Implement **mean pooling** to turn a sequence of token embeddings into a single fixed-size vector, a common step in embeddings-and-retrieval pipelines. Given token embeddings for one text, you’ll average each embedding dimension across tokens.

Mean pooling is defined as:
$$
\text{pooled}_j = \frac{1}{T}\sum_{i=1}^{T} E_{i,j}
$$
where $E$ is the token-embedding matrix with shape $(T, D)$.

## Requirements

Implement the function
```python
def mean_pool_embeddings(embeddings):
    \"""
    Computes mean pooling over token embeddings.

    Args:
        embeddings (np.ndarray): Token embeddings of shape (T, D),
            where T is number of tokens and D is embedding dimension.

    Returns:
        np.ndarray: A single pooled embedding of length D.
    \"""
    # Your solution below
```

**Rules:**
- Compute the element-wise mean across the token dimension (average over all tokens).
- Return a 1D NumPy array.
- Do not use any prebuilt pooling utilities (e.g., from PyTorch/TensorFlow).
- Use only NumPy and Python built-in libraries.
- Keep it a single function (no helper classes).

## Example

```python
embeddings = np.array([
    [1.0, 2.0, 3.0],
    [3.0, 2.0, 1.0],
    [2.0, 2.0, 2.0]
])

mean_pool_embeddings(embeddings)
```

Output:
```python
array([2.0, 2.0, 2.0])
```

Write Ahead Log

Mean Session Length

Mean pooling of embeddings

Solve this easy level ML coding question from General. The premier LeetCode for ML platform to master Python, SQL, and Machine Learning algorithms.

1426. Mean pooling of embeddings

Examples

Constraints

Similar Questions