33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
"""Embedding provider wrapper for Milvus ingestion and retrieval."""
|
||
from __future__ import annotations
|
||
|
||
import logging
|
||
|
||
from config.settings import settings
|
||
from tool.llm import llm
|
||
|
||
|
||
logger = logging.getLogger("rag.embedding")
|
||
# 单一来源：.env 的 LLM_EMBED_DIMENSIONS；Milvus 建表、入库校验、embeddings 请求参数均以此为准
|
||
EMBEDDING_DIMENSION = settings.llm.embed_dimensions
|
||
|
||
|
||
class EmbeddingError(RuntimeError):
|
||
"""Raised when the embedding provider fails or returns invalid vectors."""
|
||
|
||
|
||
async def embed_texts(texts: list[str], *, client=None) -> list[list[float]]:
|
||
if not texts:
|
||
return []
|
||
provider = client or llm
|
||
try:
|
||
vectors = await provider.embed(texts)
|
||
except Exception as exc: # provider-specific exceptions are normalized here
|
||
logger.exception("embedding provider failed")
|
||
raise EmbeddingError("Embedding service unavailable") from exc
|
||
if len(vectors) != len(texts) or any(
|
||
len(vector) != EMBEDDING_DIMENSION for vector in vectors
|
||
):
|
||
raise EmbeddingError(f"Embedding dimension must be {EMBEDDING_DIMENSION}")
|
||
return vectors
|