Suggestion: Create n8n node for pgvecto.rs like Postgres PGVector Store

tensorchord / pgvecto.rs

Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. Revolutionize Vector Search, not Database.

Apache License 2.0

1.75k stars 71 forks source link

Open ebertti opened 1 month ago

ebertti commented 1 month ago

Hi, I have a suggestion.

I tried recommending the use of pgvector.rs in a project, but it didn’t integrate smoothly with n8n as a vector store for LLM workflows.

As a result, we reverted to using pgvector.

The main issue is that we don’t have control over the queries made by the "Postgres PGVector Store" node, as it uses a hardcoded vector.