PostgresDB connection Fails sporadically with Large knowledge section.

[joco25]

Describe the bug
When you have a larger knowledge section, Postgres Supabase connection timeout sporadically.

To Reproduce

• Create a characterfile
• Load the characterfiles knowledge section with 5 PDFs of large content extracted properly
• Add Postgres URL to env, "URL" can be gotten from NeonDB or Supabase (this will allow for the use of Postgres.
• Execute repo with new character file
• Wait a couple of hours for memory creation and embeddings

Expected behavior

• Embeddings are created successfully like they work when using SQLite (Even though it takes about 8hrs with SQLite)

Screenshots

Additional context
Snippets from error:
`⚠ WARNINGS Database operation failed (attempt 1/10): {"error":"Connection terminated unexpectedly","nextRetryIn":"5.6s"}

node:events:491 throw er; // Unhandled 'error' event ^

<ref *1> Error: read ECONNRESET at TLSWrap.onStreamRead (node:internal/stream_base_commons:216:20) Emitted 'error' event on BoundPool instance at: at Client.idleListener
...
{ errno: -54, code: 'ECONNRESET', syscall: 'read', client: Client { _events: [Object: null prototype] { error: [Function (anonymous)] }, _eventsCount: 1, _maxListeners: undefined, connectionParameters:
`

[github-actions]

Hello @joco25! Welcome to the ai16z community. Thank you for opening your first issue; we appreciate your contribution. You are now a ai16z contributor!

[AIFlowML]

The connection with the DB is dropped.
What DB is this Supabase ?

Please let me know i leave the bug open.

[joco25]

Yes, @AIFlowML it happens with Supabase.