Source code for langchain_community.embeddings.modelscope_hub
from typing import Any, List, Optional
from langchain_core.embeddings import Embeddings
from langchain_core.pydantic_v1 import BaseModel, Extra
[docs]class ModelScopeEmbeddings(BaseModel, Embeddings):
"""模型范围嵌入模型。
要使用,您应该已安装``modelscope`` python包。
示例:
.. code-block:: python
from langchain_community.embeddings import ModelScopeEmbeddings
model_id = "damo/nlp_corom_sentence-embedding_english-base"
embed = ModelScopeEmbeddings(model_id=model_id, model_revision="v1.0.0")"""
embed: Any
model_id: str = "damo/nlp_corom_sentence-embedding_english-base"
"""要使用的模型名称。"""
model_revision: Optional[str] = None
def __init__(self, **kwargs: Any):
"""初始化模型范围"""
super().__init__(**kwargs)
try:
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
except ImportError as e:
raise ImportError(
"Could not import some python packages."
"Please install it with `pip install modelscope`."
) from e
self.embed = pipeline(
Tasks.sentence_embedding,
model=self.model_id,
model_revision=self.model_revision,
)
class Config:
"""此pydantic对象的配置。"""
extra = Extra.forbid
[docs] def embed_documents(self, texts: List[str]) -> List[List[float]]:
"""使用模型范围嵌入模型计算文档嵌入。
参数:
texts:要嵌入的文本列表。
返回:
每个文本的嵌入列表。
"""
texts = list(map(lambda x: x.replace("\n", " "), texts))
inputs = {"source_sentence": texts}
embeddings = self.embed(input=inputs)["text_embedding"]
return embeddings.tolist()
[docs] def embed_query(self, text: str) -> List[float]:
"""使用模型范围嵌入模型计算查询嵌入。
参数:
text:要嵌入的文本。
返回:
文本的嵌入。
"""
text = text.replace("\n", " ")
inputs = {"source_sentence": [text]}
embedding = self.embed(input=inputs)["text_embedding"][0]
return embedding.tolist()