diff --git a/docs/faq.md b/docs/faq.md index 27face2b..5ff4c939 100644 --- a/docs/faq.md +++ b/docs/faq.md @@ -1,5 +1,5 @@ --- -sidebar_position: 6 +sidebar_position: 5 title: "📋 FAQ" --- diff --git a/docs/research.md b/docs/research.md index 830b6d39..304601d7 100644 --- a/docs/research.md +++ b/docs/research.md @@ -1,5 +1,5 @@ --- -sidebar_position: 7 +sidebar_position: 8 title: "🧑‍🔬 Open WebUI for Research" --- diff --git a/docs/tutorial/images.md b/docs/tutorial/images.md index 20a9cbd7..3f4fd3f9 100644 --- a/docs/tutorial/images.md +++ b/docs/tutorial/images.md @@ -1,3 +1,8 @@ +--- +sidebar_position: 3 +title: "Image Generation" +--- + # Image Generation Open WebUI now supports image generation through two backends: **AUTOMATIC1111** and **OpenAI DALL·E**. This guide will help you set up and use both options. diff --git a/docs/tutorial/litellm.md b/docs/tutorial/litellm.md index d34c7157..d535688e 100644 --- a/docs/tutorial/litellm.md +++ b/docs/tutorial/litellm.md @@ -1,3 +1,8 @@ +--- +sidebar_position: 4 +title: "LiteLLM Configuration" +--- + # LiteLLM Configuration [LiteLLM](https://litellm.vercel.app/docs/proxy/configs#quick-start) supports a variety of APIs, both OpenAI-compatible and others. To integrate a new API model, follow these instructions: diff --git a/docs/tutorial/whitelist.md b/docs/tutorial/whitelist.md new file mode 100644 index 00000000..02262729 --- /dev/null +++ b/docs/tutorial/whitelist.md @@ -0,0 +1,27 @@ +--- +sidebar_position: 5 +title: "Model Whitelisting" +--- + +# Model Whitelisting + +Open WebUI allows you to filter specific models for use in your instance. This feature is especially useful for administrators who want to control which models are available to users. Filtering can be done through the WebUI or by adding environment variables to the backend. + +## Filtering via WebUI + +![Model Filter Configuration](/img/tutorial_model_filter.png) + +1. Go to **Admin Panel > Admin Settings**. +2. In the **Manage Models** section, you can enable or disable the feature, and add or remove models from the whitelist. +3. Click **Save** to apply your changes. + +## Filtering via Environment Variables + +You can also whitelist models by adding environment variables to the backend. This method is useful for automated deployments and can be done by adding the following environment variables to your `docker run` command: + +```bash +-e MODEL_FILTER_ENABLED=True \ +-e MODEL_FILTER_LIST="llama2:13b;mistral:latest;gpt-3.5-turbo" \ +``` + +In this example, the `MODEL_FILTER_ENABLED` variable is set to `True` to enable the feature, and the `MODEL_FILTER_LIST` variable lists the models to be whitelisted. The format for the `MODEL_FILTER_LIST` variable is `model_name:version;model_name:version;...`. diff --git a/static/img/tutorial_model_filter.png b/static/img/tutorial_model_filter.png new file mode 100644 index 00000000..b8755837 Binary files /dev/null and b/static/img/tutorial_model_filter.png differ