Видео

I can only get the no Persistence option to register into Docker. I run exactly what is prescribed, I have Docker open. I keep getting the return from the terminal that says - "docker run" requires at least 1 argument. very frustrating I have no idea why this seems to work for everyone else, but not on my machine. I am also unable to see the Port after running the localhost:8000 command in the browser

Is there a model that can give real references for academic writing? Can we add articles and books to that model?

Thank for share, I wonder when working with file, how many lenght then it can be handle?

Why don't you activate the agent by default?

It's a paid promotion and it doesn't mention it at the beginning of the video.

Hey. Nice to meet you. I’ve just come across this now and honestly, this couldn’t come at a better time. I already realised the potential of AnythingLLM and was looking at how to utilise it as I’m building some text to action agents and your video just accelerated my path to objective. I have subscribed and look forward to more of your posts. Nice work 👍🙏👍

I am curious to know if anything LLM has code interpretation capabilities like running it if not I would love to work on that and also if it is I am going to do some awsomawesomegs with it.

I am using linux. How do I find all the text files that I scrapped? I want to move it to another pc

When trying to chat with the A.I. model through AnythingLLM rather than Ollama, I noticed that the model seems to be incapable of identifying its model designation. It now only knows itself as "assistant" or "AI powered assistant".

This is by far the best AI Agents video. I've starred the github repo and will use AnythingLLM now ! :) Thanks a lot for all the info and for making this available for everyone. Legend

​@TimCarambat Im pretty tech savvy but no coding. I keep meaning to learn but what's the point now, right? I have committed to a MAAAAAASSSSIVE project that combines a together-working group (huge number) of agents thoroughly trained in all sciences theory, logic, geology, history, theology, ancient languages and a deep deep breakdown of biblical anthropology, historiography and character study, with scripture combinations to allow preachers to prepare sermons promptly and thoroughly, students to learn deeper, Christians to understand the things they are struggling with, Jews to see the references between old and new testament, educate the generally curious, resulte argument if even only in ones own mind, to understand how and why those things all fit together like a custom fact glove, including the big bang theory and Einstein's relativity theory between time and space expansion, to all, in the end, hope to lead some to Christ. We just don't generally have the resources to work that puzzle, at least for painfully logical people. It's called The Crimson Project. We are just starting to build the agents that will help gather the data necessary for all that and help organize, market and to map it out. I have been watching videos for days and ran across this. Things are still mudfully clear on where it will live but I'm starting to at least lose the headache due to multiple options. Still, one that fully works as intended, where intended, for who it's intended... long way off, for me. I still have to get familiar with GitHub AND Azure, l it do I??? (CHAT GPT feels Azure is best for such a project... Haha) Thank you for what you're doing. It's been at least a little enlightening. I'm having a little trouble grasping where they eventually function. Anything LLM is so far the fastest, easiest and most quickly-accurate, for long term memory, but still... Running out and offering the whole ball of wax to the public? That's going to be a long road.

It is unclear how to use or do the Cutomization to the Chatbot. I think you would benefit from showing also how to do this on WP. It can seam to you like the same way as on other platforms but to us users we hardly are able to do it on ower own (WP) platform. If you know then you can but if not then you dont know how to begin. I like to use AnywereLMM as a backend to our website and CRM (our own dev) and need an api.

This is so amazing!

this video is extremely boring and useless, it only helped me to lose more time trying to use this shitty web worker

Your llm being able to do an api post and use the return data back as rag would be the best. Do you have that yet?

I have loved everything llm since the beginning.

Awesome presentation.

Excellent work🎉 , Offline- RAG-Opensource!!! Very useful, working well in my pc. at 5:46 when I type & select ollama, base url is detected automatically 👍 thank you for this master piece Anything LLM👏👏

Can you make a complete video on the installation of Docker Anything LLM please ??

Can you make a complete video on the installation of Docker Anything LLM please ??

Wow, AI research tools are really changing the game! As a researcher, I've found SmythOS to be a game-changer for automating complex workflows. It's amazing how AI agents can now collaborate to tackle big research challenges.#SmythOS #AItools

This is absolutely absurd. Thank you so much, this is an incredible project and I hope it gets more attention. I'm sold!

Great. Thanks a ton. I was searching for this precise thing. I need to talk to you. How do i do that?

also how can I add some custom tools?

this is a great tool indeed, installed it and works great !. Could you help me understand how you got Ollama models to have function call to work, I find it errors out when I use with langchain. Appreciate your help. It seems to work ok in Anything LLM, at least better than using langchain

support for mem0 long term triple-mem-db support and sciphi/triplex embeddings model via ollama for contextual graph?

I guess I'm just not smart enough to get to use these tools. I can to this video trying to find out what you mention @5:55 about the Ollama URL, I can't find out how to get this you say when Ollama launches but I can't even get it to do that, it is installed but how do I get to that URL? I really am trying to learn how to do this but it seems everyone can figure it out but me.

@6:37 you mention copy paste from Ngrok? What is this? where do I find the URL to paste for this, can you make a more beginner step by step of this you go so fast over it, I'm basically going frame by frame trying to understand everything you go over so fast. I'm stuck on the LLM preferences page on Anything LLM trying to figure out where I get this URL and it stays waiting for URL to load chat model selection.

What's the best small quantized model to work with agent?

Hi Followed instructions ... When I try to import a document, I get an error message : "Error 1: the documents failed to add. The specified module could not be found" and it refers to \\?\C:\program files\ .. \onnxruntime_binding.node. This file is present on the system - I have checked. Running in debug, I get: [nativeembedder] The native embedding model has never been run and will be downloaded right now ... [nativeembedder] Failed to download model from primary URL. Using fallback error : addDocumenttoNamespace The specified model could not be found \\?\C:\program files\ .. \onnxruntime_binding.node Again, I can confirm that the file is there. So am unable to import docs for training - please can someone help me in working out how to get AnythingLLM to download the native embedding model?

waiting for local install video

@tim carabat - Legend! Can you show how Anthing LLM can interface / co-ordinate / use your defined oLlama's Agents?

If I may ask.... my powerPC with a GPU where Ive installed LM Studio, is in the same room, but connected by wire to the same Network as I am with my Laptop that is using WiFi. Both devives have NordVPN with Meshnet options, allowing to simulate LANConnections ... However, I cant fully connect to the LM Studio (CORSHeaders on). In AnythingLLM it doesnt list the available models.

Thanks for the video, Tim! Quick question: Will this work with scanned PDFs, or is it only for digital PDFs?

FOR ANYONE THATS CURIOUS UNSLOTH DOES THIS FREE

Hi, Thanks for the tutorial. I am making a RAG within AnythingLMM. I use: 1. LM studio : Llamma 3.1 8b. 2.Connected to AnythingLLM 3.New Workspace. Question: What did you choose under setting: Chat: LM studio or Ollama? and Agent:... LM Studio or Ollama? Thanks!

this not worked as expected. i can do request without any token

I'm sorry, I'm aware that it may be an incredibly stupid question, but If my LLM runs on the virtual Linux under Windows, then do i need the Linux or the Windows version of AnythingLLM?:) I'm sorry again about it.

Self Promotion for AnythingLLM

thanks for video, only thing coming to mind for me rn, is a struggle with docs, files, etc beeing spread all over between 5 disks and would love to not go through it all my self to see it a file is duped, and yea, short words, i need an orginaizer.

Cant make a custom any LLM ?

Is there a way to include the knowledge from the RAG assets into fine tuning? Can you fine tune with multi modal assets?

Hi Tim, I recently installed your software, and in my Set Up list, I cannot obtain the embedded code because the software does not have an icon for it.

Thanks for building anything llm with these features. For many days I was searching for better UI than a terminal and more features for ollama models. And you have done it. Thank you very much.

Is there an AI that we can use to fact check with citations the output given by the AI so we don’t get “hallucinations” which is politically correct speech for AI gas lighting.😂

Will we see an iOS version to run on iPads like the new M4 iPad Pro?

This is so cool! 🎉🎉🎉🎉❤

You are awesome <3

Hey, How to deploy chroma vector in AWS without using docker.

Thank you