Compute Quality Score • AI Agent SDK

compute_quality_score: Combine multiple sub-metrics into one final score, as an example.

compute_quality_score

Method

This is a method of the Memory class in the memory module.

Combine multiple sub-metrics into one final score, as an example.

Signature

def compute_quality_score(completeness: float, relevance: float, clarity: float, accuracy: float, weights: Dict[str, float]) -> float

Parameters

completeness · float · required

0-1

relevance · float · required

0-1

clarity · float · required

0-1

accuracy · float · required

0-1

weights · Dict

optional weighting like {“completeness”: 0.25, “relevance”: 0.3, …}

Returns

Returns · float

Weighted average 0-1

Source

View on GitHub

praisonaiagents/memory/memory.py at line 501