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

libs/partners/deepseek/langchain_deepseek/chat_models.py

@@ -5,13 +5,18 @@ from __future__ import annotations
 import json
 from collections.abc import Callable, Iterator, Sequence
 from json import JSONDecodeError
-from typing import Any, Literal, TypeAlias
+from typing import Any, Literal, TypeAlias, cast
 
 import openai
 from langchain_core.callbacks import (
     CallbackManagerForLLMRun,
 )
-from langchain_core.language_models import LangSmithParams, LanguageModelInput
+from langchain_core.language_models import (
+    LangSmithParams,
+    LanguageModelInput,
+    ModelProfile,
+    ModelProfileRegistry,
+)
 from langchain_core.messages import AIMessage, AIMessageChunk, BaseMessage
 from langchain_core.outputs import ChatGenerationChunk, ChatResult
 from langchain_core.runnables import Runnable
@@ -21,6 +26,8 @@ from langchain_openai.chat_models.base import BaseChatOpenAI
 from pydantic import BaseModel, ConfigDict, Field, SecretStr, model_validator
 from typing_extensions import Self
 
+from langchain_deepseek.data._profiles import _PROFILES
+
 DEFAULT_API_BASE = "https://api.deepseek.com/v1"
 DEFAULT_BETA_API_BASE = "https://api.deepseek.com/beta"
 
@@ -28,6 +35,14 @@ _DictOrPydanticClass: TypeAlias = dict[str, Any] | type[BaseModel]
 _DictOrPydantic: TypeAlias = dict[str, Any] | BaseModel
 
 
+_MODEL_PROFILES = cast("ModelProfileRegistry", _PROFILES)
+
+
+def _get_default_model_profile(model_name: str) -> ModelProfile:
+    default = _MODEL_PROFILES.get(model_name) or {}
+    return default.copy()
+
+
 class ChatDeepSeek(BaseChatOpenAI):
     """DeepSeek chat model integration to access models hosted in DeepSeek's API.
 
@@ -232,6 +247,13 @@ class ChatDeepSeek(BaseChatOpenAI):
             self.async_client = self.root_async_client.chat.completions
         return self
 
+    @model_validator(mode="after")
+    def _set_model_profile(self) -> Self:
+        """Set model profile if not overridden."""
+        if self.profile is None:
+            self.profile = _get_default_model_profile(self.model_name)
+        return self
+
     def _get_request_payload(
         self,
         input_: LanguageModelInput,

libs/partners/deepseek/langchain_deepseek/data/__init__.py

@@ -0,0 +1 @@
+"""Model profile data. All edits should be made in profile_augmentations.toml."""

libs/partners/deepseek/langchain_deepseek/data/_profiles.py

@@ -0,0 +1,43 @@
+"""Auto-generated model profiles.
+
+DO NOT EDIT THIS FILE MANUALLY.
+This file is generated by the langchain-profiles CLI tool.
+
+It contains data derived from the models.dev project.
+
+Source: https://github.com/sst/models.dev
+License: MIT License
+
+To update these data, refer to the instructions here:
+
+https://docs.langchain.com/oss/python/langchain/models#updating-or-overwriting-profile-data
+"""
+
+from typing import Any
+
+_PROFILES: dict[str, dict[str, Any]] = {
+    "deepseek-chat": {
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8192,
+        "image_inputs": False,
+        "audio_inputs": False,
+        "video_inputs": False,
+        "image_outputs": False,
+        "audio_outputs": False,
+        "video_outputs": False,
+        "reasoning_output": False,
+        "tool_calling": True,
+    },
+    "deepseek-reasoner": {
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "image_inputs": False,
+        "audio_inputs": False,
+        "video_inputs": False,
+        "image_outputs": False,
+        "audio_outputs": False,
+        "video_outputs": False,
+        "reasoning_output": True,
+        "tool_calling": True,
+    },
+}