[Bug] groq的deepseek r1的思考过程渲染错误

[xingpingcn]

📦 部署环境

Docker

📌 软件版本

lastest

💻 系统环境

Windows

🌐 浏览器

Chrome

🐛 问题描述

📷 复现步骤

No response

🚦 期望结果

像deepseek官网一样显示思考时间，而且能够折叠思考过程

📝 补充信息

No response

[lobehubbot]

👀 @xingpingcn

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。

[lobehubbot]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

📦 deployment environment

Docker

📌 Software version

lastst

💻 System environment

Windows

🌐 browser

Chrome

🐛 Problem description

! [Image] (https://github.com/user-attachments/assets/f418ed47-7De9-4d11-B02D-2685CF22BC80))

📷 Reapped steps

NO Response

🚦 expectation result

Show thinking time like DeepSeek's official website, and can fold the process of thinking

📝 Supplementary information

_NO Response

[dosubot]

Hey there, @xingpingcn! I'm here to help you with any bugs, questions, or contributions. Let's work together to resolve your issue.

The issue you're experiencing with the "deepspeek-r1-distill-llama-70b" model in the lobe-chat framework is a known problem. Specifically, when using the DeepSeek-R1 model with Ollama deployment in Lobe Chat (versions v1.47.9 and v1.48.0), the <think></think> tags are not properly handled, leading to text truncation and display issues. This affects all self-deployed DeepSeek-R1 models ^[1].

To address this, you might want to check if there are any updates or patches available for the lobe-chat framework that resolve this issue. Additionally, reviewing the implementation in src/features/Conversation/Messages/Assistant/Reasoning/index.tsx might provide insights into how the thought process rendering is handled and if any adjustments can be made to improve the display ^[2].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}

[lobehubbot]

✅ @xingpingcn

This issue is closed, If you have any questions, you can comment and reply.
此问题已经关闭。如果您有任何问题，可以留言并回复。