community[minor]: Add support for modle2vec embeddings (#28507)

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>

libs/community/langchain_community/embeddings/__init__.py

@@ -145,6 +145,9 @@ if TYPE_CHECKING:
     from langchain_community.embeddings.mlflow_gateway import (
         MlflowAIGatewayEmbeddings,
     )
+    from langchain_community.embeddings.model2vec import (
+        Model2vecEmbeddings,
+    )
     from langchain_community.embeddings.modelscope_hub import (
         ModelScopeEmbeddings,
     )
@@ -289,6 +292,7 @@ __all__ = [
     "MlflowAIGatewayEmbeddings",
     "MlflowCohereEmbeddings",
     "MlflowEmbeddings",
+    "Model2vecEmbeddings",
     "ModelScopeEmbeddings",
     "MosaicMLInstructorEmbeddings",
     "NLPCloudEmbeddings",
@@ -372,6 +376,7 @@ _module_lookup = {
     "MlflowAIGatewayEmbeddings": "langchain_community.embeddings.mlflow_gateway",
     "MlflowCohereEmbeddings": "langchain_community.embeddings.mlflow",
     "MlflowEmbeddings": "langchain_community.embeddings.mlflow",
+    "Model2vecEmbeddings": "langchain_community.embeddings.model2vec",
     "ModelScopeEmbeddings": "langchain_community.embeddings.modelscope_hub",
     "MosaicMLInstructorEmbeddings": "langchain_community.embeddings.mosaicml",
     "NLPCloudEmbeddings": "langchain_community.embeddings.nlpcloud",

libs/community/langchain_community/embeddings/model2vec.py

@@ -0,0 +1,66 @@
+"""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)

libs/community/tests/unit_tests/embeddings/test_imports.py

@@ -26,6 +26,7 @@ EXPECTED_ALL = [
     "MlflowAIGatewayEmbeddings",
     "MlflowEmbeddings",
     "MlflowCohereEmbeddings",
+    "Model2vecEmbeddings",
     "ModelScopeEmbeddings",
     "TensorflowHubEmbeddings",
     "SagemakerEndpointEmbeddings",

libs/community/tests/unit_tests/embeddings/test_model2vec.py

@@ -0,0 +1,11 @@
+from langchain_community.embeddings.model2vec import Model2vecEmbeddings
+
+
+def test_hugginggface_inferenceapi_embedding_documents_init() -> None:
+    """Test model2vec embeddings."""
+    try:
+        embedding = Model2vecEmbeddings("minishlab/potion-base-8M")
+        assert len(embedding.embed_query("hi")) == 256
+    except Exception:
+        # model2vec is not installed
+        assert True