# sparse_maximal_marginal_relevance

> **Function** in `langchain_pinecone`

📖 [View in docs](https://reference.langchain.com/python/langchain-pinecone/_utilities/sparse_maximal_marginal_relevance)

Calculate maximal marginal relevance for sparse vectors.

## Signature

```python
sparse_maximal_marginal_relevance(
    query_embedding: SparseValues,
    embedding_list: List[SparseValues],
    lambda_mult: float = 0.5,
    k: int = 4,
) -> List[int]
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `query_embedding` | `SparseValues` | Yes | A sparse vector representation of the query |
| `embedding_list` | `List[SparseValues]` | Yes | A list of sparse vector representations to compare against |
| `lambda_mult` | `float` | No | Controls the weight given to query similarity vs diversity (default: `0.5`) |
| `k` | `int` | No | The number of results to return (default: `4`) |

## Returns

`List[int]`

A list of indices of the selected items in order of relevance

---

[View source on GitHub](https://github.com/langchain-ai/langchain-pinecone/blob/199d069b8d2b8195605c333bc59684f65cfe0fc7/libs/pinecone/langchain_pinecone/_utilities.py#L87)