style(core): more refs work (#33664)

Author: mdrxy

libs/core/langchain_core/document_loaders/base.py

@@ -27,7 +27,7 @@ class BaseLoader(ABC):  # noqa: B024
     """Interface for Document Loader.
 
     Implementations should implement the lazy-loading method using generators
-    to avoid loading all Documents into memory at once.
+    to avoid loading all documents into memory at once.
 
     `load` is provided just for user convenience and should not be overridden.
     """
@@ -53,9 +53,11 @@ async def aload(self) -> list[Document]:
     def load_and_split(
         self, text_splitter: TextSplitter | None = None
     ) -> list[Document]:
-        """Load Documents and split into chunks. Chunks are returned as `Document`.
+        """Load `Document` and split into chunks. Chunks are returned as `Document`.
 
-        Do not override this method. It should be considered to be deprecated!
+        !!! danger
+
+            Do not override this method. It should be considered to be deprecated!
 
         Args:
             text_splitter: `TextSplitter` instance to use for splitting documents.
@@ -135,7 +137,7 @@ def lazy_parse(self, blob: Blob) -> Iterator[Document]:
         """
 
     def parse(self, blob: Blob) -> list[Document]:
-        """Eagerly parse the blob into a `Document` or `Document` objects.
+        """Eagerly parse the blob into a `Document` or list of `Document` objects.
 
         This is a convenience method for interactive development environment.
 

libs/core/langchain_core/document_loaders/blob_loaders.py

@@ -28,7 +28,7 @@ class BlobLoader(ABC):
     def yield_blobs(
         self,
     ) -> Iterable[Blob]:
-        """A lazy loader for raw data represented by LangChain's Blob object.
+        """A lazy loader for raw data represented by LangChain's `Blob` object.
 
         Returns:
             A generator over blobs

libs/core/langchain_core/document_loaders/langsmith.py

@@ -14,13 +14,13 @@
 
 
 class LangSmithLoader(BaseLoader):
-    """Load LangSmith Dataset examples as Documents.
+    """Load LangSmith Dataset examples as `Document` objects.
 
-    Loads the example inputs as the Document page content and places the entire example
-    into the Document metadata. This allows you to easily create few-shot example
-    retrievers from the loaded documents.
+    Loads the example inputs as the `Document` page content and places the entire
+    example into the `Document` metadata. This allows you to easily create few-shot
+    example retrievers from the loaded documents.
 
-    ??? note "Lazy load"
+    ??? note "Lazy loading example"
 
         ```python
         from langchain_core.document_loaders import LangSmithLoader
@@ -66,12 +66,11 @@ def __init__(
             format_content: Function for converting the content extracted from the example
                 inputs into a string. Defaults to JSON-encoding the contents.
             example_ids: The IDs of the examples to filter by.
-            as_of: The dataset version tag OR
-                timestamp to retrieve the examples as of.
-                Response examples will only be those that were present at the time
-                of the tagged (or timestamped) version.
+            as_of: The dataset version tag or timestamp to retrieve the examples as of.
+                Response examples will only be those that were present at the time of
+                the tagged (or timestamped) version.
             splits: A list of dataset splits, which are
-                divisions of your dataset such as 'train', 'test', or 'validation'.
+                divisions of your dataset such as `train`, `test`, or `validation`.
                 Returns examples only from the specified splits.
             inline_s3_urls: Whether to inline S3 URLs.
             offset: The offset to start from.

libs/core/langchain_core/documents/base.py

@@ -51,7 +51,7 @@ class Blob(BaseMedia):
     help to decouple the development of data loaders from the downstream parsing of
     the raw data.
 
-    Inspired by: https://developer.mozilla.org/en-US/docs/Web/API/Blob
+    Inspired by [Mozilla's `Blob`](https://developer.mozilla.org/en-US/docs/Web/API/Blob)
 
     Example: Initialize a blob from in-memory data
 
@@ -103,7 +103,7 @@ class Blob(BaseMedia):
     """
 
     data: bytes | str | None = None
-    """Raw data associated with the blob."""
+    """Raw data associated with the `Blob`."""
     mimetype: str | None = None
     """MimeType not to be confused with a file extension."""
     encoding: str = "utf-8"
@@ -123,7 +123,7 @@ class Blob(BaseMedia):
     def source(self) -> str | None:
         """The source location of the blob as string if known otherwise none.
 
-        If a path is associated with the blob, it will default to the path location.
+        If a path is associated with the `Blob`, it will default to the path location.
 
         Unless explicitly set via a metadata field called `"source"`, in which
         case that value will be used instead.
@@ -211,13 +211,13 @@ def from_path(
         Args:
             path: Path-like object to file to be read
             encoding: Encoding to use if decoding the bytes into a string
-            mime_type: If provided, will be set as the mime-type of the data
-            guess_type: If `True`, the mimetype will be guessed from the file extension,
-                if a mime-type was not provided
-            metadata: Metadata to associate with the blob
+            mime_type: If provided, will be set as the MIME type of the data
+            guess_type: If `True`, the MIME type will be guessed from the file
+                extension, if a mime-type was not provided
+            metadata: Metadata to associate with the `Blob`
 
         Returns:
-            Blob instance
+            `Blob` instance
         """
         if mime_type is None and guess_type:
             mimetype = mimetypes.guess_type(path)[0] if guess_type else None
@@ -243,17 +243,17 @@ def from_data(
         path: str | None = None,
         metadata: dict | None = None,
     ) -> Blob:
-        """Initialize the blob from in-memory data.
+        """Initialize the `Blob` from in-memory data.
 
         Args:
-            data: The in-memory data associated with the blob
+            data: The in-memory data associated with the `Blob`
             encoding: Encoding to use if decoding the bytes into a string
-            mime_type: If provided, will be set as the mime-type of the data
+            mime_type: If provided, will be set as the MIME type of the data
             path: If provided, will be set as the source from which the data came
-            metadata: Metadata to associate with the blob
+            metadata: Metadata to associate with the `Blob`
 
         Returns:
-            Blob instance
+            `Blob` instance
         """
         return cls(
             data=data,

libs/core/langchain_core/load/dump.py

@@ -17,7 +17,7 @@ def default(obj: Any) -> Any:
         obj: The object to serialize to json if it is a Serializable object.
 
     Returns:
-        A json serializable object or a SerializedNotImplemented object.
+        A JSON serializable object or a SerializedNotImplemented object.
     """
     if isinstance(obj, Serializable):
         return obj.to_json()

libs/core/langchain_core/load/serializable.py

@@ -194,7 +194,7 @@ def to_json(self) -> SerializedConstructor | SerializedNotImplemented:
             ValueError: If the class has deprecated attributes.
 
         Returns:
-            A json serializable object or a `SerializedNotImplemented` object.
+            A JSON serializable object or a `SerializedNotImplemented` object.
         """
         if not self.is_lc_serializable():
             return self.to_json_not_implemented()