diff --git a/langchain/embeddings/huggingface.py b/langchain/embeddings/huggingface.py
new file mode 100644
index 0000000000..cf59a300d4
--- /dev/null
+++ b/langchain/embeddings/huggingface.py
@@ -0,0 +1,66 @@
+"""Wrapper around HuggingFace embedding models."""
+from typing import Any, List
+
+from pydantic import BaseModel, Extra
+
+from langchain.embeddings.base import Embeddings
+
+
+class HuggingFaceEmbeddings(BaseModel, Embeddings):
+    """Wrapper around sentence_transformers embedding models.
+
+    To use, you should have the ``sentence_transformers`` python package installed.
+
+    Example:
+        .. code-block:: python
+
+            from langchain.embeddings import HuggingFaceEmbeddings
+            huggingface = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+    """
+
+    client: Any  #: :meta private:
+    model_name: str = "sentence-transformers/all-mpnet-base-v2"
+    """Model name to use."""
+
+    def __init__(self, **kwargs: Any):
+        super().__init__(**kwargs)
+        try:
+            import sentence_transformers
+
+            self.client = sentence_transformers.SentenceTransformer(self.model_name)
+        except ImportError:
+            raise ValueError(
+                "Could not import sentence_transformers python package. "
+                "Please install it with `pip install sentence_transformers`."
+            )
+
+    class Config:
+        """Configuration for this pydantic object."""
+
+        extra = Extra.forbid
+
+    def embed_documents(self, texts: List[str]) -> List[List[float]]:
+        """Computes doc embeddings using a HuggingFace transformer model
+
+        Args:
+            texts: The list of texts to embed.
+
+        Returns:
+            List of embeddings, one for each text.
+        """
+        texts = list(map(lambda x: x.replace("\n", " "), texts))
+        embeddings = self.client.encode(texts)
+        return embeddings
+
+    def embed_query(self, text: str) -> List[float]:
+        """Computes query embeddings using a HuggingFace transformer model
+
+        Args:
+            text: The text to embed.
+
+        Returns:
+            Embeddings for the text.
+        """
+        text = text.replace("\n", " ")
+        embedding = self.client.encode(text)
+        return embedding
diff --git a/requirements.txt b/requirements.txt
index 1dd1e8a215..c60ee0cd91 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -13,5 +13,6 @@ playwright
 wikipedia
 huggingface_hub
 faiss
+sentence_transformers
 # For development
 jupyter
diff --git a/tests/integration_tests/embeddings/test_huggingface.py b/tests/integration_tests/embeddings/test_huggingface.py
new file mode 100644
index 0000000000..5c031ee045
--- /dev/null
+++ b/tests/integration_tests/embeddings/test_huggingface.py
@@ -0,0 +1,19 @@
+"""Test huggingface embeddings."""
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+
+
+def test_huggingface_embedding_documents() -> None:
+    """Test huggingface embeddings."""
+    documents = ["foo bar"]
+    embedding = HuggingFaceEmbeddings()
+    output = embedding.embed_documents(documents)
+    assert len(output) == 1
+    assert len(output[0]) == 768
+
+
+def test_huggingface_embedding_query() -> None:
+    """Test huggingface embeddings."""
+    document = "foo bar"
+    embedding = HuggingFaceEmbeddings()
+    output = embedding.embed_query(document)
+    assert len(output) == 768