src/embedder.py

from sentence_transformers import SentenceTransformer
from sklearn.preprocessing import normalize
from config.rag_config import RAGConfig

class Embedder:
    def __init__(self, config: RAGConfig):
        self.model = SentenceTransformer(config.embedding_model_name)
        self.normalize = config.normalize_embeddings

    def embed_texts(self, texts):
        embeddings = self.model.encode(texts, convert_to_numpy=True)
        if self.normalize:
            embeddings = normalize(embeddings)
        return embeddings