From 24b26a922a03fd0352ae1e2cba814d7a8597a0e2 Mon Sep 17 00:00:00 2001
From: Leonid Ganeline <leo.gan.57@gmail.com>
Date: Thu, 20 Jul 2023 06:26:44 -0700
Subject: [PATCH] docstrings for `embeddings` (#7973)

Added/updated docstrings for the `embeddings`

@baskaryan
---
 langchain/embeddings/aleph_alpha.py              |  6 +++---
 langchain/embeddings/base.py                     |  5 ++---
 langchain/embeddings/bedrock.py                  |  4 ++--
 langchain/embeddings/clarifai.py                 | 12 ++++--------
 langchain/embeddings/cohere.py                   |  4 ++--
 langchain/embeddings/dashscope.py                |  6 +++---
 langchain/embeddings/deepinfra.py                |  2 +-
 langchain/embeddings/elasticsearch.py            |  3 +--
 langchain/embeddings/embaas.py                   |  3 +--
 langchain/embeddings/fake.py                     |  3 +++
 langchain/embeddings/google_palm.py              |  3 ++-
 langchain/embeddings/gpt4all.py                  |  5 ++---
 langchain/embeddings/huggingface.py              |  3 +--
 langchain/embeddings/huggingface_hub.py          |  5 ++---
 langchain/embeddings/jina.py                     |  4 ++--
 langchain/embeddings/llamacpp.py                 |  3 +--
 langchain/embeddings/minimax.py                  |  3 +--
 langchain/embeddings/mlflow_gateway.py           |  4 ++++
 langchain/embeddings/modelscope_hub.py           |  3 +--
 langchain/embeddings/mosaicml.py                 |  3 +--
 langchain/embeddings/nlpcloud.py                 |  3 +--
 langchain/embeddings/octoai_embeddings.py        |  4 +---
 langchain/embeddings/openai.py                   |  4 ++--
 langchain/embeddings/sagemaker_endpoint.py       |  5 ++---
 langchain/embeddings/self_hosted.py              |  3 +--
 langchain/embeddings/self_hosted_hugging_face.py |  5 ++---
 langchain/embeddings/sentence_transformer.py     |  2 +-
 langchain/embeddings/spacy_embeddings.py         |  4 ++--
 langchain/embeddings/tensorflow_hub.py           |  3 +--
 langchain/embeddings/vertexai.py                 |  3 ++-
 30 files changed, 54 insertions(+), 66 deletions(-)

diff --git a/langchain/embeddings/aleph_alpha.py b/langchain/embeddings/aleph_alpha.py
index e5e9664ee89..f53d509a9ca 100644
--- a/langchain/embeddings/aleph_alpha.py
+++ b/langchain/embeddings/aleph_alpha.py
@@ -7,8 +7,8 @@ from langchain.utils import get_from_dict_or_env
 
 
 class AlephAlphaAsymmetricSemanticEmbedding(BaseModel, Embeddings):
-    """
-    Wrapper for Aleph Alpha's Asymmetric Embeddings
+    """Aleph Alpha's asymmetric semantic embedding.
+
     AA provides you with an endpoint to embed a document and a query.
     The models were optimized to make the embeddings of documents and
     the query for a document as similar as possible.
@@ -30,7 +30,7 @@ class AlephAlphaAsymmetricSemanticEmbedding(BaseModel, Embeddings):
     """
 
     client: Any  #: :meta private:
-
+    """Aleph Alpha client."""
     model: Optional[str] = "luminous-base"
     """Model name to use."""
     hosting: Optional[str] = "https://api.aleph-alpha.com"
diff --git a/langchain/embeddings/base.py b/langchain/embeddings/base.py
index 6dd700c4e38..2cae8c14065 100644
--- a/langchain/embeddings/base.py
+++ b/langchain/embeddings/base.py
@@ -1,4 +1,3 @@
-"""Interface for embedding models."""
 from abc import ABC, abstractmethod
 from typing import List
 
@@ -15,9 +14,9 @@ class Embeddings(ABC):
         """Embed query text."""
 
     async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
-        """Embed search docs."""
+        """Asynchronous Embed search docs."""
         raise NotImplementedError
 
     async def aembed_query(self, text: str) -> List[float]:
-        """Embed query text."""
+        """Asynchronous Embed query text."""
         raise NotImplementedError
diff --git a/langchain/embeddings/bedrock.py b/langchain/embeddings/bedrock.py
index 35a7eab5cc5..ca1fae15dda 100644
--- a/langchain/embeddings/bedrock.py
+++ b/langchain/embeddings/bedrock.py
@@ -8,7 +8,7 @@ from langchain.embeddings.base import Embeddings
 
 
 class BedrockEmbeddings(BaseModel, Embeddings):
-    """Embeddings provider to invoke Bedrock embedding models.
+    """Bedrock embedding models.
 
     To authenticate, the AWS client uses the following methods to
     automatically load credentials:
@@ -39,7 +39,7 @@ class BedrockEmbeddings(BaseModel, Embeddings):
     """
 
     client: Any  #: :meta private:
-
+    """Bedrock client."""
     region_name: Optional[str] = None
     """The aws region e.g., `us-west-2`. Fallsback to AWS_DEFAULT_REGION env variable
     or region specified in ~/.aws/config in case it is not provided here.
diff --git a/langchain/embeddings/clarifai.py b/langchain/embeddings/clarifai.py
index 94bd30ef28d..6d97fc075ef 100644
--- a/langchain/embeddings/clarifai.py
+++ b/langchain/embeddings/clarifai.py
@@ -1,4 +1,3 @@
-"""Wrapper around Clarifai embedding models."""
 import logging
 from typing import Any, Dict, List, Optional
 
@@ -11,7 +10,7 @@ logger = logging.getLogger(__name__)
 
 
 class ClarifaiEmbeddings(BaseModel, Embeddings):
-    """Wrapper around Clarifai embedding models.
+    """Clarifai embedding models.
 
     To use, you should have the ``clarifai`` python package installed, and the
     environment variable ``CLARIFAI_PAT`` set with your personal access token or pass it
@@ -27,22 +26,19 @@ class ClarifaiEmbeddings(BaseModel, Embeddings):
     """
 
     stub: Any  #: :meta private:
+    """Clarifai stub."""
     userDataObject: Any
-
+    """Clarifai user data object."""
     model_id: Optional[str] = None
     """Model id to use."""
-
     model_version_id: Optional[str] = None
     """Model version id to use."""
-
     app_id: Optional[str] = None
     """Clarifai application id to use."""
-
     user_id: Optional[str] = None
     """Clarifai user id to use."""
-
     pat: Optional[str] = None
-
+    """Clarifai personal access token to use."""
     api_base: str = "https://api.clarifai.com"
 
     class Config:
diff --git a/langchain/embeddings/cohere.py b/langchain/embeddings/cohere.py
index e4fe18b247d..ba4b472635c 100644
--- a/langchain/embeddings/cohere.py
+++ b/langchain/embeddings/cohere.py
@@ -1,4 +1,3 @@
-"""Wrapper around Cohere embedding models."""
 from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel, Extra, root_validator
@@ -8,7 +7,7 @@ from langchain.utils import get_from_dict_or_env
 
 
 class CohereEmbeddings(BaseModel, Embeddings):
-    """Wrapper around Cohere embedding models.
+    """Cohere embedding models.
 
     To use, you should have the ``cohere`` python package installed, and the
     environment variable ``COHERE_API_KEY`` set with your API key or pass it
@@ -24,6 +23,7 @@ class CohereEmbeddings(BaseModel, Embeddings):
     """
 
     client: Any  #: :meta private:
+    """Cohere client."""
     model: str = "embed-english-v2.0"
     """Model name to use."""
 
diff --git a/langchain/embeddings/dashscope.py b/langchain/embeddings/dashscope.py
index 1db6dd1d536..475c7a5940a 100644
--- a/langchain/embeddings/dashscope.py
+++ b/langchain/embeddings/dashscope.py
@@ -1,4 +1,3 @@
-"""Wrapper around DashScope embedding models."""
 from __future__ import annotations
 
 import logging
@@ -65,7 +64,7 @@ def embed_with_retry(embeddings: DashScopeEmbeddings, **kwargs: Any) -> Any:
 
 
 class DashScopeEmbeddings(BaseModel, Embeddings):
-    """Wrapper around DashScope embedding models.
+    """DashScope embedding models.
 
     To use, you should have the ``dashscope`` python package installed, and the
     environment variable ``DASHSCOPE_API_KEY`` set with your API key or pass it
@@ -93,10 +92,11 @@ class DashScopeEmbeddings(BaseModel, Embeddings):
     """
 
     client: Any  #: :meta private:
+    """The DashScope client."""
     model: str = "text-embedding-v1"
     dashscope_api_key: Optional[str] = None
-    """Maximum number of retries to make when generating."""
     max_retries: int = 5
+    """Maximum number of retries to make when generating."""
 
     class Config:
         """Configuration for this pydantic object."""
diff --git a/langchain/embeddings/deepinfra.py b/langchain/embeddings/deepinfra.py
index 9c66dda0be7..2fb15ce1882 100644
--- a/langchain/embeddings/deepinfra.py
+++ b/langchain/embeddings/deepinfra.py
@@ -10,7 +10,7 @@ DEFAULT_MODEL_ID = "sentence-transformers/clip-ViT-B-32"
 
 
 class DeepInfraEmbeddings(BaseModel, Embeddings):
-    """Wrapper around Deep Infra's embedding inference service.
+    """Deep Infra's embedding inference service.
 
     To use, you should have the
     environment variable ``DEEPINFRA_API_TOKEN`` set with your API token, or pass
diff --git a/langchain/embeddings/elasticsearch.py b/langchain/embeddings/elasticsearch.py
index 7574a39b15d..d7da2df07e2 100644
--- a/langchain/embeddings/elasticsearch.py
+++ b/langchain/embeddings/elasticsearch.py
@@ -12,8 +12,7 @@ from langchain.embeddings.base import Embeddings
 
 
 class ElasticsearchEmbeddings(Embeddings):
-    """
-    Wrapper around Elasticsearch embedding models.
+    """Elasticsearch embedding models.
 
     This class provides an interface to generate embeddings using a model deployed
     in an Elasticsearch cluster. It requires an Elasticsearch connection object
diff --git a/langchain/embeddings/embaas.py b/langchain/embeddings/embaas.py
index e0a42e46d57..945861dc832 100644
--- a/langchain/embeddings/embaas.py
+++ b/langchain/embeddings/embaas.py
@@ -1,4 +1,3 @@
-"""Wrapper around embaas embeddings API."""
 from typing import Any, Dict, List, Mapping, Optional
 
 import requests
@@ -22,7 +21,7 @@ class EmbaasEmbeddingsPayload(TypedDict):
 
 
 class EmbaasEmbeddings(BaseModel, Embeddings):
-    """Wrapper around embaas's embedding service.
+    """Embaas's embedding service.
 
     To use, you should have the
     environment variable ``EMBAAS_API_KEY`` set with your API key, or pass
diff --git a/langchain/embeddings/fake.py b/langchain/embeddings/fake.py
index 9328f927e26..65bf7cfa21c 100644
--- a/langchain/embeddings/fake.py
+++ b/langchain/embeddings/fake.py
@@ -7,7 +7,10 @@ from langchain.embeddings.base import Embeddings
 
 
 class FakeEmbeddings(Embeddings, BaseModel):
+    """Fake embedding model."""
+
     size: int
+    """The size of the embedding vector."""
 
     def _get_embedding(self) -> List[float]:
         return list(np.random.normal(size=self.size))
diff --git a/langchain/embeddings/google_palm.py b/langchain/embeddings/google_palm.py
index 2818ec13091..8633ce7a945 100644
--- a/langchain/embeddings/google_palm.py
+++ b/langchain/embeddings/google_palm.py
@@ -1,4 +1,3 @@
-"""Wrapper around Google's PaLM Embeddings APIs."""
 from __future__ import annotations
 
 import logging
@@ -55,6 +54,8 @@ def embed_with_retry(
 
 
 class GooglePalmEmbeddings(BaseModel, Embeddings):
+    """Google's PaLM Embeddings APIs."""
+
     client: Any
     google_api_key: Optional[str]
     model_name: str = "models/embedding-gecko-001"
diff --git a/langchain/embeddings/gpt4all.py b/langchain/embeddings/gpt4all.py
index bf145316b12..0f109b8453c 100644
--- a/langchain/embeddings/gpt4all.py
+++ b/langchain/embeddings/gpt4all.py
@@ -1,4 +1,3 @@
-"""Wrapper around GPT4All embedding models."""
 from typing import Any, Dict, List
 
 from pydantic import BaseModel, root_validator
@@ -7,7 +6,7 @@ from langchain.embeddings.base import Embeddings
 
 
 class GPT4AllEmbeddings(BaseModel, Embeddings):
-    """Wrapper around GPT4All embedding models.
+    """GPT4All embedding models.
 
     To use, you should have the gpt4all python package installed
 
@@ -30,7 +29,7 @@ class GPT4AllEmbeddings(BaseModel, Embeddings):
 
             values["client"] = Embed4All()
         except ImportError:
-            raise ModuleNotFoundError(
+            raise ImportError(
                 "Could not import gpt4all library. "
                 "Please install the gpt4all library to "
                 "use this embedding model: pip install gpt4all"
diff --git a/langchain/embeddings/huggingface.py b/langchain/embeddings/huggingface.py
index 4420484febf..3531c5537fa 100644
--- a/langchain/embeddings/huggingface.py
+++ b/langchain/embeddings/huggingface.py
@@ -1,4 +1,3 @@
-"""Wrapper around HuggingFace embedding models."""
 from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel, Extra, Field
@@ -14,7 +13,7 @@ DEFAULT_QUERY_INSTRUCTION = (
 
 
 class HuggingFaceEmbeddings(BaseModel, Embeddings):
-    """Wrapper around sentence_transformers embedding models.
+    """HuggingFace sentence_transformers embedding models.
 
     To use, you should have the ``sentence_transformers`` python package installed.
 
diff --git a/langchain/embeddings/huggingface_hub.py b/langchain/embeddings/huggingface_hub.py
index 6273ac26051..0ca9985a154 100644
--- a/langchain/embeddings/huggingface_hub.py
+++ b/langchain/embeddings/huggingface_hub.py
@@ -1,4 +1,3 @@
-"""Wrapper around HuggingFace Hub embedding models."""
 from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel, Extra, root_validator
@@ -11,7 +10,7 @@ VALID_TASKS = ("feature-extraction",)
 
 
 class HuggingFaceHubEmbeddings(BaseModel, Embeddings):
-    """Wrapper around HuggingFaceHub embedding models.
+    """HuggingFaceHub embedding models.
 
     To use, you should have the ``huggingface_hub`` python package installed, and the
     environment variable ``HUGGINGFACEHUB_API_TOKEN`` set with your API token, or pass
@@ -71,7 +70,7 @@ class HuggingFaceHubEmbeddings(BaseModel, Embeddings):
                 )
             values["client"] = client
         except ImportError:
-            raise ValueError(
+            raise ImportError(
                 "Could not import huggingface_hub python package. "
                 "Please install it with `pip install huggingface_hub`."
             )
diff --git a/langchain/embeddings/jina.py b/langchain/embeddings/jina.py
index d980ee3a8ce..1931a9c4ee4 100644
--- a/langchain/embeddings/jina.py
+++ b/langchain/embeddings/jina.py
@@ -1,5 +1,3 @@
-"""Wrapper around Jina embedding models."""
-
 import os
 from typing import Any, Dict, List, Optional
 
@@ -11,6 +9,8 @@ from langchain.utils import get_from_dict_or_env
 
 
 class JinaEmbeddings(BaseModel, Embeddings):
+    """Jina embedding models."""
+
     client: Any  #: :meta private:
 
     model_name: str = "ViT-B-32::openai"
diff --git a/langchain/embeddings/llamacpp.py b/langchain/embeddings/llamacpp.py
index 0c11731e98d..5c31d53bf32 100644
--- a/langchain/embeddings/llamacpp.py
+++ b/langchain/embeddings/llamacpp.py
@@ -1,4 +1,3 @@
-"""Wrapper around llama.cpp embedding models."""
 from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel, Extra, Field, root_validator
@@ -7,7 +6,7 @@ from langchain.embeddings.base import Embeddings
 
 
 class LlamaCppEmbeddings(BaseModel, Embeddings):
-    """Wrapper around llama.cpp embedding models.
+    """llama.cpp embedding models.
 
     To use, you should have the llama-cpp-python library installed, and provide the
     path to the Llama model as a named parameter to the constructor.
diff --git a/langchain/embeddings/minimax.py b/langchain/embeddings/minimax.py
index c33ca0f2929..3ac9a7ef430 100644
--- a/langchain/embeddings/minimax.py
+++ b/langchain/embeddings/minimax.py
@@ -1,4 +1,3 @@
-"""Wrapper around MiniMax APIs."""
 from __future__ import annotations
 
 import logging
@@ -47,7 +46,7 @@ def embed_with_retry(embeddings: MiniMaxEmbeddings, *args: Any, **kwargs: Any) -
 
 
 class MiniMaxEmbeddings(BaseModel, Embeddings):
-    """Wrapper around MiniMax's embedding inference service.
+    """MiniMax's embedding service.
 
     To use, you should have the environment variable ``MINIMAX_GROUP_ID`` and
     ``MINIMAX_API_KEY`` set with your API token, or pass it as a named parameter to
diff --git a/langchain/embeddings/mlflow_gateway.py b/langchain/embeddings/mlflow_gateway.py
index e3a647f5ba2..349e848092a 100644
--- a/langchain/embeddings/mlflow_gateway.py
+++ b/langchain/embeddings/mlflow_gateway.py
@@ -13,8 +13,12 @@ def _chunk(texts: List[str], size: int) -> Iterator[List[str]]:
 
 
 class MlflowAIGatewayEmbeddings(Embeddings, BaseModel):
+    """MLflow AI Gateway Embeddings APIs."""
+
     route: str
+    """The route to use for the MLflow AI Gateway API."""
     gateway_uri: Optional[str] = None
+    """The URI for the MLflow AI Gateway API."""
 
     def __init__(self, **kwargs: Any):
         try:
diff --git a/langchain/embeddings/modelscope_hub.py b/langchain/embeddings/modelscope_hub.py
index 23c0bfc0bbf..6b6ebab4247 100644
--- a/langchain/embeddings/modelscope_hub.py
+++ b/langchain/embeddings/modelscope_hub.py
@@ -1,4 +1,3 @@
-"""Wrapper around ModelScopeHub embedding models."""
 from typing import Any, List
 
 from pydantic import BaseModel, Extra
@@ -7,7 +6,7 @@ from langchain.embeddings.base import Embeddings
 
 
 class ModelScopeEmbeddings(BaseModel, Embeddings):
-    """Wrapper around modelscope_hub embedding models.
+    """ModelScopeHub embedding models.
 
     To use, you should have the ``modelscope`` python package installed.
 
diff --git a/langchain/embeddings/mosaicml.py b/langchain/embeddings/mosaicml.py
index e8e0de84753..d2e448da7c1 100644
--- a/langchain/embeddings/mosaicml.py
+++ b/langchain/embeddings/mosaicml.py
@@ -1,4 +1,3 @@
-"""Wrapper around MosaicML APIs."""
 from typing import Any, Dict, List, Mapping, Optional, Tuple
 
 import requests
@@ -9,7 +8,7 @@ from langchain.utils import get_from_dict_or_env
 
 
 class MosaicMLInstructorEmbeddings(BaseModel, Embeddings):
-    """Wrapper around MosaicML's embedding inference service.
+    """MosaicML embedding service.
 
     To use, you should have the
     environment variable ``MOSAICML_API_TOKEN`` set with your API token, or pass
diff --git a/langchain/embeddings/nlpcloud.py b/langchain/embeddings/nlpcloud.py
index 204f22bade9..2e80d8d232c 100644
--- a/langchain/embeddings/nlpcloud.py
+++ b/langchain/embeddings/nlpcloud.py
@@ -1,4 +1,3 @@
-"""Wrapper around NLP Cloud embedding models."""
 from typing import Any, Dict, List
 
 from pydantic import BaseModel, root_validator
@@ -8,7 +7,7 @@ from langchain.utils import get_from_dict_or_env
 
 
 class NLPCloudEmbeddings(BaseModel, Embeddings):
-    """Wrapper around NLP Cloud embedding models.
+    """NLP Cloud embedding models.
 
     To use, you should have the nlpcloud python package installed
 
diff --git a/langchain/embeddings/octoai_embeddings.py b/langchain/embeddings/octoai_embeddings.py
index 552c3c75f5a..4a9d0a5120f 100644
--- a/langchain/embeddings/octoai_embeddings.py
+++ b/langchain/embeddings/octoai_embeddings.py
@@ -1,5 +1,3 @@
-"""Module providing a wrapper around OctoAI Compute Service embedding models."""
-
 from typing import Any, Dict, List, Mapping, Optional
 
 from pydantic import BaseModel, Extra, Field, root_validator
@@ -12,7 +10,7 @@ DEFAULT_QUERY_INSTRUCTION = "Represent the question for retrieving similar docum
 
 
 class OctoAIEmbeddings(BaseModel, Embeddings):
-    """Wrapper around OctoAI Compute Service embedding models.
+    """OctoAI Compute Service embedding models.
 
     The environment variable ``OCTOAI_API_TOKEN`` should be set
     with your API token, or it can be passed
diff --git a/langchain/embeddings/openai.py b/langchain/embeddings/openai.py
index e9b3f7f6406..2234975f0a9 100644
--- a/langchain/embeddings/openai.py
+++ b/langchain/embeddings/openai.py
@@ -1,4 +1,3 @@
-"""Wrapper around OpenAI embedding models."""
 from __future__ import annotations
 
 import logging
@@ -120,7 +119,7 @@ async def async_embed_with_retry(embeddings: OpenAIEmbeddings, **kwargs: Any) ->
 
 
 class OpenAIEmbeddings(BaseModel, Embeddings):
-    """Wrapper around OpenAI embedding models.
+    """OpenAI embedding models.
 
     To use, you should have the ``openai`` python package installed, and the
     environment variable ``OPENAI_API_KEY`` set with your API key or pass it
@@ -171,6 +170,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
     # to support explicit proxy for OpenAI
     openai_proxy: Optional[str] = None
     embedding_ctx_length: int = 8191
+    """The maximum number of tokens to embed at once."""
     openai_api_key: Optional[str] = None
     openai_organization: Optional[str] = None
     allowed_special: Union[Literal["all"], Set[str]] = set()
diff --git a/langchain/embeddings/sagemaker_endpoint.py b/langchain/embeddings/sagemaker_endpoint.py
index 25ba961df58..d0fd864a6bd 100644
--- a/langchain/embeddings/sagemaker_endpoint.py
+++ b/langchain/embeddings/sagemaker_endpoint.py
@@ -1,4 +1,3 @@
-"""Wrapper around Sagemaker InvokeEndpoint API."""
 from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel, Extra, root_validator
@@ -12,7 +11,7 @@ class EmbeddingsContentHandler(ContentHandlerBase[List[str], List[List[float]]])
 
 
 class SagemakerEndpointEmbeddings(BaseModel, Embeddings):
-    """Wrapper around custom Sagemaker Inference Endpoints.
+    """Custom Sagemaker Inference Endpoints.
 
     To use, you must supply the endpoint name from your deployed
     Sagemaker model & the region where it is deployed.
@@ -133,7 +132,7 @@ class SagemakerEndpointEmbeddings(BaseModel, Embeddings):
                 ) from e
 
         except ImportError:
-            raise ValueError(
+            raise ImportError(
                 "Could not import boto3 python package. "
                 "Please install it with `pip install boto3`."
             )
diff --git a/langchain/embeddings/self_hosted.py b/langchain/embeddings/self_hosted.py
index c010d5d500a..3ef31366924 100644
--- a/langchain/embeddings/self_hosted.py
+++ b/langchain/embeddings/self_hosted.py
@@ -1,4 +1,3 @@
-"""Running custom embedding models on self-hosted remote hardware."""
 from typing import Any, Callable, List
 
 from pydantic import Extra
@@ -17,7 +16,7 @@ def _embed_documents(pipeline: Any, *args: Any, **kwargs: Any) -> List[List[floa
 
 
 class SelfHostedEmbeddings(SelfHostedPipeline, Embeddings):
-    """Runs custom embedding models on self-hosted remote hardware.
+    """Custom embedding models on self-hosted remote hardware.
 
     Supported hardware includes auto-launched instances on AWS, GCP, Azure,
     and Lambda, as well as servers specified
diff --git a/langchain/embeddings/self_hosted_hugging_face.py b/langchain/embeddings/self_hosted_hugging_face.py
index 346f0791672..e12263d67f0 100644
--- a/langchain/embeddings/self_hosted_hugging_face.py
+++ b/langchain/embeddings/self_hosted_hugging_face.py
@@ -1,4 +1,3 @@
-"""Wrapper around HuggingFace embedding models for self-hosted remote hardware."""
 import importlib
 import logging
 from typing import Any, Callable, List, Optional
@@ -58,7 +57,7 @@ def load_embedding_model(model_id: str, instruct: bool = False, device: int = 0)
 
 
 class SelfHostedHuggingFaceEmbeddings(SelfHostedEmbeddings):
-    """Runs sentence_transformers embedding models on self-hosted remote hardware.
+    """HuggingFace embedding models on self-hosted remote hardware.
 
     Supported hardware includes auto-launched instances on AWS, GCP, Azure,
     and Lambda, as well as servers specified
@@ -101,7 +100,7 @@ class SelfHostedHuggingFaceEmbeddings(SelfHostedEmbeddings):
 
 
 class SelfHostedHuggingFaceInstructEmbeddings(SelfHostedHuggingFaceEmbeddings):
-    """Runs InstructorEmbedding embedding models on self-hosted remote hardware.
+    """HuggingFace InstructEmbedding models on self-hosted remote hardware.
 
     Supported hardware includes auto-launched instances on AWS, GCP, Azure,
     and Lambda, as well as servers specified
diff --git a/langchain/embeddings/sentence_transformer.py b/langchain/embeddings/sentence_transformer.py
index 0a69f2c2e5f..ae3b7caaa35 100644
--- a/langchain/embeddings/sentence_transformer.py
+++ b/langchain/embeddings/sentence_transformer.py
@@ -1,4 +1,4 @@
-"""Wrapper around sentence transformer embedding models."""
+"""HuggingFace sentence_transformer embedding models."""
 from langchain.embeddings.huggingface import HuggingFaceEmbeddings
 
 SentenceTransformerEmbeddings = HuggingFaceEmbeddings
diff --git a/langchain/embeddings/spacy_embeddings.py b/langchain/embeddings/spacy_embeddings.py
index 66f4baa2f69..ded1fbbd8ac 100644
--- a/langchain/embeddings/spacy_embeddings.py
+++ b/langchain/embeddings/spacy_embeddings.py
@@ -7,8 +7,8 @@ from langchain.embeddings.base import Embeddings
 
 
 class SpacyEmbeddings(BaseModel, Embeddings):
-    """
-    SpacyEmbeddings is a class for generating embeddings using the Spacy library.
+    """Embeddings by SpaCy models.
+
     It only supports the 'en_core_web_sm' model.
 
     Attributes:
diff --git a/langchain/embeddings/tensorflow_hub.py b/langchain/embeddings/tensorflow_hub.py
index 1e699ecbd31..514c7e1c1fd 100644
--- a/langchain/embeddings/tensorflow_hub.py
+++ b/langchain/embeddings/tensorflow_hub.py
@@ -1,4 +1,3 @@
-"""Wrapper around TensorflowHub embedding models."""
 from typing import Any, List
 
 from pydantic import BaseModel, Extra
@@ -9,7 +8,7 @@ DEFAULT_MODEL_URL = "https://tfhub.dev/google/universal-sentence-encoder-multili
 
 
 class TensorflowHubEmbeddings(BaseModel, Embeddings):
-    """Wrapper around tensorflow_hub embedding models.
+    """TensorflowHub embedding models.
 
     To use, you should have the ``tensorflow_text`` python package installed.
 
diff --git a/langchain/embeddings/vertexai.py b/langchain/embeddings/vertexai.py
index 6ff2a95f79c..6ea6d023033 100644
--- a/langchain/embeddings/vertexai.py
+++ b/langchain/embeddings/vertexai.py
@@ -1,4 +1,3 @@
-"""Wrapper around Google VertexAI embedding models."""
 from typing import Dict, List
 
 from pydantic import root_validator
@@ -9,6 +8,8 @@ from langchain.utilities.vertexai import raise_vertex_import_error
 
 
 class VertexAIEmbeddings(_VertexAICommon, Embeddings):
+    """Google Cloud VertexAI embedding models."""
+
     model_name: str = "textembedding-gecko"
 
     @root_validator()