resolutionflow/backend/app/services/embedding_service.py

"""Embedding provider abstraction for RAG.

Uses Voyage AI (voyage-3.5, 1024 dims) as the embedding provider.
Supports document and query input types for asymmetric search.
"""
import logging
from typing import Optional

from app.core.config import settings

logger = logging.getLogger(__name__)


async def get_embedding(
    text: str,
    input_type: str = "document",
) -> Optional[list[float]]:
    """Get embedding vector for text using Voyage AI.

    Args:
        text: The text to embed.
        input_type: "document" for indexing, "query" for search queries.

    Returns:
        List of floats (1024 dims) or None if embedding service unavailable.
    """
    if not settings.VOYAGE_API_KEY:
        logger.warning("VOYAGE_API_KEY not set — embedding service unavailable")
        return None

    try:
        import voyageai

        client = voyageai.AsyncClient(api_key=settings.VOYAGE_API_KEY)
        result = await client.embed(
            texts=[text],
            model=settings.EMBEDDING_MODEL,
            input_type=input_type,
        )
        return result.embeddings[0]
    except Exception as e:
        logger.error("Embedding failed: %s", e)
        return None


async def get_embeddings_batch(
    texts: list[str],
    input_type: str = "document",
) -> Optional[list[list[float]]]:
    """Get embedding vectors for multiple texts in a single API call.

    Args:
        texts: List of texts to embed.
        input_type: "document" for indexing, "query" for search queries.

    Returns:
        List of embedding vectors or None if service unavailable.
    """
    if not texts:
        return []

    if not settings.VOYAGE_API_KEY:
        logger.warning("VOYAGE_API_KEY not set — embedding service unavailable")
        return None

    try:
        import voyageai

        client = voyageai.AsyncClient(api_key=settings.VOYAGE_API_KEY)
        result = await client.embed(
            texts=texts,
            model=settings.EMBEDDING_MODEL,
            input_type=input_type,
        )
        return result.embeddings
    except Exception as e:
        logger.error("Batch embedding failed: %s", e)
        return None