Retrieval-Augmented Self-Recall — Part 2: Hybrid RAG on Nothing but Postgres

Part 2 of Retrieval-Augmented Self-Recall. Code: RE-call. Part 1: the self-recall problem.

Say "vector search" and the reflex is a dedicated vector database: Pinecone, Weaviate, Qdrant. I didn't install one. RE-call keeps the dense vectors, the full-text index, and the metadata you filter them by in a single Postgres.

Not as a shortcut, and not out of allergy to new infrastructure. Because for agent memory a separate vector store is the wrong shape, and it quietly costs you the one property this whole system depends on.

Here's the argument, and the retrieval pipeline it buys you.

Why not a dedicated vector DB

Retrieval-Augmented Self-Recall — Part 2: Hybrid RAG on Nothing but Postgres

Related reading

Retrieval-Augmented Self-Recall — Part 3: Teaching RAG to Say \"I Don't Know\

Retrieval-Augmented Self-Recall: The RAG Problem Nobody Talks About

RAG and Vector Search with pgvector and Amazon Bedrock (Part 4)

RAG Database Design: SQL, Full-Text Search, Vector Search, and Context Retrieval

Retrieval-Augmented Self-Recall — What the Comments Taught Me (RE-call v0.3)

From Manual RAG to Real Retrieval — Embedding-Based RAG with NVIDIA NIM