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

Feature Request: Limit number of intereactions with GPT #36

Open
michael-milette opened this issue Dec 22, 2023 · 2 comments
Open

Feature Request: Limit number of intereactions with GPT #36

michael-milette opened this issue Dec 22, 2023 · 2 comments

Comments

@michael-milette
Copy link
Contributor

Hi @Limekiller ,

Would it be possible to add an optional setting to limit the number of interactions that a user can have with the GPT chatbot? Kind of like the way Bing Chat limits you to 30 questions.

The number of interactions should be configurable at a site level and also at an instance level with a maximum equal to the value set in the plugin's settings, if one is set. Once a user runs out of questions, they would be able to restart a new chat session but lose the context of the current conversation. An interaction counter should be displayed with each interaction.

The reason for this request is to try to curb abuse (and cost) associated with people using the chatbot for unrelated purposes and also to reduce the cost of resubmitting an ever-growing history.

Another option might be to limit its memory to X number of interactions and then drop the oldest one as the conversation goes on. I must confess that I have not thought this option through and suspect that loss of context might end up being confusing.

Let me know if you have any questions.

Best regards,

Michael

@binu-joy
Copy link

binu-joy commented Jun 20, 2024

Totally agree, @michael-milette. We definitely need this.

@sorydi3
Copy link

sorydi3 commented Nov 30, 2024

If you are using the open ai assistant the truncation (smart) of the context can be done very easy by setting one of the properties of the thread to auto , then everything get handled by the API. https://platform.openai.com/docs/assistants/deep-dive#truncation-strategy

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

3 participants