​
Introduction

Cognee is a knowledge graph platform that transforms your raw data into intelligent, searchable memory. It combines the power of vector search (for semantic understanding) with graph databases (for relationship reasoning) to create a system that doesn’t just store information — it understands and connects it. What makes Cognee special:
  • Dual storage architecture that gives you both semantic search and structural reasoning
  • Building block approach where you compose Tasks, Pipelines, and DataPoints
  • Main operations that handle the complete workflow from ingestion to search
  • Advanced concepts for organizing and grounding your knowledge

​
Architecture overview

Cognee uses three complementary storage systems, each playing a different role:
  • Relational store — Tracks documents, chunks, and provenance (where data came from and how it’s linked)
  • Vector store — Holds embeddings for semantic similarity (numerical representations that find conceptually related content)
  • Graph store — Captures entities and relationships in a knowledge graph (nodes and edges that show connections between concepts)
This architecture makes your data both searchable (via vectors) and connected (via graphs). Cognee ships with lightweight defaults that run locally, and you can swap in production-ready backends when needed. For detailed information about the storage architecture, see Architecture.

​
Building blocks overview

Cognee’s processing system is built from three fundamental components:
  • DataPoints — Structured data units that become graph nodes, carrying both content and metadata for indexing
  • Tasks — Individual processing units that transform data, from text analysis to relationship extraction
  • Pipelines — Orchestration of Tasks into coordinated workflows, like assembly lines for data transformation
These building blocks work together to create a flexible system where you can:
  • Use built-in Tasks for common operations
  • Create custom Tasks for domain-specific logic
  • Compose Tasks into Pipelines that match your workflow
  • Process data incrementally to avoid redundant work

​
Main operations overview

Cognee provides three main operations that users interact with:
  • Add — Ingest and prepare data for processing, handling various file formats and data sources
  • Cognify — Create knowledge graphs from processed data through cognitive processing and entity extraction
  • Search — Query and retrieve information using semantic similarity, graph traversal, or hybrid approaches
These operations use the building blocks under the hood:
  • .add() creates a pipeline of ingestion Tasks
  • .cognify() runs a pipeline of processing Tasks
  • .search() leverages both vector and graph stores for comprehensive results

​
Further concepts overview

Beyond the core workflow, Cognee offers advanced features for sophisticated knowledge management:
  • Node Sets — Tagging and organization system that helps categorize and filter your knowledge base content
  • Ontologies — External knowledge grounding through RDF/XML ontologies that connect your data to established knowledge structures
These concepts extend Cognee’s capabilities for:
  • Organization — Managing growing knowledge bases with systematic tagging
  • Knowledge grounding — Connecting your data to external, validated knowledge sources
  • Domain expertise — Leveraging existing ontologies for specialized fields like medicine, finance, or research

​
Getting started

The best way to understand Cognee is to follow this learning path:
  1. Start here — Get the big picture and understand the system architecture
  2. Explore building blocks — Learn how DataPoints, Tasks, and Pipelines work together
  3. Try main operations — Use Add, Cognify, and Search to process your own data
  4. Extend with advanced concepts — Add organization with Node Sets and knowledge grounding with Ontologies
Each section builds on the previous one, giving you a complete understanding of how to build intelligent knowledge systems with Cognee.

Architecture

Understand Cognee’s three storage systems and how they work together

Building Blocks

Learn about DataPoints, Tasks, and Pipelines that power the system

Main Operations

Master Add, Cognify, and Search operations for your workflows