ai-group-tabs icon indicating copy to clipboard operation
ai-group-tabs copied to clipboard

Organize and group your Chrome tabs with AI

Results 11 ai-group-tabs issues
Sort by recently updated
recently updated
newest added

大多数情况下同一个域名下的页面内容方向是相似的,得到的标签也应该是相同的 短时间内打开同一域名下的多个页面也是常见的事情 是不是可以将同一域名的所有页面作为一个整体来获取标签,来避免因为识别错误导致的标签页位置跳动

enhancement

enhancement
help wanted
good first issue

After a few test, i found that using the open source model like mistral 7B can also do this job well. By support these self-hosted model, users don't need to...

enhancement
need more discussion

I've pasted my OpenAI Key and Opened many different tabs. When I press button "Group Existing Tabs" the button shows throbber (loading icon) about 1 second and then nothing happens...

bug

## 动机 当前使用 ChatGPT 的实现存在诸多问题,典型的问题如下: - 可用性问题,由于众所周知的原因,OpenAI 的 API 可能在诸多国家和地区有可用性问题,甚至用户网络也极大地影响体验。 - 隐私性问题,浏览记录的重要性不言而喻,甚至很多 url 中包含了很多隐私数据,诸如密钥等,当前的解决方案中,可能无法保证用户的隐私问题,很多对隐私极端注重的用户可能因此会弃用。 - 高门槛问题,OpenAI 的 API KEY 对诸多用户来说依旧是一个较高的门槛,甚至在某些国家和地区,无法注册订阅等等,提供中心的服务又会带来服务器成本,Token 成本,隐私性问题等等。 综上所述,使用基于本地推理的实现变得很合理,能极大的提升体验,和用户群。 ## 挑战 基于本地推理计算的实现也存在一些挑战,例如,训练难度,成本,数据集等问题,本地推理带来的性能开销,以及做为一个浏览器插件本身的桎梏,我本人是一个客户端和后端开发者,对机器学习了解不深,做了简单地调研之后,可能 Bert 等是个可行的选择,欢迎继续讨论其他方案,仅做抛砖引玉。

enhancement
help wanted
need more discussion
refactor

This PR is a demo of how to integrate Transformer.js. Not ready to be merged yet as currently Transformer.js doesn't do a good job in classification.

enhancement
help wanted
need more discussion

比如,我打开了几个视频页面,但是都自己一组 ![image](https://github.com/MichaelYuhe/ai-group-tabs/assets/153572635/530b8e8e-01bb-433b-8207-cd29cddd0bdc) 我的设置,如图(模型用的GPT 3.5 turbo): ![image](https://github.com/MichaelYuhe/ai-group-tabs/assets/153572635/badef929-fe1d-486f-b009-d21bd15bcd59)

bug

can use the site metadata to make the classification even better and also can give the user to customizee the prompt for a better and more flexible grouping.

enhancement
good first issue

- It is recommended to implement caching for request results, avoiding the need to send requests every time. This is particularly beneficial when dealing with a large number of tags,...

enhancement
help wanted
need more discussion