Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Importing litellm is slow #482

Closed
EasternJournalist opened this issue Feb 17, 2024 · 1 comment · Fixed by #488
Closed

Importing litellm is slow #482

EasternJournalist opened this issue Feb 17, 2024 · 1 comment · Fixed by #488
Assignees
@TheR1D
Labels
enhancement New feature or request

Comments

@EasternJournalist
Copy link

Though litellm is convenient, it is heavy to import. As a result, every time exceuting sgpt involves a delay of 1~2 seconds even if the request is already cached. It might be a good idea to decide whether to import openai (by default, which is faster and suits most users) or litellm (when using customized models) in accordance to the configuration.
@TheR1D TheR1D added the enhancement New feature or request label Feb 20, 2024
@TheR1D TheR1D self-assigned this Feb 20, 2024
@TheR1D TheR1D linked a pull request Feb 21, 2024 that will close this issue
Use OpenAI by default, make LiteLLM optional #488
Merged
7 tasks
@TheR1D
Copy link
Owner

TheR1D commented Feb 22, 2024

Released in 1.4.0.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@TheR1D TheR1D

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Use OpenAI by default, make LiteLLM optional TheR1D/shell_gpt
2 participants
@TheR1D @EasternJournalist