Aug 15, 2025
RAG evaluation notes: recall@k vs latency
Benchmarking recall@k trade-offs against multilingual latency budgets.
RAGEvaluation
Read noteLab Notes
Short-form experiments, evaluation logs, and behind-the-scenes process.
Daniel Cárdenas
I build practical AI systems: RAG pipelines, voice and document automation, Python APIs, and the embedded telemetry that makes edge ML useful in the real world.
Short-form experiments, evaluation logs, and behind-the-scenes process.
Benchmarking recall@k trade-offs against multilingual latency budgets.