feat: Add option for OpenWebui to use the context length of a currently loaded model in Ollama to keep the model from being reloaded.

[hainesk]

Check Existing Issues

• I have searched for all existing open AND closed issues and discussions for similar requests. I have found none that is comparable to my request.

Verify Feature Scope

• I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.

Problem Description

When using a model that is already loaded in Ollama, OpenWebUI sees that it's already loaded and highlights it green. However if the model was loaded with a non-standard context window, OpenWebui will apply the default context, causing the model to reload for a chat session, delaying the response. The model will then have to be reloaded again when used at the custom context length.

Desired Solution you'd like

An option in settings for chats without pre-defined context lengths to use the currently loaded model context length to keep the model from being reloaded. This will allow for immediate processing of requests for quick chats with pre-loaded models. This option won't apply to custom models created in the workspace with customized context lengths.

Alternatives Considered

No response

Additional Context

No response