วีดีโอ

Thanks.

Possible without a gpu?

hello tim. i am pretty interested in the possibilities anythingLLM and Ollama presents, but the question for you (as a person with lots of experience in my book): if I want to make an agent, who would analyse some twitter threads / post in a theme (let's say, nature, or sports), and then write / reply based on what was read. what would be the tool or a service to make such a beast? would it be done greatly in a no-code pipeline (many of them, possibly), or there would be an easier way around?

Great work , congrats . Im Very impressed with your gift of comunicate and the impressive amount of work that it took to develop this tool!!!

Omg I've found u !!!! Been searching over the net. None of it are legit. Yours are true value

This does not work as expected. I still can do the request without any token to the server.

Amazing🎉

Hey Tim, great video! I have a question: I write short 10-minute stories, all based on a five-step storytelling structure. Is it possible to fine-tune a model so that, whenever I ask it to write a story on a given topic, the model consistently follows this five-step process?

why you need anythingLLM when LMStudio already got chat function?

Excuse me. I use the Agent Skill SQL Connector and seems it doesn't work. How can I verify that my LLM is connect to SQL database?

@TimCarambat is multimodal coming? website form data entry? THANKS for the wonderful work. Starring github now.

what are the recommended minimally needed windows and mac hardware specs for this... I'm asking for a friend on a budget :;p ? eGPU possible?

That was a really good video. Thank you so much.

Hi, I'm new to llama. How to start with a Windows computer?

Hey @Tim, I didn't see it on the github page but do you have support for SAML? I want to deploy this at work.

Hi, is there a way I can have this running on my machine but then access it from my phone or another laptop through the browser when im on 4g or a different network?

Great content! Thanks for "birthing" this cool tech. I'm a documentarian with a library of interview transcripts. I'm trying to find the best local method to create a RAG to search and interact with them. Currently, they're PDFs and CSV files. I installed AnythingLLM and have been getting some lackluster results. Probably my fault! What's the best set-up for my use case re. LLM, embedder, vector db, etc? Currently, I'm using all the native options and I find the RAG is hallucinating a lot and/or not showing all results of a search term. Any tips would be appreciated! Thank you!

Great software, great video, a lot to learn from it so, way to go man! thanks for such a brilliant AI piece.

50usd pm min ?!

Thanks Tim for this excellent tutorial. Best wishes for your venture .

So good!! Thank You Man.

Can you make a tutorial how we can make either or the other to TTS for the AI-Response in a chat? I don't mean speech-recognition. just AI voice output.

Could not respond to message. Ollama call failed with status code 404: model "llama2" not found, try pulling it first

Is possible to use AnythingLLM, RAG and then download model and upload to other local device ? I dont want to use AnythingLLM on linux device and use its API

Can I finetune models from the cloud version? I have absolutely no coding skills.

Bro, this is exactly what I was looking for. Would love to see a video of the cloud option at $50/month

It works on my desktop with an nVidia RTX4080 Super . However, what I need is to be able to upload a 120 pages .pdf technical document (eg 9MB pdf) and get a brief extract of main issues raised in the document. I use Ollama models - so far all say that they can only see snippets , so useless. ChatGPT can do it perfectly, but there is a confidentiality problem. Can anybody help , what is the best way to run such an analysis on my private desktop? Can I uise Anything LLM and how ?

Amazing, the way you have explained a complex concept. Thank you

Ok, the Claude API works very well. I have a question: how can I fetch an entire website, not just a single page link? If I want to load all pages of a website, how can I do that?

Either I don't know how to set it up correctly, or it works extremely slowly on the local computer. It's practically unusable.

Screw giving a Github star (I did anyway). Tell me when you're going public so I can buy shares!! lol Seriously, you have a winner here.

THANKS! how to port on WEBSIDE local ??

have one doubt from langchain.from langchain.llms import Ollama llm=Ollama(model='llama3') The response going through rest api using post method , can we acess server side code as it is local host , I want to see the internal working how my input is going to lma model and all the internal detail of model in .py itself

Is it possible to stay in OpenWEBUI and use AnythingLLM by using API on port 3001 like RAG ? I don't find solution in Internet :(

This guy looks like my former dealer lmao 😂

Do you have agent zero support?

Could we set up a trigger to then use the ai agent? For example a new slack message comes in then it uses the agent we built in anything llm?

Really awesome stuff. Thank you for bringing such quality aspects and making it open-source. Could you please help to understand on how efficiently the RAG pipeline in AnythingLLM works ? For example: If I upload a pdf with MultiModal content or If I want my document to be embedded in a semantic way or use Multi-vector search, Can we customize such advanced RAG features ?

yeah we need this, rather then deleting entire namespace

You're an excellent teacher. Thanks

Very cool. Thanks You! This open-source, ethically crafted and versatile application makes ollama RAG and more easy. Clear and transparent Linux install and update instructions too. Well done.

Followed the instructions. At my first question in chat with mistral-7b, I get "Only user and assistant roles are supported!"

Greetings! And thanks for your dedicated work! I'm no great programmer but I'm getting the hang of AnythingLLM. How can Vector-Admin be set up to run with AnythingLLM vector databases? Thanks.

After integrating with Chroma and making a Workspace in AnythingLLM every chat in that Workspace generates the following in the AnythingLLM logs. Any ideas? [backend] error: ChromaDB::namespaceExists InvalidCollection

Instead of dragging files, can you connect it to a local folder? Also, why does the first query work but the second always fail? (it says "Could not respond to message. an error occured while streaming response")

This is great! So we woukd always have to run lm studio before running anything llm?

good tutorial. helped me make my script

Wao what a great tool. Congratulations and thank you. Can you make a video explaining licence and commercial use to sell this to clients? Thank you.

love u !! that's crazy stuff dude i test it for special case .. that's insane can i specialize my llm with my local architecture ?