Infrastructure Updated 2026-04

Knowledge Graph

Definition

A Knowledge Graph organizes knowledge as a network of relationships between entities, enabling AI to reason over structured facts.

See also in the glossary

R
RAG (Retrieval-Augmented Generation)
RAG is a technique that connects an LLM to external data sources to generate more accurate and up-to-date answers.
E
Embedding
An embedding is a numerical representation (vector) of text or data, capturing its semantic meaning.
G
Grounding
Grounding connects LLM responses to factual data sources to reduce hallucinations and increase reliability.
L
LLM (Large Language Model)
An LLM is an AI model trained on billions of texts, capable of understanding and generating human language.

Tools that use knowledge graph

P
Perplexity
The AI answer engine that cites its sources
4.5/5
C
Consensus
The AI search engine for scientific literature
4.7/5
G
Gemini
Google's AI assistant with 1M token context
4.5/5
N
NotebookLM
Google's AI that turns your docs into an expert assistant
4.5/5

Frequently Asked Questions

Does Google use a Knowledge Graph?
Yes. The Google Knowledge Graph contains billions of structured facts. It powers the info panels in search results.
Knowledge Graph vs vector database?
Complementary. Vector database finds semantically similar content. Knowledge Graph stores factual relationships (Paris IS the capital OF France).