Retrieve the **top‑k most similar embeddings** for a query embedding using cosine similarity, which is a common building block in embedding search. You’ll compute similarity scores and return the indices of the best matches.

Cosine similarity is:
$$
\text{cos\_sim}(q, x_i) = \frac{q \cdot x_i}{\|q\|\;\|x_i\|}
$$

## Requirements

Implement the function
```python
def top_k_cosine_retrieval(query, embeddings, k):
    \"""
    Finds the top-k most similar embeddings to a query using cosine similarity.

    Args:
        query (np.ndarray): Query embedding of length d.
        embeddings (np.ndarray): Database of embeddings of shape (n, d).
        k (int): Number of most similar embeddings to retrieve.

    Returns:
        list[int]: Indices of the top-k embeddings in descending similarity order.
    \"""
    # Your solution below
```

**Rules:**
- Compute cosine similarity between `query` and every row in `embeddings`.
- Return the **indices** of the top `k` most similar embeddings, sorted from most similar to least similar.
- Do not use any prebuilt nearest-neighbor/search libraries (e.g., FAISS, sklearn NearestNeighbors).
- Use NumPy for vectorized computation.
- If there are ties in similarity, break ties by smaller index first.

## Example

```python
query = [1.0, 0.0]
embeddings = [
    [1.0, 0.0],   # cos = 1.0
    [0.0, 1.0],   # cos = 0.0
    [0.5, 0.0],   # cos = 1.0
]
k = 2

top_k_cosine_retrieval(query, embeddings, k)
```

Output:
```python
[0, 2]
```

Cheapest Flights Within K Stops

Network AB Test Estimator

Top k embeddings retrieval

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

1394. Top k embeddings retrieval

Examples

Constraints

Similar Questions

Argument	Type
k	int
query	np.ndarray
embeddings	np.ndarray