Skip to content

Conversation

@andy-k-improving
Copy link
Contributor

Description

Update existing documentation to reflect the appropriate ENV setting for Neptune and Neptune Analytics use-cases

Type of Change

  • Update memory_agent.py to include the configuration reference for Neptune and Neptune Analytics service

Motivation and Context

  • To make sure user aware of the the correct and up-to-date configuration for the respective service.

Areas Affected

  • memory_agent.py

Screenshots

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

Signed-off-by: Andy Kwok <andy.kwok@improving.com>
# Setup Neptune Analytics vector backend
# os.environ['NEPTUNE_ANALYTICS_GRAPH_IDENTIFIER_VECTOR'] = "g-sample-graph-id"
# Setup optional Neptune Analytics graph backend
# Setup optional Neptune Database graph backend
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

it is not clear here. Neptune database doesn't supoort vector backend?

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Neptune DB != Neptune Analytics.
Neptune DB does not support vectors, and can only be used as a graph backend.
Neptune Analytics does support vectors, and can be used as both graph and vector backend.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yep, I spent couple mins read docs but it has too long to follow all, if you could add related link it would be really helpful to users.

# Setup optional Neptune Analytics graph backend
# Setup optional Neptune Database graph backend
# os.environ['NEPTUNE_DATABASE_ENDPOINT'] = "your-neptune-host.us-west-2.neptune.amazonaws.com"
# Setup optional Neptune Analytics vector and graph backend
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Continue with above, Neptune Analytics supprots vector and graph backend? and below only configure graph right?
s.environ['NEPTUNE_ANALYTICS_GRAPH_IDENTIFIER'] = "g-sample-graph-id"

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Right. NEPTUNE_ANALYTICS_GRAPH_IDENTIFIER is used for both stores, one connection identifier.

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@andy-k-improving should we link to the mem0 docs here?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think so, example itself should be self-contained and information sufficient for users.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants