What are knowledge graphs?
Knowledge graphs represent information as interconnected triplets: Subject → Predicate → Object Examples:Sarah Chen→works_at→Acme CorpUser→prefers→Dark modeFastAPI→is_used_for→Building APIs
Retrieve triplets
Building knowledge graphs
Knowledge graphs are automatically built from your memories:Use cases
Build user profiles
Build user profiles
Create comprehensive user profiles from their interactions and preferences.
Map organizational knowledge
Map organizational knowledge
Build company knowledge graphs with people, teams, and technologies.
Connect research findings
Connect research findings
Link research papers, concepts, and discoveries.
Track product features
Track product features
Map product requirements, dependencies, and technologies.
Best practices
Use clear, factual statements
Use clear, factual statements
Write memories as clear subject-predicate-object statements.Good:
"Sarah Chen is the VP of Engineering at Acme Corp"Less good: "Sarah is pretty high up in engineering I think"Be specific with relationships
Be specific with relationships
Use precise language for relationships.Good:
"The API uses PostgreSQL for data storage"Less good: "We have PostgreSQL"Avoid ambiguity
Avoid ambiguity
Use full names and clear references.Good:
"John Smith manages the DevOps team"Less good: "John manages it" (ambiguous)Next steps
Memories
Add more memories to build graphs
Advanced usage
Advanced SDK features