x

libs/langchain/langchain/__init__.py

@@ -1,38 +1,7 @@
-# ruff: noqa: E402
 """Main entrypoint into package."""
-import importlib
-import sys
 from importlib import metadata
 from typing import Optional
 
-## Create namespaces for pydantic v1 and v2.
-# This code must stay at the top of the file before other modules may
-# attempt to import pydantic since it adds pydantic_v1 and pydantic_v2 to sys.modules.
-#
-# This hack is done for the following reasons:
-# * Langchain will attempt to remain compatible with both pydantic v1 and v2 since
-#   both dependencies and dependents may be stuck on either version of v1 or v2.
-# * Creating namespaces for pydantic v1 and v2 should allow us to write code that
-#   unambiguously uses either v1 or v2 API.
-# * This change is easier to roll out and roll back.
-
-try:
-    pydantic_v1 = importlib.import_module("pydantic.v1")
-except ImportError:
-    pydantic_v1 = importlib.import_module("pydantic")
-
-if "pydantic_v1" not in sys.modules:
-    # Use a conditional because langchain experimental
-    # will use the same strategy to add pydantic_v1 to sys.modules
-    # and may run prior to langchain core package.
-    sys.modules["pydantic_v1"] = pydantic_v1
-
-try:
-    _PYDANTIC_MAJOR_VERSION: int = int(metadata.version("pydantic").split(".")[0])
-except metadata.PackageNotFoundError:
-    _PYDANTIC_MAJOR_VERSION = 0
-
-
 from langchain.agents import MRKLChain, ReActChain, SelfAskWithSearchChain
 from langchain.cache import BaseCache
 from langchain.chains import (

libs/langchain/langchain/agents/agent.py

@@ -10,7 +10,7 @@ from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Sequence, Tuple, Union
 
 import yaml
-from pydantic_v1 import BaseModel, root_validator
+from pydantic import model_validator, BaseModel
 
 from langchain.agents.agent_iterator import AgentExecutorIterator
 from langchain.agents.agent_types import AgentType
@@ -495,7 +495,8 @@ class Agent(BaseSingleActionAgent):
         """
         return list(set(self.llm_chain.input_keys) - {"agent_scratchpad"})
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_prompt(cls, values: Dict) -> Dict:
         """Validate that prompt matches format."""
         prompt = values["llm_chain"].prompt
@@ -694,7 +695,8 @@ s
             agent=agent, tools=tools, callback_manager=callback_manager, **kwargs
         )
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_tools(cls, values: Dict) -> Dict:
         """Validate that tools are compatible with agent."""
         agent = values["agent"]
@@ -708,7 +710,8 @@ s
                 )
         return values
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_return_direct_tool(cls, values: Dict) -> Dict:
         """Validate that tools are compatible with agent."""
         agent = values["agent"]

libs/langchain/langchain/agents/agent_toolkits/amadeus/toolkit.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING, List
 
-from pydantic_v1 import Field
+from pydantic import ConfigDict, Field
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.tools import BaseTool
@@ -18,11 +18,7 @@ class AmadeusToolkit(BaseToolkit):
     """Toolkit for interacting with Office365."""
 
     client: Client = Field(default_factory=authenticate)
-
-    class Config:
-        """Pydantic config."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def get_tools(self) -> List[BaseTool]:
         """Get the tools in the toolkit."""

libs/langchain/langchain/agents/agent_toolkits/base.py

@@ -2,7 +2,7 @@
 from abc import ABC, abstractmethod
 from typing import List
 
-from pydantic_v1 import BaseModel
+from pydantic import BaseModel
 
 from langchain.tools import BaseTool
 

libs/langchain/langchain/agents/agent_toolkits/file_management/toolkit.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from typing import List, Optional
 
-from pydantic_v1 import root_validator
+from pydantic import root_validator
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.tools import BaseTool

libs/langchain/langchain/agents/agent_toolkits/gmail/toolkit.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING, List
 
-from pydantic_v1 import Field
+from pydantic import ConfigDict, Field
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.tools import BaseTool
@@ -31,11 +31,7 @@ class GmailToolkit(BaseToolkit):
     """Toolkit for interacting with Gmail."""
 
     api_resource: Resource = Field(default_factory=build_resource_service)
-
-    class Config:
-        """Pydantic config."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def get_tools(self) -> List[BaseTool]:
         """Get the tools in the toolkit."""

libs/langchain/langchain/agents/agent_toolkits/multion/toolkit.py

@@ -7,15 +7,12 @@ from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.tools import BaseTool
 from langchain.tools.multion.create_session import MultionCreateSession
 from langchain.tools.multion.update_session import MultionUpdateSession
+from pydantic import ConfigDict
 
 
 class MultionToolkit(BaseToolkit):
     """Toolkit for interacting with the Browser Agent"""
-
-    class Config:
-        """Pydantic config."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def get_tools(self) -> List[BaseTool]:
         """Get the tools in the toolkit."""

libs/langchain/langchain/agents/agent_toolkits/nla/toolkit.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from typing import Any, List, Optional, Sequence
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.agents.agent_toolkits.nla.tool import NLATool

libs/langchain/langchain/agents/agent_toolkits/office365/toolkit.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING, List
 
-from pydantic_v1 import Field
+from pydantic import ConfigDict, Field
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.tools import BaseTool
@@ -21,11 +21,7 @@ class O365Toolkit(BaseToolkit):
     """Toolkit for interacting with Office 365."""
 
     account: Account = Field(default_factory=authenticate)
-
-    class Config:
-        """Pydantic config."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def get_tools(self) -> List[BaseTool]:
         """Get the tools in the toolkit."""

libs/langchain/langchain/agents/agent_toolkits/openapi/planner.py

@@ -5,7 +5,7 @@ from functools import partial
 from typing import Any, Callable, Dict, List, Optional
 
 import yaml
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.agents.agent import AgentExecutor
 from langchain.agents.agent_toolkits.openapi.planner_prompt import (

libs/langchain/langchain/agents/agent_toolkits/playwright/toolkit.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING, List, Optional, Type, cast
 
-from pydantic_v1 import Extra, root_validator
+from pydantic import ConfigDict, root_validator
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.tools.base import BaseTool
@@ -36,12 +36,7 @@ class PlayWrightBrowserToolkit(BaseToolkit):
 
     sync_browser: Optional["SyncBrowser"] = None
     async_browser: Optional["AsyncBrowser"] = None
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @root_validator
     def validate_imports_and_browser_provided(cls, values: dict) -> dict:

libs/langchain/langchain/agents/agent_toolkits/powerbi/toolkit.py

@@ -1,7 +1,7 @@
 """Toolkit for interacting with a Power BI dataset."""
 from typing import List, Optional, Union
 
-from pydantic_v1 import Field
+from pydantic import ConfigDict, Field
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.callbacks.base import BaseCallbackManager
@@ -38,11 +38,7 @@ class PowerBIToolkit(BaseToolkit):
     callback_manager: Optional[BaseCallbackManager] = None
     output_token_limit: Optional[int] = None
     tiktoken_model_name: Optional[str] = None
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def get_tools(self) -> List[BaseTool]:
         """Get the tools in the toolkit."""

libs/langchain/langchain/agents/agent_toolkits/spark_sql/toolkit.py

@@ -1,7 +1,7 @@
 """Toolkit for interacting with Spark SQL."""
 from typing import List
 
-from pydantic_v1 import Field
+from pydantic import ConfigDict, Field
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.schema.language_model import BaseLanguageModel
@@ -20,11 +20,7 @@ class SparkSQLToolkit(BaseToolkit):
 
     db: SparkSQL = Field(exclude=True)
     llm: BaseLanguageModel = Field(exclude=True)
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def get_tools(self) -> List[BaseTool]:
         """Get the tools in the toolkit."""

libs/langchain/langchain/agents/agent_toolkits/sql/toolkit.py

@@ -1,7 +1,7 @@
 """Toolkit for interacting with an SQL database."""
 from typing import List
 
-from pydantic_v1 import Field
+from pydantic import ConfigDict, Field
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.schema.language_model import BaseLanguageModel
@@ -25,11 +25,7 @@ class SQLDatabaseToolkit(BaseToolkit):
     def dialect(self) -> str:
         """Return string representation of SQL dialect to use."""
         return self.db.dialect
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def get_tools(self) -> List[BaseTool]:
         """Get the tools in the toolkit."""

libs/langchain/langchain/agents/agent_toolkits/vectorstore/toolkit.py

@@ -1,7 +1,7 @@
 """Toolkit for interacting with a vector store."""
 from typing import List
 
-from pydantic_v1 import BaseModel, Field
+from pydantic import ConfigDict, BaseModel, Field
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.llms.openai import OpenAI
@@ -20,11 +20,7 @@ class VectorStoreInfo(BaseModel):
     vectorstore: VectorStore = Field(exclude=True)
     name: str
     description: str
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
 
 class VectorStoreToolkit(BaseToolkit):
@@ -32,11 +28,7 @@ class VectorStoreToolkit(BaseToolkit):
 
     vectorstore_info: VectorStoreInfo = Field(exclude=True)
     llm: BaseLanguageModel = Field(default_factory=lambda: OpenAI(temperature=0))
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def get_tools(self) -> List[BaseTool]:
         """Get the tools in the toolkit."""
@@ -66,11 +58,7 @@ class VectorStoreRouterToolkit(BaseToolkit):
 
     vectorstores: List[VectorStoreInfo] = Field(exclude=True)
     llm: BaseLanguageModel = Field(default_factory=lambda: OpenAI(temperature=0))
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def get_tools(self) -> List[BaseTool]:
         """Get the tools in the toolkit."""

libs/langchain/langchain/agents/chat/base.py

@@ -1,6 +1,6 @@
 from typing import Any, List, Optional, Sequence, Tuple
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.agents.agent import Agent, AgentOutputParser
 from langchain.agents.chat.output_parser import ChatOutputParser

libs/langchain/langchain/agents/conversational/base.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any, List, Optional, Sequence
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.agents.agent import Agent, AgentOutputParser
 from langchain.agents.agent_types import AgentType

libs/langchain/langchain/agents/conversational_chat/base.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any, List, Optional, Sequence, Tuple
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.agents.agent import Agent, AgentOutputParser
 from langchain.agents.conversational_chat.output_parser import ConvoOutputParser

libs/langchain/langchain/agents/mrkl/base.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any, Callable, List, NamedTuple, Optional, Sequence
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.agents.agent import Agent, AgentExecutor, AgentOutputParser
 from langchain.agents.agent_types import AgentType

libs/langchain/langchain/agents/openai_functions_agent/base.py

@@ -4,7 +4,7 @@ from dataclasses import dataclass
 from json import JSONDecodeError
 from typing import Any, List, Optional, Sequence, Tuple, Union
 
-from pydantic_v1 import root_validator
+from pydantic import root_validator
 
 from langchain.agents import BaseSingleActionAgent
 from langchain.callbacks.base import BaseCallbackManager

libs/langchain/langchain/agents/openai_functions_multi_agent/base.py

@@ -4,7 +4,7 @@ from dataclasses import dataclass
 from json import JSONDecodeError
 from typing import Any, List, Optional, Sequence, Tuple, Union
 
-from pydantic_v1 import root_validator
+from pydantic import root_validator
 
 from langchain.agents import BaseMultiActionAgent
 from langchain.callbacks.base import BaseCallbackManager

libs/langchain/langchain/agents/react/base.py

@@ -1,7 +1,7 @@
 """Chain that implements the ReAct paper from https://arxiv.org/pdf/2210.03629.pdf."""
 from typing import Any, List, Optional, Sequence
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.agents.agent import Agent, AgentExecutor, AgentOutputParser
 from langchain.agents.agent_types import AgentType

libs/langchain/langchain/agents/self_ask_with_search/base.py

@@ -1,7 +1,7 @@
 """Chain that does self-ask with search."""
 from typing import Any, Sequence, Union
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.agents.agent import Agent, AgentExecutor, AgentOutputParser
 from langchain.agents.agent_types import AgentType

libs/langchain/langchain/agents/structured_chat/base.py

@@ -1,7 +1,7 @@
 import re
 from typing import Any, List, Optional, Sequence, Tuple
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.agents.agent import Agent, AgentOutputParser
 from langchain.agents.structured_chat.output_parser import (

libs/langchain/langchain/agents/structured_chat/output_parser.py

@@ -5,7 +5,7 @@ import logging
 import re
 from typing import Optional, Union
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.agents.agent import AgentOutputParser
 from langchain.agents.structured_chat.prompt import FORMAT_INSTRUCTIONS

libs/langchain/langchain/callbacks/tracers/schemas.py

@@ -5,14 +5,26 @@ import datetime
 import warnings
 from typing import Any, Dict, List, Optional
 from uuid import UUID
+from enum import Enum
 
-from langsmith.schemas import RunBase as BaseRunV2
-from langsmith.schemas import RunTypeEnum as RunTypeEnumDep
-from pydantic_v1 import BaseModel, Field, root_validator
+from pydantic import model_validator, BaseModel, Field
 
+# from langsmith.schemas import RunBase as BaseRunV2
 from langchain.schema import LLMResult
 
 
+class RunTypeEnumDep(str, Enum):
+    """(Deprecated) Enum for run types. Use string directly."""
+
+    tool = "tool"
+    chain = "chain"
+    llm = "llm"
+    retriever = "retriever"
+    embedding = "embedding"
+    prompt = "prompt"
+    parser = "parser"
+
+
 def RunTypeEnum() -> RunTypeEnumDep:
     """RunTypeEnum."""
     warnings.warn(
@@ -96,7 +108,46 @@ class ToolRun(BaseRun):
     child_tool_runs: List[ToolRun] = Field(default_factory=list)
 
 
-# Begin V2 API Schemas
+# class RunBase(BaseModel):
+#     """Base Run schema."""
+#
+#     id: UUID
+#     name: str
+#     start_time: datetime
+#     run_type: str
+#     """The type of run, such as tool, chain, llm, retriever,
+#     embedding, prompt, parser."""
+#     end_time: Optional[datetime] = None
+#     extra: Optional[dict] = None
+#     error: Optional[str] = None
+#     serialized: Optional[dict]
+#     events: Optional[List[Dict]] = None
+#     inputs: dict
+#     outputs: Optional[dict] = None
+#     reference_example_id: Optional[UUID] = None
+#     parent_run_id: Optional[UUID] = None
+#     tags: Optional[List[str]] = None
+
+
+class BaseRunV2(BaseModel):
+    """Base Run schema."""
+
+    id: UUID
+    name: str
+    start_time: datetime.datetime
+    run_type: str
+    """The type of run, such as tool, chain, llm, retriever,
+    embedding, prompt, parser."""
+    end_time: Optional[datetime.datetime] = None
+    extra: Optional[dict] = None
+    error: Optional[str] = None
+    serialized: Optional[dict]
+    events: Optional[List[Dict]] = None
+    inputs: dict
+    outputs: Optional[dict] = None
+    reference_example_id: Optional[UUID] = None
+    parent_run_id: Optional[UUID] = None
+    tags: Optional[List[str]] = None
 
 
 class Run(BaseRunV2):
@@ -107,7 +158,8 @@ class Run(BaseRunV2):
     child_runs: List[Run] = Field(default_factory=list)
     tags: Optional[List[str]] = Field(default_factory=list)
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def assign_name(cls, values: dict) -> dict:
         """Assign name to the run."""
         if values.get("name") is None:
@@ -126,7 +178,7 @@ __all__ = [
     "ChainRun",
     "LLMRun",
     "Run",
-    "RunTypeEnum",
+    "RunTypeEnumDep",
     "ToolRun",
     "TracerSession",
     "TracerSessionBase",

libs/langchain/langchain/chains/api/base.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Field, root_validator
+from pydantic import model_validator, Field
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,
@@ -43,7 +43,8 @@ class APIChain(Chain):
         """
         return [self.output_key]
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def validate_api_request_prompt(cls, values: Dict) -> Dict:
         """Check that api request prompt expects the right variables."""
         input_vars = values["api_request_chain"].prompt.input_variables
@@ -54,7 +55,8 @@ class APIChain(Chain):
             )
         return values
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def validate_api_answer_prompt(cls, values: Dict) -> Dict:
         """Check that api answer prompt expects the right variables."""
         input_vars = values["api_answer_chain"].prompt.input_variables

libs/langchain/langchain/chains/api/openapi/chain.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import json
 from typing import Any, Dict, List, NamedTuple, Optional, cast
 
-from pydantic_v1 import BaseModel, Field
+from pydantic import BaseModel, Field
 from requests import Response
 
 from langchain.callbacks.manager import CallbackManagerForChainRun, Callbacks
@@ -29,7 +29,7 @@ class OpenAPIEndpointChain(Chain, BaseModel):
     """Chain interacts with an OpenAPI endpoint using natural language."""
 
     api_request_chain: LLMChain
-    api_response_chain: Optional[LLMChain]
+    api_response_chain: Optional[LLMChain] = None
     api_operation: APIOperation
     requests: Requests = Field(exclude=True, default_factory=Requests)
     param_mapping: _ParamMapping = Field(alias="param_mapping")

libs/langchain/langchain/chains/base.py

@@ -10,7 +10,7 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 
 import yaml
-from pydantic_v1 import Field, root_validator, validator
+from pydantic import model_validator, ConfigDict, Field, validator
 
 import langchain
 from langchain.callbacks.base import BaseCallbackManager
@@ -122,17 +122,14 @@ class Chain(Serializable, Runnable[Dict[str, Any], Dict[str, Any]], ABC):
     and passed as arguments to the handlers defined in `callbacks`.
     You can use these to eg identify a specific instance of a chain with its use case.
     """
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     @property
     def _chain_type(self) -> str:
         raise NotImplementedError("Saving not supported for this chain type.")
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def raise_callback_manager_deprecation(cls, values: Dict) -> Dict:
         """Raise deprecation warning if callback_manager is used."""
         if values.get("callback_manager") is not None:
@@ -143,6 +140,8 @@ class Chain(Serializable, Runnable[Dict[str, Any], Dict[str, Any]], ABC):
             values["callbacks"] = values.pop("callback_manager", None)
         return values
 
+    # TODO[pydantic]: We couldn't refactor the `validator`, please replace it by `field_validator` manually.
+    # Check https://docs.pydantic.dev/dev-v2/migration/#changes-to-validators for more information.
     @validator("verbose", pre=True, always=True)
     def set_verbose(cls, verbose: Optional[bool]) -> bool:
         """Set the chain verbosity.

libs/langchain/langchain/chains/combine_documents/base.py

@@ -3,7 +3,7 @@
 from abc import ABC, abstractmethod
 from typing import Any, Dict, List, Optional, Tuple
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,

libs/langchain/langchain/chains/combine_documents/map_reduce.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional, Tuple
 
-from pydantic_v1 import Extra, root_validator
+from pydantic import model_validator, ConfigDict
 
 from langchain.callbacks.manager import Callbacks
 from langchain.chains.combine_documents.base import BaseCombineDocumentsChain
@@ -109,14 +109,10 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
         if self.return_intermediate_steps:
             _output_keys = _output_keys + ["intermediate_steps"]
         return _output_keys
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def get_reduce_chain(cls, values: Dict) -> Dict:
         """For backwards compatibility."""
         if "combine_document_chain" in values:
@@ -139,7 +135,8 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
 
         return values
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def get_return_intermediate_steps(cls, values: Dict) -> Dict:
         """For backwards compatibility."""
         if "return_map_steps" in values:
@@ -147,7 +144,8 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
             del values["return_map_steps"]
         return values
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def get_default_document_variable_name(cls, values: Dict) -> Dict:
         """Get default document variable name, if not provided."""
         if "document_variable_name" not in values:

libs/langchain/langchain/chains/combine_documents/map_rerank.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional, Sequence, Tuple, Union, cast
 
-from pydantic_v1 import Extra, root_validator
+from pydantic import model_validator, ConfigDict
 
 from langchain.callbacks.manager import Callbacks
 from langchain.chains.combine_documents.base import BaseCombineDocumentsChain
@@ -71,12 +71,7 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
     return_intermediate_steps: bool = False
     """Return intermediate steps.
     Intermediate steps include the results of calling llm_chain on each document."""
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def output_keys(self) -> List[str]:
@@ -91,7 +86,8 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
             _output_keys += self.metadata_keys
         return _output_keys
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_llm_output(cls, values: Dict) -> Dict:
         """Validate that the combine chain outputs a dictionary."""
         output_parser = values["llm_chain"].prompt.output_parser
@@ -113,7 +109,8 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
             )
         return values
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def get_default_document_variable_name(cls, values: Dict) -> Dict:
         """Get default document variable name, if not provided."""
         if "document_variable_name" not in values:

libs/langchain/langchain/chains/combine_documents/reduce.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 from typing import Any, Callable, List, Optional, Protocol, Tuple
 
-from pydantic_v1 import Extra
+from pydantic import ConfigDict
 
 from langchain.callbacks.manager import Callbacks
 from langchain.chains.combine_documents.base import BaseCombineDocumentsChain
@@ -156,12 +156,7 @@ class ReduceDocumentsChain(BaseCombineDocumentsChain):
     """The maximum number of tokens to group documents into. For example, if
     set to 3000 then documents will be grouped into chunks of no greater than
     3000 tokens before trying to combine them into a smaller chunk."""
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def _collapse_chain(self) -> BaseCombineDocumentsChain:

libs/langchain/langchain/chains/combine_documents/refine.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Tuple
 
-from pydantic_v1 import Extra, Field, root_validator
+from pydantic import model_validator, ConfigDict, Field
 
 from langchain.callbacks.manager import Callbacks
 from langchain.chains.combine_documents.base import (
@@ -97,14 +97,10 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
         if self.return_intermediate_steps:
             _output_keys = _output_keys + ["intermediate_steps"]
         return _output_keys
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def get_return_intermediate_steps(cls, values: Dict) -> Dict:
         """For backwards compatibility."""
         if "return_refine_steps" in values:
@@ -112,7 +108,8 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
             del values["return_refine_steps"]
         return values
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def get_default_document_variable_name(cls, values: Dict) -> Dict:
         """Get default document variable name, if not provided."""
         if "document_variable_name" not in values:

libs/langchain/langchain/chains/combine_documents/stuff.py

@@ -2,7 +2,7 @@
 
 from typing import Any, Dict, List, Optional, Tuple
 
-from pydantic_v1 import Extra, Field, root_validator
+from pydantic import model_validator, ConfigDict, Field
 
 from langchain.callbacks.manager import Callbacks
 from langchain.chains.combine_documents.base import (
@@ -68,14 +68,10 @@ class StuffDocumentsChain(BaseCombineDocumentsChain):
     If only one variable in the llm_chain, this need not be provided."""
     document_separator: str = "\n\n"
     """The string with which to join the formatted documents"""
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def get_default_document_variable_name(cls, values: Dict) -> Dict:
         """Get default document variable name, if not provided.
 

libs/langchain/langchain/chains/constitutional_ai/models.py

@@ -1,5 +1,5 @@
 """Models for the Constitutional AI chain."""
-from pydantic_v1 import BaseModel
+from pydantic import BaseModel
 
 
 class ConstitutionalPrinciple(BaseModel):

libs/langchain/langchain/chains/conversation/base.py

@@ -1,7 +1,7 @@
 """Chain that carries on a conversation and calls an LLM."""
 from typing import Dict, List
 
-from pydantic_v1 import Extra, Field, root_validator
+from pydantic import model_validator, ConfigDict, Field
 
 from langchain.chains.conversation.prompt import PROMPT
 from langchain.chains.llm import LLMChain
@@ -27,19 +27,15 @@ class ConversationChain(LLMChain):
 
     input_key: str = "input"  #: :meta private:
     output_key: str = "response"  #: :meta private:
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:
         """Use this since so some prompt vars come from history."""
         return [self.input_key]
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_prompt_input_variables(cls, values: Dict) -> Dict:
         """Validate that prompt input variables are consistent."""
         memory_keys = values["memory"].memory_variables

libs/langchain/langchain/chains/conversational_retrieval/base.py

@@ -7,7 +7,7 @@ from abc import abstractmethod
 from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
-from pydantic_v1 import Extra, Field, root_validator
+from pydantic import model_validator, ConfigDict, Field
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,
@@ -75,13 +75,7 @@ class BaseConversationalRetrievalChain(Chain):
     get_chat_history: Optional[Callable[[List[CHAT_TURN_TYPE]], str]] = None
     """An optional function to get a string of the chat history.
     If None is provided, will use a default."""
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-        allow_population_by_field_name = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True, populate_by_name=True)
 
     @property
     def input_keys(self) -> List[str]:
@@ -374,7 +368,8 @@ class ChatVectorDBChain(BaseConversationalRetrievalChain):
     def _chain_type(self) -> str:
         return "chat-vector-db"
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def raise_deprecation(cls, values: Dict) -> Dict:
         warnings.warn(
             "`ChatVectorDBChain` is deprecated - "

libs/langchain/langchain/chains/elasticsearch_database/base.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING, Any, Dict, List, Optional
 
-from pydantic_v1 import Extra, root_validator
+from pydantic import model_validator, ConfigDict
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
@@ -36,7 +36,7 @@ class ElasticsearchDatabaseChain(Chain):
     """Chain for creating the ES query."""
     answer_chain: LLMChain
     """Chain for answering the user question."""
-    database: Any
+    database: Any = None
     """Elasticsearch database to connect to of type elasticsearch.Elasticsearch."""
     top_k: int = 10
     """Number of results to return from the query"""
@@ -47,14 +47,10 @@ class ElasticsearchDatabaseChain(Chain):
     sample_documents_in_index_info: int = 3
     return_intermediate_steps: bool = False
     """Whether or not to return the intermediate steps along with the final answer."""
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_indices(cls, values: dict) -> dict:
         if values["include_indices"] and values["ignore_indices"]:
             raise ValueError(

libs/langchain/langchain/chains/flare/base.py

@@ -5,7 +5,7 @@ from abc import abstractmethod
 from typing import Any, Dict, List, Optional, Sequence, Tuple
 
 import numpy as np
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import (
     CallbackManagerForChainRun,

libs/langchain/langchain/chains/graph_qa/arangodb.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import re
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.manager import CallbackManagerForChainRun

libs/langchain/langchain/chains/graph_qa/base.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain

libs/langchain/langchain/chains/graph_qa/cypher.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import re
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain

libs/langchain/langchain/chains/graph_qa/hugegraph.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain

libs/langchain/langchain/chains/graph_qa/kuzu.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain

libs/langchain/langchain/chains/graph_qa/nebulagraph.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain

libs/langchain/langchain/chains/graph_qa/neptune_cypher.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import re
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.manager import CallbackManagerForChainRun

libs/langchain/langchain/chains/graph_qa/sparql.py

@@ -5,7 +5,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain

libs/langchain/langchain/chains/hyde/base.py

@@ -7,7 +7,7 @@ from __future__ import annotations
 from typing import Any, Dict, List, Optional
 
 import numpy as np
-from pydantic_v1 import Extra
+from pydantic import ConfigDict
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
@@ -25,12 +25,7 @@ class HypotheticalDocumentEmbedder(Chain, Embeddings):
 
     base_embeddings: Embeddings
     llm_chain: LLMChain
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:

libs/langchain/langchain/chains/llm.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import warnings
 from typing import Any, Dict, List, Optional, Sequence, Tuple, Union
 
-from pydantic_v1 import Extra, Field
+from pydantic import ConfigDict, Field
 
 from langchain.callbacks.manager import (
     AsyncCallbackManager,
@@ -58,12 +58,7 @@ class LLMChain(Chain):
     """Whether to return only the final parsed result. Defaults to True.
     If false, will return a bunch of extra information about the generation."""
     llm_kwargs: dict = Field(default_factory=dict)
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:

libs/langchain/langchain/chains/llm_bash/base.py

@@ -5,7 +5,7 @@ import logging
 import warnings
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Extra, Field, root_validator
+from pydantic import model_validator, ConfigDict, Field, root_validator
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
@@ -36,14 +36,10 @@ class LLMBashChain(Chain):
     prompt: BasePromptTemplate = PROMPT
     """[Deprecated]"""
     bash_process: BashProcess = Field(default_factory=BashProcess)  #: :meta private:
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def raise_deprecation(cls, values: Dict) -> Dict:
         if "llm" in values:
             warnings.warn(

libs/langchain/langchain/chains/llm_checker/base.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import warnings
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Extra, root_validator
+from pydantic import model_validator, ConfigDict
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
@@ -87,14 +87,10 @@ class LLMCheckerChain(Chain):
     """[Deprecated] Prompt to use when questioning the documents."""
     input_key: str = "query"  #: :meta private:
     output_key: str = "result"  #: :meta private:
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def raise_deprecation(cls, values: Dict) -> Dict:
         if "llm" in values:
             warnings.warn(

libs/langchain/langchain/chains/llm_math/base.py

@@ -7,7 +7,7 @@ import warnings
 from typing import Any, Dict, List, Optional
 
 import numexpr
-from pydantic_v1 import Extra, root_validator
+from pydantic import model_validator, ConfigDict
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,
@@ -37,14 +37,10 @@ class LLMMathChain(Chain):
     """[Deprecated] Prompt to use to translate to python if necessary."""
     input_key: str = "question"  #: :meta private:
     output_key: str = "answer"  #: :meta private:
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def raise_deprecation(cls, values: Dict) -> Dict:
         if "llm" in values:
             warnings.warn(

libs/langchain/langchain/chains/llm_requests.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Extra, Field, root_validator
+from pydantic import model_validator, ConfigDict, Field
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains import LLMChain
@@ -27,12 +27,7 @@ class LLMRequestsChain(Chain):
     requests_key: str = "requests_result"  #: :meta private:
     input_key: str = "url"  #: :meta private:
     output_key: str = "output"  #: :meta private:
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:
@@ -50,7 +45,8 @@ class LLMRequestsChain(Chain):
         """
         return [self.output_key]
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""
         try:

libs/langchain/langchain/chains/llm_summarization_checker/base.py

@@ -6,7 +6,7 @@ import warnings
 from pathlib import Path
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Extra, root_validator
+from pydantic import model_validator, ConfigDict
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
@@ -101,14 +101,10 @@ class LLMSummarizationCheckerChain(Chain):
     output_key: str = "result"  #: :meta private:
     max_checks: int = 2
     """Maximum number of times to check the assertions. Default to double-checking."""
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def raise_deprecation(cls, values: Dict) -> Dict:
         if "llm" in values:
             warnings.warn(

libs/langchain/langchain/chains/llm_symbolic_math/base.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import re
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Extra
+from pydantic import ConfigDict
 
 from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.manager import (
@@ -30,12 +30,7 @@ class LLMSymbolicMathChain(Chain):
     llm_chain: LLMChain
     input_key: str = "question"  #: :meta private:
     output_key: str = "answer"  #: :meta private:
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:

libs/langchain/langchain/chains/mapreduce.py

@@ -7,7 +7,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Mapping, Optional
 
-from pydantic_v1 import Extra
+from pydantic import ConfigDict
 
 from langchain.callbacks.manager import CallbackManagerForChainRun, Callbacks
 from langchain.chains import ReduceDocumentsChain
@@ -65,12 +65,7 @@ class MapReduceChain(Chain):
             callbacks=callbacks,
             **kwargs,
         )
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:

libs/langchain/langchain/chains/moderation.py

@@ -1,7 +1,7 @@
 """Pass input through a moderation endpoint."""
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import root_validator
+from pydantic import model_validator
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
@@ -34,7 +34,8 @@ class OpenAIModerationChain(Chain):
     openai_api_key: Optional[str] = None
     openai_organization: Optional[str] = None
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""
         openai_api_key = get_from_dict_or_env(

libs/langchain/langchain/chains/natbot/base.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import warnings
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Extra, root_validator
+from pydantic import model_validator, ConfigDict
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
@@ -33,14 +33,10 @@ class NatBotChain(Chain):
     input_browser_content_key: str = "browser_content"  #: :meta private:
     previous_command: str = ""  #: :meta private:
     output_key: str = "command"  #: :meta private:
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def raise_deprecation(cls, values: Dict) -> Dict:
         if "llm" in values:
             warnings.warn(

libs/langchain/langchain/chains/openai_functions/base.py

@@ -12,7 +12,7 @@ from typing import (
     Union,
 )
 
-from pydantic_v1 import BaseModel
+from pydantic import BaseModel
 
 from langchain.base_language import BaseLanguageModel
 from langchain.chains import LLMChain

libs/langchain/langchain/chains/openai_functions/citation_fuzzy_match.py

@@ -1,6 +1,6 @@
 from typing import Iterator, List
 
-from pydantic_v1 import BaseModel, Field
+from pydantic import BaseModel, Field
 
 from langchain.chains.llm import LLMChain
 from langchain.chains.openai_functions.utils import get_llm_kwargs

libs/langchain/langchain/chains/openai_functions/extraction.py

@@ -1,6 +1,6 @@
 from typing import Any, List
 
-from pydantic_v1 import BaseModel
+from pydantic import BaseModel
 
 from langchain.chains.base import Chain
 from langchain.chains.llm import LLMChain

libs/langchain/langchain/chains/openai_functions/qa_with_structure.py

@@ -1,6 +1,6 @@
 from typing import Any, List, Optional, Type, Union
 
-from pydantic_v1 import BaseModel, Field
+from pydantic import BaseModel, Field
 
 from langchain.chains.llm import LLMChain
 from langchain.chains.openai_functions.utils import get_llm_kwargs

libs/langchain/langchain/chains/prompt_selector.py

@@ -1,7 +1,7 @@
 from abc import ABC, abstractmethod
 from typing import Callable, List, Tuple
 
-from pydantic_v1 import BaseModel, Field
+from pydantic import BaseModel, Field
 
 from langchain.chat_models.base import BaseChatModel
 from langchain.llms.base import BaseLLM

libs/langchain/langchain/chains/qa_generation/base.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import json
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain

libs/langchain/langchain/chains/qa_with_sources/base.py

@@ -7,7 +7,7 @@ import re
 from abc import ABC, abstractmethod
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Extra, root_validator
+from pydantic import model_validator, ConfigDict
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,
@@ -86,12 +86,7 @@ class BaseQAWithSourcesChain(Chain, ABC):
             llm, chain_type=chain_type, **_chain_kwargs
         )
         return cls(combine_documents_chain=combine_documents_chain, **kwargs)
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:
@@ -112,7 +107,8 @@ class BaseQAWithSourcesChain(Chain, ABC):
             _output_keys = _output_keys + ["source_documents"]
         return _output_keys
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def validate_naming(cls, values: Dict) -> Dict:
         """Fix backwards compatibility in naming."""
         if "combine_document_chain" in values:

libs/langchain/langchain/chains/qa_with_sources/retrieval.py

@@ -2,7 +2,7 @@
 
 from typing import Any, Dict, List
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,

libs/langchain/langchain/chains/qa_with_sources/vector_db.py

@@ -3,7 +3,7 @@
 import warnings
 from typing import Any, Dict, List
 
-from pydantic_v1 import Field, root_validator
+from pydantic import model_validator, Field
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,
@@ -63,7 +63,8 @@ class VectorDBQAWithSourcesChain(BaseQAWithSourcesChain):
     ) -> List[Document]:
         raise NotImplementedError("VectorDBQAWithSourcesChain does not support async")
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def raise_deprecation(cls, values: Dict) -> Dict:
         warnings.warn(
             "`VectorDBQAWithSourcesChain` is deprecated - "

libs/langchain/langchain/chains/query_constructor/ir.py

@@ -5,7 +5,7 @@ from abc import ABC, abstractmethod
 from enum import Enum
 from typing import Any, List, Optional, Sequence, Union
 
-from pydantic_v1 import BaseModel
+from pydantic import BaseModel
 
 
 class Visitor(ABC):
@@ -98,7 +98,7 @@ class Comparison(FilterDirective):
 
     comparator: Comparator
     attribute: str
-    value: Any
+    value: Any = None
 
 
 class Operation(FilterDirective):
@@ -113,7 +113,7 @@ class StructuredQuery(Expr):
 
     query: str
     """Query string."""
-    filter: Optional[FilterDirective]
+    filter: Optional[FilterDirective] = None
     """Filtering expression."""
-    limit: Optional[int]
+    limit: Optional[int] = None
     """Limit on the number of results."""

libs/langchain/langchain/chains/query_constructor/schema.py

@@ -1,4 +1,4 @@
-from pydantic_v1 import BaseModel
+from pydantic import ConfigDict, BaseModel
 
 
 class AttributeInfo(BaseModel):
@@ -7,9 +7,4 @@ class AttributeInfo(BaseModel):
     name: str
     description: str
     type: str
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
-        frozen = True
+    model_config = ConfigDict(arbitrary_types_allowed=True, frozen=True)

libs/langchain/langchain/chains/retrieval_qa/base.py

@@ -6,7 +6,7 @@ import warnings
 from abc import abstractmethod
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Extra, Field, root_validator
+from pydantic import model_validator, ConfigDict, Field
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,
@@ -34,13 +34,7 @@ class BaseRetrievalQA(Chain):
     output_key: str = "result"  #: :meta private:
     return_source_documents: bool = False
     """Return the source documents or not."""
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
-        allow_population_by_field_name = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True, populate_by_name=True)
 
     @property
     def input_keys(self) -> List[str]:
@@ -247,7 +241,8 @@ class VectorDBQA(BaseRetrievalQA):
     search_kwargs: Dict[str, Any] = Field(default_factory=dict)
     """Extra search args."""
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def raise_deprecation(cls, values: Dict) -> Dict:
         warnings.warn(
             "`VectorDBQA` is deprecated - "
@@ -255,7 +250,8 @@ class VectorDBQA(BaseRetrievalQA):
         )
         return values
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_search_type(cls, values: Dict) -> Dict:
         """Validate search type."""
         if "search_type" in values:

libs/langchain/langchain/chains/router/base.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 from abc import ABC
 from typing import Any, Dict, List, Mapping, NamedTuple, Optional
 
-from pydantic_v1 import Extra
+from pydantic import ConfigDict
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,
@@ -59,12 +59,7 @@ class MultiRouteChain(Chain):
     silent_errors: bool = False
     """If True, use default_chain when an invalid destination name is provided. 
     Defaults to False."""
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:

libs/langchain/langchain/chains/router/embedding_router.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional, Sequence, Tuple, Type
 
-from pydantic_v1 import Extra
+from pydantic import ConfigDict
 
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.router.base import RouterChain
@@ -16,12 +16,7 @@ class EmbeddingRouterChain(RouterChain):
 
     vectorstore: VectorStore
     routing_keys: List[str] = ["query"]
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:

libs/langchain/langchain/chains/router/llm_router.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional, Type, cast
 
-from pydantic_v1 import root_validator
+from pydantic import model_validator
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,
@@ -22,7 +22,8 @@ class LLMRouterChain(RouterChain):
     llm_chain: LLMChain
     """LLM chain used to perform routing"""
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_prompt(cls, values: dict) -> dict:
         prompt = values["llm_chain"].prompt
         if prompt.output_parser is None:

libs/langchain/langchain/chains/sequential.py

@@ -1,7 +1,7 @@
 """Chain pipeline where the outputs of one step feed directly into next."""
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import Extra, root_validator
+from pydantic import model_validator, ConfigDict
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,
@@ -18,12 +18,7 @@ class SequentialChain(Chain):
     input_variables: List[str]
     output_variables: List[str]  #: :meta private:
     return_all: bool = False
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:
@@ -41,7 +36,8 @@ class SequentialChain(Chain):
         """
         return self.output_variables
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def validate_chains(cls, values: Dict) -> Dict:
         """Validate that the correct inputs exist for all chains."""
         chains = values["chains"]
@@ -129,12 +125,7 @@ class SimpleSequentialChain(Chain):
     strip_outputs: bool = False
     input_key: str = "input"  #: :meta private:
     output_key: str = "output"  #: :meta private:
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        extra = Extra.forbid
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     @property
     def input_keys(self) -> List[str]:
@@ -152,7 +143,8 @@ class SimpleSequentialChain(Chain):
         """
         return [self.output_key]
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_chains(cls, values: Dict) -> Dict:
         """Validate that chains are all single input/output."""
         for chain in values["chains"]:

libs/langchain/langchain/chains/transform.py

@@ -3,7 +3,7 @@ import functools
 import logging
 from typing import Any, Awaitable, Callable, Dict, List, Optional
 
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForChainRun,

libs/langchain/langchain/chat_models/anyscale.py

@@ -7,7 +7,7 @@ import sys
 from typing import TYPE_CHECKING, Optional, Set
 
 import requests
-from pydantic_v1 import Field, root_validator
+from pydantic import model_validator, Field
 
 from langchain.adapters.openai import convert_message_to_dict
 from langchain.chat_models.openai import (
@@ -95,7 +95,8 @@ class ChatAnyscale(ChatOpenAI):
 
         return {model["id"] for model in models_response.json()["data"]}
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def validate_environment_override(cls, values: dict) -> dict:
         """Validate that api key and python package exists in environment."""
         values["openai_api_key"] = get_from_dict_or_env(

libs/langchain/langchain/chat_models/azure_openai.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import logging
 from typing import Any, Dict, Mapping
 
-from pydantic_v1 import root_validator
+from pydantic import model_validator
 
 from langchain.chat_models.openai import ChatOpenAI
 from langchain.schema import ChatResult
@@ -61,7 +61,8 @@ class AzureChatOpenAI(ChatOpenAI):
     openai_organization: str = ""
     openai_proxy: str = ""
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""
         values["openai_api_key"] = get_from_dict_or_env(

libs/langchain/langchain/chat_models/azureml_endpoint.py

@@ -1,7 +1,7 @@
 import json
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import validator
+from pydantic import validator
 
 from langchain.callbacks.manager import CallbackManagerForLLMRun
 from langchain.chat_models.base import SimpleChatModel
@@ -96,6 +96,8 @@ class AzureMLChatOnlineEndpoint(SimpleChatModel):
     model_kwargs: Optional[dict] = None
     """Key word arguments to pass to the model."""
 
+    # TODO[pydantic]: We couldn't refactor the `validator`, please replace it by `field_validator` manually.
+    # Check https://docs.pydantic.dev/dev-v2/migration/#changes-to-validators for more information.
     @validator("http_client", always=True, allow_reuse=True)
     @classmethod
     def validate_client(cls, field_value: Any, values: Dict) -> AzureMLEndpointClient:

libs/langchain/langchain/chat_models/base.py

@@ -14,7 +14,7 @@ from typing import (
     cast,
 )
 
-from pydantic_v1 import Field, root_validator
+from pydantic import model_validator, ConfigDict, Field
 
 import langchain
 from langchain.callbacks.base import BaseCallbackManager
@@ -66,7 +66,8 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
     metadata: Optional[Dict[str, Any]] = Field(default=None, exclude=True)
     """Metadata to add to the run trace."""
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def raise_deprecation(cls, values: Dict) -> Dict:
         """Raise deprecation warning if callback_manager is used."""
         if values.get("callback_manager") is not None:
@@ -76,11 +77,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
             )
             values["callbacks"] = values.pop("callback_manager", None)
         return values
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     # --- Runnable methods ---
 

libs/langchain/langchain/chat_models/ernie.py

@@ -3,7 +3,7 @@ import threading
 from typing import Any, Dict, List, Mapping, Optional
 
 import requests
-from pydantic_v1 import root_validator
+from pydantic import model_validator
 
 from langchain.callbacks.manager import CallbackManagerForLLMRun
 from langchain.chat_models.base import BaseChatModel
@@ -69,7 +69,8 @@ class ErnieBotChat(BaseChatModel):
 
     _lock = threading.Lock()
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         values["ernie_client_id"] = get_from_dict_or_env(
             values,

libs/langchain/langchain/chat_models/google_palm.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import logging
 from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional
 
-from pydantic_v1 import BaseModel, root_validator
+from pydantic import model_validator, BaseModel
 from tenacity import (
     before_sleep_log,
     retry,
@@ -231,7 +231,7 @@ class ChatGooglePalm(BaseChatModel, BaseModel):
 
     """
 
-    client: Any  #: :meta private:
+    client: Any = None  #: :meta private:
     model_name: str = "models/chat-bison-001"
     """Model name to use."""
     google_api_key: Optional[str] = None
@@ -248,7 +248,8 @@ class ChatGooglePalm(BaseChatModel, BaseModel):
     """Number of chat completions to generate for each prompt. Note that the API may
        not return the full n completions if duplicates are generated."""
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate api key, python package exists, temperature, top_p, and top_k."""
         google_api_key = get_from_dict_or_env(

libs/langchain/langchain/chat_models/human.py

@@ -5,7 +5,7 @@ from io import StringIO
 from typing import Any, Callable, Dict, List, Mapping, Optional
 
 import yaml
-from pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForLLMRun,

libs/langchain/langchain/chat_models/jinachat.py

@@ -15,7 +15,7 @@ from typing import (
     Union,
 )
 
-from pydantic_v1 import Field, root_validator
+from pydantic import model_validator, ConfigDict, Field
 from tenacity import (
     before_sleep_log,
     retry,
@@ -180,13 +180,10 @@ class JinaChat(BaseChatModel):
     """Whether to stream the results or not."""
     max_tokens: Optional[int] = None
     """Maximum number of tokens to generate."""
+    model_config = ConfigDict(populate_by_name=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        allow_population_by_field_name = True
-
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def build_extra(cls, values: Dict[str, Any]) -> Dict[str, Any]:
         """Build extra kwargs from additional params that were passed in."""
         all_required_field_names = get_pydantic_field_names(cls)
@@ -212,7 +209,8 @@ class JinaChat(BaseChatModel):
         values["model_kwargs"] = extra
         return values
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""
         values["jinachat_api_key"] = get_from_dict_or_env(

libs/langchain/langchain/chat_models/litellm.py

@@ -15,7 +15,7 @@ from typing import (
     Union,
 )
 
-from pydantic_v1 import Field, root_validator
+from pydantic import model_validator, Field
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForLLMRun,
@@ -272,7 +272,8 @@ class ChatLiteLLM(BaseChatModel):
 
         return _completion_with_retry(**kwargs)
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate api key, python package exists, temperature, top_p, and top_k."""
         try:

libs/langchain/langchain/chat_models/mlflow_ai_gateway.py

@@ -3,7 +3,7 @@ import logging
 from functools import partial
 from typing import Any, Dict, List, Mapping, Optional
 
-from pydantic_v1 import BaseModel, Extra
+from pydantic import BaseModel, Extra
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForLLMRun,

libs/langchain/langchain/chat_models/openai.py

@@ -17,7 +17,7 @@ from typing import (
     Union,
 )
 
-from pydantic_v1 import Field, root_validator
+from pydantic import model_validator, ConfigDict, Field
 
 from langchain.adapters.openai import convert_dict_to_message, convert_message_to_dict
 from langchain.callbacks.manager import (
@@ -175,13 +175,10 @@ class ChatOpenAI(BaseChatModel):
     when using one of the many model providers that expose an OpenAI-like 
     API but with different models. In those cases, in order to avoid erroring 
     when tiktoken is called, you can specify a model name to use here."""
+    model_config = ConfigDict(populate_by_name=True)
 
-    class Config:
-        """Configuration for this pydantic object."""
-
-        allow_population_by_field_name = True
-
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def build_extra(cls, values: Dict[str, Any]) -> Dict[str, Any]:
         """Build extra kwargs from additional params that were passed in."""
         all_required_field_names = get_pydantic_field_names(cls)
@@ -207,7 +204,8 @@ class ChatOpenAI(BaseChatModel):
         values["model_kwargs"] = extra
         return values
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""
         values["openai_api_key"] = get_from_dict_or_env(

libs/langchain/langchain/chat_models/vertexai.py

@@ -2,7 +2,7 @@
 from dataclasses import dataclass, field
 from typing import TYPE_CHECKING, Any, Dict, List, Optional
 
-from pydantic_v1 import root_validator
+from pydantic import model_validator
 
 from langchain.callbacks.manager import CallbackManagerForLLMRun
 from langchain.chat_models.base import BaseChatModel
@@ -97,7 +97,8 @@ class ChatVertexAI(_VertexAICommon, BaseChatModel):
 
     model_name: str = "chat-bison"
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that the python package exists in environment."""
         cls._try_init_vertexai(values)

libs/langchain/langchain/document_loaders/apify_dataset.py

@@ -1,6 +1,6 @@
 from typing import Any, Callable, Dict, List
 
-from pydantic_v1 import BaseModel, root_validator
+from pydantic import model_validator, BaseModel
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader
@@ -26,7 +26,7 @@ class ApifyDatasetLoader(BaseLoader, BaseModel):
             documents = loader.load()
     """  # noqa: E501
 
-    apify_client: Any
+    apify_client: Any = None
     """An instance of the ApifyClient class from the apify-client Python package."""
     dataset_id: str
     """The ID of the dataset on the Apify platform."""
@@ -49,7 +49,8 @@ class ApifyDatasetLoader(BaseLoader, BaseModel):
             dataset_id=dataset_id, dataset_mapping_function=dataset_mapping_function
         )
 
-    @root_validator()
+    @model_validator(mode='before')
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate environment.
 

libs/langchain/langchain/document_loaders/blob_loaders/schema.py

@@ -13,7 +13,7 @@ from io import BufferedReader, BytesIO
 from pathlib import PurePath
 from typing import Any, Generator, Iterable, Mapping, Optional, Union
 
-from pydantic_v1 import BaseModel, root_validator
+from pydantic import model_validator, ConfigDict, BaseModel
 
 PathLike = Union[str, PurePath]
 
@@ -28,7 +28,7 @@ class Blob(BaseModel):
     Inspired by: https://developer.mozilla.org/en-US/docs/Web/API/Blob
     """
 
-    data: Union[bytes, str, None]  # Raw data
+    data: Union[bytes, str, None] = None  # Raw data
     mimetype: Optional[str] = None  # Not to be confused with a file extension
     encoding: str = "utf-8"  # Use utf-8 as default encoding, if decoding to string
     # Location where the original content was found
@@ -36,17 +36,15 @@ class Blob(BaseModel):
     # Useful for situations where downstream code assumes it must work with file paths
     # rather than in-memory content.
     path: Optional[PathLike] = None
-
-    class Config:
-        arbitrary_types_allowed = True
-        frozen = True
+    model_config = ConfigDict(arbitrary_types_allowed=True, frozen=True)
 
     @property
     def source(self) -> Optional[str]:
         """The source location of the blob as string if known otherwise none."""
         return str(self.path) if self.path else None
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def check_blob_is_valid(cls, values: Mapping[str, Any]) -> Mapping[str, Any]:
         """Verify that either data or path is provided."""
         if "data" not in values and "path" not in values:

libs/langchain/langchain/document_loaders/docugami.py

@@ -6,7 +6,7 @@ from pathlib import Path
 from typing import Any, Dict, List, Mapping, Optional, Sequence, Union
 
 import requests
-from pydantic_v1 import BaseModel, root_validator
+from pydantic import BaseModel, root_validator
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader
@@ -37,11 +37,11 @@ class DocugamiLoader(BaseLoader, BaseModel):
 
     access_token: Optional[str] = os.environ.get("DOCUGAMI_API_KEY")
     """The Docugami API access token to use."""
-    docset_id: Optional[str]
+    docset_id: Optional[str] = None
     """The Docugami API docset ID to use."""
-    document_ids: Optional[Sequence[str]]
+    document_ids: Optional[Sequence[str]] = None
     """The Docugami API document IDs to use."""
-    file_paths: Optional[Sequence[Union[Path, str]]]
+    file_paths: Optional[Sequence[Union[Path, str]]] = None
     """The local file paths to use."""
     min_chunk_size: int = 32  # appended to the next chunk to avoid over-chunking
     """The minimum chunk size to use when parsing DGML. Defaults to 32."""

libs/langchain/langchain/document_loaders/dropbox.py

@@ -11,7 +11,7 @@ import tempfile
 from pathlib import Path
 from typing import Any, Dict, List, Optional
 
-from pydantic_v1 import BaseModel, root_validator
+from pydantic import BaseModel, root_validator
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader

libs/langchain/langchain/document_loaders/embaas.py

@@ -3,7 +3,7 @@ import warnings
 from typing import Any, Dict, Iterator, List, Optional
 
 import requests
-from pydantic_v1 import BaseModel, root_validator, validator
+from pydantic import model_validator, BaseModel, validator
 from typing_extensions import NotRequired, TypedDict
 
 from langchain.docstore.document import Document
@@ -61,7 +61,8 @@ class BaseEmbaasLoader(BaseModel):
     params: EmbaasDocumentExtractionParameters = EmbaasDocumentExtractionParameters()
     """Additional parameters to pass to the Embaas document extraction API."""
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""
         embaas_api_key = get_from_dict_or_env(
@@ -208,9 +209,11 @@ class EmbaasLoader(BaseEmbaasLoader, BaseLoader):
 
     file_path: str
     """The path to the file to load."""
-    blob_loader: Optional[EmbaasBlobLoader]
+    blob_loader: Optional[EmbaasBlobLoader] = None
     """The blob loader to use. If not provided, a default one will be created."""
 
+    # TODO[pydantic]: We couldn't refactor the `validator`, please replace it by `field_validator` manually.
+    # Check https://docs.pydantic.dev/dev-v2/migration/#changes-to-validators for more information.
     @validator("blob_loader", always=True)
     def validate_blob_loader(
         cls, v: EmbaasBlobLoader, values: Dict

libs/langchain/langchain/document_loaders/github.py

@@ -3,7 +3,7 @@ from datetime import datetime
 from typing import Dict, Iterator, List, Literal, Optional, Union
 
 import requests
-from pydantic_v1 import BaseModel, root_validator, validator
+from pydantic import BaseModel, root_validator, validator
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader

libs/langchain/langchain/document_loaders/googledrive.py

@@ -11,7 +11,7 @@ import os
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Sequence, Union
 
-from pydantic_v1 import BaseModel, root_validator, validator
+from pydantic import field_validator, BaseModel, root_validator
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader
@@ -94,7 +94,8 @@ class GoogleDriveLoader(BaseLoader, BaseModel):
             values["file_types"] = [full_form(file_type) for file_type in file_types]
         return values
 
-    @validator("credentials_path")
+    @field_validator("credentials_path")
+    @classmethod
     def validate_credentials_path(cls, v: Any, **kwargs: Any) -> Any:
         """Validate that credentials_path exists."""
         if not v.exists():

libs/langchain/langchain/document_loaders/onedrive.py

@@ -8,11 +8,12 @@ from enum import Enum
 from pathlib import Path
 from typing import TYPE_CHECKING, Dict, List, Optional, Type, Union
 
-from pydantic_v1 import BaseModel, BaseSettings, Field, FilePath, SecretStr
+from pydantic import BaseModel, Field, FilePath, SecretStr
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader
 from langchain.document_loaders.onedrive_file import OneDriveFileLoader
+from pydantic_settings import BaseSettings, SettingsConfigDict
 
 if TYPE_CHECKING:
     from O365 import Account
@@ -23,13 +24,9 @@ logger = logging.getLogger(__name__)
 
 
 class _OneDriveSettings(BaseSettings):
-    client_id: str = Field(..., env="O365_CLIENT_ID")
-    client_secret: SecretStr = Field(..., env="O365_CLIENT_SECRET")
-
-    class Config:
-        env_prefix = ""
-        case_sentive = False
-        env_file = ".env"
+    client_id: str = Field(..., validation_alias="O365_CLIENT_ID")
+    client_secret: SecretStr = Field(..., validation_alias="O365_CLIENT_SECRET")
+    model_config = SettingsConfigDict(env_prefix="", case_sentive=False, env_file=".env")
 
 
 class _OneDriveTokenStorage(BaseSettings):

libs/langchain/langchain/document_loaders/onedrive_file.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import tempfile
 from typing import TYPE_CHECKING, List
 
-from pydantic_v1 import BaseModel, Field
+from pydantic import ConfigDict, BaseModel, Field
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader
@@ -20,11 +20,7 @@ class OneDriveFileLoader(BaseLoader, BaseModel):
 
     file: File = Field(...)
     """The file to load."""
-
-    class Config:
-        arbitrary_types_allowed = True
-        """Allow arbitrary types. This is needed for the File type. Default is True.
-         See https://pydantic-docs.helpmanual.io/usage/types/#arbitrary-types-allowed"""
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def load(self) -> List[Document]:
         """Load Documents"""

libs/langchain/langchain/document_loaders/youtube.py

@@ -6,8 +6,8 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Sequence, Union
 from urllib.parse import parse_qs, urlparse
 
-from pydantic_v1 import root_validator
-from pydantic_v1.dataclasses import dataclass
+from pydantic import root_validator
+from pydantic.dataclasses import dataclass
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader

libs/langchain/langchain/document_transformers/embeddings_redundant_filter.py

@@ -2,7 +2,7 @@
 from typing import Any, Callable, List, Sequence
 
 import numpy as np
-from pydantic_v1 import BaseModel, Field
+from pydantic import ConfigDict, BaseModel, Field
 
 from langchain.embeddings.base import Embeddings
 from langchain.schema import BaseDocumentTransformer, Document
@@ -133,11 +133,7 @@ class EmbeddingsRedundantFilter(BaseDocumentTransformer, BaseModel):
     similarity_threshold: float = 0.95
     """Threshold for determining when two documents are similar enough
     to be considered redundant."""
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def transform_documents(
         self, documents: Sequence[Document], **kwargs: Any
@@ -188,11 +184,7 @@ class EmbeddingsClusteringFilter(BaseDocumentTransformer, BaseModel):
     This could dramatically reduce results when there is a lot of overlap between 
     clusters.
     """
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def transform_documents(
         self, documents: Sequence[Document], **kwargs: Any

libs/langchain/langchain/document_transformers/long_context_reorder.py

@@ -1,7 +1,7 @@
 """Reorder documents"""
 from typing import Any, List, Sequence
 
-from pydantic_v1 import BaseModel
+from pydantic import ConfigDict, BaseModel
 
 from langchain.schema import BaseDocumentTransformer, Document
 
@@ -26,11 +26,7 @@ class LongContextReorder(BaseDocumentTransformer, BaseModel):
     Performance degrades when models must access relevant information
     in the middle of long contexts.
     See: https://arxiv.org/abs//2307.03172"""
-
-    class Config:
-        """Configuration for this pydantic object."""
-
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def transform_documents(
         self, documents: Sequence[Document], **kwargs: Any