multiple: pydantic 2 compatibility, v0.3 (#26443)

Signed-off-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Dan O'Donovan <dan.odonovan@gmail.com>
Co-authored-by: Tom Daniel Grande <tomdgrande@gmail.com>
Co-authored-by: Grande <Tom.Daniel.Grande@statsbygg.no>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Tomaz Bratanic <bratanic.tomaz@gmail.com>
Co-authored-by: ZhangShenao <15201440436@163.com>
Co-authored-by: Friso H. Kingma <fhkingma@gmail.com>
Co-authored-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Nuno Campos <nuno@langchain.dev>
Co-authored-by: Morgante Pell <morgantep@google.com>

libs/core/langchain_core/documents/base.py

@@ -4,10 +4,11 @@ import contextlib
 import mimetypes
 from io import BufferedReader, BytesIO
 from pathlib import PurePath
-from typing import Any, Generator, List, Literal, Mapping, Optional, Union, cast
+from typing import Any, Dict, Generator, List, Literal, Optional, Union, cast
+
+from pydantic import ConfigDict, Field, field_validator, model_validator
 
 from langchain_core.load.serializable import Serializable
-from langchain_core.pydantic_v1 import Field, root_validator
 
 PathLike = Union[str, PurePath]
 
@@ -39,6 +40,13 @@ class BaseMedia(Serializable):
     metadata: dict = Field(default_factory=dict)
     """Arbitrary metadata associated with the content."""
 
+    @field_validator("id", mode="before")
+    def cast_id_to_str(cls, id_value: Any) -> Optional[str]:
+        if id_value is not None:
+            return str(id_value)
+        else:
+            return id_value
+
 
 class Blob(BaseMedia):
     """Blob represents raw data by either reference or value.
@@ -110,9 +118,10 @@ class Blob(BaseMedia):
     path: Optional[PathLike] = None
     """Location where the original content was found."""
 
-    class Config:
-        arbitrary_types_allowed = True
-        frozen = True
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+        frozen=True,
+    )
 
     @property
     def source(self) -> Optional[str]:
@@ -127,8 +136,9 @@ class Blob(BaseMedia):
             return cast(Optional[str], self.metadata["source"])
         return str(self.path) if self.path else None
 
-    @root_validator(pre=True)
-    def check_blob_is_valid(cls, values: Mapping[str, Any]) -> Mapping[str, Any]:
+    @model_validator(mode="before")
+    @classmethod
+    def check_blob_is_valid(cls, values: Dict[str, Any]) -> Any:
         """Verify that either data or path is provided."""
         if "data" not in values and "path" not in values:
             raise ValueError("Either data or path must be provided")

libs/core/langchain_core/documents/compressor.py

@@ -3,9 +3,10 @@ from __future__ import annotations
 from abc import ABC, abstractmethod
 from typing import Optional, Sequence
 
+from pydantic import BaseModel
+
 from langchain_core.callbacks import Callbacks
 from langchain_core.documents import Document
-from langchain_core.pydantic_v1 import BaseModel
 from langchain_core.runnables import run_in_executor