* move aoss to driver * add indexes * don't save vectors to neo4j with aoss * load embeddings from aoss * add group_id routing * add search filters and similarity search * neptune regression update * update neptune for regression purposes * update index creation with aliasing * regression tested * update version * edits * claude suggestions * cleanup * updates * add embedding dim env var * use cosine sim * updates * updates * remove unused imports * update
38 lines
1.1 KiB
Python
38 lines
1.1 KiB
Python
"""
|
|
Copyright 2024, Zep Software, Inc.
|
|
|
|
Licensed under the Apache License, Version 2.0 (the "License");
|
|
you may not use this file except in compliance with the License.
|
|
You may obtain a copy of the License at
|
|
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
Unless required by applicable law or agreed to in writing, software
|
|
distributed under the License is distributed on an "AS IS" BASIS,
|
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
See the License for the specific language governing permissions and
|
|
limitations under the License.
|
|
"""
|
|
|
|
import os
|
|
from abc import ABC, abstractmethod
|
|
from collections.abc import Iterable
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
EMBEDDING_DIM = int(os.getenv('EMBEDDING_DIM', 1024))
|
|
|
|
|
|
class EmbedderConfig(BaseModel):
|
|
embedding_dim: int = Field(default=EMBEDDING_DIM, frozen=True)
|
|
|
|
|
|
class EmbedderClient(ABC):
|
|
@abstractmethod
|
|
async def create(
|
|
self, input_data: str | list[str] | Iterable[int] | Iterable[Iterable[int]]
|
|
) -> list[float]:
|
|
pass
|
|
|
|
async def create_batch(self, input_data_list: list[str]) -> list[list[float]]:
|
|
raise NotImplementedError()
|