| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| shell_gpt-1.4.0.tar.gz | 2024-02-22 | 38.9 kB | |
| shell_gpt-1.4.0-py3-none-any.whl | 2024-02-22 | 29.5 kB | |
| 1.4.0 source code.tar.gz | 2024-02-22 | 30.9 kB | |
| 1.4.0 source code.zip | 2024-02-22 | 47.1 kB | |
| README.md | 2024-02-22 | 706 Bytes | |
| Totals: 5 Items | 147.0 kB | 0 | |
What's Changed
- Added new option
—mdand—no-mdto disable or enable markdown output. - Added new config variable
PRETTIFY_MARKDOWNto disable or enable markdown output by default. - Added new config variable
USE_LITELLMto enforce usage of LiteLLM library.
OpenAI and LiteLLM
Because LiteLLM facilitates requests for numerous other LLM backends, it is heavy to import, adding 1-2 seconds of runtime. ShellGPT, by default will use OpenAI's library, which is suitable for most users. Optionally, ShellGPT can be installed with LiteLLM by running pip install shell-gpt[litellm]. To enforce LiteLLM usage set USE_LITELLM to true in the config file ~/.config/shell_gpt/.sgptrc.