Articles about RAG from the ConsultorIA blog: cloud, applied AI and security in production.
Most teams pick a vector store from a benchmark chart and then discover the thing that hurts is metadata filtering, tenancy or reindexing. If you already run PostgreSQL, pgvector is usually the right answer for longer than people expect.
Teams upgrade the generation model to fix a retrieval problem. The chunk boundaries, what context travels with each chunk, the embedding model and a reranker account for most of the quality gap.
Teams argue about which model to use and then ship an assistant that answers confidently from the wrong document. The decisions that actually decide quality are about chunks, permissions, evaluation and cost.
Knowledge Bases, Guardrails and Agents remove a lot of plumbing. They do not remove the retrieval, permission and evaluation decisions, and that is where projects still fail.
Vertex gives you a managed vector search, a grounding API and an evaluation service. Two of those are worth taking as-is. Here is how we assemble a production assistant on Google Cloud.
The model is the easy part. What decides whether an Azure OpenAI assistant reaches production is token quota per region, private networking and whether retrieval respects who is asking.