How to Create a Mock Text Embedding with Hash in Python

import hashlib
import numpy as np

def mock_embed(text: str, dim: int = 10, seed: int = 42) -> np.ndarray:
    """Generate a deterministic mock embedding using a hash function.
    
    Args:
        text: Input text to embed
        dim: Dimension of the output vector
        seed: Seed for reproducibility
    
    Returns:
        A normalized numpy array of shape (dim,)
    """
    # Generate a stable hash digest for the text
    digest = hashlib.sha256(text.encode("utf-8")).hexdigest()
    
    # Use the digest to seed a deterministic random generator
    rng = np.random.default_rng(int(digest[:16], 16) + seed)
    
    # Generate a random vector and normalize it
    vector = rng.random(dim)
    vector = vector / np.linalg.norm(vector)
    
    return vector

if __name__ == "__main__":
    text1 = "python programming"
    text2 = "python programming"
    text3 = "data science"
    
    emb1 = mock_embed(text1)
    emb2 = mock_embed(text2)
    emb3 = mock_embed(text3)
    
    print(f"Embedding for '{text1}':")
    print(emb1)
    print(f"\nEmbedding for '{text3}':")
    print(emb3)
    print(f"\nSame text similarity (cosine): {np.dot(emb1, emb2):.4f}")
    print(f"Different text similarity (cosine): {np.dot(emb1, emb3):.4f}")