langchain-core 1.0.0a5__py3-none-any.whl → 1.0.0a7__py3-none-any.whl

langchain_core/document_loaders/langsmith.py

@@ -3,8 +3,8 @@
 import datetime
 import json
 import uuid
-from collections.abc import Iterator, Sequence
-from typing import Any, Callable, Optional, Union
+from collections.abc import Callable, Iterator, Sequence
+from typing import Any
 
 from langsmith import Client as LangSmithClient
 from typing_extensions import override
@@ -20,7 +20,7 @@ class LangSmithLoader(BaseLoader):
     into the Document metadata. This allows you to easily create few-shot example
     retrievers from the loaded documents.
 
-    .. dropdown:: Lazy load
+    ??? note "Lazy load"
 
         .. code-block:: python
 
@@ -35,26 +35,26 @@ class LangSmithLoader(BaseLoader):
 
             # -> [Document("...", metadata={"inputs": {...}, "outputs": {...}, ...}), ...]
 
-    .. versionadded:: 0.2.34
+    !!! version-added "Added in version 0.2.34"
 
     """  # noqa: E501
 
     def __init__(
         self,
         *,
-        dataset_id: Optional[Union[uuid.UUID, str]] = None,
-        dataset_name: Optional[str] = None,
-        example_ids: Optional[Sequence[Union[uuid.UUID, str]]] = None,
-        as_of: Optional[Union[datetime.datetime, str]] = None,
-        splits: Optional[Sequence[str]] = None,
+        dataset_id: uuid.UUID | str | None = None,
+        dataset_name: str | None = None,
+        example_ids: Sequence[uuid.UUID | str] | None = None,
+        as_of: datetime.datetime | str | None = None,
+        splits: Sequence[str] | None = None,
         inline_s3_urls: bool = True,
         offset: int = 0,
-        limit: Optional[int] = None,
-        metadata: Optional[dict] = None,
-        filter: Optional[str] = None,  # noqa: A002
+        limit: int | None = None,
+        metadata: dict | None = None,
+        filter: str | None = None,  # noqa: A002
         content_key: str = "",
-        format_content: Optional[Callable[..., str]] = None,
-        client: Optional[LangSmithClient] = None,
+        format_content: Callable[..., str] | None = None,
+        client: LangSmithClient | None = None,
         **client_kwargs: Any,
     ) -> None:
         """Create a LangSmith loader.
@@ -129,7 +129,7 @@ class LangSmithLoader(BaseLoader):
             yield Document(content_str, metadata=metadata)
 
 
-def _stringify(x: Union[str, dict]) -> str:
+def _stringify(x: str | dict) -> str:
     if isinstance(x, str):
         return x
     try:

langchain_core/documents/base.py

@@ -6,7 +6,7 @@ import contextlib
 import mimetypes
 from io import BufferedReader, BytesIO
 from pathlib import Path, PurePath
-from typing import TYPE_CHECKING, Any, Literal, Optional, Union, cast
+from typing import TYPE_CHECKING, Any, Literal, cast
 
 from pydantic import ConfigDict, Field, model_validator
 
@@ -15,7 +15,7 @@ from langchain_core.load.serializable import Serializable
 if TYPE_CHECKING:
     from collections.abc import Generator
 
-PathLike = Union[str, PurePath]
+PathLike = str | PurePath
 
 
 class BaseMedia(Serializable):
@@ -33,13 +33,13 @@ class BaseMedia(Serializable):
     # The ID field is optional at the moment.
     # It will likely become required in a future major release after
     # it has been adopted by enough vectorstore implementations.
-    id: Optional[str] = Field(default=None, coerce_numbers_to_str=True)
+    id: str | None = Field(default=None, coerce_numbers_to_str=True)
     """An optional identifier for the document.
 
     Ideally this should be unique across the document collection and formatted
     as a UUID, but this will not be enforced.
 
-    .. versionadded:: 0.2.11
+    !!! version-added "Added in version 0.2.11"
     """
 
     metadata: dict = Field(default_factory=dict)
@@ -105,16 +105,16 @@ class Blob(BaseMedia):
 
     """
 
-    data: Union[bytes, str, None] = None
+    data: bytes | str | None = None
     """Raw data associated with the blob."""
-    mimetype: Optional[str] = None
+    mimetype: str | None = None
     """MimeType not to be confused with a file extension."""
     encoding: str = "utf-8"
     """Encoding to use if decoding the bytes into a string.
 
     Use utf-8 as default encoding, if decoding to string.
     """
-    path: Optional[PathLike] = None
+    path: PathLike | None = None
     """Location where the original content was found."""
 
     model_config = ConfigDict(
@@ -123,7 +123,7 @@ class Blob(BaseMedia):
     )
 
     @property
-    def source(self) -> Optional[str]:
+    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.
@@ -132,7 +132,7 @@ class Blob(BaseMedia):
         case that value will be used instead.
         """
         if self.metadata and "source" in self.metadata:
-            return cast("Optional[str]", self.metadata["source"])
+            return cast("str | None", self.metadata["source"])
         return str(self.path) if self.path else None
 
     @model_validator(mode="before")
@@ -181,7 +181,7 @@ class Blob(BaseMedia):
         raise ValueError(msg)
 
     @contextlib.contextmanager
-    def as_bytes_io(self) -> Generator[Union[BytesIO, BufferedReader], None, None]:
+    def as_bytes_io(self) -> Generator[BytesIO | BufferedReader, None, None]:
         """Read data as a byte stream.
 
         Raises:
@@ -205,9 +205,9 @@ class Blob(BaseMedia):
         path: PathLike,
         *,
         encoding: str = "utf-8",
-        mime_type: Optional[str] = None,
+        mime_type: str | None = None,
         guess_type: bool = True,
-        metadata: Optional[dict] = None,
+        metadata: dict | None = None,
     ) -> Blob:
         """Load the blob from a path like object.
 
@@ -239,12 +239,12 @@ class Blob(BaseMedia):
     @classmethod
     def from_data(
         cls,
-        data: Union[str, bytes],
+        data: str | bytes,
         *,
         encoding: str = "utf-8",
-        mime_type: Optional[str] = None,
-        path: Optional[str] = None,
-        metadata: Optional[dict] = None,
+        mime_type: str | None = None,
+        path: str | None = None,
+        metadata: dict | None = None,
     ) -> Blob:
         """Initialize the blob from in-memory data.
 

langchain_core/documents/compressor.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from abc import ABC, abstractmethod
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING
 
 from pydantic import BaseModel
 
@@ -27,7 +27,7 @@ class BaseDocumentCompressor(BaseModel, ABC):
 
     For example, one could re-rank the retrieved documents using an LLM.
 
-    .. note::
+    !!! note
         Users should favor using a RunnableLambda instead of sub-classing from this
         interface.
 
@@ -38,7 +38,7 @@ class BaseDocumentCompressor(BaseModel, ABC):
         self,
         documents: Sequence[Document],
         query: str,
-        callbacks: Optional[Callbacks] = None,
+        callbacks: Callbacks | None = None,
     ) -> Sequence[Document]:
         """Compress retrieved documents given the query context.
 
@@ -56,7 +56,7 @@ class BaseDocumentCompressor(BaseModel, ABC):
         self,
         documents: Sequence[Document],
         query: str,
-        callbacks: Optional[Callbacks] = None,
+        callbacks: Callbacks | None = None,
     ) -> Sequence[Document]:
         """Async compress retrieved documents given the query context.
 

langchain_core/example_selectors/length_based.py

@@ -1,7 +1,7 @@
 """Select examples based on length."""
 
 import re
-from typing import Callable
+from collections.abc import Callable
 
 from pydantic import BaseModel, Field, model_validator
 from typing_extensions import Self

langchain_core/example_selectors/semantic_similarity.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from abc import ABC
-from typing import TYPE_CHECKING, Any, Optional
+from typing import TYPE_CHECKING, Any
 
 from pydantic import BaseModel, ConfigDict
 
@@ -35,12 +35,12 @@ class _VectorStoreExampleSelector(BaseExampleSelector, BaseModel, ABC):
     """VectorStore that contains information about examples."""
     k: int = 4
     """Number of examples to select."""
-    example_keys: Optional[list[str]] = None
+    example_keys: list[str] | None = None
     """Optional keys to filter examples to."""
-    input_keys: Optional[list[str]] = None
+    input_keys: list[str] | None = None
     """Optional keys to filter input to. If provided, the search is based on
     the input variables instead of all variables."""
-    vectorstore_kwargs: Optional[dict[str, Any]] = None
+    vectorstore_kwargs: dict[str, Any] | None = None
     """Extra arguments passed to similarity_search function of the vectorstore."""
 
     model_config = ConfigDict(
@@ -49,9 +49,7 @@ class _VectorStoreExampleSelector(BaseExampleSelector, BaseModel, ABC):
     )
 
     @staticmethod
-    def _example_to_text(
-        example: dict[str, str], input_keys: Optional[list[str]]
-    ) -> str:
+    def _example_to_text(example: dict[str, str], input_keys: list[str] | None) -> str:
         if input_keys:
             return " ".join(sorted_values({key: example[key] for key in input_keys}))
         return " ".join(sorted_values(example))
@@ -142,10 +140,10 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
         embeddings: Embeddings,
         vectorstore_cls: type[VectorStore],
         k: int = 4,
-        input_keys: Optional[list[str]] = None,
+        input_keys: list[str] | None = None,
         *,
-        example_keys: Optional[list[str]] = None,
-        vectorstore_kwargs: Optional[dict] = None,
+        example_keys: list[str] | None = None,
+        vectorstore_kwargs: dict | None = None,
         **vectorstore_cls_kwargs: Any,
     ) -> SemanticSimilarityExampleSelector:
         """Create k-shot example selector using example list and embeddings.
@@ -186,10 +184,10 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
         embeddings: Embeddings,
         vectorstore_cls: type[VectorStore],
         k: int = 4,
-        input_keys: Optional[list[str]] = None,
+        input_keys: list[str] | None = None,
         *,
-        example_keys: Optional[list[str]] = None,
-        vectorstore_kwargs: Optional[dict] = None,
+        example_keys: list[str] | None = None,
+        vectorstore_kwargs: dict | None = None,
         **vectorstore_cls_kwargs: Any,
     ) -> SemanticSimilarityExampleSelector:
         """Async create k-shot example selector using example list and embeddings.
@@ -273,10 +271,10 @@ class MaxMarginalRelevanceExampleSelector(_VectorStoreExampleSelector):
         embeddings: Embeddings,
         vectorstore_cls: type[VectorStore],
         k: int = 4,
-        input_keys: Optional[list[str]] = None,
+        input_keys: list[str] | None = None,
         fetch_k: int = 20,
-        example_keys: Optional[list[str]] = None,
-        vectorstore_kwargs: Optional[dict] = None,
+        example_keys: list[str] | None = None,
+        vectorstore_kwargs: dict | None = None,
         **vectorstore_cls_kwargs: Any,
     ) -> MaxMarginalRelevanceExampleSelector:
         """Create k-shot example selector using example list and embeddings.
@@ -321,10 +319,10 @@ class MaxMarginalRelevanceExampleSelector(_VectorStoreExampleSelector):
         vectorstore_cls: type[VectorStore],
         *,
         k: int = 4,
-        input_keys: Optional[list[str]] = None,
+        input_keys: list[str] | None = None,
         fetch_k: int = 20,
-        example_keys: Optional[list[str]] = None,
-        vectorstore_kwargs: Optional[dict] = None,
+        example_keys: list[str] | None = None,
+        vectorstore_kwargs: dict | None = None,
         **vectorstore_cls_kwargs: Any,
     ) -> MaxMarginalRelevanceExampleSelector:
         """Create k-shot example selector using example list and embeddings.

langchain_core/exceptions.py

@@ -1,7 +1,7 @@
 """Custom **exceptions** for LangChain."""
 
 from enum import Enum
-from typing import Any, Optional
+from typing import Any
 
 
 class LangChainException(Exception):  # noqa: N818
@@ -24,8 +24,8 @@ class OutputParserException(ValueError, LangChainException):  # noqa: N818
     def __init__(
         self,
         error: Any,
-        observation: Optional[str] = None,
-        llm_output: Optional[str] = None,
+        observation: str | None = None,
+        llm_output: str | None = None,
         send_to_llm: bool = False,  # noqa: FBT001,FBT002
     ):
         """Create an OutputParserException.

langchain_core/globals.py

@@ -1,18 +1,10 @@
 """Global values and configuration that apply to all of LangChain."""
 
-import warnings
 from typing import TYPE_CHECKING, Optional
 
 if TYPE_CHECKING:
     from langchain_core.caches import BaseCache
 
-try:
-    import langchain  # type: ignore[import-not-found]
-
-    _HAS_LANGCHAIN = True
-except ImportError:
-    _HAS_LANGCHAIN = False
-
 
 # DO NOT USE THESE VALUES DIRECTLY!
 # Use them only via `get_<X>()` and `set_<X>()` below,
@@ -29,26 +21,6 @@ def set_verbose(value: bool) -> None:  # noqa: FBT001
     Args:
         value: The new value for the `verbose` global setting.
     """
-    if _HAS_LANGCHAIN:
-        # We're about to run some deprecated code, don't report warnings from it.
-        # The user called the correct (non-deprecated) code path and shouldn't get
-        # warnings.
-        with warnings.catch_warnings():
-            warnings.filterwarnings(
-                "ignore",
-                message=(
-                    "Importing verbose from langchain root module "
-                    "is no longer supported"
-                ),
-            )
-            # N.B.: This is a workaround for an unfortunate quirk of Python's
-            #       module-level `__getattr__()` implementation:
-            # https://github.com/langchain-ai/langchain/pull/11311#issuecomment-1743780004
-            #
-            # Remove it once `langchain.verbose` is no longer supported, and once all
-            # users have migrated to using `set_verbose()` here.
-            langchain.verbose = value
-
     global _verbose  # noqa: PLW0603
     _verbose = value
 
@@ -59,35 +31,7 @@ def get_verbose() -> bool:
     Returns:
         The value of the `verbose` global setting.
     """
-    if _HAS_LANGCHAIN:
-        # We're about to run some deprecated code, don't report warnings from it.
-        # The user called the correct (non-deprecated) code path and shouldn't get
-        # warnings.
-        with warnings.catch_warnings():
-            warnings.filterwarnings(
-                "ignore",
-                message=(
-                    ".*Importing verbose from langchain root module "
-                    "is no longer supported"
-                ),
-            )
-            # N.B.: This is a workaround for an unfortunate quirk of Python's
-            #       module-level `__getattr__()` implementation:
-            # https://github.com/langchain-ai/langchain/pull/11311#issuecomment-1743780004
-            #
-            # Remove it once `langchain.verbose` is no longer supported, and once all
-            # users have migrated to using `set_verbose()` here.
-            #
-            # In the meantime, the `verbose` setting is considered True if either the
-            # old or the new value are True. This accommodates users who haven't
-            # migrated to using `set_verbose()` yet. Those users are getting
-            # deprecation warnings directing them to use `set_verbose()` when they
-            # import `langchain.verbose`.
-            old_verbose = langchain.verbose
-    else:
-        old_verbose = False
-
-    return _verbose or old_verbose
+    return _verbose
 
 
 def set_debug(value: bool) -> None:  # noqa: FBT001
@@ -96,24 +40,6 @@ def set_debug(value: bool) -> None:  # noqa: FBT001
     Args:
         value: The new value for the `debug` global setting.
     """
-    if _HAS_LANGCHAIN:
-        # We're about to run some deprecated code, don't report warnings from it.
-        # The user called the correct (non-deprecated) code path and shouldn't get
-        # warnings.
-        with warnings.catch_warnings():
-            warnings.filterwarnings(
-                "ignore",
-                message="Importing debug from langchain root module "
-                "is no longer supported",
-            )
-            # N.B.: This is a workaround for an unfortunate quirk of Python's
-            #       module-level `__getattr__()` implementation:
-            # https://github.com/langchain-ai/langchain/pull/11311#issuecomment-1743780004
-            #
-            # Remove it once `langchain.debug` is no longer supported, and once all
-            # users have migrated to using `set_debug()` here.
-            langchain.debug = value
-
     global _debug  # noqa: PLW0603
     _debug = value
 
@@ -124,32 +50,7 @@ def get_debug() -> bool:
     Returns:
         The value of the `debug` global setting.
     """
-    if _HAS_LANGCHAIN:
-        # We're about to run some deprecated code, don't report warnings from it.
-        # The user called the correct (non-deprecated) code path and shouldn't get
-        # warnings.
-        with warnings.catch_warnings():
-            warnings.filterwarnings(
-                "ignore",
-                message="Importing debug from langchain root module "
-                "is no longer supported",
-            )
-            # N.B.: This is a workaround for an unfortunate quirk of Python's
-            #       module-level `__getattr__()` implementation:
-            # https://github.com/langchain-ai/langchain/pull/11311#issuecomment-1743780004
-            #
-            # Remove it once `langchain.debug` is no longer supported, and once all
-            # users have migrated to using `set_debug()` here.
-            #
-            # In the meantime, the `debug` setting is considered True if either the old
-            # or the new value are True. This accommodates users who haven't migrated
-            # to using `set_debug()` yet. Those users are getting deprecation warnings
-            # directing them to use `set_debug()` when they import `langchain.debug`.
-            old_debug = langchain.debug
-    else:
-        old_debug = False
-
-    return _debug or old_debug
+    return _debug
 
 
 def set_llm_cache(value: Optional["BaseCache"]) -> None:
@@ -158,26 +59,6 @@ def set_llm_cache(value: Optional["BaseCache"]) -> None:
     Args:
         value: The new LLM cache to use. If `None`, the LLM cache is disabled.
     """
-    if _HAS_LANGCHAIN:
-        # We're about to run some deprecated code, don't report warnings from it.
-        # The user called the correct (non-deprecated) code path and shouldn't get
-        # warnings.
-        with warnings.catch_warnings():
-            warnings.filterwarnings(
-                "ignore",
-                message=(
-                    "Importing llm_cache from langchain root module "
-                    "is no longer supported"
-                ),
-            )
-            # N.B.: This is a workaround for an unfortunate quirk of Python's
-            #       module-level `__getattr__()` implementation:
-            # https://github.com/langchain-ai/langchain/pull/11311#issuecomment-1743780004
-            #
-            # Remove it once `langchain.llm_cache` is no longer supported, and
-            # once all users have migrated to using `set_llm_cache()` here.
-            langchain.llm_cache = value
-
     global _llm_cache  # noqa: PLW0603
     _llm_cache = value
 
@@ -188,33 +69,4 @@ def get_llm_cache() -> Optional["BaseCache"]:
     Returns:
         The value of the `llm_cache` global setting.
     """
-    if _HAS_LANGCHAIN:
-        # We're about to run some deprecated code, don't report warnings from it.
-        # The user called the correct (non-deprecated) code path and shouldn't get
-        # warnings.
-        with warnings.catch_warnings():
-            warnings.filterwarnings(
-                "ignore",
-                message=(
-                    "Importing llm_cache from langchain root module "
-                    "is no longer supported"
-                ),
-            )
-            # N.B.: This is a workaround for an unfortunate quirk of Python's
-            #       module-level `__getattr__()` implementation:
-            # https://github.com/langchain-ai/langchain/pull/11311#issuecomment-1743780004
-            #
-            # Remove it once `langchain.llm_cache` is no longer supported, and
-            # once all users have migrated to using `set_llm_cache()` here.
-            #
-            # In the meantime, the `llm_cache` setting returns whichever of
-            # its two backing sources is truthy (not `None` and non-empty),
-            # or the old value if both are falsy. This accommodates users
-            # who haven't migrated to using `set_llm_cache()` yet.
-            # Those users are getting deprecation warnings directing them
-            # to use `set_llm_cache()` when they import `langchain.llm_cache`.
-            old_llm_cache = langchain.llm_cache
-    else:
-        old_llm_cache = None
-
-    return _llm_cache or old_llm_cache
+    return _llm_cache