You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When running deepseek-r1:8b via Ollama, Lobe displays the <think> tag in text instead of prompting the deep thinking feature as it did when calling the official DeepSeek API. Additionally, there is a padding issue at the top of the message box when displaying the <think> tag, see it in the screenshot.
📷 Recurrence Steps
No response
🚦 Expected Behavior
No response
📝 Additional Information
No response
The text was updated successfully, but these errors were encountered:
Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事,并尽快回复您。 请确保您已经提供了尽可能多的背景信息。
The issue you're experiencing with the <think> tag not triggering the 'deep thinking' feature for the Ollama DeepSeek R1 model might be due to differences in how the feature is implemented or integrated for different AI providers. The <think> tag is rendered by the Render component in the src/features/Conversation/components/MarkdownElements/LobeThinking/Render.tsx file, which interacts with the chat interface to manage the display of the tag's content [1].
For the padding issue at the top of the message box, the padding is defined in the ActionBar component within the src/features/ChatInput/ActionBar/index.tsx file. You can adjust the padding by changing the value of the padding prop when using the ActionBar component [2].
To resolve the issue with the 'deep thinking' feature, you may need to check the integration logic for the Ollama DeepSeek R1 model and ensure it aligns with how the feature is triggered for the official DeepSeek API. This might involve reviewing the configuration files or settings that define how different AI models and their features are integrated into Lobe, which are located in the src/config/aiModels/index.ts file [3].
📦 Environment
Docker
📌 Version
v1.48.0
💻 Operating System
macOS
🌐 Browser
Chrome
🐛 Bug Description
When running deepseek-r1:8b via Ollama, Lobe displays the <think> tag in text instead of prompting the
deep thinking
feature as it did when calling the official DeepSeek API. Additionally, there is a padding issue at the top of the message box when displaying the <think> tag, see it in the screenshot.📷 Recurrence Steps
No response
🚦 Expected Behavior
No response
📝 Additional Information
No response
The text was updated successfully, but these errors were encountered: