Data structures representing knowledge as networks of entities and relationships, enabling reasoning, connection discovery, and semantic queries over complex domains.
A knowledge graph is a structure that represents information as a network of entities (nodes) connected by relationships (edges). Unlike a tabular database, a graph naturally captures connections between concepts, enabling discovery of implicit relationships and reasoning over complex domains.
This site uses a knowledge graph: each concept is a node, and relationships between concepts are edges forming a navigable network.
(Entity) --[Relationship]--> (Entity)
(Git) --[is base of]--> (GitHub)
(GitHub) --[has feature]--> (GitHub Actions)
(GitHub Actions) --[implements]--> (CI/CD)
The fundamental unit is the triple: subject → predicate → object.
(LLM) --[uses]--> (Transformer)
(RAG) --[reduces]--> (Hallucinations)
(MCP) --[standardizes]--> (Tool Use)
Combining knowledge graphs with RAG:
Using the graph as a source of truth to reduce hallucinations.
Finding non-obvious connections between concepts — exactly what this site's /graph page does.
| Tool | Type |
|---|---|
| Neo4j | Graph database |
| Amazon Neptune | Managed graph on AWS |
| NetworkX | Python graph library |
| D3.js / vis.js | Graph visualization |
Knowledge graphs represent information as entities and relationships, enabling the discovery of connections that are not evident in tabular data. They are the foundation of recommendation systems, semantic search, and knowledge bases like the one powering this site.
Information retrieval technique that uses vector embeddings to find results by meaning, not just exact keyword matching.
Field of computer science dedicated to creating systems capable of performing tasks that normally require human intelligence, from reasoning and perception to language generation.
Architecture design for scaling a personal second brain to a production system with AWS serverless — from the current prototype to specialized use cases in legal, research, and community building.
Chronicle of building a second brain with a knowledge graph, bilingual pipeline, and agent endpoints — in days, not weeks, and what that teaches about the gap between theory and working systems.
Production-ready serverless backend for a personal knowledge graph — DynamoDB, Lambda, Bedrock, MCP, Step Functions. The implementation of the architecture described in the 'From Prototype to Production' essay.