71 lines
2.4 KiB
Python
71 lines
2.4 KiB
Python
# coding=utf-8
|
||
"""
|
||
@project: MaxKB
|
||
@Author:虎
|
||
@file: embedding.py
|
||
@date:2024/7/12 15:02
|
||
@desc:
|
||
"""
|
||
from typing import Dict, List
|
||
|
||
from langchain_community.embeddings import OllamaEmbeddings
|
||
|
||
from models_provider.base_model_provider import MaxKBBaseModel
|
||
|
||
|
||
class OllamaEmbedding(MaxKBBaseModel, OllamaEmbeddings):
|
||
model_resource_id: str | None = None
|
||
runtime_keep_alive: int = 300
|
||
batch_size: int = 10
|
||
|
||
@property
|
||
def _default_params(self):
|
||
return {**super()._default_params, 'keep_alive': self.runtime_keep_alive}
|
||
@staticmethod
|
||
def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
|
||
try:
|
||
batch_size = int(model_credential.get('batch_size') or 10)
|
||
except (TypeError, ValueError):
|
||
batch_size = 10
|
||
instance = OllamaEmbedding(
|
||
model=model_name,
|
||
base_url=model_credential.get('api_base'),
|
||
model_resource_id=str(model_kwargs['model_id']) if model_kwargs.get('model_id') else None,
|
||
)
|
||
instance.batch_size = batch_size
|
||
return instance
|
||
|
||
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
||
"""Embed documents using an Ollama deployed embedding model.
|
||
|
||
Args:
|
||
texts: The list of texts to embed.
|
||
|
||
Returns:
|
||
List of embeddings, one for each text.
|
||
"""
|
||
instruction_pairs = [f"{text}" for text in texts]
|
||
if not texts:
|
||
return []
|
||
from common.model_runtime_client import inference_lease
|
||
with inference_lease(self.model_resource_id) as state:
|
||
if state:
|
||
self.runtime_keep_alive = -1 if state['strategy'] == 'PRELOAD' else state['idle_seconds']
|
||
return self._embed(instruction_pairs)
|
||
|
||
def embed_query(self, text: str) -> List[float]:
|
||
"""Embed a query using a Ollama deployed embedding model.
|
||
|
||
Args:
|
||
text: The text to embed.
|
||
|
||
Returns:
|
||
Embeddings for the text.
|
||
"""
|
||
instruction_pair = f"{text}"
|
||
from common.model_runtime_client import inference_lease
|
||
with inference_lease(self.model_resource_id) as state:
|
||
if state:
|
||
self.runtime_keep_alive = -1 if state['strategy'] == 'PRELOAD' else state['idle_seconds']
|
||
return self._embed([instruction_pair])[0]
|