david.koh·Nov 28, 2025Part 4: The Art of the Split — Perfecting RAG Context Quality with Chunking StrategiesHow semantic chunking and LLM token optimization transform scattered document fragments into meaningful, searchable knowledge units
InGoPenAIbydavid.koh·Oct 31, 2025Part 3: Beyond Semantics — Achieving Keyword Precision with Hybrid SearchCombining Dense and Sparse vectors in Qdrant to find exactly what users are searching for
InGoPenAIbydavid.koh·Oct 1, 2025Part 2: Mastering Qdrant — A Deep Dive into Vector Storage and Dense SearchA complete guide to building production-grade vector databases with Docker and metadata filtering
InGoPenAIbydavid.koh·Sep 19, 2025Part 1: The RAG Revolution — Building Your First Naive PipelineA step-by-step guide to creating a basic Retrieval-Augmented Generation system from scratch