Skip to content

This issue was moved to a discussion.

You can continue the conversation there. Go to discussion →

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

Specifications for how to integrate services in AI models #805

Closed
PengXing opened this issue Apr 6, 2023 · 1 comment
Closed

Specifications for how to integrate services in AI models #805

PengXing opened this issue Apr 6, 2023 · 1 comment

Comments

@PengXing
Copy link

PengXing commented Apr 6, 2023

Please join discussion.

Here is a repository I created for specs, for now it's empty. Discussion is welcome. https://github.com/openservices4ai/spec

What is an AI-integrated sevice

As AI models trained on a fixed set of data and cannot learn something new in real-time while serving, services integrated in AI models help provide real-time information and services. For example, a chatbot model may be integrated with a todo list service to help users add/remove todos, or create a timer.

Why an unified specification for AI-integrated services matters

First, it can help improve compatibility between different AI platforms, making it easier for developers to integrate various plugins into their AIs. This can save time and resources for developers who would otherwise have to manually modify each plugin to work with their chatbot.

Second, an unified specification can help ensure that services adhere to certain standards for functionality, security, and user privacy. This can help promote trust and confidence among users who interact with chatbots using these services.

Finally, it can also help promote innovation and collaboration among developers working on AI chatbots. By providing a common framework for plugin development, developers can more easily share their work and collaborate on new features and functionalities, ultimately leading to better and more sophisticated chatbots for users.

@BarfingLemurs
Copy link
Contributor

@ggml-org ggml-org locked and limited conversation to collaborators Apr 6, 2023
@prusnak prusnak converted this issue into discussion #810 Apr 6, 2023

This issue was moved to a discussion.

You can continue the conversation there. Go to discussion →

Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants