Retrieval Recall at k
~12 mincode completion
Implement recall_at_k(query, passages, relevant, k) returning recall@k as a float. relevant holds passage indices and is never empty.
Where this shows up
~12 min
••••••••••••••••
8 employers weight this skill
3 AI product companies, 2 frontier labs, 1 health and bio company, 1 big tech firm, 1 autonomy company. Top match scores 93.
Python
import numpy as np
def recall_at_k(query, passages, relevant, k):
"""
Recall@k of a dot-product retriever.
Args:
query: query embedding, shape (d,)
passages: passage embeddings, shape (n, d)
relevant: indices of the relevant passages (non-empty)
k: number of passages retrieved
Returns:
float: fraction of relevant passages found in the top k
"""
# YOUR CODE HERE
pass