Skip to content

Retrieval-Augmented Generation (RAG)

Retrieval-augmented generation beyond the demo: pgvector, chunking, ranking, and where RAG actually fits (and doesn't) inside an agent system.

1 post with the tag “rag”

Giving Agents Memory: An Async ETL Pipeline, Not a Vector Database

Conversation → extract → consolidate → store → inject: memory as a pipeline
- 20 min read - 4200 words
Oyinlola Olasunkanmi Raymond
Oyinlola Olasunkanmi Raymond
Creator of CodeBuddy

A customer tells your agent their budget on Monday. On Tuesday they come back through a different channel and it has forgotten. ‘Give it memory,’ everyone says, as if that means plugging in a vector database. It doesn’t. Memory is an extract-consolidate-store-inject pipeline that runs after the turn, and almost all the hard parts are policy, not storage. Here’s how we built one, grounded in the actual code.