RRF

A developer built a hybrid RAG API that combines dense and sparse retrieval with reciprocal rank fusion (RRF) to answer questions from PDFs. The system uses Qdrant for vector storage, a cross-encoder …

A developer discovered that non-deterministic retrieval ordering in a RAG pipeline caused fluctuating Recall@8 scores, even with identical queries and models. The fix was adding a deterministic tie-br…

Mariana Souza describes a three-index Elasticsearch architecture for persistent LLM agent memory that achieves 0.89 recall without tenant leaks. The system separates episodic, semantic, and procedural…