关于进行问答时多模态输入数据的处理问题 #1896
Answered
by
Jasonxia007
Rhapsody0x1
asked this question in
Q&A
-
问题当前的行为图片似乎被Nexent平台尝试调用一个多模态模型来进行解析,但尽管已经配置了多模态模型并验证连接性,仍然会出错。 期望的行为
环境与版本信息
相关的问题之前已经有人在Discussion的#1761 This allows llm to use tools to process user-uploaded images.中指出一种可行的处理方式。 |
Beta Was this translation helpful? Give feedback.
Answered by
Jasonxia007
Dec 1, 2025
Replies: 1 comment 1 reply
-
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment


Hi there! We have released this feature in v1.7.7. You can update Nexent and try it.