Arch Linux User Repository

Search Criteria

Enter search criteria

Search by

Keywords

Out of Date

Sort by

Sort order

Per page

Package Details: litellm-ollama 4-3

Package Actions

Git Clone URL:	https://aur.archlinux.org/litellm-ollama.git (read-only, click to copy)
Package Base:	litellm-ollama
Description:	Metapackage to setup ollama models with OpenAI API locally
Upstream URL:	None
Keywords:	ai llm local openai server
Licenses:	MIT
Submitter:	Sir-Photch
Maintainer:	None
Last Packager:	dnim
Votes:	2
Popularity:	0.144587
First Submitted:	2023-10-08 16:16 (UTC)
Last Updated:	2024-01-30 03:59 (UTC)

Dependencies (8)

gunicorn
litellm^AUR
ollama (ollama-rocm-git^AUR, ollama-cuda-git^AUR, ollama-generic-git^AUR, ollama-openmpi-git^AUR, ollama-openblas-git^AUR, ollama-vulkan-git^AUR, ollama-cuda)
python-apscheduler
python-backoff^AUR
python-fastapi
python-orjson (python-orjson-git^AUR)
uvicorn

Required by (0)

Sources (6)

Latest Comments

lumnn commented on 2024-01-18 15:45 (UTC)

Thank you for this package.

I believe port 8000 is quite popular and may conflict with many other software. In case anyone looks for easiest way to change ports then the best option would be to start/enable service and then

$ systemctl edit litellm-ollama@[model].service

And add there following content

[Service] Environment="PORT=--port='31000'"