[Script request] Ollama

[damnsanga]

Application Name

Ollama

Website

https://github.com/ollama/ollama

Description

Ollama is an open-source tool that lets you run large language models (LLMs) locally on your computer. You can use Ollama to:
Run LLMs: Run LLMs like Llama 2 on your computer's CPU or GPU
Create models: Create and customize your own models
Integrate models: Integrate models into your own projects using programming languages like Python or JavaScript
Summarize text: Summarize key points from multiple sources, such as meeting notes
Draft documents: Draft emails, professional correspondence, and to-do lists
Set goals: Assist in personal goal setting and planning

Benefits of Ollama
Local control: Host models locally, so your data stays private and secure
Offline access: Run AI models locally without an internet connection
Cost savings: Avoid recurring costs related to cloud storage, data transfer, and usage fees
Customization: Tweak models according to specific project requirements

It would be great if a community script for Ollama could be developed.

It could also be helpful to integrate into the Script the optional installation of other tools, such as Open-webui during LXC setup and installation.

Due Diligence

• I have searched existing scripts and found no duplicates.
• I have searched existing discussions and found no duplicate requests.

[MickLesk]

ollama is already present and also available via openwebui.

Ollama as a single file is just not on the website.

bash -c "$(wget -qLO - https://github.com/community-scripts/ProxmoxVE/raw/main/ct/ollama.sh)"

[DAE51D]

I'd like to add that it would be great if this LXC script would set up to share/use GPUs like the Plex script does