mirror of
https://github.com/langgenius/dify-official-plugins.git
synced 2026-07-21 17:45:23 -04:00
Cannot add LLM model and Text Embedding model simultaneously #159
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @aitting on GitHub (Mar 31, 2025).
Self Checks
Dify version
1.0.1
Cloud or Self Hosted
Self Hosted (Docker)
Steps to reproduce
When adding LLM model and Text Embedding model simultaneously under Ollama, only one can be successfully added. As long as one is successfully added, the other will be automatically invalidated。
✔️ Expected Behavior
No response
❌ Actual Behavior
No response
@dosubot[bot] commented on GitHub (Mar 31, 2025):
Hello, @aitting! I'm here to help you with any bugs, questions, or contributions you have for Dify. Let's tackle this issue together!
To address the issue of not being able to add both LLM and Text Embedding models simultaneously in a self-hosted Docker setup for Dify, consider the following steps:
Model Configuration: Ensure that each model type (LLM and Text Embedding) is configured correctly in separate submodules under the provider module. This involves creating distinct folders for each model type under the
/modelspath, as outlined in the Dify documentation [1].Model Management: Check if there are any conflicts in the model management settings. Dify uses a snapshot system for model configurations, which might cause issues if models are not properly enabled or disabled. Ensure that the models are not conflicting with each other in terms of configuration settings [2].
Ollama Configuration: Verify that the Ollama service is correctly set up and accessible. Ensure that the base URL and other settings are properly configured for both LLM and Text Embedding models. This includes setting the
OLLAMA_HOSTenvironment variable to0.0.0.0if needed, especially when using Docker [3].Logs and Errors: Check the logs for any error messages that might indicate why one model is invalidated when the other is added. This can provide insights into potential conflicts or misconfigurations.
Docker Network: Ensure that the Docker network settings allow for proper communication between the Dify platform and the Ollama service. This might involve checking network configurations and ensuring that the correct ports are open and accessible.
By following these steps, you should be able to troubleshoot and resolve the issue of adding both LLM and Text Embedding models simultaneously.
To continue talking to Dosu, mention @dosu.
Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other