RAG vectors

The vectors used for RAG (knowledge bases) and the document index are stored directly in HocNota's PostgreSQL database (pgvector extension), alongside the rest of the data — no separate service to configure. This means organization isolation applies to vectors exactly like to any other data: no organization can ever see or query another organization's vectors.

Admin → Vectors

• Collections — list of vector collections (one per knowledge base, plus temporary collections automatically created and deleted while a pipeline runs) with the vector count and last indexing date.
• Deletion — removes a collection individually. This only deletes the vectors; the knowledge base's documents remain in place and will need reindexing (see Task Management).
• Orphans — a button lets you purge, in one go, any collections that no longer correspond to an existing knowledge base.