langchain-core 0.3.71__tar.gz → 0.3.73__tar.gz

{langchain_core-0.3.71 → langchain_core-0.3.73}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langchain-core
-Version: 0.3.71
+Version: 0.3.73
 Summary: Building applications with LLMs through composability
 License: MIT
 Project-URL: Source Code, https://github.com/langchain-ai/langchain/tree/master/libs/core

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/__init__.py

@@ -4,7 +4,7 @@ The interfaces for core components like chat models, LLMs, vector stores, retrie
 and more are defined here. The universal invocation protocol (Runnables) along with
 a syntax for combining components (LangChain Expression Language) are also defined here.
 
-No third-party integrations are defined here. The dependencies are kept purposefully
+**No third-party integrations are defined here.** The dependencies are kept purposefully
 very lightweight.
 """
 

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/_api/beta_decorator.py

@@ -70,6 +70,7 @@ def beta(
             @beta
             def the_function_to_annotate():
                 pass
+
     """
 
     def beta(

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/_api/deprecation.py

@@ -136,6 +136,7 @@ def deprecated(
             @deprecated('1.4.0')
             def the_function_to_deprecate():
                 pass
+
     """
     _validate_deprecation_params(
         removal, alternative, alternative_import, pending=pending
@@ -549,6 +550,7 @@ def rename_parameter(
 
             @_api.rename_parameter("3.1", "bad_name", "good_name")
             def func(good_name): ...
+
     """
 
     def decorator(f: Callable[_P, _R]) -> Callable[_P, _R]:

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/beta/runnables/context.py

@@ -363,6 +363,7 @@ class Context:
             print(output["result"])  # Output: "hello"
             print(output["context"])  # Output: "What's your name?"
             print(output["input"])  # Output: "What's your name?
+
     """
 
     @staticmethod

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/callbacks/file.py

@@ -53,6 +53,7 @@ class FileCallbackHandler(BaseCallbackHandler):
         When not used as a context manager, a deprecation warning will be issued
         on first use. The file will be opened immediately in ``__init__`` and closed
         in ``__del__`` or when ``close()`` is called explicitly.
+
     """
 
     def __init__(

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/callbacks/manager.py

@@ -105,6 +105,7 @@ def trace_as_chain_group(
                 # Use the callback manager for the chain group
                 res = llm.invoke(llm_input, {"callbacks": manager})
                 manager.on_chain_end({"output": res})
+
     """  # noqa: E501
     from langchain_core.tracers.context import _get_trace_callbacks
 
@@ -186,6 +187,7 @@ async def atrace_as_chain_group(
                 # Use the async callback manager for the chain group
                 res = await llm.ainvoke(llm_input, {"callbacks": manager})
                 await manager.on_chain_end({"output": res})
+
     """  # noqa: E501
     from langchain_core.tracers.context import _get_trace_callbacks
 
@@ -2575,6 +2577,7 @@ async def adispatch_custom_event(
         behalf.
 
     .. versionadded:: 0.2.15
+
     """
     from langchain_core.runnables.config import (
         ensure_config,
@@ -2645,6 +2648,7 @@ def dispatch_custom_event(
             foo_.invoke({"a": "1"}, {"callbacks": [CustomCallbackManager()]})
 
     .. versionadded:: 0.2.15
+
     """
     from langchain_core.runnables.config import (
         ensure_config,

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/callbacks/usage.py

@@ -44,6 +44,7 @@ class UsageMetadataCallbackHandler(BaseCallbackHandler):
               'input_token_details': {'cache_read': 0, 'cache_creation': 0}}}
 
     .. versionadded:: 0.3.49
+
     """
 
     def __init__(self) -> None:
@@ -98,7 +99,7 @@ def get_usage_metadata_callback(
 
     Args:
         name (str): The name of the context variable. Defaults to
-            ``"usage_metadata_callback"``.
+            ``'usage_metadata_callback'``.
 
     Example:
         .. code-block:: python
@@ -127,6 +128,7 @@ def get_usage_metadata_callback(
               'input_token_details': {'cache_read': 0, 'cache_creation': 0}}}
 
     .. versionadded:: 0.3.49
+
     """
     from langchain_core.tracers.context import register_configure_hook
 

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/chat_history.py

@@ -91,6 +91,7 @@ class BaseChatMessageHistory(ABC):
                 def clear(self):
                     with open(os.path.join(storage_path, session_id), "w") as f:
                         f.write("[]")
+
     """
 
     messages: list[BaseMessage]

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/document_loaders/langsmith.py

@@ -36,6 +36,7 @@ class LangSmithLoader(BaseLoader):
             # -> [Document("...", metadata={"inputs": {...}, "outputs": {...}, ...}), ...]
 
     .. versionadded:: 0.2.34
+
     """  # noqa: E501
 
     def __init__(
@@ -61,7 +62,7 @@ class LangSmithLoader(BaseLoader):
         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
+            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"]))``

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/documents/base.py

@@ -102,6 +102,7 @@ class Blob(BaseMedia):
             # Read the blob as a byte stream
             with blob.as_bytes_io() as f:
                 print(f.read())
+
     """
 
     data: Union[bytes, str, None] = None
@@ -265,6 +266,7 @@ class Document(BaseMedia):
                 page_content="Hello, world!",
                 metadata={"source": "https://example.com"}
             )
+
     """
 
     page_content: str

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/embeddings/fake.py

@@ -46,6 +46,7 @@ class FakeEmbeddings(Embeddings, BaseModel):
 
             2
             [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257]
+
     """
 
     size: int
@@ -103,6 +104,7 @@ class DeterministicFakeEmbedding(Embeddings, BaseModel):
 
             2
             [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257]
+
     """
 
     size: int

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/indexing/api.py

@@ -444,6 +444,9 @@ def index(
     scoped_full_cleanup_source_ids: set[str] = set()
 
     for doc_batch in _batch(batch_size, doc_iterator):
+        # Track original batch size before deduplication
+        original_batch_size = len(doc_batch)
+
         hashed_docs = list(
             _deduplicate_in_order(
                 [
@@ -452,6 +455,8 @@ def index(
                 ]
             )
         )
+        # Count documents removed by within-batch deduplication
+        num_skipped += original_batch_size - len(hashed_docs)
 
         source_ids: Sequence[Optional[str]] = [
             source_id_assigner(hashed_doc) for hashed_doc in hashed_docs
@@ -784,6 +789,9 @@ async def aindex(
     scoped_full_cleanup_source_ids: set[str] = set()
 
     async for doc_batch in _abatch(batch_size, async_doc_iterator):
+        # Track original batch size before deduplication
+        original_batch_size = len(doc_batch)
+
         hashed_docs = list(
             _deduplicate_in_order(
                 [
@@ -792,6 +800,8 @@ async def aindex(
                 ]
             )
         )
+        # Count documents removed by within-batch deduplication
+        num_skipped += original_batch_size - len(hashed_docs)
 
         source_ids: Sequence[Optional[str]] = [
             source_id_assigner(doc) for doc in hashed_docs

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/language_models/_utils.py

@@ -51,6 +51,7 @@ def _parse_data_uri(uri: str) -> Optional[dict]:
                 "mime_type": "image/jpeg",
                 "data": "/9j/4AAQSkZJRg...",
             }
+
     """
     regex = r"^data:(?P<mime_type>[^;]+);base64,(?P<data>.+)$"
     match = re.match(regex, uri)

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/language_models/chat_models.py

@@ -11,22 +11,9 @@ from abc import ABC, abstractmethod
 from collections.abc import AsyncIterator, Iterator, Sequence
 from functools import cached_property
 from operator import itemgetter
-from typing import (
-    TYPE_CHECKING,
-    Any,
-    Callable,
-    Literal,
-    Optional,
-    Union,
-    cast,
-)
+from typing import TYPE_CHECKING, Any, Callable, Literal, Optional, Union, cast
 
-from pydantic import (
-    BaseModel,
-    ConfigDict,
-    Field,
-    model_validator,
-)
+from pydantic import BaseModel, ConfigDict, Field, model_validator
 from typing_extensions import override
 
 from langchain_core._api import deprecated
@@ -63,6 +50,7 @@ from langchain_core.outputs import (
     ChatGeneration,
     ChatGenerationChunk,
     ChatResult,
+    Generation,
     LLMResult,
     RunInfo,
 )
@@ -653,6 +641,44 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
     def _combine_llm_outputs(self, llm_outputs: list[Optional[dict]]) -> dict:  # noqa: ARG002
         return {}
 
+    def _convert_cached_generations(self, cache_val: list) -> list[ChatGeneration]:
+        """Convert cached Generation objects to ChatGeneration objects.
+
+        Handle case where cache contains Generation objects instead of
+        ChatGeneration objects. This can happen due to serialization/deserialization
+        issues or legacy cache data (see #22389).
+
+        Args:
+            cache_val: List of cached generation objects.
+
+        Returns:
+            List of ChatGeneration objects.
+        """
+        converted_generations = []
+        for gen in cache_val:
+            if isinstance(gen, Generation) and not isinstance(gen, ChatGeneration):
+                # Convert Generation to ChatGeneration by creating AIMessage
+                # from the text content
+                chat_gen = ChatGeneration(
+                    message=AIMessage(content=gen.text),
+                    generation_info=gen.generation_info,
+                )
+                converted_generations.append(chat_gen)
+            else:
+                # Already a ChatGeneration or other expected type
+                if hasattr(gen, "message") and isinstance(gen.message, AIMessage):
+                    # We zero out cost on cache hits
+                    gen.message = gen.message.model_copy(
+                        update={
+                            "usage_metadata": {
+                                **(gen.message.usage_metadata or {}),
+                                "total_cost": 0,
+                            }
+                        }
+                    )
+                converted_generations.append(gen)
+        return converted_generations
+
     def _get_invocation_params(
         self,
         stop: Optional[list[str]] = None,
@@ -1010,7 +1036,8 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
                 prompt = dumps(messages)
                 cache_val = llm_cache.lookup(prompt, llm_string)
                 if isinstance(cache_val, list):
-                    return ChatResult(generations=cache_val)
+                    converted_generations = self._convert_cached_generations(cache_val)
+                    return ChatResult(generations=converted_generations)
             elif self.cache is None:
                 pass
             else:
@@ -1082,7 +1109,8 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
                 prompt = dumps(messages)
                 cache_val = await llm_cache.alookup(prompt, llm_string)
                 if isinstance(cache_val, list):
-                    return ChatResult(generations=cache_val)
+                    converted_generations = self._convert_cached_generations(cache_val)
+                    return ChatResult(generations=converted_generations)
             elif self.cache is None:
                 pass
             else:
@@ -1367,12 +1395,13 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
         """Model wrapper that returns outputs formatted to match the given schema.
 
         Args:
-            schema:
-                The output schema. Can be passed in as:
-                    - an OpenAI function/tool schema,
-                    - a JSON Schema,
-                    - a TypedDict class,
-                    - or a Pydantic class.
+            schema: The output schema. Can be passed in as:
+
+                - an OpenAI function/tool schema,
+                - a JSON Schema,
+                - a TypedDict class,
+                - or a Pydantic class.
+
                 If ``schema`` is a Pydantic class then the model output will be a
                 Pydantic instance of that class, and the model-generated fields will be
                 validated by the Pydantic class. Otherwise the model output will be a
@@ -1386,7 +1415,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
                 then both the raw model response (a BaseMessage) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
-                with keys "raw", "parsed", and "parsing_error".
+                with keys ``'raw'``, ``'parsed'``, and ``'parsing_error'``.
 
         Returns:
             A Runnable that takes same inputs as a :class:`langchain_core.language_models.chat.BaseChatModel`.
@@ -1397,9 +1426,10 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
             Otherwise, if ``include_raw`` is False then Runnable outputs a dict.
 
             If ``include_raw`` is True, then Runnable outputs a dict with keys:
-                - ``"raw"``: BaseMessage
-                - ``"parsed"``: None if there was a parsing error, otherwise the type depends on the ``schema`` as described above.
-                - ``"parsing_error"``: Optional[BaseException]
+
+            - ``'raw'``: BaseMessage
+            - ``'parsed'``: None if there was a parsing error, otherwise the type depends on the ``schema`` as described above.
+            - ``'parsing_error'``: Optional[BaseException]
 
         Example: Pydantic schema (include_raw=False):
             .. code-block:: python
@@ -1465,6 +1495,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
         .. versionchanged:: 0.2.26
 
                 Added support for TypedDict class.
+
         """  # noqa: E501
         _ = kwargs.pop("method", None)
         _ = kwargs.pop("strict", None)

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/language_models/llms.py

@@ -1418,6 +1418,7 @@ class BaseLLM(BaseLanguageModel[str], ABC):
             .. code-block:: python
 
                 llm.save(file_path="path/llm.yaml")
+
         """
         # Convert file to Path object.
         save_path = Path(file_path)

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/memory.py

@@ -53,6 +53,7 @@ class BaseMemory(Serializable, ABC):
 
                 def clear(self) -> None:
                     pass
+
     """  # noqa: E501
 
     model_config = ConfigDict(

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/messages/ai.py

@@ -57,6 +57,7 @@ class InputTokenDetails(TypedDict, total=False):
     .. versionadded:: 0.3.9
 
     May also hold extra provider-specific keys.
+
     """
 
     audio: int
@@ -89,6 +90,7 @@ class OutputTokenDetails(TypedDict, total=False):
             }
 
     .. versionadded:: 0.3.9
+
     """
 
     audio: int
@@ -128,6 +130,7 @@ class UsageMetadata(TypedDict):
     .. versionchanged:: 0.3.9
 
         Added ``input_token_details`` and ``output_token_details``.
+
     """
 
     input_tokens: int

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/messages/human.py

@@ -28,6 +28,7 @@ class HumanMessage(BaseMessage):
             # Instantiate a chat model and invoke it with the messages
             model = ...
             print(model.invoke(messages))
+
     """
 
     example: bool = False

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/messages/tool.py

@@ -59,6 +59,7 @@ class ToolMessage(BaseMessage, ToolOutputMixin):
     The tool_call_id field is used to associate the tool call request with the
     tool call response. This is useful in situations where a chat model is able
     to request multiple tool calls in parallel.
+
     """  # noqa: E501
 
     tool_call_id: str
@@ -191,6 +192,7 @@ class ToolCall(TypedDict):
 
         This represents a request to call the tool named "foo" with arguments {"a": 1}
         and an identifier of "123".
+
     """
 
     name: str
@@ -240,6 +242,7 @@ class ToolCallChunk(TypedDict):
             AIMessageChunk(content="", tool_call_chunks=left_chunks)
             + AIMessageChunk(content="", tool_call_chunks=right_chunks)
         ).tool_call_chunks == [ToolCallChunk(name='foo', args='{"a":1}', index=0)]
+
     """
 
     name: Optional[str]

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/messages/utils.py

@@ -111,6 +111,7 @@ def get_buffer_string(
             ]
             get_buffer_string(messages)
             # -> "Human: Hi, how are you?\nAI: Good, how are you?"
+
     """
     string_messages = []
     for m in messages:
@@ -463,6 +464,7 @@ def filter_messages(
                 SystemMessage("you're a good assistant."),
                 HumanMessage("what's your name", id="foo", name="example_user"),
             ]
+
     """  # noqa: E501
     messages = convert_to_messages(messages)
     filtered: list[BaseMessage] = []
@@ -869,6 +871,7 @@ def trim_messages(
                     HumanMessage("This is a 4 token text. The full message is 10 tokens.", id="first"),
                     AIMessage( [{"type": "text", "text": "This is the FIRST 4 token block."}], id="second"),
                 ]
+
     """  # noqa: E501
     # Validate arguments
     if start_on and strategy == "first":
@@ -1176,7 +1179,9 @@ def convert_to_openai_messages(
                                 "id": block["id"],
                                 "function": {
                                     "name": block["name"],
-                                    "arguments": json.dumps(block["input"]),
+                                    "arguments": json.dumps(
+                                        block["input"], ensure_ascii=False
+                                    ),
                                 },
                             }
                         )
@@ -1550,7 +1555,7 @@ def _convert_to_openai_tool_calls(tool_calls: list[ToolCall]) -> list[dict]:
             "id": tool_call["id"],
             "function": {
                 "name": tool_call["name"],
-                "arguments": json.dumps(tool_call["args"]),
+                "arguments": json.dumps(tool_call["args"], ensure_ascii=False),
             },
         }
         for tool_call in tool_calls

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/output_parsers/base.py

@@ -155,6 +155,7 @@ class BaseOutputParser(
                 @property
                 def _type(self) -> str:
                     return "boolean_output_parser"
+
     """  # noqa: E501
 
     @property

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/output_parsers/openai_functions.py

@@ -214,6 +214,7 @@ class PydanticOutputFunctionsParser(OutputFunctionsParser):
                 pydantic_schema={"cookie": Cookie, "dog": Dog}
             )
             result = parser.parse_result([chat_generation])
+
     """
 
     pydantic_schema: Union[type[BaseModel], dict[str, type[BaseModel]]]

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/outputs/llm_result.py

@@ -46,7 +46,10 @@ class LLMResult(BaseModel):
     relevant information from standardized fields present in AIMessage.
     """
     run: Optional[list[RunInfo]] = None
-    """List of metadata info for model call for each input."""
+    """List of metadata info for model call for each input.
+
+    See :class:`~langchain_core.outputs.run_info.RunInfo` for details.
+    """
 
     type: Literal["LLMResult"] = "LLMResult"
     """Type is used exclusively for serialization purposes."""

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/prompts/base.py

@@ -307,6 +307,7 @@ class BasePromptTemplate(
         .. code-block:: python
 
             prompt.format(variable1="foo")
+
         """
 
     async def aformat(self, **kwargs: Any) -> FormatOutputType:
@@ -323,6 +324,7 @@ class BasePromptTemplate(
         .. code-block:: python
 
             await prompt.aformat(variable1="foo")
+
         """
         return self.format(**kwargs)
 
@@ -363,6 +365,7 @@ class BasePromptTemplate(
         .. code-block:: python
 
             prompt.save(file_path="path/prompt.yaml")
+
         """
         if self.partial_variables:
             msg = "Cannot save prompt with partial variables."
@@ -442,6 +445,7 @@ def format_document(doc: Document, prompt: BasePromptTemplate[str]) -> str:
             prompt = PromptTemplate.from_template("Page {page}: {page_content}")
             format_document(doc, prompt)
             >>> "Page 1: This is a joke"
+
     """
     return prompt.format(**_get_document_info(doc, prompt))
 

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/prompts/chat.py

@@ -126,6 +126,7 @@ class MessagesPlaceholder(BaseMessagePromptTemplate):
             # -> [
             #     HumanMessage(content="Hello!"),
             # ]
+
     """
 
     variable_name: str
@@ -1164,6 +1165,7 @@ class ChatPromptTemplate(BaseChatPromptTemplate):
 
         Returns:
             a chat prompt template.
+
         """
         return cls(messages, template_format=template_format)
 
@@ -1248,6 +1250,7 @@ class ChatPromptTemplate(BaseChatPromptTemplate):
                 template2 = template.partial(user="Lucy", name="R2D2")
 
                 template2.format_messages(input="hello")
+
         """
         prompt_dict = self.__dict__.copy()
         prompt_dict["input_variables"] = list(

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/prompts/few_shot.py

@@ -357,6 +357,7 @@ class FewShotChatMessagePromptTemplate(
             from langchain_core.chat_models import ChatAnthropic
             chain = final_prompt | ChatAnthropic(model="claude-3-haiku-20240307")
             chain.invoke({"input": "What's 3+3?"})
+
     """
 
     input_variables: list[str] = Field(default_factory=list)

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/prompts/few_shot_with_templates.py

@@ -122,6 +122,7 @@ class FewShotPromptWithTemplates(StringPromptTemplate):
         .. code-block:: python
 
             prompt.format(variable1="foo")
+
         """
         kwargs = self._merge_partial_and_user_variables(**kwargs)
         # Get the examples to use.

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/prompts/image.py

@@ -90,6 +90,7 @@ class ImagePromptTemplate(BasePromptTemplate[ImageURL]):
             .. code-block:: python
 
                 prompt.format(variable1="foo")
+
         """
         formatted = {}
         for k, v in self.template.items():

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/prompts/pipeline.py

@@ -45,6 +45,7 @@ class PipelinePromptTemplate(BasePromptTemplate):
           Each PromptTemplate will be formatted and then passed
           to future prompt templates as a variable with
           the same name as `name`
+
     """
 
     final_prompt: BasePromptTemplate

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/prompts/prompt.py

@@ -56,6 +56,7 @@ class PromptTemplate(StringPromptTemplate):
 
             # Instantiation using initializer
             prompt = PromptTemplate(template="Say {foo}")
+
     """
 
     @property

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/prompts/structured.py

@@ -115,6 +115,7 @@ class StructuredPrompt(ChatPromptTemplate):
 
         Returns:
             a structured prompt template
+
         """
         return cls(messages, schema, **kwargs)
 

{langchain_core-0.3.71 → langchain_core-0.3.73}/langchain_core/rate_limiters.py

@@ -123,6 +123,7 @@ class InMemoryRateLimiter(BaseRateLimiter):
 
 
     .. versionadded:: 0.2.24
+
     """  # noqa: E501
 
     def __init__(