Видео

where do i put the first code, im very beginner

Dude just made my doubts clear before I finished my tea.

for the life of me i cant figure out how to connect open webui to ollama. 127.0.0.1:11434/ show ollama is running. I tried: host.docker.internal:11434, 127.0.0.1:11434/ at open webui ollama api still unsuccessful. Went inside the docker (docker exec -it name) and curl 127.0.0.1:11434, still no good. I delete ollama, remove all docker image etc, still no good :( the regular container without port mapping works fine though. Great videos btw, i have watched all your videos and follow your tutorial, I hope you do more ollama and langchain videos.

I'm really impressed with the 27B version of Gemma2. It's working well for me as a usefully competent Russian language conversation partner/tutor, which is pretty amazing for something small enough to run locally. Mistral (7B) and Llama3 (8B) weren't quite sharp enough.

First of all Thank you for making this vedio!!, can you also make vedio on how to handle when mulitple text files are there. Thank you.

I really like the way you present this stuff so clearly and directly - you have a great teaching style. I'm going to keep tinkering with the chat app: it's fun! Glad I found this channel - thanks :)

Awesome structure and explanation !

This is a great video. You teach like a Professor. You're an expert and well talented! Your organization will indeed love working with you.

You're great!

Thank You!!

Thank you!

Very helpful, thank you

Getting the error: --------------------------------------------------------------------------- ModuleNotFoundError Traceback (most recent call last) Cell In[1], line 1 ----> 1 from langchain_community.llms import Ollama 3 # llm = Ollama(model="llama3") 4 5 # print(llm.invoke("Tell me a joke")) ModuleNotFoundError: No module named 'langchain_community'

can run command on 8:01 denied permission?😕

I can only see the bin file where is the gguf file?

Man. That is amazing. It took me 10 min to set this up and I am not a coder. Thanks. That is bunkers. I got 3 immediate questions. Is that safe in terms of the information that one loads there? Can one customize the logos and the appearance? can one use it for personal and commercial purposes?

Will one lose the private LLM when using ngrok? IOW, will the prompts and responses be exposed to external servers, the Internet?

can you please add a video/short in which you tell that how to display the name what i want using open web ui i mean i write something in open web ui localhost which you have tell and i want that when i send the message its format is Me: bla bla bla the the llm reply like this [the name i want] : bla bla bla please 🥺🥺

That was an interesting one. I saw some of your videos and you've been subscribed instantly. You deserve more attention. Hope to see more from you in the future.

I have downed ollama, stroed it in my computer, but cannont open it. Why? How to deal with this?

how would you import not-quantized models?

No way I just found this in the 10 minute video. I wasted a whole day trying to set-up nginx properly. Thank you so much for your concise and informative tutorial, now it works for me. P.s. I am in deep regret that some extraterrestrial force made me find out about nginx, but it is also overshadowed by the fact that it literally took me 15 minutes to set up the whole online llm vm on gcp from zero to hero.

thank you for video! I have one issue - when i trying to chat with my model through phone, using OpenWebUI and ngrok - model generate answer edlessly after one or maybe two completed answers. But if i do this from another PC - all works as it should be. Does anyone know the solution for this?

Thanks a lot for the detailed explanation in the video! I have a question regarding Ollama: Is it possible to use Ollama and the models available on it in a production environment? I would love to hear your thoughts or any experiences you might have with it.

hello pro its very good tutorial i have some file contain some article its good to with small articles from 2 - 3 line but if lines is more than 20 line its give response from no were can i increase chunk size or any solution to solve this ? thank you in advance

Hello, how can I run Ollama for my internal network? I don't really need outside access yet; can you explain or point me in that direction, please.

THIS IS SO COOL. I've been looking for a way to do this for a couple of months now

You are doing an amazing job. Looks like you are not feeling motivated to make more videos. I see you're spending too much time editing hence the turn off. Just produce raw videos, people will excuse small mistakes. You've some great talent, spread the knowledge around. Can I request you to make similar video on crewai? thanks

Fantastic video! The RAG example given is for a single document, but a repository usually contains dozens of documents. Is there a way to bulk-upload the documents at once to the LLM (for chunking and embedding)? Thanks.

nice, small sized demo, demonstrating the principles. good job, I learnt a lot 🙂

Thanks for the video. Keep going. Your explanations are on point!

Hey man!!! Thankx You're the man You're the one who wakes the rooster up You don't wear a watch, you decide what time it is When you misspell a word, the dictionary updates You install Windows, and Microsoft agrees to your terms When you found the lamp, you gave the genie three wishes When you were born, you slapped the doctor The revolver sleeps under your pillow You ask the police for their documents When you turned 18, your parents moved out Ghosts gather around a campfire to tell stories about you hugs for brazil

Fantastic video. Yes, I could explain embeddings. I already had a basic concept, but your simple file-based cache of the embeddings really highlighted the basic functionality without needing a vector database.

Same as adding a system prompt in curl, right? without having to create a new model.

Keep it up, brother! I love the way you teach with live demos It's really effective and easy to understand

Amazing video, super clear, helped me understand and debug my code! Thank you for sharing this.

would like to see a video on pretraining and fine-tuning models

💥That´s wonderful. I´m not a programmer, don´t know Python, but I could install Open WebUI, nd it has only Ollama models, and I love those Hugging Face GGUF models. So I need a way to run them on Open WebUI. Thanks ! ❤❤❤

C:\Users mibe>ollama create arr-phi --file arr-modelfile Error: command must be one of "from", "license", "template", "system", "adapter", "parameter", or "message" Can anyone help?

thanks man

Hey man great tutorial. For some reason on my phone, I can't access my chat history. I can only start a new chat each time. Do you know how to fix this?

If you are into the Apple ecosystem, you can use Enchanted as the UI. It is native and available on Mac.

How to run this in windows, where files are safetensors? Where to create modelfile? I have multiple models on different directory of oobabooga/text-generation-webui, I have to use them in ollama.

Things worked for me on my local host, upto the stage where it asked me to select a model. No model showed up. I have Phi installed. Can someone help?

Great video! I have a question, after getting a link via NGrok, the whole AI model is still running offline, or the data is going to any other server, that is my main concern. Thanks again

Probably one of the best beginners tutorial out there!

How simply he explains the concept Chaining and Piping 👏 But I have a question, Is it a RAG model that you've developed ....??

Are the commands the same if I am using Linux ubuntu, WSL?

I love that your video is up to date with the latest Langchain imports 👍👍 Are you planning a series on LangChain ?