Adding Async Vector Memory

[amartinson193]

Description

Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.

• Adding async capabilities to vector memory

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

• N/A

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

• N/A

Type of Change

Please delete options that are not relevant.

• New feature (non-breaking change which adds functionality)

How Has This Been Tested?

We are taking our forked llama index for basejump.ai and updating llama index with our changes to try to get back in sync. To test, I ran through our own test suite, which uses all of the changes. These changes are live in our production environment (minus some minor changes when resolving conflicts for the PR).

Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.

• I added new unit tests to cover this change
• I believe this change is already covered by existing unit tests

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added Google Colab support for the newly added notebooks.
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I ran make format; make lint to appease the lint gods

[logan-markewich]

Looks like this is breaking tests (the code now assumes that timestamp is in the chat message dict, when it isn't)

[amartinson193]

Looks like this is breaking tests (the code now assumes that timestamp is in the chat message dict, when it isn't)

Fixed it to use a .get() and a None instead

[amartinson193]

@logan-markewich Fixed all errors - need help looking @ 3.9, but doesn't seem apparent it was caused by changes I made

[logan-markewich]

we actually recently added more async methods to the base index class

I might open a separate PR to handle the index-specific methods like _ainsert()