From a38902cd6473b958406af6d634e5f1dd08916d65 Mon Sep 17 00:00:00 2001 From: DrMelone <27028174+Classic298@users.noreply.github.com> Date: Sun, 21 Dec 2025 17:53:41 +0100 Subject: [PATCH] fallback behaviour --- docs/features/workspace/models.md | 1 + docs/getting-started/env-configuration.mdx | 6 ++++++ 2 files changed, 7 insertions(+) diff --git a/docs/features/workspace/models.md b/docs/features/workspace/models.md index add8249e8..d8ba3a4f2 100644 --- a/docs/features/workspace/models.md +++ b/docs/features/workspace/models.md @@ -25,6 +25,7 @@ Both actions lead to the same Model Builder interface, where you can configure t - **Avatar Photo**: Upload a custom image to represent your model in the chat interface. - **Model Name & ID**: The display name and unique identifier for your custom preset (e.g., "Python Tutor" or "Meeting Summarizer"). - **Base Model**: The actual model beneath the hood that powers the agent. You can choose *any* model connected to Open WebUI. You can create a custom preset for `gpt-4o` just as easily as `llama3`. + - **Fallback Behavior**: If the configured Base Model is unavailable and the `ENABLE_CUSTOM_MODEL_FALLBACK` environment variable is set to `True`, the system will automatically fall back to the first configured default model (set in Admin Panel > Settings > Models > Default Models). This ensures mission-critical custom models remain functional even if their specific base model is removed or temporarily unavailable. - **Description**: A short summary of what the model does. - **Tags**: Add tags to organize models in the selector dropdown. - **Visibility & Groups**: diff --git a/docs/getting-started/env-configuration.mdx b/docs/getting-started/env-configuration.mdx index e62468105..2b1e5588a 100644 --- a/docs/getting-started/env-configuration.mdx +++ b/docs/getting-started/env-configuration.mdx @@ -206,6 +206,12 @@ If you are running larger instances, you WILL NEED to set this to a higher value ::: +#### `ENABLE_CUSTOM_MODEL_FALLBACK` + +- Type: `bool` +- Default: `False` +- Description: Controls whether custom models should fall back to a default model if their assigned base model is missing. When set to `True`, if a custom model's base model is not found, the system will use the first model from the configured `DEFAULT_MODELS` list instead of returning an error. + #### `MODELS_CACHE_TTL` - Type: `int`