A simple CLI command for troubleshooting errors with LLMs
Documentation: https://di3go-sona.github.io/tshoot/
Source Code: https://github.com/di3go-sona/tshoot
The idea of tshoot is quite simple, by running the command tshoot
you'll open a chat session with one of OpenAI's LLMs, you can dialogue with it and at the same time run commands by prefixing the line with !
, the command will be executed on your local machine and the output will be displayed in the chat and added to the conversation history.
The main idea is to have a quick way to have your troubleshooting workflow overseen by an AI, potentially retrieving the information you need to solve your problem without any context switch, directly in your terminal.
The philosophy behind this project is to create a tool that should have minimal dependencies and should be easy to install and ready to use.
You can install tshoot with pip:
pip install tshoot
The project is packaged and shipped with Hatch. The following scripts are installed in your virtual environment:
hatch run docs-build
hatch run docs-serve
hatch run lint
hatch run lint-check
hatch run test
hatch run test-cov-xml
You can run all the tests with:
hatch run test
Execute the following command to apply linting and check typing:
hatch run lint
You can serve the Mkdocs documentation with:
hatch run docs-serve
It'll automatically watch for changes in your code.
Every contribution that is in synch with the package philosofy is more than welcome, feel free to open an issue or submit a pull request.
This project is licensed under the terms of the MIT license.