app/infrastructure/external/embedder.py

"""
Infrastructure - Sentence Transformers Embedding Service
"""
from typing import List

from sentence_transformers import SentenceTransformer

from app.domain.interfaces import IEmbedder


class SentenceTransformerEmbedder(IEmbedder):
    """Sentence Transformers embedding implementation"""

    def __init__(self, model_name: str = "all-MiniLM-L6-v2"):
        self.model_name = model_name
        self.model = SentenceTransformer(model_name)
        self.dimension = self.model.get_sentence_embedding_dimension()

    async def embed_text(self, text: str) -> List[float]:
        """Generate embedding for single text"""
        embedding = self.model.encode(text, convert_to_numpy=True)
        return embedding.tolist()

    async def embed_texts(self, texts: List[str]) -> List[List[float]]:
        """Generate embeddings for multiple texts"""
        embeddings = self.model.encode(texts, convert_to_numpy=True, show_progress_bar=False)
        return embeddings.tolist()

    def get_dimension(self) -> int:
        """Get embedding dimension"""
        return self.dimension