Видео

Wallpaper please

can such a llm model be used in a web app not just in a terminal locally and how?

Super helpful!!!! Thanks for making this. Going to watch more of your 'actions' videos for sure.

wait... you're on localstack's 3rd party (non-local) website managing your local resources? Something isn't right with this picture - that UI should be hosted locally.

Hello

it's work! thank you from Indonesia

Thanks for making these videos, Your videos are super helpful & awesome. You deserve success here!!

good evening, could you help me understand how this or that works and when to use it and also so that I can clearly understand how to use the workflows which are made available as an example on the site, there is only very little explanation and I don't understand

Can i also use traefik to expose not a container but instead a internal ip (a other vm) and put https externaly to it? :)

Hi amazing stuff! Is there a way to connect the ngrok to jupyter notebook? Thanks!

When presenting, enlarging type (your VS Code window) is not a bad thing. Lots of people consume media on a smaller screen nowadays.

Just wondering... Are you using Oh-my-zsh or any other plugin manager?

I can run it remotely in the terminal, but unfortunately all tools that use ollama as a backend seem to be unable to connect to it if OLLAMA_HOST is set

This is awesome stuff! Would like to know after this up can we connect this to Webui or Anythingllm?

Found a Gem 💎

How can I run this on my website or in a browser instead of terminal window

Thanks for the video. One question though, how can I avoid downloading the language models every time I run Colab notebook? Can I save Ollama and its models in Google drive and retrieve them when running the notebook?

canw e load 70B model with this same technque ?

This is awesome. Would look forward to watching how self hosting for N8N is done.

i got windows machine, do i need ollama locally tooo?

The A record you make for dev. Is that public or private ip does it matter?

Thanks for the great video! It helped me a lot!

very helpful

Thank you. I could run this succesfully in the terminal, but how can access the model or the collab through jupyter notebook instance?

awesome man

Hi bro, Can you please make clear or more details when exporting OLLAMA_HOST? Because when i export OLLAMA_HOST=…. ollama -h zsh: ollama - command is not found Do we need to do the following command line? ngrok http 11434 --host-header="localhost:11434" Please let me know. I am not clear about “export OLLAMA_HOST=…” and how to run ollama remote service in your local terminal at all Totally, your video is awesome. Thanks, bro.

Awesome ❤ Thanks

hey, how to the export step on windows? I have the ollama installed

Want some more GitHub Actions action? ruclips.net/video/0BNwAEwYZlA/видео.html

os.eviron.update({'LD_LIBRARY_PATH': "})'/usr Great for linux, what about windows machines?

Error: something went wrong, please see the ollama server logs for details am getting this error after running export OLLAMA_HOST= ... what should i do????

i got a 403 forbidden error, but replacing run_process(['ngrok', 'http', '--log', 'stderr', '11434']) with run_process(['ngrok', 'http', '--log', 'stderr', '11434', '--host-header="localhost:11434"']) fixed it for me.

but can't run stable diffusion this way?

Very usefull video also the code btw i can't get it running on windows what would be the way to set OLLAMA_HOST variable on window set OLLAMA_HOST= "--" doesn't seem to work it still runs on local machine

What did he do to open the vault at 3:45?

i get error like 403 forbidden

Can you give me some examples how to backup volumes that are managed in another docker-compose file? (And maybee how to create a weekly-backup AND a monthly-backup within the same configuration) Thanks a lot

Hi Marco, thanks for this video, definitely going to try out starship! Also, I was wondering what text editor/IDE you're using to view your .zshrc? Thank you!

Do you guys not get banned? I got a warning for using ngrok :/

Where did you store the .ipynb file so ollama could access it?

I imagine it's costly to run LLMs.. is there a limit on how much Google Colab will do for free? I'm interested in creating a Python application that uses AI.. from what I've read, I could use ChatGPT4 Assistant API and I as the developer would incur the cost whenever the app is used. Alternatively, I could host a model like Ollama, on my own computer or on the cloud (beam cloud/ Replicate/Streamlit/replit)? As a 3rd option, could Google Colab work in my situation? Is OpenAI's Assistant API totally different from the API to programmatically interact with llama2 , mistral , etc?

How can we keep our downloaded LLMs permanently, eg. on a mounted Google Drive? It would speed up the start of inference in a new ollama server start.

I have watched so much content on traefik and authelia and struggled so hard until now. Your two videos on the subject are so great. Thanks!

My issues is this error: time="2024-02-20T21:16:41Z" level=debug msg="No default certificate, fallback to the internal generated certificate" tlsStoreName=default time="2024-02-20T21:16:41Z" level=debug msg="Added outgoing tracing middleware noop@internal" middlewareName=tracing middlewareType=TracingForwarder entryPointName=web routerName=web-to-websecure@internal

I don't see pricing. Is it the same as support? And the license that will be given, can I use it on multiple devices such as my laptop and phones at the same time?

Great tutorial. Runs super fast compared to other methods. How would we ingest a document and query its contents? @techwithmarco

How did i reserve proxy outside in docker

Greate video . But i have problem how do i reserve proxy outside in docker

Nice video, short and on point

seems like you now have to pay for n8n, not sure when that change went through :(