Deep lake vector store

[adolkhan]

Background

DeepLake can be used as a new optional memory backend. It's a open-source software that can be easily installed with pip install deeplake

Changes

• existing function is not modified.
• add DeepLake as a new optional memory backend.
• part of document about memory backend is updated.

Documentation

New module and code is full documented.
A use guide about new feature is add to README.md.

Test Plan

• Auto-GPT works properly in DeepLake memory backend.
• Auto-GPT using local memory works properly too.

PR Quality Checklist

• My pull request is atomic and focuses on a single change.
• I have thoroughly tested my changes with multiple different prompts.
• I have considered potential risks and mitigations for my changes.
• I have documented my changes clearly and comprehensively.
• I have not snuck in any "extra" small tweaks changes

[github-actions]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[mikayelh]

hey @k-boikov, would you mind taking a look at this? Deep Lake is open source, AutoGPT would benefit from more open source vector stores/memory. :)

[p-i-]

This is a mass message from the AutoGPT core team.
Our apologies for the ongoing delay in processing PRs.
This is because we are re-architecting the AutoGPT core!

For more details (and for infor on joining our Discord), please refer to:
https://github.com/Significant-Gravitas/Auto-GPT/wiki/Architecting

[Pwuts]

This has been rendered incompatible by the ovehaul of the memory storage system (#4208). Further work on the memory system is tracked in #3536; once that's completed we'll start accepting contributions to support more memory stores again. For now, having only one backend to support allows us to develop and iterate more easily.

Thanks for submitting! I'll try to remember this one for when we're done with memory work.