Entity Extraction

CortexDB automatically extracts entities and relationships from ingested episodes. Extraction runs asynchronously -- it does not block the write path.

What Gets Extracted

• Named entities: People, organizations, technologies, services, projects, features
• Relationships: How entities relate (owns, uses, depends_on, caused, etc.)
• Entity types: Categorization into predefined and discovered types
• Aliases: Different names for the same entity are resolved (e.g., "Bob", "[email protected]", "Robert")

Configuration

Control entity extraction through environment variables:

| Variable | Default | Description | |---|---|---| | CORTEX_EXTRACTION_ENABLED | true | Enable/disable extraction |

See the self-hosted configuration guide for additional extraction settings.

Extraction Quality

For best results, provide well-structured episode content with clear entity mentions. CortexDB uses LLM-based extraction to identify entities and relationships from natural language.