search

chatgpt-web-dev / chatgpt-web

A third-party ChatGPT Web UI page built with Express and Vue3, through the official OpenAI completion API. / 用 Express 和 Vue3 搭建的第三方 ChatGPT 前端页面, 基于 OpenAI 官方 completion API.
https://chatgpt-web.dev
MIT License
1.61k stars 439 forks source link

Feature request #337

Open Urmi10799 opened 1 year ago

Urmi10799 commented 1 year ago

Implement password reset for user. User can change their password from settings after login.

additionally, 2FA will be a cool feature...

Kerwin1202 commented 1 year ago

2 FA will not be considered, changing the password will be considered

Urmi10799 commented 10 months ago

@Kerwin1202 is it possible to make ROLE based or USER based or MODEL based rate-limiting system?

Kerwin1202 commented 10 months ago

@Kerwin1202 is it possible to make ROLE based or USER based or MODEL based rate-limiting system?

Is it similar to 10 times every 10 minutes? In what scenario is it needed?

Urmi10799 commented 10 months ago

@Kerwin1202 is it possible to make ROLE based or USER based or MODEL based rate-limiting system?

Is it similar to 10 times every 10 minutes? In what scenario is it needed?

For example, only 'Guest' role user can make 10 request per hour and 'Tester' can make 120 request per hour. rest of the role have default rate-limiting. Another example is: If user have 'Premium' role only that user can make 120 request per hour and rest of the user will have a default rate-limiting which could be 30 request per hour.

Like ChatGPT's GPT-4 have 25 message per three hour.

Kerwin1202 commented 10 months ago

@Kerwin1202 is it possible to make ROLE based or USER based or MODEL based rate-limiting system?

Is it similar to 10 times every 10 minutes? In what scenario is it needed?

For example, only 'Guest' role user can make 10 request per hour and 'Tester' can make 120 request per hour. rest of the role have default rate-limiting. Another example is: If user have 'Premium' role only that user can make 120 request per hour and rest of the user will have a default rate-limiting which could be 30 request per hour.

Like ChatGPT's GPT-4 have 25 message per three hour.

Will be considered