AutoGPT
AutoGPT copied to clipboard
Significant-Gravitas
Add aiohttp server
Background
Fixes #1222 See #1216
Changes
Added an aiohttp server that can be used to build alternative frontends and use cases for Auto-GPT.
Documentation
Test Plan
PR Quality Checklist
- [x] My pull request is atomic and focuses on a single change.
- [x] I have thoroughly tested my changes with multiple different prompts.
- [x] I have considered potential risks and mitigations for my changes.
- [x] I have documented my changes clearly and comprehensively.
- [x] I have not snuck in any "extra" small tweaks changes
Hi, Could you take a look at: https://github.com/Torantulino/Auto-GPT/pull/386?
This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.
@Pwuts Please do correct me if I'm wrong but it is my understanding that the plugin system is about AutoGPT calling into a backend extension, whereas this PR is about a frontend extension calling into AutoGPT via an API.
Coverage report
The coverage rate went from 31.23% to 31.23% :arrow_right:
The branch rate is 17%.
None of the new lines are part of the tested code. Therefore, there is no coverage data about them.
We're looking into it. Question for us is mainly whether this fits into our more long-term plan, which does involve an API but in a different architecture.
We're moving forwards async-ing the code with trio. We're also working on achieving 'stateless'. We should get these things in place before we consider implementing a webserver. @Androbin You're welcome to ping me on the AutoGPT Discord pi#8377
I love the idea and agree it's needed, but we need to make some changes for this to work. I'm going to go ahead and close this, for now, to help clear our backlog of PRs.
