Reinier van der Leer

Closing as stale

Status? :)

Since all third-party memory backends have been removed, this is no longer applicable. Still, thanks for submitting! At some point we will probably have Milvus integration again, and we'll try...

This is saving ~18MB overall.. just over 1% of the release image :')

Is this PR still relevant, now that OpenAI has announced deprecation/deprioritization of their traditional Completion models, in favor of ChatCompletion? https://openai.com/blog/gpt-4-api-general-availability#:~:text=As%20part%20of%20our%20increased%20investment,new%20models%20using%20the%20Completions%20API.

@Significant-Gravitas/benchmarkers this PR may be interesting for the challenge it proposes.

Seems this is already implemented in the form of agents, no?

@0xArty is working on that atm: https://github.com/0xArty/Auto-GPT/blob/async_agent/autogpt/agent/async_agent.py

Should be resolved by updating to Python 3.10. Older Python versions are not supported, at least for now. @primaryobjects that fix can be considered dangerous since it breaks workspace confinement...

@darrynv ~~please post a log when reporting an issue...~~ found it Can you provide some more info: platform/OS, Auto-GPT version, how you installed Python