask, but it would be great if it could listen to a inputs and active windows. it could be really cool if it could capture and describe my workflow, i could analyze what i am doing, and than generate macros for me.

Hi, Tim. Great work. I'm trying to use Google. But... it is free for 100 queries per day. How I can control it or limit it? Other options are payable :)

Hi, have to thank you for the tutorial. It is very useful to quick test different LLM models, vector databases and other points with different data content. And just after that think about what stack is suitable to index your own data and try to deploy it on a server-side. Thanks!

this is out of date.