Create simple_embedding.py

simple_embedding.py

@@ -0,0 +1,37 @@
+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