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.

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, reducing hallucination by 30-60% and enabling 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.