> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Calculate Quality Metrics • AI Agent SDK

> calculate_quality_metrics: Calculate quality metrics using LLM

# calculate\_quality\_metrics

<div className="flex items-center gap-2">
  <Badge color="purple">Method</Badge>
</div>

> This is a method of the [**Memory**](../classes/Memory) class in the [**memory**](../modules/memory) module.

Calculate quality metrics using LLM

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def calculate_quality_metrics(output: str, expected_output: str, llm: Optional[str], custom_prompt: Optional[str]) -> Dict[str, float]
```

## Parameters

<ParamField query="output" type="str" required={true}>
  No description available.
</ParamField>

<ParamField query="expected_output" type="str" required={true}>
  No description available.
</ParamField>

<ParamField query="llm" type="Optional" required={false}>
  No description available.
</ParamField>

<ParamField query="custom_prompt" type="Optional" required={false}>
  No description available.
</ParamField>

### Returns

<ResponseField name="Returns" type="Dict[str, float]">
  The result of the operation.
</ResponseField>

## Uses

* `logger.info`
* `litellm.completion`
* `OpenAI`
* `create`
* `logger.error`
* `json.loads`
* `ValueError`

## Used By

* [`Task.execute_callback`](../functions/Task-execute_callback)

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/memory/memory.py#L1636">
  `praisonaiagents/memory/memory.py` at line 1636
</Card>