Replies: 5 comments
-
|
很想试试做这个功能,不知道难度如何 |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
非常支持,用了半年cherry studio觉得最麻烦的就是这个了,得手动丢给OCR识别,有时候嫌麻烦甚至单独打开deepseek网页版用 |
Beta Was this translation helpful? Give feedback.
0 replies
-
现在有系统OCR支持。但是我没找到怎么用到非视觉模型的输入当中。 |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
我也非常需要这个,以支持许多国产的非多模态模型 |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
目前用cherry感到最不方便的就是这个了,别的都非常好 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
您的功能建议是否与某个问题相关?
否
请描述您希望实现的解决方案
参考deepseek官网,他们应该是有一个专门的OCR模型,可以提取图片和扫描版的文档的文字作为上下文发起提问

想要在默认模型中增加一个“视觉模型”,为无视觉能力的AI提供图片和文档对话的可能。
硅基流动有便宜的视觉模型,智谱也有免费的视觉模型,用来做ocr足够了。
请描述您考虑过的其他方案
No response
其他补充信息
No response
Beta Was this translation helpful? Give feedback.
All reactions