Separate memory index for Pinecone, Redis and local cache memory backends

[Tymec]

Background

This change proposes to replace memory_index which is used in both Redis and LocalCache memory backends, with separate config options for each memory backend. This would make the code more flexible and configurable, as well as consistent with other memory backends.

Changes

• Create redis_index, local_cache_index and pinecone_index config options for each memory backend
• Remove memory_index config option
• Remove hardcoded table name in Pinecone and replace it with pinecone_index

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.
• [ ] I have documented my changes clearly and comprehensively.
• [x] I have not snuck in any "extra" small tweaks changes

[Tymec]

Since both Redis and Local memory types shared the same memory index, I assumed that's what was meant. Having each memory type have it's own memory index does sound like a better overall approach. Either way, I implemented the changes and now each memory type (except NoMemory) should have it's own index.

[nponeccop]

@Tymec There are conflicts now

[richbeales]

Run flake8 autogpt/ tests/ --select E303,W293,W291,W292,E305,E231,E302 autogpt/config/config.py:85:1: W293 blank line contains whitespace

[richbeales]

Conflicting files autogpt/config/config.py autogpt/memory/redismem.py

[github-actions[bot]]

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

[github-actions[bot]]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[github-actions[bot]]

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

[github-actions[bot]]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[github-actions[bot]]

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

[github-actions[bot]]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[codecov[bot]]

Codecov Report

Patch coverage: 33.33% and project coverage change: +0.36 :tada:

Comparison is base (4a20616) 41.66% compared to head (e927f48) 42.03%.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #1461      +/-   ##
==========================================
+ Coverage   41.66%   42.03%   +0.36%     
==========================================
  Files          65       65              
  Lines        3029     3031       +2     
  Branches      507      507              
==========================================
+ Hits         1262     1274      +12     
+ Misses       1702     1692      -10     
  Partials       65       65              

Impacted Files	Coverage Δ
autogpt/memory/pinecone.py	28.57% <0.00%> (ø)
autogpt/memory/redismem.py	29.23% <0.00%> (ø)
autogpt/config/config.py	75.16% <100.00%> (+0.32%)	:arrow_up:
autogpt/memory/local.py	95.91% <100.00%> (ø)

... and 1 file with indirect coverage changes

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.

[github-actions[bot]]

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

[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