Semantic Similarity (Text Embedding + Cosine Similarity)

Semantic Similarity (Embedding + Cosine Similarity) Given two texts text1 and text2, and an available encoder function encode(text) -> vector (think of a Sentence Encoder or any text embedding model), implement a function to compute the semantic similarity between the two texts as the cosine similarity of their embedding vectors: [ \text{sim}(a,b) = \frac{a \cdot b}{||a||_2 ||b||_2} ] Input Line 1: string text1 Line 2: string text2 Output Print one floating-point number: the cosine similarity. Constraints & Requirements encode(text) returns a real-valued vector of fixed dimension d (possibly large, e.g., 256/768). Handle zero-norm vectors: if ||a||==0 or ||b||==0, output 0.0. Print the result with 6 digits after the decimal point. Example (Only format is shown; actual value depends on encode.) Input: I love machine learning. I enjoy studying AI. Output: 0.823456 Note In interviews, pseudocode is acceptable if the encoder is assumed to exist; the key is the cosine similarity computation and edge cases. Example Input I love machine learning. I enjoy studying AI. Output 0.000000