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/community/langchain_community/document_compressors/dashscope_rerank.py

@@ -5,8 +5,8 @@ from typing import Any, Dict, List, Optional, Sequence, Union
 
 from langchain_core.callbacks.base import Callbacks
 from langchain_core.documents import BaseDocumentCompressor, Document
-from langchain_core.pydantic_v1 import Field, root_validator
 from langchain_core.utils import get_from_dict_or_env
+from pydantic import ConfigDict, Field, model_validator
 
 
 class DashScopeRerank(BaseDocumentCompressor):
@@ -25,13 +25,15 @@ class DashScopeRerank(BaseDocumentCompressor):
     """DashScope API key. Must be specified directly or via environment variable 
         DASHSCOPE_API_KEY."""
 
-    class Config:
-        allow_population_by_field_name = True
-        arbitrary_types_allowed = True
-        extra = "forbid"
+    model_config = ConfigDict(
+        populate_by_name=True,
+        arbitrary_types_allowed=True,
+        extra="forbid",
+    )
 
-    @root_validator(pre=True)
-    def validate_environment(cls, values: Dict) -> Dict:
+    @model_validator(mode="before")
+    @classmethod
+    def validate_environment(cls, values: Dict) -> Any:
         """Validate that api key and python package exists in environment."""
 
         if not values.get("client"):

libs/community/langchain_community/document_compressors/flashrank_rerank.py

@@ -1,10 +1,10 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict, Optional, Sequence
+from typing import TYPE_CHECKING, Any, Dict, Optional, Sequence
 
 from langchain_core.callbacks.manager import Callbacks
 from langchain_core.documents import BaseDocumentCompressor, Document
-from langchain_core.pydantic_v1 import root_validator
+from pydantic import ConfigDict, model_validator
 
 if TYPE_CHECKING:
     from flashrank import Ranker, RerankRequest
@@ -33,12 +33,14 @@ class FlashrankRerank(BaseDocumentCompressor):
     prefix_metadata: str = ""
     """Prefix for flashrank_rerank metadata keys"""
 
-    class Config:
-        arbitrary_types_allowed = True
-        extra = "forbid"
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+        extra="forbid",
+    )
 
-    @root_validator(pre=True)
-    def validate_environment(cls, values: Dict) -> Dict:
+    @model_validator(mode="before")
+    @classmethod
+    def validate_environment(cls, values: Dict) -> Any:
         """Validate that api key and python package exists in environment."""
         if "client" in values:
             return values

libs/community/langchain_community/document_compressors/jina_rerank.py

@@ -6,8 +6,8 @@ from typing import Any, Dict, List, Optional, Sequence, Union
 import requests
 from langchain_core.callbacks import Callbacks
 from langchain_core.documents import BaseDocumentCompressor, Document
-from langchain_core.pydantic_v1 import root_validator
 from langchain_core.utils import get_from_dict_or_env
+from pydantic import ConfigDict, model_validator
 
 JINA_API_URL: str = "https://api.jina.ai/v1/rerank"
 
@@ -27,12 +27,14 @@ class JinaRerank(BaseDocumentCompressor):
     user_agent: str = "langchain"
     """Identifier for the application making the request."""
 
-    class Config:
-        arbitrary_types_allowed = True
-        extra = "forbid"
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+        extra="forbid",
+    )
 
-    @root_validator(pre=True)
-    def validate_environment(cls, values: Dict) -> Dict:
+    @model_validator(mode="before")
+    @classmethod
+    def validate_environment(cls, values: Dict) -> Any:
         """Validate that api key exists in environment."""
         jina_api_key = get_from_dict_or_env(values, "jina_api_key", "JINA_API_KEY")
         user_agent = values.get("user_agent", "langchain")

libs/community/langchain_community/document_compressors/llmlingua_filter.py

@@ -8,7 +8,7 @@ from langchain_core.documents import Document
 from langchain_core.documents.compressor import (
     BaseDocumentCompressor,
 )
-from langchain_core.pydantic_v1 import root_validator
+from pydantic import ConfigDict, Field, model_validator
 
 DEFAULT_LLM_LINGUA_INSTRUCTION = (
     "Given this documents, please answer the final question"
@@ -35,9 +35,9 @@ class LLMLinguaCompressor(BaseDocumentCompressor):
     """The target number of compressed tokens"""
     rank_method: str = "longllmlingua"
     """The ranking method to use"""
-    model_config: dict = {}
+    model_configuration: dict = Field(default_factory=dict, alias="model_config")
     """Custom configuration for the model"""
-    open_api_config: dict = {}
+    open_api_config: dict = Field(default_factory=dict)
     """open_api configuration"""
     instruction: str = DEFAULT_LLM_LINGUA_INSTRUCTION
     """The instruction for the LLM"""
@@ -49,11 +49,12 @@ class LLMLinguaCompressor(BaseDocumentCompressor):
         "dynamic_context_compression_ratio": 0.4,
     }
     """Extra compression arguments"""
-    lingua: Any
+    lingua: Any = None
     """The instance of the llm linqua"""
 
-    @root_validator(pre=True)
-    def validate_environment(cls, values: Dict) -> Dict:
+    @model_validator(mode="before")
+    @classmethod
+    def validate_environment(cls, values: Dict) -> Any:
         """Validate that the python package exists in environment."""
         try:
             from llmlingua import PromptCompressor
@@ -71,9 +72,12 @@ class LLMLinguaCompressor(BaseDocumentCompressor):
             )
         return values
 
-    class Config:
-        arbitrary_types_allowed = True
-        extra = "forbid"
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+        extra="forbid",
+        populate_by_name=True,
+        protected_namespaces=(),
+    )
 
     @staticmethod
     def _format_context(docs: Sequence[Document]) -> List[str]:

libs/community/langchain_community/document_compressors/openvino_rerank.py

@@ -5,7 +5,7 @@ import numpy as np
 from langchain_core.callbacks import Callbacks
 from langchain_core.documents import Document
 from langchain_core.documents.compressor import BaseDocumentCompressor
-from langchain_core.pydantic_v1 import Field
+from pydantic import Field
 
 
 class RerankRequest:
@@ -21,9 +21,9 @@ class OpenVINOReranker(BaseDocumentCompressor):
     OpenVINO rerank models.
     """
 
-    ov_model: Any
+    ov_model: Any = None
     """OpenVINO model object."""
-    tokenizer: Any
+    tokenizer: Any = None
     """Tokenizer for embedding model."""
     model_name_or_path: str
     """HuggingFace model id."""

libs/community/langchain_community/document_compressors/rankllm_rerank.py

@@ -7,8 +7,8 @@ from typing import TYPE_CHECKING, Any, Dict, Optional, Sequence
 from langchain.retrievers.document_compressors.base import BaseDocumentCompressor
 from langchain_core.callbacks.manager import Callbacks
 from langchain_core.documents import Document
-from langchain_core.pydantic_v1 import Field, PrivateAttr, root_validator
 from langchain_core.utils import get_from_dict_or_env
+from pydantic import ConfigDict, Field, PrivateAttr, model_validator
 
 if TYPE_CHECKING:
     from rank_llm.data import Candidate, Query, Request
@@ -36,12 +36,14 @@ class RankLLMRerank(BaseDocumentCompressor):
     """OpenAI model name."""
     _retriever: Any = PrivateAttr()
 
-    class Config:
-        arbitrary_types_allowed = True
-        extra = "forbid"
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+        extra="forbid",
+    )
 
-    @root_validator(pre=True)
-    def validate_environment(cls, values: Dict) -> Dict:
+    @model_validator(mode="before")
+    @classmethod
+    def validate_environment(cls, values: Dict) -> Any:
         """Validate python package exists in environment."""
 
         if not values.get("client"):

libs/community/langchain_community/document_compressors/volcengine_rerank.py

@@ -5,8 +5,8 @@ from typing import Any, Dict, List, Optional, Sequence, Union
 
 from langchain_core.callbacks.base import Callbacks
 from langchain_core.documents import BaseDocumentCompressor, Document
-from langchain_core.pydantic_v1 import root_validator
 from langchain_core.utils import get_from_dict_or_env
+from pydantic import ConfigDict, model_validator
 
 
 class VolcengineRerank(BaseDocumentCompressor):
@@ -32,13 +32,15 @@ class VolcengineRerank(BaseDocumentCompressor):
     top_n: Optional[int] = 3
     """Number of documents to return."""
 
-    class Config:
-        allow_population_by_field_name = True
-        arbitrary_types_allowed = True
-        extra = "forbid"
+    model_config = ConfigDict(
+        populate_by_name=True,
+        arbitrary_types_allowed=True,
+        extra="forbid",
+    )
 
-    @root_validator(pre=True)
-    def validate_environment(cls, values: Dict) -> Dict:
+    @model_validator(mode="before")
+    @classmethod
+    def validate_environment(cls, values: Dict) -> Any:
         """Validate that api key and python package exists in environment."""
 
         if not values.get("client"):