I have deployed two embedding models locally. How do I switch between them on the diff page? I can’t select the embedding model on the page.

[smart-aiops]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit report (我已阅读并同意 Language Policy).
• Pleas do not modify this template :) and fill in all the required fields.

Provide a description of requested docs changes

I have deployed two embedding models locally. How do I switch between them on the diff page? I can’t select the embedding model on the page.

[dosubot]

To switch between two locally deployed embedding models on the diff page, ensure both models are correctly set up and integrated with LocalAI and Dify. Here's a streamlined approach to troubleshoot and enable model selection:

1. Check LocalAI Deployment: Confirm that LocalAI is correctly deployed with your models. This involves setting up LocalAI, downloading your models, configuring the .env file, and starting LocalAI with Docker.

2. Configure Models in Dify: Navigate to Settings > Model Providers > LocalAI in Dify and ensure your models are correctly configured there. You'll need to specify the Model Type as Embeddings, provide the Model Name, and the Server URL pointing to your LocalAI endpoint.

3. Verify Model List: Ensure the embeddingModelList in Dify includes your models. This list is crucial for the model selection process.

4. Utilize ModelSelector Component: The ModelSelector component should be used for model selection. It must be properly configured to display and allow selection from the embeddingModelList.

5. Ensure UI Accessibility: Make sure the UI component for model selection is accessible and its visibility can be toggled through the UI.

6. Save Selection: After selecting the model, ensure you save the selection to update the default model settings with the new configuration.

If the model selection option is still not visible, double-check the LocalAI and Dify setup, ensure the embeddingModelList is correctly populated, and there are no rendering issues or errors in the console. For detailed setup and troubleshooting, refer to the Dify and LocalAI documentation.

Details

Sources

• Possible Select preferred model or compare against each other in the same ChatUI
• web/app/components/header/account-setting/model-provider-page/system-model-selector/index.tsx
• en/tutorials/model-configuration/localai.md
• web/app/components/base/portal-to-follow-elem/index.tsx
• api/core/model_runtime/model_providers/xinference/text_embedding/text_embedding.py
• en/tutorials/model-configuration/README.md
• api/core/app/app_config/easy_ui_based_app/model_config/converter.py
• api/controllers/console/workspace/models.py

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.