Originally created by @Michelklingler on GitHub (Apr 8, 2024).
Originally assigned to: @tjbck on GitHub.
Is your feature request related to a problem? Please describe.
As an admin I would need to be able to easily change model name or setting of the LiteLLM backend through the interface. Everytime I need to do an adjustmnent, server address, model name, etc... I need to recreate a model from scratch.
Describe the solution you'd like
The possibility to pull and edit the LiteLLM model configuration via the WebUI
Originally created by @Michelklingler on GitHub (Apr 8, 2024).
Originally assigned to: @tjbck on GitHub.
**Is your feature request related to a problem? Please describe.**
As an admin I would need to be able to easily change model name or setting of the LiteLLM backend through the interface. Everytime I need to do an adjustmnent, server address, model name, etc... I need to recreate a model from scratch.
**Describe the solution you'd like**
The possibility to pull and edit the LiteLLM model configuration via the WebUI
Bundled LiteLLM support will be deprecated for our future releases, I'd recommend you start migrating your LiteLLM config.yaml to a self-hosted LiteLLM instance. You'd still be able to add them to our webui via OpenAI Connections.
@tjbck commented on GitHub (May 26, 2024):
Bundled LiteLLM support will be deprecated for our future releases, I'd recommend you start migrating your LiteLLM config.yaml to a self-hosted LiteLLM instance. You'd still be able to add them to our webui via OpenAI Connections.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @Michelklingler on GitHub (Apr 8, 2024).
Originally assigned to: @tjbck on GitHub.
Is your feature request related to a problem? Please describe.
As an admin I would need to be able to easily change model name or setting of the LiteLLM backend through the interface. Everytime I need to do an adjustmnent, server address, model name, etc... I need to recreate a model from scratch.
Describe the solution you'd like
The possibility to pull and edit the LiteLLM model configuration via the WebUI
@justinh-rahb commented on GitHub (Apr 15, 2024):
Agreed, this would remove a major friction point in using LiteLLM as it is currently.
@tjbck commented on GitHub (May 26, 2024):
Bundled LiteLLM support will be deprecated for our future releases, I'd recommend you start migrating your LiteLLM config.yaml to a self-hosted LiteLLM instance. You'd still be able to add them to our webui via OpenAI Connections.