langchain-core 1.0.0a8__py3-none-any.whl → 1.0.0rc2__py3-none-any.whl

langchain_core/document_loaders/langsmith.py

@@ -22,22 +22,22 @@ class LangSmithLoader(BaseLoader):
 
     ??? note "Lazy load"
 
-        .. code-block:: python
+        ```python
+        from langchain_core.document_loaders import LangSmithLoader
 
-            from langchain_core.document_loaders import LangSmithLoader
+        loader = LangSmithLoader(dataset_id="...", limit=100)
+        docs = []
+        for doc in loader.lazy_load():
+            docs.append(doc)
+        ```
 
-            loader = LangSmithLoader(dataset_id="...", limit=100)
-            docs = []
-            for doc in loader.lazy_load():
-                docs.append(doc)
-
-        .. code-block:: python
-
-            # -> [Document("...", metadata={"inputs": {...}, "outputs": {...}, ...}), ...]
+        ```python
+        # -> [Document("...", metadata={"inputs": {...}, "outputs": {...}, ...}), ...]
+        ```
 
     !!! version-added "Added in version 0.2.34"
 
-    """  # noqa: E501
+    """
 
     def __init__(
         self,
@@ -60,15 +60,15 @@ class LangSmithLoader(BaseLoader):
         """Create a LangSmith loader.
 
         Args:
-            dataset_id: The ID of the dataset to filter by. Defaults to None.
-            dataset_name: The name of the dataset to filter by. Defaults to None.
-            content_key: The inputs key to set as Document page content. ``'.'`` characters
-                are interpreted as nested keys. E.g. ``content_key="first.second"`` will
+            dataset_id: The ID of the dataset to filter by.
+            dataset_name: The name of the dataset to filter by.
+            content_key: The inputs key to set as Document page content. `'.'` characters
+                are interpreted as nested keys. E.g. `content_key="first.second"` will
                 result in
-                ``Document(page_content=format_content(example.inputs["first"]["second"]))``
+                `Document(page_content=format_content(example.inputs["first"]["second"]))`
             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. Defaults to None.
+            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
@@ -76,17 +76,17 @@ class LangSmithLoader(BaseLoader):
             splits: A list of dataset splits, which are
                 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. Defaults to True.
-            offset: The offset to start from. Defaults to 0.
+            inline_s3_urls: Whether to inline S3 URLs.
+            offset: The offset to start from.
             limit: The maximum number of examples to return.
-            metadata: Metadata to filter by. Defaults to None.
+            metadata: Metadata to filter by.
             filter: A structured filter string to apply to the examples.
             client: LangSmith Client. If not provided will be initialized from below args.
             client_kwargs: Keyword args to pass to LangSmith client init. Should only be
-                specified if ``client`` isn't.
+                specified if `client` isn't.
 
         Raises:
-            ValueError: If both ``client`` and ``client_kwargs`` are provided.
+            ValueError: If both `client` and `client_kwargs` are provided.
         """  # noqa: E501
         if client and client_kwargs:
             raise ValueError

langchain_core/documents/__init__.py

@@ -2,7 +2,6 @@
 
 **Document** module is a collection of classes that handle documents
 and their transformations.
-
 """
 
 from typing import TYPE_CHECKING

langchain_core/documents/base.py

@@ -57,52 +57,51 @@ class Blob(BaseMedia):
 
     Example: Initialize a blob from in-memory data
 
-        .. code-block:: python
+    ```python
+    from langchain_core.documents import Blob
 
-            from langchain_core.documents import Blob
+    blob = Blob.from_data("Hello, world!")
 
-            blob = Blob.from_data("Hello, world!")
+    # Read the blob as a string
+    print(blob.as_string())
 
-            # Read the blob as a string
-            print(blob.as_string())
+    # Read the blob as bytes
+    print(blob.as_bytes())
 
-            # Read the blob as bytes
-            print(blob.as_bytes())
-
-            # Read the blob as a byte stream
-            with blob.as_bytes_io() as f:
-                print(f.read())
+    # Read the blob as a byte stream
+    with blob.as_bytes_io() as f:
+        print(f.read())
+    ```
 
     Example: Load from memory and specify mime-type and metadata
 
-        .. code-block:: python
-
-            from langchain_core.documents import Blob
+    ```python
+    from langchain_core.documents import Blob
 
-            blob = Blob.from_data(
-                data="Hello, world!",
-                mime_type="text/plain",
-                metadata={"source": "https://example.com"},
-            )
+    blob = Blob.from_data(
+        data="Hello, world!",
+        mime_type="text/plain",
+        metadata={"source": "https://example.com"},
+    )
+    ```
 
     Example: Load the blob from a file
 
-        .. code-block:: python
-
-            from langchain_core.documents import Blob
-
-            blob = Blob.from_path("path/to/file.txt")
+    ```python
+    from langchain_core.documents import Blob
 
-            # Read the blob as a string
-            print(blob.as_string())
+    blob = Blob.from_path("path/to/file.txt")
 
-            # Read the blob as bytes
-            print(blob.as_bytes())
+    # Read the blob as a string
+    print(blob.as_string())
 
-            # Read the blob as a byte stream
-            with blob.as_bytes_io() as f:
-                print(f.read())
+    # Read the blob as bytes
+    print(blob.as_bytes())
 
+    # Read the blob as a byte stream
+    with blob.as_bytes_io() as f:
+        print(f.read())
+    ```
     """
 
     data: bytes | str | None = None
@@ -112,7 +111,7 @@ class Blob(BaseMedia):
     encoding: str = "utf-8"
     """Encoding to use if decoding the bytes into a string.
 
-    Use utf-8 as default encoding, if decoding to string.
+    Use `utf-8` as default encoding, if decoding to string.
     """
     path: PathLike | None = None
     """Location where the original content was found."""
@@ -128,7 +127,7 @@ class Blob(BaseMedia):
 
         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
+        Unless explicitly set via a metadata field called `"source"`, in which
         case that value will be used instead.
         """
         if self.metadata and "source" in self.metadata:
@@ -212,11 +211,11 @@ class Blob(BaseMedia):
         """Load the blob from a path like object.
 
         Args:
-            path: path like object to file to be read
+            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
+            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
 
         Returns:
@@ -249,10 +248,10 @@ class Blob(BaseMedia):
         """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
-            path: if provided, will be set as the source from which the data came
+            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
 
         Returns:
@@ -278,15 +277,13 @@ class Document(BaseMedia):
     """Class for storing a piece of text and associated metadata.
 
     Example:
+        ```python
+        from langchain_core.documents import Document
 
-        .. code-block:: python
-
-            from langchain_core.documents import Document
-
-            document = Document(
-                page_content="Hello, world!", metadata={"source": "https://example.com"}
-            )
-
+        document = Document(
+            page_content="Hello, world!", metadata={"source": "https://example.com"}
+        )
+        ```
     """
 
     page_content: str
@@ -306,7 +303,7 @@ class Document(BaseMedia):
 
     @classmethod
     def get_lc_namespace(cls) -> list[str]:
-        """Get the namespace of the langchain object.
+        """Get the namespace of the LangChain object.
 
         Returns:
             ["langchain", "schema", "document"]

langchain_core/documents/transformers.py

@@ -20,35 +20,34 @@ class BaseDocumentTransformer(ABC):
     sequence of transformed Documents.
 
     Example:
-        .. code-block:: python
-
-            class EmbeddingsRedundantFilter(BaseDocumentTransformer, BaseModel):
-                embeddings: Embeddings
-                similarity_fn: Callable = cosine_similarity
-                similarity_threshold: float = 0.95
-
-                class Config:
-                    arbitrary_types_allowed = True
-
-                def transform_documents(
-                    self, documents: Sequence[Document], **kwargs: Any
-                ) -> Sequence[Document]:
-                    stateful_documents = get_stateful_documents(documents)
-                    embedded_documents = _get_embeddings_from_stateful_docs(
-                        self.embeddings, stateful_documents
-                    )
-                    included_idxs = _filter_similar_embeddings(
-                        embedded_documents,
-                        self.similarity_fn,
-                        self.similarity_threshold,
-                    )
-                    return [stateful_documents[i] for i in sorted(included_idxs)]
-
-                async def atransform_documents(
-                    self, documents: Sequence[Document], **kwargs: Any
-                ) -> Sequence[Document]:
-                    raise NotImplementedError
-
+        ```python
+        class EmbeddingsRedundantFilter(BaseDocumentTransformer, BaseModel):
+            embeddings: Embeddings
+            similarity_fn: Callable = cosine_similarity
+            similarity_threshold: float = 0.95
+
+            class Config:
+                arbitrary_types_allowed = True
+
+            def transform_documents(
+                self, documents: Sequence[Document], **kwargs: Any
+            ) -> Sequence[Document]:
+                stateful_documents = get_stateful_documents(documents)
+                embedded_documents = _get_embeddings_from_stateful_docs(
+                    self.embeddings, stateful_documents
+                )
+                included_idxs = _filter_similar_embeddings(
+                    embedded_documents,
+                    self.similarity_fn,
+                    self.similarity_threshold,
+                )
+                return [stateful_documents[i] for i in sorted(included_idxs)]
+
+            async def atransform_documents(
+                self, documents: Sequence[Document], **kwargs: Any
+            ) -> Sequence[Document]:
+                raise NotImplementedError
+        ```
     """
 
     @abstractmethod

langchain_core/embeddings/fake.py

@@ -18,40 +18,38 @@ class FakeEmbeddings(Embeddings, BaseModel):
 
     This embedding model creates embeddings by sampling from a normal distribution.
 
-    Do not use this outside of testing, as it is not a real embedding model.
+    !!! warning
+        Do not use this outside of testing, as it is not a real embedding model.
 
     Instantiate:
-        .. code-block:: python
+        ```python
+        from langchain_core.embeddings import FakeEmbeddings
 
-            from langchain_core.embeddings import FakeEmbeddings
-
-            embed = FakeEmbeddings(size=100)
+        embed = FakeEmbeddings(size=100)
+        ```
 
     Embed single text:
-        .. code-block:: python
-
-            input_text = "The meaning of life is 42"
-            vector = embed.embed_query(input_text)
-            print(vector[:3])
-
-        .. code-block:: python
-
-            [-0.700234640213188, -0.581266257710429, -1.1328482266445354]
+        ```python
+        input_text = "The meaning of life is 42"
+        vector = embed.embed_query(input_text)
+        print(vector[:3])
+        ```
+        ```python
+        [-0.700234640213188, -0.581266257710429, -1.1328482266445354]
+        ```
 
     Embed multiple texts:
-        .. code-block:: python
-
-            input_texts = ["Document 1...", "Document 2..."]
-            vectors = embed.embed_documents(input_texts)
-            print(len(vectors))
-            # The first 3 coordinates for the first vector
-            print(vectors[0][:3])
-
-        .. code-block:: python
-
-            2
-            [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257]
-
+        ```python
+        input_texts = ["Document 1...", "Document 2..."]
+        vectors = embed.embed_documents(input_texts)
+        print(len(vectors))
+        # The first 3 coordinates for the first vector
+        print(vectors[0][:3])
+        ```
+        ```python
+        2
+        [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257]
+        ```
     """
 
     size: int
@@ -75,40 +73,38 @@ class DeterministicFakeEmbedding(Embeddings, BaseModel):
     This embedding model creates embeddings by sampling from a normal distribution
     with a seed based on the hash of the text.
 
-    Do not use this outside of testing, as it is not a real embedding model.
+    !!! warning
+        Do not use this outside of testing, as it is not a real embedding model.
 
     Instantiate:
-        .. code-block:: python
+        ```python
+        from langchain_core.embeddings import DeterministicFakeEmbedding
 
-            from langchain_core.embeddings import DeterministicFakeEmbedding
-
-            embed = DeterministicFakeEmbedding(size=100)
+        embed = DeterministicFakeEmbedding(size=100)
+        ```
 
     Embed single text:
-        .. code-block:: python
-
-            input_text = "The meaning of life is 42"
-            vector = embed.embed_query(input_text)
-            print(vector[:3])
-
-        .. code-block:: python
-
-            [-0.700234640213188, -0.581266257710429, -1.1328482266445354]
+        ```python
+        input_text = "The meaning of life is 42"
+        vector = embed.embed_query(input_text)
+        print(vector[:3])
+        ```
+        ```python
+        [-0.700234640213188, -0.581266257710429, -1.1328482266445354]
+        ```
 
     Embed multiple texts:
-        .. code-block:: python
-
-            input_texts = ["Document 1...", "Document 2..."]
-            vectors = embed.embed_documents(input_texts)
-            print(len(vectors))
-            # The first 3 coordinates for the first vector
-            print(vectors[0][:3])
-
-        .. code-block:: python
-
-            2
-            [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257]
-
+        ```python
+        input_texts = ["Document 1...", "Document 2..."]
+        vectors = embed.embed_documents(input_texts)
+        print(len(vectors))
+        # The first 3 coordinates for the first vector
+        print(vectors[0][:3])
+        ```
+        ```python
+        2
+        [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257]
+        ```
     """
 
     size: int

langchain_core/example_selectors/semantic_similarity.py

@@ -154,7 +154,7 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
             examples: List of examples to use in the prompt.
             embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
             vectorstore_cls: A vector store DB interface class, e.g. FAISS.
-            k: Number of examples to select. Default is 4.
+            k: Number of examples to select.
             input_keys: If provided, the search is based on the input variables
                 instead of all variables.
             example_keys: If provided, keys to filter examples to.
@@ -198,7 +198,7 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
             examples: List of examples to use in the prompt.
             embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
             vectorstore_cls: A vector store DB interface class, e.g. FAISS.
-            k: Number of examples to select. Default is 4.
+            k: Number of examples to select.
             input_keys: If provided, the search is based on the input variables
                 instead of all variables.
             example_keys: If provided, keys to filter examples to.
@@ -285,9 +285,8 @@ class MaxMarginalRelevanceExampleSelector(_VectorStoreExampleSelector):
             examples: List of examples to use in the prompt.
             embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
             vectorstore_cls: A vector store DB interface class, e.g. FAISS.
-            k: Number of examples to select. Default is 4.
+            k: Number of examples to select.
             fetch_k: Number of Documents to fetch to pass to MMR algorithm.
-                Default is 20.
             input_keys: If provided, the search is based on the input variables
                 instead of all variables.
             example_keys: If provided, keys to filter examples to.
@@ -333,9 +332,8 @@ class MaxMarginalRelevanceExampleSelector(_VectorStoreExampleSelector):
             examples: List of examples to use in the prompt.
             embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
             vectorstore_cls: A vector store DB interface class, e.g. FAISS.
-            k: Number of examples to select. Default is 4.
+            k: Number of examples to select.
             fetch_k: Number of Documents to fetch to pass to MMR algorithm.
-                Default is 20.
             input_keys: If provided, the search is based on the input variables
                 instead of all variables.
             example_keys: If provided, keys to filter examples to.

langchain_core/exceptions.py

@@ -16,7 +16,7 @@ class OutputParserException(ValueError, LangChainException):  # noqa: N818
     """Exception that output parsers should raise to signify a parsing error.
 
     This exists to differentiate parsing errors from other code or execution errors
-    that also may arise inside the output parser. OutputParserExceptions will be
+    that also may arise inside the output parser. `OutputParserException` will be
     available to catch and handle in ways to fix the parsing error, while other
     errors will be raised.
     """
@@ -28,24 +28,23 @@ class OutputParserException(ValueError, LangChainException):  # noqa: N818
         llm_output: str | None = None,
         send_to_llm: bool = False,  # noqa: FBT001,FBT002
     ):
-        """Create an OutputParserException.
+        """Create an `OutputParserException`.
 
         Args:
             error: The error that's being re-raised or an error message.
             observation: String explanation of error which can be passed to a
-                model to try and remediate the issue. Defaults to None.
+                model to try and remediate the issue.
             llm_output: String model output which is error-ing.
-                Defaults to None.
+
             send_to_llm: Whether to send the observation and llm_output back to an Agent
-                after an OutputParserException has been raised.
+                after an `OutputParserException` has been raised.
                 This gives the underlying model driving the agent the context that the
                 previous output was improperly structured, in the hopes that it will
                 update the output to the correct format.
-                Defaults to False.
 
         Raises:
-            ValueError: If ``send_to_llm`` is True but either observation or
-                ``llm_output`` are not provided.
+            ValueError: If `send_to_llm` is True but either observation or
+                `llm_output` are not provided.
         """
         if isinstance(error, str):
             error = create_message(

langchain_core/indexing/api.py

@@ -299,9 +299,9 @@ def index(
     are not able to specify the uid of the document.
 
     !!! warning "Behavior changed in 0.3.25"
-        Added ``scoped_full`` cleanup mode.
+        Added `scoped_full` cleanup mode.
 
-    !!! important
+    !!! warning
 
         * In full mode, the loader should be returning
           the entire dataset, and not just a subset of the dataset.
@@ -315,7 +315,7 @@ def index(
           chunks, and we index them using a batch size of 5, we'll have 3 batches
           all with the same source id. In general, to avoid doing too much
           redundant work select as big a batch size as possible.
-        * The ``scoped_full`` mode is suitable if determining an appropriate batch size
+        * The `scoped_full` mode is suitable if determining an appropriate batch size
           is challenging or if your data loader cannot return the entire dataset at
           once. This mode keeps track of source IDs in memory, which should be fine
           for most use cases. If your dataset is large (10M+ docs), you will likely
@@ -326,8 +326,8 @@ def index(
         record_manager: Timestamped set to keep track of which documents were
             updated.
         vector_store: VectorStore or DocumentIndex to index the documents into.
-        batch_size: Batch size to use when indexing. Default is 100.
-        cleanup: How to handle clean up of documents. Default is None.
+        batch_size: Batch size to use when indexing.
+        cleanup: How to handle clean up of documents.
 
             - incremental: Cleans up all documents that haven't been updated AND
               that are associated with source ids that were seen during indexing.
@@ -342,15 +342,12 @@ def index(
               source ids that were seen during indexing.
             - None: Do not delete any documents.
         source_id_key: Optional key that helps identify the original source
-            of the document. Default is None.
+            of the document.
         cleanup_batch_size: Batch size to use when cleaning up documents.
-            Default is 1_000.
         force_update: Force update documents even if they are present in the
             record manager. Useful if you are re-indexing with updated embeddings.
-            Default is False.
         key_encoder: Hashing algorithm to use for hashing the document content and
-            metadata. Default is "sha1".
-            Other options include "blake2b", "sha256", and "sha512".
+            metadata. Options include "blake2b", "sha256", and "sha512".
 
             !!! version-added "Added in version 0.3.66"
 
@@ -381,8 +378,8 @@ def index(
         ValueError: If vectorstore does not have
             "delete" and "add_documents" required methods.
         ValueError: If source_id_key is not None, but is not a string or callable.
-        TypeError: If ``vectorstore`` is not a VectorStore or a DocumentIndex.
-        AssertionError: If ``source_id`` is None when cleanup mode is incremental.
+        TypeError: If `vectorstore` is not a VectorStore or a DocumentIndex.
+        AssertionError: If `source_id` is None when cleanup mode is incremental.
             (should be unreachable code).
     """
     # Behavior is deprecated, but we keep it for backwards compatibility.
@@ -640,9 +637,9 @@ async def aindex(
     are not able to specify the uid of the document.
 
     !!! warning "Behavior changed in 0.3.25"
-        Added ``scoped_full`` cleanup mode.
+        Added `scoped_full` cleanup mode.
 
-    !!! important
+    !!! warning
 
         * In full mode, the loader should be returning
           the entire dataset, and not just a subset of the dataset.
@@ -656,7 +653,7 @@ async def aindex(
           chunks, and we index them using a batch size of 5, we'll have 3 batches
           all with the same source id. In general, to avoid doing too much
           redundant work select as big a batch size as possible.
-        * The ``scoped_full`` mode is suitable if determining an appropriate batch size
+        * The `scoped_full` mode is suitable if determining an appropriate batch size
           is challenging or if your data loader cannot return the entire dataset at
           once. This mode keeps track of source IDs in memory, which should be fine
           for most use cases. If your dataset is large (10M+ docs), you will likely
@@ -667,8 +664,8 @@ async def aindex(
         record_manager: Timestamped set to keep track of which documents were
             updated.
         vector_store: VectorStore or DocumentIndex to index the documents into.
-        batch_size: Batch size to use when indexing. Default is 100.
-        cleanup: How to handle clean up of documents. Default is None.
+        batch_size: Batch size to use when indexing.
+        cleanup: How to handle clean up of documents.
 
             - incremental: Cleans up all documents that haven't been updated AND
               that are associated with source ids that were seen during indexing.
@@ -683,15 +680,12 @@ async def aindex(
               source ids that were seen during indexing.
             - None: Do not delete any documents.
         source_id_key: Optional key that helps identify the original source
-            of the document. Default is None.
+            of the document.
         cleanup_batch_size: Batch size to use when cleaning up documents.
-            Default is 1_000.
         force_update: Force update documents even if they are present in the
             record manager. Useful if you are re-indexing with updated embeddings.
-            Default is False.
         key_encoder: Hashing algorithm to use for hashing the document content and
-            metadata. Default is "sha1".
-            Other options include "blake2b", "sha256", and "sha512".
+            metadata. Options include "blake2b", "sha256", and "sha512".
 
             !!! version-added "Added in version 0.3.66"
 
@@ -722,9 +716,9 @@ async def aindex(
         ValueError: If vectorstore does not have
             "adelete" and "aadd_documents" required methods.
         ValueError: If source_id_key is not None, but is not a string or callable.
-        TypeError: If ``vector_store`` is not a VectorStore or DocumentIndex.
-        AssertionError: If ``source_id_key`` is None when cleanup mode is
-            incremental or ``scoped_full`` (should be unreachable).
+        TypeError: If `vector_store` is not a VectorStore or DocumentIndex.
+        AssertionError: If `source_id_key` is None when cleanup mode is
+            incremental or `scoped_full` (should be unreachable).
     """
     # Behavior is deprecated, but we keep it for backwards compatibility.
     # # Warn only once per process.