Ollama Web UI Tutorial- Alternate To ChatGPT With Open Source Models

[@shivampradhan3645]

there is no one who is able to capture the changing genai domain like you sir

[@gsignup0987]

One of the best channel on RUclips
Learn alot from you sir

[@rohulamin496]

your are so a great teacher keep continue uploading videos

[@mspicela]

Great video, I had not heard of it yet. Got it working. I had been looking for something just like this.

[@FranciscoMonteiro25]

open-webui has moved on such a lot since this video, functionality that can boost productivy much much more. time you did a new video with the new functionality, like function, prompts, RAG etc

[@jawwadhussain8457]

It's good but as new to this, we are missing a point where how to use this chatbot on website a live demonstration of linking this chatbot with website any WordPress etc etc could be helpful

[@rahulmanocha4533]

Hello sir, hows your membership works? Is there any group or something? As per yt membership tab its 3 months ago content, please let me know how i can access your latest live streaming projects?

[@Cine95]

Thanks brother but would love if you could cover modes who allow api cause not everyone is out here running 4000 grand worth of equipment

[@techiemedic]

Hi Krish I am having a laptop with Nvidia RTX3050 GPU but docker always gives me error saying gpu not found. can you show us how you've set up docker environment to get gpu cuda option?

[@TheScriptx]

How can integrate this with other applications so that this can build API?

[@SubinKrishnaKT]

When I open the web UI along with my local LLM Lllama 2, I can see GPT-4 and GPT-4o in the choose LLM dropdown. Do you know what is causing this?

[@Maisonier]

There is anyway to use FAISS with Pipelines in Open WebUI? liked and subscribed.

[@joekustek2623]

Existing models do not pull in like yours what did you do so your existing models are shown in webui?

[@muhammedyaseenkm9292]

Krish, can you give the complete tutorial on distributed computing

[@SRK-ub6fe]

I did all steps, localhost is opening. When I try to find the models from the list, its showing no models found. How to fix it now. ?

[@beyondbelief8458]

I think you need to download the models using command prompt. Correct me if I am wrong

[@inesoueslati6037]

have you any idea how to use functiog calling with open web-ui plzz?

[@mahanteshpattakal4445]

@Krish, I intend to use Ollama with my VS Code, so that it can help me code better, how can I achieve it using Ollama-Codellama model and VS Code?

[@shubhammaurya3671]

I was looking for same kind of solution. Can we collaborate on this to make some kind of npm library or extension for vscode?

[@rsraman123]

this is nice. how can i passthrough a colab GPU like I do for Ollama on cmd to use the colab GPU for the open webUI app as well?

[@samridhhfincoach4243]

Though the language models are open source and free but I think we need to pay for subscription for docker desktop. Can you please confirm. Please also make a video on the minimum configuration that is required for running these models effectively locally.

[@RishiRajxtrim]

🙏👍

[@AasherKamal]

What configurations are required to run this?

[@shivampradhan3645]

i ran on macbook m1 which has storage of 128gb and 8gb RAM,it is working.

[@hassanahmad1483]

is there any way to deploy these custom trained models?

[@lakshmikanth1988]

Hi How to download models in local host? like codeguru, code llamma..

[@TGajanan]

What is the accuracy of this model ?

[@chillakalyan]

😢Shows Impacts on Chat Gpt

[@A_k_h_i_l_007]

Is it possible on linux?

[@mohsinkhan-bw3cd]

Why u keep shaving from now on

[@krishnaik06]

Bhai there are much other thing to discuss...focus on ur learnings

[@mohsinkhan-bw3cd]

Sorry sir if i hurt you

[@AzarMohammad-gx6mz]

hloo sir