feat(model-profiles): distribute data across packages (#34024)

Author: ccurme

libs/core/langchain_core/language_models/__init__.py

@@ -53,6 +53,10 @@
         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 @@
     "LanguageModelInput",
     "LanguageModelLike",
     "LanguageModelOutput",
+    "ModelProfile",
+    "ModelProfileRegistry",
     "ParrotFakeChatModel",
     "SimpleChatModel",
     "get_tokenizer",
@@ -90,6 +96,8 @@
     "GenericFakeChatModel": "fake_chat_models",
     "ParrotFakeChatModel": "fake_chat_models",
     "LLM": "llms",
+    "ModelProfile": "model_profile",
+    "ModelProfileRegistry": "model_profile",
     "BaseLLM": "llms",
     "is_openai_data_block": "_utils",
 }

libs/core/langchain_core/language_models/chat_models.py

@@ -15,7 +15,6 @@
 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 @@
     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 @@
 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
@@ -339,6 +337,21 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
 
     """
 
+    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"
+    """
+
     model_config = ConfigDict(
         arbitrary_types_allowed=True,
     )
@@ -1688,40 +1701,6 @@ class AnswerWithJustification(BaseModel):
             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.

libs/core/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."""

libs/core/pyproject.toml

@@ -36,7 +36,6 @@ typing = [
     "mypy>=1.18.1,<1.19.0",
     "types-pyyaml>=6.0.12.2,<7.0.0.0",
     "types-requests>=2.28.11.5,<3.0.0.0",
-    "langchain-model-profiles",
     "langchain-text-splitters",
 ]
 dev = [
@@ -58,15 +57,13 @@ test = [
     "blockbuster>=1.5.18,<1.6.0",
     "numpy>=1.26.4; python_version<'3.13'",
     "numpy>=2.1.0; python_version>='3.13'",
-    "langchain-model-profiles",
     "langchain-tests",
     "pytest-benchmark",
     "pytest-codspeed",
 ]
 test_integration = []
 
 [tool.uv.sources]
-langchain-model-profiles = { path = "../model-profiles" }
 langchain-tests = { path = "../standard-tests" }
 langchain-text-splitters = { path = "../text-splitters" }
 

libs/core/tests/unit_tests/language_models/chat_models/test_base.py

@@ -1222,19 +1222,12 @@ def _llm_type(self) -> str:
 
 def test_model_profiles() -> None:
     model = GenericFakeChatModel(messages=iter([]))
-    profile = model.profile
-    assert profile == {}
+    assert model.profile is None
 
-    class MyModel(GenericFakeChatModel):
-        model: str = "gpt-5"
-
-        @property
-        def _llm_type(self) -> str:
-            return "openai-chat"
-
-    model = MyModel(messages=iter([]))
-    profile = model.profile
-    assert profile
+    model_with_profile = GenericFakeChatModel(
+        messages=iter([]), profile={"max_input_tokens": 100}
+    )
+    assert model_with_profile.profile == {"max_input_tokens": 100}
 
 
 class MockResponse:

libs/core/tests/unit_tests/language_models/test_imports.py

@@ -18,6 +18,8 @@
     "FakeStreamingListLLM",
     "FakeListLLM",
     "ParrotFakeChatModel",
+    "ModelProfile",
+    "ModelProfileRegistry",
     "is_openai_data_block",
 ]
 

libs/core/uv.lock

@@ -64,7 +64,7 @@
 STRUCTURED_OUTPUT_ERROR_TEMPLATE = "Error: {error}\n Please fix your mistakes."
 
 FALLBACK_MODELS_WITH_STRUCTURED_OUTPUT = [
-    # if langchain-model-profiles is not installed, these models are assumed to support
+    # if model profile data are not available, these models are assumed to support
     # structured output
     "grok",
     "gpt-5",
@@ -381,18 +381,15 @@ def _supports_provider_strategy(model: str | BaseChatModel, tools: list | None =
             or getattr(model, "model", None)
             or getattr(model, "model_id", "")
         )
-        try:
-            model_profile = model.profile
-        except ImportError:
-            pass
-        else:
-            if (
-                model_profile.get("structured_output")
-                # We make an exception for Gemini models, which currently do not support
-                # simultaneous tool use with structured output
-                and not (tools and isinstance(model_name, str) and "gemini" in model_name.lower())
-            ):
-                return True
+        model_profile = model.profile
+        if (
+            model_profile is not None
+            and model_profile.get("structured_output")
+            # We make an exception for Gemini models, which currently do not support
+            # simultaneous tool use with structured output
+            and not (tools and isinstance(model_name, str) and "gemini" in model_name.lower())
+        ):
+            return True
 
     return (
         any(part in model_name.lower() for part in FALLBACK_MODELS_WITH_STRUCTURED_OUTPUT)

libs/langchain_v1/langchain/agents/factory.py

@@ -159,9 +159,11 @@ def __init__(
             requires_profile = True
         if requires_profile and self._get_profile_limits() is None:
             msg = (
-                "Model profile information is required to use fractional token limits. "
-                'pip install "langchain[model-profiles]" or use absolute token counts '
-                "instead."
+                "Model profile information is required to use fractional token limits, "
+                "and is unavailable for the specified model. Please use absolute token "
+                "counts instead, or pass "
+                '`\n\nChatModel(..., profile={"max_input_tokens": ...})`.\n\n'
+                "with a desired integer value of the model's maximum input tokens."
             )
             raise ValueError(msg)
 
@@ -308,7 +310,7 @@ def _get_profile_limits(self) -> int | None:
         """Retrieve max input token limit from the model profile."""
         try:
             profile = self.model.profile
-        except (AttributeError, ImportError):
+        except AttributeError:
             return None
 
         if not isinstance(profile, Mapping):