Rag
Filed under
Pick a Vector Database by What Breaks First
Almost every RAG system should start on pgvector. The useful question is not which vector database is fastest, but which failure mode reaches you first.
One Door to the Models, Part 7: Azure AI Search or a Vector Database
Azure AI Search bills capacity by SKU, not by vectors, and the vector index is capped by tier memory. Part 7 decides retrieval on limits, not features.
Prompt Injection via Your Own Docs: The RAG Attack Surface
Your knowledge base is untrusted input. Retrieval hands attacker-authored text to the model, so the control that pays off is scanning at ingestion time.
The Context Window Is Not Your Friend
A huge context window is not a replacement for retrieval. Recall degrades as the prompt grows, cost scales with every token, and the middle gets skimmed.
Agentic RAG Is Mostly Latency You Don't Need
Agentic RAG loops through retrieval hops, each a model round trip. For most questions one good query wins. Reach for the loop only when it earns the latency.
Stop Fine-Tuning. You Need RAG, a Cache, and Better Prompts
Fine-tuning plus provisioned throughput is the expensive answer to most LLM problems. The cheaper path is retrieval, prompt caching, and better prompts.
Knowledge Base Chunking Is Where Your RAG Quality Dies
Most bad RAG answers are a retrieval problem, not a model problem. How fixed, semantic, and hierarchical chunking in Bedrock Knowledge Bases set your quality.