Knowledge Graph

Full definition

Knowledge graphs encode the world as nodes (entities) and edges (relationships), often with rich attributes and provenance. Google's Knowledge Graph powers Search facts panels; enterprise knowledge graphs in pharma, banking, and supply chain encode regulated relationships. The 2024–2025 "GraphRAG" movement combines vector retrieval with knowledge-graph traversal to produce richer, more accurate LLM grounding than vector-only RAG.

Why it matters

Knowledge graphs are the structured counterpart to vector embeddings. Where vectors capture similarity, graphs capture relationships and provenance — what cures what, who reports to whom, which suppliers serve which products. For high-stakes enterprise AI, hybrid graph + vector retrieval often delivers materially better factuality than vector-only RAG.

Example

A pharma company combines a 50M-edge knowledge graph (drug-target-disease-trial relationships) with vector RAG over its internal research library. The combined system answers complex queries like "which Phase 3 trials targeting the same pathway as drug X failed for safety reasons?" — impossible with either system alone.

Next steps

• Get a free workflow map →We map one of your workflows and give you a written verdict: software, a process change or AI. No obligation.
• AI consulting cost guide →Hourly rates and project budgets by firm tier, from independents to the Big Four.

Related terms

• Retrieval-Augmented Generation (RAG)
  Retrieval-Augmented Generation (RAG) is a technique where a language model retrieves relevant documents from an external knowledge base before generating a response, which reduces hallucination and enables citation of sources.
• Embedding
  An embedding is a dense numerical vector — typically 384 to 4096 dimensions — that represents the semantic meaning of a piece of text, image, audio, or other content, so that semantically similar items end up near each other in vector space.
• Vector Database
  A vector database is a database optimized for storing and searching high-dimensional vectors (embeddings) by similarity rather than by exact match — the storage layer of every RAG and semantic-search system.
• Large Language Model (LLM)
  A Large Language Model (LLM) is a deep neural network — almost always a transformer — trained on hundreds of billions to trillions of words to predict the next token, and to generate, summarize, translate, or reason over text.
• AI Governance
  AI governance is the framework of policies, roles, controls, and processes an organization uses to ensure its AI systems are lawful, safe, fair, accountable, and aligned with business intent — across the full lifecycle from problem framing to retirement.

More deployment & operations terms

• Feature Store
  A feature store is a centralized data system that stores, versions, serves, and reuses curated machine-learning features — guaranteeing the same feature definitions are used at training time and at online inference time.
• Model Registry
  A model registry is a versioned catalog that tracks every trained ML model artifact, along with its metadata, training data lineage, evaluation metrics, approval status, and deployment stage (staging, production, archived).
• A/B Testing for ML
  A/B testing for ML is the practice of randomly splitting live traffic between a control model and a candidate model to measure the candidate's causal impact on real business metrics — revenue, conversion, retention, defect rate.