NextChat
NextChat copied to clipboard
ChatGPTNextWeb
[Feature Request] Support streamWithThink for other models
🥰 Feature Description
Currently, only the deepseek-reasoner model supports streamWithThink. However, when we use a third-party DeepSeek API through the OpenAI interface, streamWithThink is disabled.
🧐 Proposed Solution
I have a naive idea but I'm not sure if it‘ll work: detect <think> in stream for all models and turn on "think" mode automatically.
📝 Additional Information
No response
Bot detected the issue body's language is not English, translate it automatically.
! [Image] (https://github.com/user-attachments/aSSETS/E037AB30-5F53-410d-b74b-a537ca019612)) Can you also support the thinking process of Google model? Thanks!
Bot detected the issue body's language is not English, translate it automatically.
related: https://github.com/ChatGPTNextWeb/NextChat/pull/6141
Bot detected the issue body's language is not English, translate it automatically.
Fixed format at https://github.com/ChatGPTNextWeb/NextChat/pull/6186
Bot detected the issue body's language is not English, translate it automatically.
Fixed format in #6186
Can it be made into a general solution? Now it looks like it only works for SiliconFlow.
在 #6186 修复了格式
可以做成一个通用的方案吗？现在看起来只对SiliconFlow生效。
因为只有openai原版api带有的的规范变成通用的自定义endpoint才比较合适，现在这个field是deepseek 特有的，所以不太好一口气全改（比如有些模型输出有可能是<think>）。现在的代码本身是通用的，每个模型实现自己的parseSSE函数。
Bot detected the issue body's language is not English, translate it automatically.
Fixed format in #6186
Can it be made into a general solution? Now it looks like it only works for SiliconFlow.
Because it is more appropriate to only the specifications included in the original openai API become general custom endpoints, this field is now unique to deepseek, so it is not easy to modify them all in one go (for example, some model output may be
在 #6186 修复了格式
可以做成一个通用的方案吗？现在看起来只对SiliconFlow生效。
因为只有openai原版api带有的的规范变成通用的自定义endpoint才比较合适，现在这个field是deepseek 特有的，所以不太好一口气全改（比如有些模型输出有可能是
<think>）。现在的代码本身是通用的，每个模型实现自己的parseSSE函数。
ENABLE_MCP这个环境变量的实现会统一这部分推理输出嘛？后续是否有计划会实现？
Bot detected the issue body's language is not English, translate it automatically.
Fixed format in #6186
Can it be made into a general solution? Now it looks like it only works for SiliconFlow.
Because it is more appropriate to only if the specifications included in the original openai API become general custom endpoints, this field is now unique to deepseek, so it is not easy to modify them all in one go (for example, some model output may be
<think>). The code now is general in itself, and each model implements its own parseSSE function.
Will the implementation of the environment variable ENABLE_MCP unify this part of the inference output? Are there any plans to come true?
在 #6186 修复了格式
可以做成一个通用的方案吗？现在看起来只对SiliconFlow生效。
因为只有openai原版api带有的的规范变成通用的自定义endpoint才比较合适，现在这个field是deepseek 特有的，所以不太好一口气全改（比如有些模型输出有可能是
<think>）。现在的代码本身是通用的，每个模型实现自己的parseSSE函数。ENABLE_MCP这个环境变量的实现会统一这部分推理输出嘛？后续是否有计划会实现？
我现在在我的fork实现成渲染两个markdown，生成引用还是太麻烦了
Bot detected the issue body's language is not English, translate it automatically.
Fixed format in #6186
Can it be made into a general solution? Now it looks like it only works for SiliconFlow.
Because it is more appropriate to only become a general custom endpoint for the specifications included in the openai original API, this field is unique to deepseek, so it is not easy to modify it in one go (for example, some model output may be
<think>). The code now is general in itself, and each model implements its own parseSSE function.Will the implementation of the environment variable ENABLE_MCP unify this part of the inference output? Are there any plans to come true?
I'm now implementing two markdowns in my fork, generating references is still too troublesome