simple_embedding.py

import numpy as np
import re
from collections import Counter
import math

class SimpleEmbedder:
    def __init__(self, vector_size=384):
        self.vector_size = vector_size
        self.word_vectors = {}
        
    def create_embedding(self, text: str) -> np.ndarray:
        """Create a simple embedding for text"""
        # Clean text
        text = text.lower()
        text = re.sub(r'[^a-z\\s]', ' ', text)
        words = text.split()
        
        if not words:
            return np.zeros(self.vector_size)
        
        # Create word frequency vector
        word_counts = Counter(words)
        
        # Create embedding
        embedding = np.zeros(self.vector_size)
        
        for word, count in word_counts.items():
            # Create deterministic hash-based position
            hash_val = hash(word) % self.vector_size
            embedding[hash_val] += count
        
        # Normalize
        norm = np.linalg.norm(embedding)
        if norm > 0:
            embedding = embedding / norm
        
        return embedding