memory.search
Searches for memories using semantic similarity. Converts your query to an embedding and finds the most similar memories using cosine similarity.
Parameters
Natural language search query. Will be converted to an embedding for semantic matching.
Minimum similarity score (0-1) for results. Higher values = stricter matching.
0.9+: Very similar (almost exact matches)0.8-0.9: Highly relevant0.7-0.8: Relevant (default)0.6-0.7: Somewhat relevant<0.6: Loosely related
Response
Returns an array of memories with similarity scores:Examples
Semantic Search Examples
- Concept Matching
- Synonym Recognition
- Context Understanding
Tuning Search Results
Adjusting Threshold
Performance
- Latency: 10-50ms for typical datasets
- Scalability: Handles millions of memories efficiently
- Index: Uses pgvector IVFFlat for fast similarity search
Related Endpoints
Add Memory
Save new memories to search
Get All Memories
Retrieve all memories without search
How It Works
Learn about semantic search
Integration Guide
Use search in your app