Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

改成了调用gemini pro 的api,效果不太好,没有成功实现演示中发邮件的示例 #28

Open
wstszx opened this issue Jan 8, 2024 · 4 comments

Comments

@wstszx
Copy link

wstszx commented Jan 8, 2024

No description provided.

@mnotgod96
Copy link
Owner

暂时还没有在Gemini上测过agent的能力。不过以我的经验来看Gmail发邮件的难点主要在于让模型填写收件人后点击下拉栏中的邮箱地址确认收件人这一步,如果模型生成的文档里没有关于这一步的说明的话,有很大概率会失败的。可以尝试手动优化一下ui文档或者一些别的邮箱app看看。

@wstszx
Copy link
Author

wstszx commented Jan 9, 2024

是的,就是卡在确认收件人这一步,导致标题输入框和内容输入框不能显示,最后它会把标题和内容都填入到收件人那一栏里

@zyxcambridge
Copy link

想将 Google 官方的 Gemini API 转换为标准的 OpenAI 调用

@gordonchanfz
Copy link

想将 Google 官方的 Gemini API 转换为标准的 OpenAI 调用

试了华为平板,调用gemini pro vision,learn的时候都好好的,run起来,空跑代码,界面交互看几率,点到的也未必是learn的东西。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants