Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: knowledge-graph
Ontology Shape vs Model Size: What a Graph's Design Costs an AI Agent
How three lossless shapes of one insurance knowledge graph changed accuracy, tool calls, tokens and cost for small and large models on Azure Cosmos DB.
30 min readGraphify, OKF and RAG: Which Context Layer Does Your Codebase Need
Benchmarks show Graphify ties vector RAG on accuracy. Here is how Graphify, Google's OKF and vector RAG fit together, with failure triggers and a decision matrix.
12 min readNeo4j and LangChain4j: GraphRAG Ingestors, Filtering and Chat Memory
Neo4j with LangChain4j for GraphRAG: schema discovery, LLM graph building, Cypher DSL, in-index filtering, parent-child retrieval and graph-backed chat memory.
18 min readContext Engineering for a Quant Research Agent: Proof Levels and Data Stores
Context engineering for a WorldQuant research agent: rules, observations and beliefs at separate proof levels, spread across a ledger, event store and graph.
12 min readRAG or Knowledge Graph? 2,160 Graded Answers and a Model Effect
RAG vs knowledge graph, measured: 2,160 graded answers across three model families and 120 questions. The winner flips by model, and the model matters most.
9 min readRAG-Anything on 65 Wine Books: Where Graph Retrieval Wins and Fails
A hands-on test of RAG-Anything's knowledge graph on 65 wine PDFs: parser choice, costs, graph versus vector answers, and the sparkling wine blind spot.
12 min readROE Versus TechRAG: GraphRAG on Docker and Qdrant or on SQLite and LanceDB
Two takes on one GraphRAG thesis: Qdrant, MongoDB and a 120B model against LanceDB, SQLite and qwen2.5 7B, with retrieval logic compared and lessons drawn.
7 min readFixing RAG With an Ontology and Knowledge Graph in Semiconductor Docs
Semiconductor EDA docs got an RDF/OWL ontology, a Neo4j knowledge graph and ontology-constrained retrieval, cutting RAG follow-up questions by 30 percent.
8 min readOpen Knowledge Format: Portable Memory for AI Coding Agents
The Open Knowledge Format stores what coding agents learn as linked markdown files. How it differs from CLAUDE.md and MCP, and how to start using it today.
11 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.