langchain-core 1.0.5__tar.gz → 1.1.1__tar.gz

{langchain_core-1.0.5 → langchain_core-1.1.1}/.gitignore

@@ -163,3 +163,6 @@ node_modules
 
 prof
 virtualenv/
+scratch/
+
+.langgraph_api/

{langchain_core-1.0.5 → langchain_core-1.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langchain-core
-Version: 1.0.5
+Version: 1.1.1
 Summary: Building applications with LLMs through composability
 Project-URL: Homepage, https://docs.langchain.com/
 Project-URL: Documentation, https://reference.langchain.com/python/langchain_core/
@@ -18,6 +18,7 @@ Requires-Dist: pydantic<3.0.0,>=2.7.4
 Requires-Dist: pyyaml<7.0.0,>=5.3.0
 Requires-Dist: tenacity!=8.4.0,<10.0.0,>=8.1.0
 Requires-Dist: typing-extensions<5.0.0,>=4.7.0
+Requires-Dist: uuid-utils<1.0,>=0.12.0
 Description-Content-Type: text/markdown
 
 # 🦜🍎️ LangChain Core

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/callbacks/manager.py

@@ -6,7 +6,6 @@ import asyncio
 import atexit
 import functools
 import logging
-import uuid
 from abc import ABC, abstractmethod
 from collections.abc import Callable
 from concurrent.futures import ThreadPoolExecutor
@@ -41,6 +40,7 @@ from langchain_core.tracers.context import (
 from langchain_core.tracers.langchain import LangChainTracer
 from langchain_core.tracers.stdout import ConsoleCallbackHandler
 from langchain_core.utils.env import env_var_is_set
+from langchain_core.utils.uuid import uuid7
 
 if TYPE_CHECKING:
     from collections.abc import AsyncGenerator, Coroutine, Generator, Sequence
@@ -504,7 +504,7 @@ class BaseRunManager(RunManagerMixin):
 
         """
         return cls(
-            run_id=uuid.uuid4(),
+            run_id=uuid7(),
             handlers=[],
             inheritable_handlers=[],
             tags=[],
@@ -1330,7 +1330,7 @@ class CallbackManager(BaseCallbackManager):
         managers = []
         for i, prompt in enumerate(prompts):
             # Can't have duplicate runs with the same run ID (if provided)
-            run_id_ = run_id if i == 0 and run_id is not None else uuid.uuid4()
+            run_id_ = run_id if i == 0 and run_id is not None else uuid7()
             handle_event(
                 self.handlers,
                 "on_llm_start",
@@ -1384,7 +1384,7 @@ class CallbackManager(BaseCallbackManager):
                 run_id_ = run_id
                 run_id = None
             else:
-                run_id_ = uuid.uuid4()
+                run_id_ = uuid7()
             handle_event(
                 self.handlers,
                 "on_chat_model_start",
@@ -1433,7 +1433,7 @@ class CallbackManager(BaseCallbackManager):
 
         """
         if run_id is None:
-            run_id = uuid.uuid4()
+            run_id = uuid7()
         handle_event(
             self.handlers,
             "on_chain_start",
@@ -1488,7 +1488,7 @@ class CallbackManager(BaseCallbackManager):
 
         """
         if run_id is None:
-            run_id = uuid.uuid4()
+            run_id = uuid7()
 
         handle_event(
             self.handlers,
@@ -1537,7 +1537,7 @@ class CallbackManager(BaseCallbackManager):
             The callback manager for the retriever run.
         """
         if run_id is None:
-            run_id = uuid.uuid4()
+            run_id = uuid7()
 
         handle_event(
             self.handlers,
@@ -1594,7 +1594,7 @@ class CallbackManager(BaseCallbackManager):
             )
             raise ValueError(msg)
         if run_id is None:
-            run_id = uuid.uuid4()
+            run_id = uuid7()
 
         handle_event(
             self.handlers,
@@ -1816,7 +1816,7 @@ class AsyncCallbackManager(BaseCallbackManager):
                 run_id_ = run_id
                 run_id = None
             else:
-                run_id_ = uuid.uuid4()
+                run_id_ = uuid7()
 
             if inline_handlers:
                 inline_tasks.append(
@@ -1900,7 +1900,7 @@ class AsyncCallbackManager(BaseCallbackManager):
                 run_id_ = run_id
                 run_id = None
             else:
-                run_id_ = uuid.uuid4()
+                run_id_ = uuid7()
 
             for handler in self.handlers:
                 task = ahandle_event(
@@ -1962,7 +1962,7 @@ class AsyncCallbackManager(BaseCallbackManager):
             The async callback manager for the chain run.
         """
         if run_id is None:
-            run_id = uuid.uuid4()
+            run_id = uuid7()
 
         await ahandle_event(
             self.handlers,
@@ -2010,7 +2010,7 @@ class AsyncCallbackManager(BaseCallbackManager):
             The async callback manager for the tool run.
         """
         if run_id is None:
-            run_id = uuid.uuid4()
+            run_id = uuid7()
 
         await ahandle_event(
             self.handlers,
@@ -2060,7 +2060,7 @@ class AsyncCallbackManager(BaseCallbackManager):
         if not self.handlers:
             return
         if run_id is None:
-            run_id = uuid.uuid4()
+            run_id = uuid7()
 
         if kwargs:
             msg = (
@@ -2102,7 +2102,7 @@ class AsyncCallbackManager(BaseCallbackManager):
             The async callback manager for the retriever run.
         """
         if run_id is None:
-            run_id = uuid.uuid4()
+            run_id = uuid7()
 
         await ahandle_event(
             self.handlers,

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/indexing/api.py

@@ -302,6 +302,7 @@ def index(
     are not able to specify the uid of the document.
 
     !!! warning "Behavior changed in `langchain-core` 0.3.25"
+
         Added `scoped_full` cleanup mode.
 
     !!! warning
@@ -640,6 +641,7 @@ async def aindex(
     are not able to specify the uid of the document.
 
     !!! warning "Behavior changed in `langchain-core` 0.3.25"
+
         Added `scoped_full` cleanup mode.
 
     !!! warning

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/language_models/__init__.py

@@ -53,6 +53,10 @@ if TYPE_CHECKING:
         ParrotFakeChatModel,
     )
     from langchain_core.language_models.llms import LLM, BaseLLM
+    from langchain_core.language_models.model_profile import (
+        ModelProfile,
+        ModelProfileRegistry,
+    )
 
 __all__ = (
     "LLM",
@@ -68,6 +72,8 @@ __all__ = (
     "LanguageModelInput",
     "LanguageModelLike",
     "LanguageModelOutput",
+    "ModelProfile",
+    "ModelProfileRegistry",
     "ParrotFakeChatModel",
     "SimpleChatModel",
     "get_tokenizer",
@@ -90,6 +96,8 @@ _dynamic_imports = {
     "GenericFakeChatModel": "fake_chat_models",
     "ParrotFakeChatModel": "fake_chat_models",
     "LLM": "llms",
+    "ModelProfile": "model_profile",
+    "ModelProfileRegistry": "model_profile",
     "BaseLLM": "llms",
     "is_openai_data_block": "_utils",
 }

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/language_models/_utils.py

@@ -140,6 +140,7 @@ def _normalize_messages(
     - LangChain v0 standard content blocks for backward compatibility
 
     !!! warning "Behavior changed in `langchain-core` 1.0.0"
+
         In previous versions, this function returned messages in LangChain v0 format.
         Now, it returns messages in LangChain v1 format, which upgraded chat models now
         expect to receive when passing back in message history. For backward

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/language_models/chat_models.py

@@ -15,7 +15,6 @@ from typing import TYPE_CHECKING, Any, Literal, cast
 from pydantic import BaseModel, ConfigDict, Field
 from typing_extensions import override
 
-from langchain_core._api.beta_decorator import beta
 from langchain_core.caches import BaseCache
 from langchain_core.callbacks import (
     AsyncCallbackManager,
@@ -34,6 +33,7 @@ from langchain_core.language_models.base import (
     LangSmithParams,
     LanguageModelInput,
 )
+from langchain_core.language_models.model_profile import ModelProfile
 from langchain_core.load import dumpd, dumps
 from langchain_core.messages import (
     AIMessage,
@@ -76,8 +76,6 @@ from langchain_core.utils.utils import LC_ID_PREFIX, from_env
 if TYPE_CHECKING:
     import uuid
 
-    from langchain_model_profiles import ModelProfile  # type: ignore[import-untyped]
-
     from langchain_core.output_parsers.base import OutputParserLike
     from langchain_core.runnables import Runnable, RunnableConfig
     from langchain_core.tools import BaseTool
@@ -335,8 +333,23 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
     [`langchain-openai`](https://pypi.org/project/langchain-openai)) can also use this
     field to roll out new content formats in a backward-compatible way.
 
-    !!! version-added "Added in `langchain-core` 1.0"
+    !!! version-added "Added in `langchain-core` 1.0.0"
+
+    """
+
+    profile: ModelProfile | None = Field(default=None, exclude=True)
+    """Profile detailing model capabilities.
+
+    !!! warning "Beta feature"
+        This is a beta feature. The format of model profiles is subject to change.
 
+    If not specified, automatically loaded from the provider package on initialization
+    if data is available.
+
+    Example profile data includes context window sizes, supported modalities, or support
+    for tool calling, structured output, and other features.
+
+    !!! version-added "Added in `langchain-core` 1.1.0"
     """
 
     model_config = ConfigDict(
@@ -1619,7 +1632,7 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
         # }
         ```
 
-        Example: `dict` schema (`include_raw=False`):
+        Example: Dictionary schema (`include_raw=False`):
 
         ```python
         from pydantic import BaseModel
@@ -1647,6 +1660,7 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
         ```
 
         !!! warning "Behavior changed in `langchain-core` 0.2.26"
+
             Added support for `TypedDict` class.
 
         """  # noqa: E501
@@ -1688,40 +1702,6 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
             return RunnableMap(raw=llm) | parser_with_fallback
         return llm | output_parser
 
-    @property
-    @beta()
-    def profile(self) -> ModelProfile:
-        """Return profiling information for the model.
-
-        This property relies on the `langchain-model-profiles` package to retrieve chat
-        model capabilities, such as context window sizes and supported features.
-
-        Raises:
-            ImportError: If `langchain-model-profiles` is not installed.
-
-        Returns:
-            A `ModelProfile` object containing profiling information for the model.
-        """
-        try:
-            from langchain_model_profiles import get_model_profile  # noqa: PLC0415
-        except ImportError as err:
-            informative_error_message = (
-                "To access model profiling information, please install the "
-                "`langchain-model-profiles` package: "
-                "`pip install langchain-model-profiles`."
-            )
-            raise ImportError(informative_error_message) from err
-
-        provider_id = self._llm_type
-        model_name = (
-            # Model name is not standardized across integrations. New integrations
-            # should prefer `model`.
-            getattr(self, "model", None)
-            or getattr(self, "model_name", None)
-            or getattr(self, "model_id", "")
-        )
-        return get_model_profile(provider_id, model_name) or {}
-
 
 class SimpleChatModel(BaseChatModel):
     """Simplified implementation for a chat model to inherit from.

langchain_core-1.1.1/langchain_core/language_models/model_profile.py

@@ -0,0 +1,84 @@
+"""Model profile types and utilities."""
+
+from typing_extensions import TypedDict
+
+
+class ModelProfile(TypedDict, total=False):
+    """Model profile.
+
+    !!! warning "Beta feature"
+        This is a beta feature. The format of model profiles is subject to change.
+
+    Provides information about chat model capabilities, such as context window sizes
+    and supported features.
+    """
+
+    # --- Input constraints ---
+
+    max_input_tokens: int
+    """Maximum context window (tokens)"""
+
+    image_inputs: bool
+    """Whether image inputs are supported."""
+    # TODO: add more detail about formats?
+
+    image_url_inputs: bool
+    """Whether [image URL inputs](https://docs.langchain.com/oss/python/langchain/models#multimodal)
+    are supported."""
+
+    pdf_inputs: bool
+    """Whether [PDF inputs](https://docs.langchain.com/oss/python/langchain/models#multimodal)
+    are supported."""
+    # TODO: add more detail about formats? e.g. bytes or base64
+
+    audio_inputs: bool
+    """Whether [audio inputs](https://docs.langchain.com/oss/python/langchain/models#multimodal)
+    are supported."""
+    # TODO: add more detail about formats? e.g. bytes or base64
+
+    video_inputs: bool
+    """Whether [video inputs](https://docs.langchain.com/oss/python/langchain/models#multimodal)
+    are supported."""
+    # TODO: add more detail about formats? e.g. bytes or base64
+
+    image_tool_message: bool
+    """Whether images can be included in tool messages."""
+
+    pdf_tool_message: bool
+    """Whether PDFs can be included in tool messages."""
+
+    # --- Output constraints ---
+
+    max_output_tokens: int
+    """Maximum output tokens"""
+
+    reasoning_output: bool
+    """Whether the model supports [reasoning / chain-of-thought](https://docs.langchain.com/oss/python/langchain/models#reasoning)"""
+
+    image_outputs: bool
+    """Whether [image outputs](https://docs.langchain.com/oss/python/langchain/models#multimodal)
+    are supported."""
+
+    audio_outputs: bool
+    """Whether [audio outputs](https://docs.langchain.com/oss/python/langchain/models#multimodal)
+    are supported."""
+
+    video_outputs: bool
+    """Whether [video outputs](https://docs.langchain.com/oss/python/langchain/models#multimodal)
+    are supported."""
+
+    # --- Tool calling ---
+    tool_calling: bool
+    """Whether the model supports [tool calling](https://docs.langchain.com/oss/python/langchain/models#tool-calling)"""
+
+    tool_choice: bool
+    """Whether the model supports [tool choice](https://docs.langchain.com/oss/python/langchain/models#forcing-tool-calls)"""
+
+    # --- Structured output ---
+    structured_output: bool
+    """Whether the model supports a native [structured output](https://docs.langchain.com/oss/python/langchain/models#structured-outputs)
+    feature"""
+
+
+ModelProfileRegistry = dict[str, ModelProfile]
+"""Registry mapping model identifiers or names to their ModelProfile."""

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/messages/ai.py

@@ -124,9 +124,11 @@ class UsageMetadata(TypedDict):
         ```
 
     !!! warning "Behavior changed in `langchain-core` 0.3.9"
+
         Added `input_token_details` and `output_token_details`.
 
     !!! note "LangSmith SDK"
+
         The LangSmith SDK also has a `UsageMetadata` class. While the two share fields,
         LangSmith's `UsageMetadata` has additional fields to capture cost information
         used by the LangSmith platform.

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/messages/content.py

@@ -654,7 +654,7 @@ class PlainTextContentBlock(TypedDict):
 
     !!! note
         Title and context are optional fields that may be passed to the model. See
-        Anthropic [example](https://docs.claude.com/en/docs/build-with-claude/citations#citable-vs-non-citable-content).
+        Anthropic [example](https://platform.claude.com/docs/en/build-with-claude/citations#citable-vs-non-citable-content).
 
     !!! note "Factory function"
         `create_plaintext_block` may also be used as a factory to create a

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/messages/utils.py

@@ -738,8 +738,10 @@ def trim_messages(
             Set to `len` to count the number of **messages** in the chat history.
 
             !!! note
+
                 Use `count_tokens_approximately` to get fast, approximate token
                 counts.
+
                 This is recommended for using `trim_messages` on the hot path, where
                 exact token counting is not necessary.
 

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/output_parsers/pydantic.py

@@ -37,7 +37,7 @@ class PydanticOutputParser(JsonOutputParser, Generic[TBaseModel]):
     def _parser_exception(
         self, e: Exception, json_object: dict
     ) -> OutputParserException:
-        json_string = json.dumps(json_object)
+        json_string = json.dumps(json_object, ensure_ascii=False)
         name = self.pydantic_object.__name__
         msg = f"Failed to parse {name} from completion {json_string}. Got: {e}"
         return OutputParserException(msg, llm_output=json_string)

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/prompts/chat.py

@@ -903,23 +903,28 @@ class ChatPromptTemplate(BaseChatPromptTemplate):
                 5. A string which is shorthand for `("human", template)`; e.g.,
                     `"{user_input}"`
             template_format: Format of the template.
-            input_variables: A list of the names of the variables whose values are
-                required as inputs to the prompt.
-            optional_variables: A list of the names of the variables for placeholder
-                or MessagePlaceholder that are optional.
-
-                These variables are auto inferred from the prompt and user need not
-                provide them.
-            partial_variables: A dictionary of the partial variables the prompt
-                template carries.
-
-                Partial variables populate the template so that you don't need to pass
-                them in every time you call the prompt.
-            validate_template: Whether to validate the template.
-            input_types: A dictionary of the types of the variables the prompt template
-                expects.
-
-                If not provided, all variables are assumed to be strings.
+            **kwargs: Additional keyword arguments passed to `BasePromptTemplate`,
+                including (but not limited to):
+
+                - `input_variables`: A list of the names of the variables whose values
+                    are required as inputs to the prompt.
+                - `optional_variables`: A list of the names of the variables for
+                    placeholder or `MessagePlaceholder` that are optional.
+
+                    These variables are auto inferred from the prompt and user need not
+                    provide them.
+
+                - `partial_variables`: A dictionary of the partial variables the prompt
+                    template carries.
+
+                    Partial variables populate the template so that you don't need to
+                    pass them in every time you call the prompt.
+
+                - `validate_template`: Whether to validate the template.
+                - `input_types`: A dictionary of the types of the variables the prompt
+                    template expects.
+
+                    If not provided, all variables are assumed to be strings.
 
         Examples:
             Instantiation from a list of message templates:

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/prompts/string.py

@@ -19,9 +19,66 @@ if TYPE_CHECKING:
     from collections.abc import Callable, Sequence
 
 try:
-    from jinja2 import Environment, meta
+    from jinja2 import meta
+    from jinja2.exceptions import SecurityError
     from jinja2.sandbox import SandboxedEnvironment
 
+    class _RestrictedSandboxedEnvironment(SandboxedEnvironment):
+        """A more restrictive Jinja2 sandbox that blocks all attribute/method access.
+
+        This sandbox only allows simple variable lookups, no attribute or method access.
+        This prevents template injection attacks via methods like parse_raw().
+        """
+
+        def is_safe_attribute(self, _obj: Any, _attr: str, _value: Any) -> bool:
+            """Block ALL attribute access for security.
+
+            Only allow accessing variables directly from the context dict,
+            no attribute access on those objects.
+
+            Args:
+                _obj: The object being accessed (unused, always blocked).
+                _attr: The attribute name (unused, always blocked).
+                _value: The attribute value (unused, always blocked).
+
+            Returns:
+                False - all attribute access is blocked.
+            """
+            # Block all attribute access
+            return False
+
+        def is_safe_callable(self, _obj: Any) -> bool:
+            """Block all method calls for security.
+
+            Args:
+                _obj: The object being checked (unused, always blocked).
+
+            Returns:
+                False - all callables are blocked.
+            """
+            return False
+
+        def getattr(self, obj: Any, attribute: str) -> Any:
+            """Override getattr to block all attribute access.
+
+            Args:
+                obj: The object.
+                attribute: The attribute name.
+
+            Returns:
+                Never returns.
+
+            Raises:
+                SecurityError: Always, to block attribute access.
+            """
+            msg = (
+                f"Access to attributes is not allowed in templates. "
+                f"Attempted to access '{attribute}' on {type(obj).__name__}. "
+                f"Use only simple variable names like {{{{variable}}}} "
+                f"without dots or methods."
+            )
+            raise SecurityError(msg)
+
     _HAS_JINJA2 = True
 except ImportError:
     _HAS_JINJA2 = False
@@ -61,14 +118,10 @@ def jinja2_formatter(template: str, /, **kwargs: Any) -> str:
         )
         raise ImportError(msg)
 
-    # This uses a sandboxed environment to prevent arbitrary code execution.
-    # Jinja2 uses an opt-out rather than opt-in approach for sand-boxing.
-    # Please treat this sand-boxing as a best-effort approach rather than
-    # a guarantee of security.
-    # We recommend to never use jinja2 templates with untrusted inputs.
-    # https://jinja.palletsprojects.com/en/3.1.x/sandbox/
-    # approach not a guarantee of security.
-    return SandboxedEnvironment().from_string(template).render(**kwargs)
+    # Use a restricted sandbox that blocks ALL attribute/method access
+    # Only simple variable lookups like {{variable}} are allowed
+    # Attribute access like {{variable.attr}} or {{variable.method()}} is blocked
+    return _RestrictedSandboxedEnvironment().from_string(template).render(**kwargs)
 
 
 def validate_jinja2(template: str, input_variables: list[str]) -> None:
@@ -103,7 +156,7 @@ def _get_jinja2_variables_from_template(template: str) -> set[str]:
             "Please install it with `pip install jinja2`."
         )
         raise ImportError(msg)
-    env = Environment()  # noqa: S701
+    env = _RestrictedSandboxedEnvironment()
     ast = env.parse(template)
     return meta.find_undeclared_variables(ast)
 
@@ -273,6 +326,30 @@ def get_template_variables(template: str, template_format: str) -> list[str]:
         msg = f"Unsupported template format: {template_format}"
         raise ValueError(msg)
 
+    # For f-strings, block attribute access and indexing syntax
+    # This prevents template injection attacks via accessing dangerous attributes
+    if template_format == "f-string":
+        for var in input_variables:
+            # Formatter().parse() returns field names with dots/brackets if present
+            # e.g., "obj.attr" or "obj[0]" - we need to block these
+            if "." in var or "[" in var or "]" in var:
+                msg = (
+                    f"Invalid variable name {var!r} in f-string template. "
+                    f"Variable names cannot contain attribute "
+                    f"access (.) or indexing ([])."
+                )
+                raise ValueError(msg)
+
+            # Block variable names that are all digits (e.g., "0", "100")
+            # These are interpreted as positional arguments, not keyword arguments
+            if var.isdigit():
+                msg = (
+                    f"Invalid variable name {var!r} in f-string template. "
+                    f"Variable names cannot be all digits as they are interpreted "
+                    f"as positional arguments."
+                )
+                raise ValueError(msg)
+
     return sorted(input_variables)
 
 

{langchain_core-1.0.5 → langchain_core-1.1.1}/langchain_core/prompts/structured.py

@@ -49,7 +49,13 @@ class StructuredPrompt(ChatPromptTemplate):
             structured_output_kwargs: additional kwargs for structured output.
             template_format: template format for the prompt.
         """
-        schema_ = schema_ or kwargs.pop("schema")
+        schema_ = schema_ or kwargs.pop("schema", None)
+        if not schema_:
+            err_msg = (
+                "Must pass in a non-empty structured output schema. Received: "
+                f"{schema_}"
+            )
+            raise ValueError(err_msg)
         structured_output_kwargs = structured_output_kwargs or {}
         for k in set(kwargs).difference(get_pydantic_field_names(self.__class__)):
             structured_output_kwargs[k] = kwargs.pop(k)