mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-11 01:56:12 +00:00
d7c14cb6f9
Create a Class which allows to use the "text2vec" open source embedding
model.
It should install the model by running 'pip install -U text2vec'.
Example to call the model through LangChain:
from langchain_community.embeddings.text2vec import Text2vecEmbeddings
embedding = Text2vecEmbeddings()
bookend.embed_documents([
"This is a CoSENT(Cosine Sentence) model.",
"It maps sentences to a 768 dimensional dense vector space.",
])
bookend.embed_query(
"It can be used for text matching or semantic search."
)
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
79 lines
2.2 KiB
Python
79 lines
2.2 KiB
Python
"""Wrapper around text2vec embedding models."""
|
|
|
|
from typing import Any, List, Optional
|
|
|
|
from langchain_core.embeddings import Embeddings
|
|
from langchain_core.pydantic_v1 import BaseModel
|
|
|
|
|
|
class Text2vecEmbeddings(Embeddings, BaseModel):
|
|
"""text2vec embedding models.
|
|
|
|
Install text2vec first, run 'pip install -U text2vec'.
|
|
|
|
Example:
|
|
.. code-block:: python
|
|
|
|
from langchain_community.embeddings.text2vec import Text2vecEmbeddings
|
|
|
|
embedding = Text2vecEmbeddings()
|
|
bookend.embed_documents([
|
|
"This is a CoSENT(Cosine Sentence) model.",
|
|
"It maps sentences to a 768 dimensional dense vector space.",
|
|
])
|
|
bookend.embed_query(
|
|
"It can be used for text matching or semantic search."
|
|
)
|
|
"""
|
|
|
|
model_name_or_path: Optional[str] = None
|
|
encoder_type: Any = "MEAN"
|
|
max_seq_length: int = 256
|
|
device: Optional[str] = None
|
|
model: Any = None
|
|
|
|
def __init__(
|
|
self,
|
|
*,
|
|
model: Any = None,
|
|
model_name_or_path: Optional[str] = None,
|
|
**kwargs: Any,
|
|
):
|
|
try:
|
|
from text2vec import SentenceModel
|
|
except ImportError as e:
|
|
raise ImportError(
|
|
"Unable to import text2vec, please install with "
|
|
"`pip install -U text2vec`."
|
|
) from e
|
|
|
|
model_kwargs = {}
|
|
if model_name_or_path is not None:
|
|
model_kwargs["model_name_or_path"] = model_name_or_path
|
|
model = model or SentenceModel(**model_kwargs, **kwargs)
|
|
super().__init__(model=model, model_name_or_path=model_name_or_path, **kwargs)
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""Embed documents using the text2vec embeddings model.
|
|
|
|
Args:
|
|
texts: The list of texts to embed.
|
|
|
|
Returns:
|
|
List of embeddings, one for each text.
|
|
"""
|
|
|
|
return self.model.encode(texts)
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""Embed a query using the text2vec embeddings model.
|
|
|
|
Args:
|
|
text: The text to embed.
|
|
|
|
Returns:
|
|
Embeddings for the text.
|
|
"""
|
|
|
|
return self.model.encode(text)
|