Doil Kim·Aug 17Beyond RAG: Why AI Systems Need a Semantic LayerWhy RAG alone isn’t enough — and how semantic layers can help AI understand relationships, metrics, and meaning across enterprise data.A response icon2A response icon2
Doil Kim·Jul 30Knowledge Graphs in the LLM Era: A Practical Guide to Semantic EngineeringHow knowledge graphs turn scattered records into connected, explainable, and continuously updated knowledgeA response icon1A response icon1
Doil Kim·Jul 25Ontology Made Practical: From RDF and OWL to Knowledge Graphs and GraphRAGHow ontology design principles improve data quality, enable semantic validation, and build trustworthy AI systems.
Doil Kim·Jul 18Building a Financial Knowledge Database for GraphRAG with ETF Data and Amazon RDSFrom Raw ETF Data to a Relational Knowledge Base for AI-Powered Financial Retrieval
Doil Kim·May 8From Writing About LLMs to Joining the Medium Partner Program — My Journey from South KoreaHow documenting my work in AI, vLLM, and RAG turned into a global writing opportunityA response icon1A response icon1
Doil Kim·Feb 11Stop Guessing What Your Embeddings Mean — Visualize Them with Embedding AtlasTurn high-dimensional vectors into interactive insight — in minutes, not hours
Doil Kim·Nov 25, 2025Fine-Tuning Qwen3-Embedding with SWIFT and Docker: A Complete, Practical GuideA practical end-to-end guide to fine-tuning Qwen3-Embedding using ModelScope SWIFT
Doil Kim·Nov 18, 2025Bringing SPLADE to vLLM: My First Open Source Contribution StoryHow I Added SPLADE Sparse Retrieval Support to vLLM — My First Open-Source Contribution
Doil Kim·Oct 20, 2025Deploying Qwen3-Reranker-8B with vLLM: Instruction-Aware Reranking for Next-Generation Retrieval…Harnessing vLLM and Qwen3-Reranker-8B to build faster, smarter, and instruction-aware AI retrieval systems for next-generation search
Doil Kim·Sep 2, 2025BM25 for Developers: A Guide to Smarter Keyword SearchHow Best Matching 25 Balances Term Frequency, Rarity, and Document Length in Modern Search Engines