docs: community docstring updates (#21040)

Added missed docstrings. Updated docstrings to consistent format.

libs/community/langchain_community/callbacks/aim_callback.py

@@ -20,7 +20,7 @@ def import_aim() -> Any:
 
 
 class BaseMetadataCallbackHandler:
-    """This class handles the metadata and associated function states for callbacks.
+    """Callback handler for the metadata and associated function states for callbacks.
 
     Attributes:
         step (int): The current step.

libs/community/langchain_community/callbacks/uptrain_callback.py

@@ -74,6 +74,7 @@ logger.addHandler(handler)
 
 
 def import_uptrain() -> Any:
+    """Import the `uptrain` package."""
     try:
         import uptrain
     except ImportError as e:

libs/community/langchain_community/callbacks/utils.py

@@ -65,7 +65,7 @@ def _flatten_dict(
 def flatten_dict(
     nested_dict: Dict[str, Any], parent_key: str = "", sep: str = "_"
 ) -> Dict[str, Any]:
-    """Flattens a nested dictionary into a flat dictionary.
+    """Flatten a nested dictionary into a flat dictionary.
 
     Parameters:
         nested_dict (dict): The nested dictionary to flatten.
@@ -108,7 +108,7 @@ def load_json(json_path: Union[str, Path]) -> str:
 
 
 class BaseMetadataCallbackHandler:
-    """This class handles the metadata and associated function states for callbacks.
+    """Handle the metadata and associated function states for callbacks.
 
     Attributes:
         step (int): The current step.

libs/community/langchain_community/chat_message_histories/zep.py

@@ -19,7 +19,7 @@ logger = logging.getLogger(__name__)
 
 
 class SearchScope(str, Enum):
-    """Which documents to search. Messages or Summaries?"""
+    """Scope for the document search. Messages or Summaries?"""
 
     messages = "messages"
     """Search chat history messages."""

libs/community/langchain_community/chat_models/mlx.py

@@ -27,8 +27,7 @@ DEFAULT_SYSTEM_PROMPT = """You are a helpful, respectful, and honest assistant."
 
 
 class ChatMLX(BaseChatModel):
-    """
-    Wrapper for using MLX LLM's as ChatModels.
+    """MLX chat models.
 
     Works with `MLXPipeline` LLM.
 

libs/community/langchain_community/document_loaders/doc_intelligence.py

@@ -10,7 +10,7 @@ from langchain_community.document_loaders.parsers import (
 
 
 class AzureAIDocumentIntelligenceLoader(BaseLoader):
-    """Loads a PDF with Azure Document Intelligence"""
+    """Load a PDF with Azure Document Intelligence."""
 
     def __init__(
         self,

libs/community/langchain_community/document_loaders/parsers/docai.py

@@ -28,7 +28,7 @@ logger = logging.getLogger(__name__)
 
 @dataclass
 class DocAIParsingResults:
-    """A dataclass to store Document AI parsing results."""
+    """Dataclass to store Document AI parsing results."""
 
     source_path: str
     parsed_path: str

libs/community/langchain_community/document_loaders/parsers/html/bs4.py

@@ -12,7 +12,7 @@ logger = logging.getLogger(__name__)
 
 
 class BS4HTMLParser(BaseBlobParser):
-    """Pparse HTML files using `Beautiful Soup`."""
+    """Parse HTML files using `Beautiful Soup`."""
 
     def __init__(
         self,

libs/community/langchain_community/document_loaders/pdf.py

@@ -731,7 +731,7 @@ class AmazonTextractPDFLoader(BasePDFLoader):
 
 
 class DocumentIntelligenceLoader(BasePDFLoader):
-    """Loads a PDF with Azure Document Intelligence"""
+    """Load a PDF with Azure Document Intelligence"""
 
     def __init__(
         self,

libs/community/langchain_community/document_loaders/url_playwright.py

@@ -57,7 +57,7 @@ class PlaywrightEvaluator(ABC):
 
 
 class UnstructuredHtmlEvaluator(PlaywrightEvaluator):
-    """Evaluates the page HTML content using the `unstructured` library."""
+    """Evaluate the page HTML content using the `unstructured` library."""
 
     def __init__(self, remove_selectors: Optional[List[str]] = None):
         """Initialize UnstructuredHtmlEvaluator."""

libs/community/langchain_community/embeddings/infinity.py

@@ -15,11 +15,13 @@ __all__ = ["InfinityEmbeddings"]
 
 
 class InfinityEmbeddings(BaseModel, Embeddings):
-    """Embedding models for self-hosted https://github.com/michaelfeil/infinity
-    This should also work for text-embeddings-inference and other
+    """Self-hosted embedding models for `infinity` package.
+
+    See https://github.com/michaelfeil/infinity
+    This also works for text-embeddings-inference and other
     self-hosted openai-compatible servers.
 
-    Infinity is a class to interact with Embedding Models on https://github.com/michaelfeil/infinity
+    Infinity is a package to interact with Embedding Models on https://github.com/michaelfeil/infinity
 
 
     Example:
@@ -115,7 +117,9 @@ class InfinityEmbeddings(BaseModel, Embeddings):
 
 
 class TinyAsyncOpenAIInfinityEmbeddingClient:  #: :meta private:
-    """A helper tool to embed Infinity. Not part of Langchain's stable API,
+    """Helper tool to embed Infinity.
+
+    It is not a part of Langchain's stable API,
     direct use discouraged.
 
     Example:

libs/community/langchain_community/embeddings/premai.py

@@ -72,6 +72,15 @@ def create_prem_retry_decorator(
     *,
     max_retries: int = 1,
 ) -> Callable[[Any], Any]:
+    """Create a retry decorator for PremAIEmbeddings.
+
+    Args:
+        embedder (PremAIEmbeddings): The PremAIEmbeddings instance
+        max_retries (int): The maximum number of retries
+
+    Returns:
+        Callable[[Any], Any]: The retry decorator
+    """
     import premai.models
 
     errors = [

libs/community/langchain_community/embeddings/sparkllm.py

@@ -187,5 +187,7 @@ class SparkLLMTextEmbeddings(BaseModel, Embeddings):
 
 
 class AssembleHeaderException(Exception):
+    """Exception raised for errors in the header assembly."""
+
     def __init__(self, msg: str) -> None:
         self.message = msg

libs/community/langchain_community/embeddings/titan_takeoff.py

@@ -6,22 +6,24 @@ from langchain_core.pydantic_v1 import BaseModel
 
 
 class TakeoffEmbeddingException(Exception):
-    """Exceptions experienced with interfacing with Takeoff Embedding Wrapper"""
+    """Custom exception for interfacing with Takeoff Embedding class."""
 
 
 class MissingConsumerGroup(TakeoffEmbeddingException):
     """Exception raised when no consumer group is provided on initialization of
-    TitanTakeoffEmbed or in embed request"""
+    TitanTakeoffEmbed or in embed request."""
 
 
 class Device(str, Enum):
-    """The device to use for inference, cuda or cpu"""
+    """Device to use for inference, cuda or cpu."""
 
     cuda = "cuda"
     cpu = "cpu"
 
 
 class ReaderConfig(BaseModel):
+    """Configuration for the reader to be deployed in Takeoff."""
+
     class Config:
         protected_namespaces = ()
 
@@ -36,10 +38,9 @@ class ReaderConfig(BaseModel):
 
 
 class TitanTakeoffEmbed(Embeddings):
-    """Titan Takeoff Embed is a wrapper to interface with Takeoff Inference API
-    for embedding models
+    """Interface with Takeoff Inference API for embedding models.
 
-    You can use this wrapper to send embedding requests and to deploy embedding
+    Use it to send embedding requests and to deploy embedding
     readers with Takeoff.
 
     Examples:

libs/community/langchain_community/graphs/graph_store.py

@@ -5,18 +5,18 @@ from langchain_community.graphs.graph_document import GraphDocument
 
 
 class GraphStore:
-    """An abstract class wrapper for graph operations."""
+    """Abstract class for graph operations."""
 
     @property
     @abstractmethod
     def get_schema(self) -> str:
-        """Returns the schema of the Graph database"""
+        """Return the schema of the Graph database"""
         pass
 
     @property
     @abstractmethod
     def get_structured_schema(self) -> Dict[str, Any]:
-        """Returns the schema of the Graph database"""
+        """Return the schema of the Graph database"""
         pass
 
     @abstractmethod
@@ -26,7 +26,7 @@ class GraphStore:
 
     @abstractmethod
     def refresh_schema(self) -> None:
-        """Refreshes the graph schema information."""
+        """Refresh the graph schema information."""
         pass
 
     @abstractmethod

libs/community/langchain_community/graphs/gremlin_graph.py

@@ -10,6 +10,7 @@ from langchain_community.graphs.graph_store import GraphStore
 
 class GremlinGraph(GraphStore):
     """Gremlin wrapper for graph operations.
+
     Parameters:
     url (Optional[str]): The URL of the Gremlin database server or env GREMLIN_URI
     username (Optional[str]): The collection-identifier like '/dbs/database/colls/graph'

libs/community/langchain_community/graphs/neptune_graph.py

@@ -22,9 +22,11 @@ class NeptuneQueryException(Exception):
 
 
 class BaseNeptuneGraph(ABC):
+    """Abstract base class for Neptune"""
+
     @property
     def get_schema(self) -> str:
-        """Returns the schema of the Neptune database"""
+        """Return the schema of the Neptune database"""
         return self.schema
 
     @abstractmethod

libs/community/langchain_community/llms/baichuan.py

@@ -17,7 +17,7 @@ logger = logging.getLogger(__name__)
 
 class BaichuanLLM(LLM):
     # TODO: Adding streaming support.
-    """Wrapper around Baichuan large language models."""
+    """Baichuan large language models."""
 
     model: str = "Baichuan2-Turbo-192k"
     """

libs/community/langchain_community/llms/minimax.py

@@ -23,7 +23,7 @@ logger = logging.getLogger(__name__)
 
 
 class _MinimaxEndpointClient(BaseModel):
-    """An API client that talks to a Minimax llm endpoint."""
+    """API client for the Minimax LLM endpoint."""
 
     host: str
     group_id: str
@@ -117,7 +117,8 @@ class MinimaxCommon(BaseModel):
 
 
 class Minimax(MinimaxCommon, LLM):
-    """Wrapper around Minimax large language models.
+    """Minimax large language models.
+
     To use, you should have the environment variable
     ``MINIMAX_API_KEY`` and ``MINIMAX_GROUP_ID`` set with your API key,
     or pass them as a named parameter to the constructor.

libs/community/langchain_community/llms/titan_takeoff.py

@@ -17,6 +17,8 @@ class Device(str, Enum):
 
 
 class ReaderConfig(BaseModel):
+    """Configuration for the reader to be deployed in Titan Takeoff API."""
+
     class Config:
         protected_namespaces = ()
 

libs/community/langchain_community/tools/e2b_data_analysis/unparse.py

@@ -27,7 +27,7 @@ def interleave(inter, f, seq):
 
 
 class Unparser:
-    """Methods in this class recursively traverse an AST and
+    """Traverse an AST and
     output source code for the abstract syntax; original formatting
     is disregarded."""
 

libs/community/langchain_community/utilities/cassandra.py

@@ -11,6 +11,16 @@ if TYPE_CHECKING:
 async def wrapped_response_future(
     func: Callable[..., ResponseFuture], *args: Any, **kwargs: Any
 ) -> Any:
+    """Wrap a Cassandra response future in an asyncio future.
+
+    Args:
+        func: The Cassandra function to call.
+        *args: The arguments to pass to the Cassandra function.
+        **kwargs: The keyword arguments to pass to the Cassandra function.
+
+    Returns:
+        The result of the Cassandra function.
+    """
     loop = asyncio.get_event_loop()
     asyncio_future = loop.create_future()
     response_future = func(*args, **kwargs)

libs/community/langchain_community/utilities/clickup.py

@@ -196,12 +196,15 @@ def extract_dict_elements_from_component_fields(
 def load_query(
     query: str, fault_tolerant: bool = False
 ) -> Tuple[Optional[Dict], Optional[str]]:
-    """Attempts to parse a JSON string and return the parsed object.
+    """Parse a JSON string and return the parsed object.
 
     If parsing fails, returns an error message.
 
     :param query: The JSON string to parse.
     :return: A tuple containing the parsed object or None and an error message or None.
+
+    Exceptions:
+        json.JSONDecodeError: If the input is not a valid JSON string.
     """
     try:
         return json.loads(query), None

libs/community/langchain_community/utilities/passio_nutrition_ai.py

@@ -9,6 +9,8 @@ from langchain_core.utils import get_from_dict_or_env
 
 
 class NoDiskStorage:
+    """Mixin to prevent storing on disk."""
+
     @final
     def __getstate__(self) -> None:
         raise AttributeError("Do not store on disk.")
@@ -46,11 +48,12 @@ except ImportError:
 
 
 def is_http_retryable(rsp: requests.Response) -> bool:
+    """Check if a HTTP response is retryable."""
     return bool(rsp) and rsp.status_code in [408, 425, 429, 500, 502, 503, 504]
 
 
 class ManagedPassioLifeAuth(NoDiskStorage):
-    """Manages the token for the NutritionAI API."""
+    """Manage the token for the NutritionAI API."""
 
     _access_token_expiry: Optional[datetime]
 

libs/community/langchain_community/utilities/pebblo.py

@@ -192,7 +192,7 @@ def get_loader_type(loader: str) -> str:
 
 def get_loader_full_path(loader: BaseLoader) -> str:
     """Return an absolute source path of source of loader based on the
-    keys present in Document object from loader.
+    keys present in Document.
 
     Args:
         loader (BaseLoader): Langchain document loader, derived from Baseloader.

libs/community/langchain_community/utilities/powerbi.py

@@ -251,7 +251,7 @@ def json_to_md(
     json_contents: List[Dict[str, Union[str, int, float]]],
     table_name: Optional[str] = None,
 ) -> str:
-    """Converts a JSON object to a markdown table."""
+    """Convert a JSON object to a markdown table."""
     if len(json_contents) == 0:
         return ""
     output_md = ""

libs/community/langchain_community/vectorstores/cassandra.py

@@ -35,7 +35,7 @@ _NOT_SET = object()
 
 
 class Cassandra(VectorStore):
-    """Wrapper around Apache Cassandra(R) for vector-store workloads.
+    """Apache Cassandra(R) for vector-store workloads.
 
     To use it, you need a recent installation of the `cassio` library
     and a Cassandra cluster / Astra DB instance supporting vector capabilities.

libs/community/langchain_community/vectorstores/lancedb.py

@@ -11,6 +11,8 @@ from langchain_core.vectorstores import VectorStore
 
 
 def import_lancedb() -> Any:
+    """Import lancedb package."""
+
     try:
         import lancedb
     except ImportError as e:

libs/community/langchain_community/vectorstores/tencentvectordb.py

@@ -109,6 +109,15 @@ class MetaField(BaseModel):
 def translate_filter(
     lc_filter: str, allowed_fields: Optional[Sequence[str]] = None
 ) -> str:
+    """Translate LangChain filter to Tencent VectorDB filter.
+
+    Args:
+        lc_filter (str): LangChain filter.
+        allowed_fields (Optional[Sequence[str]]): Allowed fields for filter.
+
+    Returns:
+        str: Translated filter.
+    """
     from langchain.chains.query_constructor.base import fix_filter_directive
     from langchain.chains.query_constructor.parser import get_parser
     from langchain.retrievers.self_query.tencentvectordb import (