curl --request POST \ --url http://localhost:8000/v1/memory/recall \ --header 'Content-Type: application/json' \ --data '{ "user_id": "alice", "app_id": "my_app", "workspace_id": "team_1", "query": "How should I format my answers?", "top_k": 5}'
{ "context": "alice prefers dark mode and short answers.", "paths": 2, "knowledge": []}
Memory
Recall memory context
Traverse the memory graph via BFS to find the most relevant context for a natural-language query. Returns a formatted string ready to inject into your LLM prompt.
POST
/
v1
/
memory
/
recall
Recall memory context
curl --request POST \ --url http://localhost:8000/v1/memory/recall \ --header 'Content-Type: application/json' \ --data '{ "user_id": "alice", "app_id": "my_app", "workspace_id": "team_1", "query": "How should I format my answers?", "top_k": 5}'
{ "context": "alice prefers dark mode and short answers.", "paths": 2, "knowledge": []}