RAG → GraphRAG migrations, hybrid retrieval, security, and the patterns that ship when the vector DB stops being enough.
Plain vector RAG hits a ceiling around 100K documents. This is where graph-augmented retrieval becomes the right tool — and how to know if you need it.
Ordered by chapter. Each post stands alone but builds on the one before it.
Why filtering after RRF fusion loses the right chunks, and how a "drop trait → mode → grade" progressive relaxation ladder keeps narrow queries answerable without dropping retrieval quality.
A single retrieval surface over Slack, Confluence, Loom, and meeting transcripts — with cross-source ranking and source attribution that survives ingestion.
A startup-loaded domain vocabulary the generator must match against, plus framework rules baked into every prompt — a low-cost pattern that catches hallucinated terminology before the user sees it.