app/services/embedding_service.py

from sentence_transformers import SentenceTransformer
import numpy as np

# Load a smaller model for demo (better for 2GB RAM)
# 'all-MiniLM-L6-v2' is ~90MB vs original 'all-MiniLM-L6-v2' which is ~400MB
model = SentenceTransformer('all-MiniLM-L6-v2')

def get_embedding(text: str) -> np.ndarray:
    # Truncate long text to prevent memory issues
    truncated_text = text[:1000]  # Limit to 1000 chars for demo
    return model.encode(truncated_text)