> ## 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.

# similarity • AI Agent SDK

> similarity: Calculate cosine similarity between two texts.

# similarity

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

> This is a method of the [**EmbeddingAgent**](../classes/EmbeddingAgent) class in the [**embedding\_agent**](../modules/embedding_agent) module.

Calculate cosine similarity between two texts.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def similarity(text1: str, text2: str, model: Optional[str]) -> float
```

## Parameters

<ParamField query="text1" type="str" required={true}>
  First text
</ParamField>

<ParamField query="text2" type="str" required={true}>
  Second text
</ParamField>

<ParamField query="model" type="Optional" required={false}>
  Override model for this call \*\*kwargs: Additional parameters
</ParamField>

### Returns

<ResponseField name="Returns" type="float">
  Cosine similarity score (0.0 to 1.0)
</ResponseField>

## Usage

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
agent = EmbeddingAgent()
    score = agent.similarity("Hello", "Hi there")
    print(f"Similarity: {score:.2f}")
```

## Uses

* `embed_batch`

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/agent/embedding_agent.py#L266">
  `praisonaiagents/agent/embedding_agent.py` at line 266
</Card>