langchain-core 1.0.0a8__py3-none-any.whl → 1.0.0rc1__py3-none-any.whl

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
@@ -215,7 +214,7 @@ class Blob(BaseMedia):
             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,
+            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
 
@@ -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

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

@@ -21,37 +21,34 @@ class FakeEmbeddings(Embeddings, BaseModel):
     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
@@ -78,37 +75,34 @@ class DeterministicFakeEmbedding(Embeddings, BaseModel):
     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/exceptions.py

@@ -33,19 +33,19 @@ class OutputParserException(ValueError, LangChainException):  # noqa: N818
         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.
                 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.
+                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
@@ -381,8 +381,8 @@ 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 +640,9 @@ 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 +656,7 @@ 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
@@ -722,9 +722,9 @@ 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.

langchain_core/indexing/base.py

@@ -61,7 +61,7 @@ class RecordManager(ABC):
         """Initialize the record manager.
 
         Args:
-            namespace (str): The namespace for the record manager.
+            namespace: The namespace for the record manager.
         """
         self.namespace = namespace
 
@@ -244,7 +244,7 @@ class InMemoryRecordManager(RecordManager):
         """Initialize the in-memory record manager.
 
         Args:
-            namespace (str): The namespace for the record manager.
+            namespace: The namespace for the record manager.
         """
         super().__init__(namespace)
         # Each key points to a dictionary
@@ -278,10 +278,10 @@ class InMemoryRecordManager(RecordManager):
         Args:
             keys: A list of record keys to upsert.
             group_ids: A list of group IDs corresponding to the keys.
-                Defaults to None.
+
             time_at_least: Optional timestamp. Implementation can use this
                 to optionally verify that the timestamp IS at least this time
-                in the system that stores. Defaults to None.
+                in the system that stores.
                 E.g., use to validate that the time in the postgres database
                 is equal to or larger than the given timestamp, if not
                 raise an error.
@@ -315,10 +315,10 @@ class InMemoryRecordManager(RecordManager):
         Args:
             keys: A list of record keys to upsert.
             group_ids: A list of group IDs corresponding to the keys.
-                Defaults to None.
+
             time_at_least: Optional timestamp. Implementation can use this
                 to optionally verify that the timestamp IS at least this time
-                in the system that stores. Defaults to None.
+                in the system that stores.
                 E.g., use to validate that the time in the postgres database
                 is equal to or larger than the given timestamp, if not
                 raise an error.
@@ -361,13 +361,13 @@ class InMemoryRecordManager(RecordManager):
 
         Args:
             before: Filter to list records updated before this time.
-                Defaults to None.
+
             after: Filter to list records updated after this time.
-                Defaults to None.
+
             group_ids: Filter to list records with specific group IDs.
-                Defaults to None.
+
             limit: optional limit on the number of records to return.
-                Defaults to None.
+
 
         Returns:
             A list of keys for the matching records.
@@ -397,13 +397,13 @@ class InMemoryRecordManager(RecordManager):
 
         Args:
             before: Filter to list records updated before this time.
-                Defaults to None.
+
             after: Filter to list records updated after this time.
-                Defaults to None.
+
             group_ids: Filter to list records with specific group IDs.
-                Defaults to None.
+
             limit: optional limit on the number of records to return.
-                Defaults to None.
+
 
         Returns:
             A list of keys for the matching records.
@@ -529,7 +529,7 @@ class DocumentIndex(BaseRetriever):
             **kwargs: Additional keyword arguments.
 
         Returns:
-            UpsertResponse: A response object that contains the list of IDs that were
+            A response object that contains the list of IDs that were
             successfully added or updated in the vectorstore and the list of IDs that
             failed to be added or updated.
         """
@@ -552,7 +552,7 @@ class DocumentIndex(BaseRetriever):
             **kwargs: Additional keyword arguments.
 
         Returns:
-            UpsertResponse: A response object that contains the list of IDs that were
+            A response object that contains the list of IDs that were
             successfully added or updated in the vectorstore and the list of IDs that
             failed to be added or updated.
         """
@@ -571,12 +571,12 @@ class DocumentIndex(BaseRetriever):
 
         Args:
             ids: List of ids to delete.
-            kwargs: Additional keyword arguments. This is up to the implementation.
+            **kwargs: Additional keyword arguments. This is up to the implementation.
                 For example, can include an option to delete the entire index,
                 or else issue a non-blocking delete etc.
 
         Returns:
-            DeleteResponse: A response object that contains the list of IDs that were
+            A response object that contains the list of IDs that were
             successfully deleted and the list of IDs that failed to be deleted.
         """
 
@@ -589,11 +589,11 @@ class DocumentIndex(BaseRetriever):
 
         Args:
             ids: List of ids to delete.
-            kwargs: Additional keyword arguments. This is up to the implementation.
+            **kwargs: Additional keyword arguments. This is up to the implementation.
                 For example, can include an option to delete the entire index.
 
         Returns:
-            DeleteResponse: A response object that contains the list of IDs that were
+            A response object that contains the list of IDs that were
             successfully deleted and the list of IDs that failed to be deleted.
         """
         return await run_in_executor(
@@ -624,10 +624,10 @@ class DocumentIndex(BaseRetriever):
 
         Args:
             ids: List of IDs to get.
-            kwargs: Additional keyword arguments. These are up to the implementation.
+            **kwargs: Additional keyword arguments. These are up to the implementation.
 
         Returns:
-            list[Document]: List of documents that were found.
+            List of documents that were found.
         """
 
     async def aget(
@@ -650,10 +650,10 @@ class DocumentIndex(BaseRetriever):
 
         Args:
             ids: List of IDs to get.
-            kwargs: Additional keyword arguments. These are up to the implementation.
+            **kwargs: Additional keyword arguments. These are up to the implementation.
 
         Returns:
-            list[Document]: List of documents that were found.
+            List of documents that were found.
         """
         return await run_in_executor(
             None,

langchain_core/language_models/__init__.py

@@ -38,8 +38,6 @@ To implement a custom LLM, inherit from `BaseLLM` or `LLM`.
 Please see the following guide for more information on how to implement a custom LLM:
 
 https://python.langchain.com/docs/how_to/custom_llm/
-
-
 """
 
 from typing import TYPE_CHECKING