mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-29 15:28:54 +00:00
317a38b83e
This PR add an embeddings integration for model2vec, the `Model2vecEmbeddings` class. - **Description**: [Model2Vec](https://github.com/MinishLab/model2vec) lets you turn any sentence transformer into a really small static model and makes running the model faster. - **Issue**: - **Dependencies**: model2vec ([pypi](https://pypi.org/project/model2vec/)) - **Twitter handle:**: - [x] **Add tests and docs**: - [Test](https://github.com/blacksmithop/langchain/blob/model2vec_embeddings/libs/community/langchain_community/embeddings/model2vec.py), [docs](https://github.com/blacksmithop/langchain/blob/model2vec_embeddings/docs/docs/integrations/text_embedding/model2vec.ipynb) - [x] **Lint and test**: --------- Co-authored-by: Abhinav KM <abhinav.m@zerone-consulting.com> Co-authored-by: Bagatur <baskaryan@gmail.com>
67 lines
1.8 KiB
Python
67 lines
1.8 KiB
Python
"""Wrapper around model2vec embedding models."""
|
|
|
|
from typing import List
|
|
|
|
from langchain_core.embeddings import Embeddings
|
|
|
|
|
|
class Model2vecEmbeddings(Embeddings):
|
|
"""model2v embedding models.
|
|
|
|
Install model2vec first, run 'pip install -U model2vec'.
|
|
The github repository for model2vec is : https://github.com/MinishLab/model2vec
|
|
|
|
Example:
|
|
.. code-block:: python
|
|
|
|
from langchain_community.embeddings import Model2vecEmbeddings
|
|
|
|
embedding = Model2vecEmbeddings("minishlab/potion-base-8M")
|
|
embedding.embed_documents([
|
|
"It's dangerous to go alone!",
|
|
"It's a secret to everybody.",
|
|
])
|
|
embedding.embed_query(
|
|
"Take this with you."
|
|
)
|
|
"""
|
|
|
|
def __init__(self, model: str):
|
|
"""Initialize embeddings.
|
|
|
|
Args:
|
|
model: Model name.
|
|
"""
|
|
try:
|
|
from model2vec import StaticModel
|
|
except ImportError as e:
|
|
raise ImportError(
|
|
"Unable to import model2vec, please install with "
|
|
"`pip install -U model2vec`."
|
|
) from e
|
|
self._model = StaticModel.from_pretrained(model)
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""Embed documents using the model2vec embeddings model.
|
|
|
|
Args:
|
|
texts: The list of texts to embed.
|
|
|
|
Returns:
|
|
List of embeddings, one for each text.
|
|
"""
|
|
|
|
return self._model.encode_as_sequence(texts)
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""Embed a query using the model2vec embeddings model.
|
|
|
|
Args:
|
|
text: The text to embed.
|
|
|
|
Returns:
|
|
Embeddings for the text.
|
|
"""
|
|
|
|
return self._model.encode(text)
|