# maximal_marginal_relevance

> **Function** in `langchain_core`

📖 [View in docs](https://reference.langchain.com/python/langchain-core/vectorstores/utils/maximal_marginal_relevance)

Calculate maximal marginal relevance.

## Signature

```python
maximal_marginal_relevance(
    query_embedding: np.ndarray,
    embedding_list: list,
    lambda_mult: float = 0.5,
    k: int = 4,
) -> list[int]
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `query_embedding` | `np.ndarray` | Yes | The query embedding. |
| `embedding_list` | `list` | Yes | A list of embeddings. |
| `lambda_mult` | `float` | No | The lambda parameter for MMR. (default: `0.5`) |
| `k` | `int` | No | The number of embeddings to return. (default: `4`) |

## Returns

`list[int]`

A list of indices of the embeddings to return.

---

[View source on GitHub](https://github.com/langchain-ai/langchain/blob/fb6ab993a73180538f6cca876b3c85d46c08845f/libs/core/langchain_core/vectorstores/utils.py#L106)