Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support using a vector database for archival storage #142

Closed
sarahwooders opened this issue Oct 26, 2023 · 2 comments
Closed

Support using a vector database for archival storage #142

sarahwooders opened this issue Oct 26, 2023 · 2 comments
Assignees
@sarahwooders

Comments

@sarahwooders
Copy link
Collaborator

Archival and recall memory should be able to be backed up into a database, rather than in a local FAISS index.

MemGPT can support the following options for storing data:

  • Local FAISS index
  • Local vector DB
  • Remote vector DB
@lightningorb
Copy link

https://github.com/pgvector/pgvector-python/blob/master/examples/openai_embeddings.py

@sarahwooders sarahwooders self-assigned this Oct 30, 2023
@sarahwooders
Copy link
Collaborator Author

It looks like Llama Index has a nice example with Postgres, so we can add a PostgresArchivalMemory(ArchivalMemory) that uses this once #154 is merged.

@sarahwooders sarahwooders mentioned this issue Nov 1, 2023
Merged
4 tasks
@cpacker cpacker closed this as completed Dec 1, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@sarahwooders sarahwooders

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@cpacker @sarahwooders @lightningorb