giovannino/oterm
1
0
Fork 0
mirror of https://github.com/ggozad/oterm.git synced 2026-11-02 19:31:25 +01:00
Code Issues Projects Releases Packages Wiki Activity
the terminal client for LLMs
45 commits 3 branches 104 tags 42 MiB
  • Python 99.7%
  • HTML 0.3%
Find a file
Exact
Yiorgis Gozadinos c4129c3be1 vb
2023-11-01 12:18:05 +01:00
oterm Only split on the first whitespace occurence when parsing parameters, allowing for whitespace containing parameters 2023-10-27 23:06:20 +02:00
screenshots vb 2023-10-18 15:31:35 +02:00
tests configure ruff 2023-10-17 18:01:44 +02:00
.gitignore Ignore dist/ 2023-10-15 23:16:58 +02:00
CHANGES.txt vb 2023-11-01 12:18:05 +01:00
LICENSE Readme, license 2023-10-15 19:53:05 +02:00
poetry.lock Upon clicking a message, copy to clipboard 2023-10-18 00:03:28 +02:00
pyproject.toml vb 2023-11-01 12:18:05 +01:00
README.md Document OLLAMA_URL, mention that users need to pull models. 2023-10-17 09:56:51 +02:00

README.md

oterm

the text-based terminal client for Ollama.

Features

  • intuitive and simple terminal UI, no need to run servers, frontends, just type oterm in your terminal.
  • multiple persistent chat sessions, stored together with the context embeddings in sqlite.
  • can use any of the models you have pulled in Ollama, or your own custom models.

Installation

Using brew for MacOS:

brew tap ggozad/formulas
brew install ggozad/formulas/oterm

Using pip:

pip install oterm

Using

In order to use oterm you will need to have the Ollama server running. By default it expects to find the Ollama API running on http://localhost:11434/api. If you are running Ollama inside docker or on a different host/port, use the OLLAMA_URL environment variable to customize the API url.

OLLAMA_URL=http://host:port/api

oterm will not (yet) pull models for you, please use ollama to do that. All the models you have pulled or created will be available to oterm.

Screenshots

Chat Model selection

License

This project is licensed under the MIT License.