Your question is Cosine Similarity for Embeddings. Start with the requirements on the right.
Run and submit as often as you like. When you're ready, talk me through your approach or go straight to the code.
Scotiabank may compare embedding vectors to rank semantically related content, such as matching a customer query with relevant Scotia mobile app help content. Implement cosine similarity for two high-dimensional vectors.
Given two equal-length lists of numbers, compute:
similarity = (A · B) / (||A|| × ||B||)
Return a floating-point value in the range [-1.0, 1.0]. If either vector has zero magnitude, return 0.0, because cosine similarity is undefined for a zero vector.
Implement cosine_similarity(a, b), where a and b are non-empty lists of integers or floating-point values with the same length. Return the cosine similarity as a float. Do not modify either input list.
def cosine_similarity(a, b):