Spring AI Advisors: Practical RAG Without a Framework Religion
Advisors around ChatClient, QuestionAnswerAdvisor, and the retrieval details that matter: chunking, filters, and not stuffing the window.
Tag
7 articles · 26 min of reading
Advisors around ChatClient, QuestionAnswerAdvisor, and the retrieval details that matter: chunking, filters, and not stuffing the window.
Why pure vector search underperforms on keyword-heavy queries, and how to combine it with BM25 using score fusion that actually works.
Practical strategies for fitting long conversations and large documents into a context window without losing what actually matters.
The technical criteria that actually predict whether a vector database will hold up in production, beyond raw ANN benchmark numbers.
A practical framework for deciding whether your LLM problem needs prompting, retrieval, fine-tuning, or some combination of the three.
How to pick an embedding model for your retrieval stack using benchmarks that actually correlate with your data, not just MTEB leaderboard rank.
A field guide to the parts of retrieval-augmented generation that fail under real traffic, real documents, and real users.