วีดีโอ

Thanks for the detailed explanation as a beginner it's so much helpful

buddy this video could have been 10 seconds. Jeeez

Keep going I will watch it many thanks

How to save the retriever and load data from it later?

Thanks.. Just one question. You have some videos showing diferent. techniques for. rag... What is the most stable and roubust way to build a very good. RAG with higt success rate, becuase i am seen. that there are too many videos out there all say that theri techniques are the best for good RAG.

FHOST SECAND THURRD FOTH YOUR VINDOS WISTA HAS A WIRUS PLEASE CALL (TOO TOO TOO)-TOO TOO TOO-TOO TOO TOO TOO TANKS YOU FOR COLLING HP TEC SUPPORT U HAVE GRRET DAY!

i have a question if i have a pdf file in other language it will work?

is it free to use unlimited usage

Good video! Is there a way to connect to custom Ilm gateway endpoint with apikey and headers.. internally that custom llm gateway calls openai

Dhanyavad.

Dear is there any way to Hide the reference file which come in every chat, in the chat if i make custom model. i looked everywhere but i cannot find it, please can you help!!!

Nice video. Would be cool if you made a video on creating clusters and running notebooks, jobs using DB CLI as well

Watched the whole thing. Very very helpful. Thanks so much for taking the time to make this tutorial. Much appreciated.

Nice , thx.

Hi , Its nice one ..can dashboard be scheduled to run and update automatically without manually refreshing

Great Video Sir

Amazing video ! I wonder if it supports pdfs and pptx files which have tables and images in it , does this support these elements too ?

great video folk, can you suggest 1) how to run this on other pc using local home/office server as second user or admin? 2) how to place models other than C drive (while your open-webui is installed on C drive). Any help in this regard is much appreciated and thanks in advance! :)

awesome work man!

Excellent video, thank you!!

I appreciate your effort - small suggestion- it would be helpful if you use windows environment to demonstrate

Do you know if there is a way to disconnect from all must-have registrations? I want to take it and manage my own backend without Supabase or LangChain registration. Thanks

thanks for video, i just got one problem is how to make model remember long previous chats, i found about using pipelines in open webui or should i just go for the model knowledge base to make it remember each time about the conversation.

GOAT!

Thank you for the informative video! Is there a way to set token limitations (max_token_limit) for users?

IF THE MODE IS SPLITTED INTO 3 FILES LIKE Q4_1.GGUF, Q4_2.GGUF, Q4_3.GGUF, THEN HOW TO WRITE THE MODELFILE?

How can we use the retriever during inference as Multi vector (InMemorystore()) temporary for the session how can we use during inference time separately

This feature has removed as beta version is over.

Congrats! Excellent explanation! Thanks for sharing this with us!

Nicely done. Thank you.

thanks friend! great video and learned some new things, you can "set as default" the model so no need to choose is each time. see small text under the model name.

Hi , Great video , can you let me know how to call the agent from lambda? I cannot find the information anywhere.

Hey! Thank you for the video, its quite informative. Could you tell me how can I use the downloaded model from ollama to further fine tune it. Sorry I'm very new to this!

chainlit is very nice, easy and simple.

thanks alot

Thank you Daju, more videos on data science related topics would be appreciated.

Very good content- thank you.... but you need to setup a default model😁.

where where you all this time :)

Hello, at minute 1:48 you listed the models you installed on your system, so I wanted to know how or where you downloaded the gpt-3.5-turbo:latest model? or did you create a model with that name?

This project name change to open-webui.

anybody experiencing error while converting pdf to text in the shown method in the video, can use the following code to resolve: from PyPDF2 import PdfReader pdf_text = "" with open(pdf_file.path, "rb") as file: pdf_reader = PdfReader(file) for page in pdf_reader.pages: pdf_text += page.extract_text()

Pls can i use an offline AI model on my Linux laptop of 6gb ram and CPU core i5

hello sir, which one is better installing in docker or manual install. i want to customize open web ui pages and add/ restrict some of the options for normal users. can it be customized? i checked multiple places but didn't get much of documentation on that.

That was a comprehensive overview. Thanks.

Hello, I liked your content.. but it no longer works in 2024 because all libraries are outdated now, can you update to make it current. Just wanted to give you that feedback. Thanks

Sir, would you please share a tutorial for using hugging face library from the very beginning like scratch and explore the available options?

Could you explain how to properly create users, roles, and policies to execute this? I'm getting errors when assigning roles and policies when I use the default settings.

which server are you using to run all this model.? As I have installed in my machine, and it respond with very much delay.

It really works. I need to load a pdf and identify headers and headers levels correctly.. it does beautifully, better than amazon texttrack and other services that convert pdf in markdown.. but only the premium is able to do it right, and it cost a lot.. more than any other. It would me nice if the accurate mode was able to identify headers levels on markdown and Json result.