core,groq,openai,mistralai,robocorp,fireworks,anthropic[patch]: Update BaseModel subclass and instance checks to handle both v1 and proper namespaces (#24417)

After this PR chat models will correctly handle pydantic 2 with
bind_tools and with_structured_output.


```python
import pydantic
print(pydantic.__version__)
```
2.8.2

```python
from langchain_openai import ChatOpenAI
from pydantic import BaseModel, Field

class Add(BaseModel):
    x: int
    y: int

model = ChatOpenAI().bind_tools([Add])
print(model.invoke('2 + 5').tool_calls)

model = ChatOpenAI().with_structured_output(Add)
print(type(model.invoke('2 + 5')))
```

```
[{'name': 'Add', 'args': {'x': 2, 'y': 5}, 'id': 'call_PNUFa4pdfNOYXxIMHc6ps2Do', 'type': 'tool_call'}]
<class '__main__.Add'>
```


```python
from langchain_openai import ChatOpenAI
from pydantic.v1 import BaseModel, Field

class Add(BaseModel):
    x: int
    y: int

model = ChatOpenAI().bind_tools([Add])
print(model.invoke('2 + 5').tool_calls)

model = ChatOpenAI().with_structured_output(Add)
print(type(model.invoke('2 + 5')))
```

```python
[{'name': 'Add', 'args': {'x': 2, 'y': 5}, 'id': 'call_hhiHYP441cp14TtrHKx3Upg0', 'type': 'tool_call'}]
<class '__main__.Add'>
```

Addresses issues: https://github.com/langchain-ai/langchain/issues/22782

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>

libs/experimental/langchain_experimental/llms/ollama_functions.py

@@ -34,11 +34,14 @@ from langchain_core.output_parsers.json import JsonOutputParser
 from langchain_core.output_parsers.pydantic import PydanticOutputParser
 from langchain_core.outputs import ChatGeneration, ChatResult
 from langchain_core.prompts import SystemMessagePromptTemplate
-from langchain_core.pydantic_v1 import BaseModel
+from langchain_core.pydantic_v1 import (
+    BaseModel,
+)
 from langchain_core.runnables import Runnable, RunnableLambda
 from langchain_core.runnables.base import RunnableMap
 from langchain_core.runnables.passthrough import RunnablePassthrough
 from langchain_core.tools import BaseTool
+from langchain_core.utils.pydantic import is_basemodel_instance, is_basemodel_subclass
 
 DEFAULT_SYSTEM_TEMPLATE = """You have access to the following tools:
 
@@ -75,14 +78,10 @@ _DictOrPydantic = Union[Dict, _BM]
 
 def _is_pydantic_class(obj: Any) -> bool:
     return isinstance(obj, type) and (
-        issubclass(obj, BaseModel) or BaseModel in obj.__bases__
+        is_basemodel_subclass(obj) or BaseModel in obj.__bases__
     )
 
 
-def _is_pydantic_object(obj: Any) -> bool:
-    return isinstance(obj, BaseModel)
-
-
 def convert_to_ollama_tool(tool: Any) -> Dict:
     """Convert a tool to an Ollama tool."""
     description = None
@@ -93,7 +92,7 @@ def convert_to_ollama_tool(tool: Any) -> Dict:
         schema = tool.tool_call_schema.schema()
         name = tool.get_name()
         description = tool.description
-    elif _is_pydantic_object(tool):
+    elif is_basemodel_instance(tool):
         schema = tool.get_input_schema().schema()
         name = tool.get_name()
         description = tool.description

libs/experimental/langchain_experimental/tabular_synthetic_data/base.py

@@ -1,11 +1,12 @@
 import asyncio
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional, Union, cast
 
 from langchain.chains.base import Chain
 from langchain.chains.llm import LLMChain
 from langchain.pydantic_v1 import BaseModel, root_validator
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.prompts.few_shot import FewShotPromptTemplate
+from langchain_core.utils.pydantic import is_basemodel_instance
 
 
 class SyntheticDataGenerator(BaseModel):
@@ -63,8 +64,10 @@ class SyntheticDataGenerator(BaseModel):
         """Prevents duplicates by adding previously generated examples to the few shot
         list."""
         if self.template and self.template.examples:
-            if isinstance(example, BaseModel):
-                formatted_example = self._format_dict_to_string(example.dict())
+            if is_basemodel_instance(example):
+                formatted_example = self._format_dict_to_string(
+                    cast(BaseModel, example).dict()
+                )
             elif isinstance(example, dict):
                 formatted_example = self._format_dict_to_string(example)
             else: