langchain 0.2.15__py3-none-any.whl → 0.3.0__py3-none-any.whl

langchain/evaluation/qa/eval_chain.py

@@ -9,6 +9,7 @@ from typing import Any, List, Optional, Sequence, Tuple
 from langchain_core.callbacks.manager import Callbacks
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.prompts import PromptTemplate
+from pydantic import ConfigDict
 
 from langchain.chains.llm import LLMChain
 from langchain.evaluation.qa.eval_prompt import CONTEXT_PROMPT, COT_PROMPT, PROMPT
@@ -72,8 +73,9 @@ class QAEvalChain(LLMChain, StringEvaluator, LLMEvalChain):
 
     output_key: str = "results"  #: :meta private:
 
-    class Config:
-        extra = "ignore"
+    model_config = ConfigDict(
+        extra="ignore",
+    )
 
     @classmethod
     def is_lc_serializable(cls) -> bool:
@@ -220,8 +222,9 @@ class ContextQAEvalChain(LLMChain, StringEvaluator, LLMEvalChain):
         """Whether the chain requires an input string."""
         return True
 
-    class Config:
-        extra = "ignore"
+    model_config = ConfigDict(
+        extra="ignore",
+    )
 
     @classmethod
     def _validate_input_vars(cls, prompt: PromptTemplate) -> None:

langchain/evaluation/qa/generate_chain.py

@@ -6,7 +6,7 @@ from typing import Any
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.output_parsers import BaseLLMOutputParser
-from langchain_core.pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.chains.llm import LLMChain
 from langchain.evaluation.qa.generate_prompt import PROMPT

langchain/evaluation/scoring/eval_chain.py

@@ -10,7 +10,7 @@ from langchain_core.callbacks.manager import Callbacks
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.output_parsers import BaseOutputParser
 from langchain_core.prompts.prompt import PromptTemplate
-from langchain_core.pydantic_v1 import Field
+from pydantic import ConfigDict, Field
 
 from langchain.chains.constitutional_ai.models import ConstitutionalPrinciple
 from langchain.chains.llm import LLMChain
@@ -179,8 +179,9 @@ class ScoreStringEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
     criterion_name: str
     """The name of the criterion being evaluated."""
 
-    class Config:
-        extra = "ignore"
+    model_config = ConfigDict(
+        extra="ignore",
+    )
 
     @classmethod
     def is_lc_serializable(cls) -> bool:

langchain/evaluation/string_distance/base.py

@@ -8,8 +8,8 @@ from langchain_core.callbacks.manager import (
     CallbackManagerForChainRun,
     Callbacks,
 )
-from langchain_core.pydantic_v1 import Field
 from langchain_core.utils import pre_init
+from pydantic import Field
 
 from langchain.chains.base import Chain
 from langchain.evaluation.schema import PairwiseStringEvaluator, StringEvaluator

langchain/indexes/vectorstore.py

@@ -4,9 +4,9 @@ from langchain_core.document_loaders import BaseLoader
 from langchain_core.documents import Document
 from langchain_core.embeddings import Embeddings
 from langchain_core.language_models import BaseLanguageModel
-from langchain_core.pydantic_v1 import BaseModel, Field
 from langchain_core.vectorstores import VectorStore
 from langchain_text_splitters import RecursiveCharacterTextSplitter, TextSplitter
+from pydantic import BaseModel, ConfigDict, Field
 
 from langchain.chains.qa_with_sources.retrieval import RetrievalQAWithSourcesChain
 from langchain.chains.retrieval_qa.base import RetrievalQA
@@ -21,9 +21,10 @@ class VectorStoreIndexWrapper(BaseModel):
 
     vectorstore: VectorStore
 
-    class Config:
-        arbitrary_types_allowed = True
-        extra = "forbid"
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+        extra="forbid",
+    )
 
     def query(
         self,
@@ -142,9 +143,10 @@ class VectorstoreIndexCreator(BaseModel):
     text_splitter: TextSplitter = Field(default_factory=_get_default_text_splitter)
     vectorstore_kwargs: dict = Field(default_factory=dict)
 
-    class Config:
-        arbitrary_types_allowed = True
-        extra = "forbid"
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+        extra="forbid",
+    )
 
     def from_loaders(self, loaders: List[BaseLoader]) -> VectorStoreIndexWrapper:
         """Create a vectorstore index from loaders."""

langchain/memory/chat_memory.py

@@ -8,7 +8,7 @@ from langchain_core.chat_history import (
 )
 from langchain_core.memory import BaseMemory
 from langchain_core.messages import AIMessage, HumanMessage
-from langchain_core.pydantic_v1 import Field
+from pydantic import Field
 
 from langchain.memory.utils import get_prompt_input_key
 

langchain/memory/combined.py

@@ -2,7 +2,7 @@ import warnings
 from typing import Any, Dict, List, Set
 
 from langchain_core.memory import BaseMemory
-from langchain_core.pydantic_v1 import validator
+from pydantic import field_validator
 
 from langchain.memory.chat_memory import BaseChatMemory
 
@@ -13,7 +13,8 @@ class CombinedMemory(BaseMemory):
     memories: List[BaseMemory]
     """For tracking all the memories that should be accessed."""
 
-    @validator("memories")
+    @field_validator("memories")
+    @classmethod
     def check_repeated_memory_variable(
         cls, value: List[BaseMemory]
     ) -> List[BaseMemory]:
@@ -29,7 +30,8 @@ class CombinedMemory(BaseMemory):
 
         return value
 
-    @validator("memories")
+    @field_validator("memories")
+    @classmethod
     def check_input_key(cls, value: List[BaseMemory]) -> List[BaseMemory]:
         """Check that if memories are of type BaseChatMemory that input keys exist."""
         for val in value:

langchain/memory/entity.py

@@ -6,7 +6,7 @@ from typing import Any, Dict, Iterable, List, Optional
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.messages import BaseMessage, get_buffer_string
 from langchain_core.prompts import BasePromptTemplate
-from langchain_core.pydantic_v1 import BaseModel, Field
+from pydantic import BaseModel, ConfigDict, Field
 
 from langchain.chains.llm import LLMChain
 from langchain.memory.chat_memory import BaseChatMemory
@@ -245,8 +245,9 @@ class SQLiteEntityStore(BaseEntityStore):
     table_name: str = "memory_store"
     conn: Any = None
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+    )
 
     def __init__(
         self,

langchain/memory/summary.py

@@ -7,8 +7,8 @@ from langchain_core.chat_history import BaseChatMessageHistory
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.messages import BaseMessage, SystemMessage, get_buffer_string
 from langchain_core.prompts import BasePromptTemplate
-from langchain_core.pydantic_v1 import BaseModel
 from langchain_core.utils import pre_init
+from pydantic import BaseModel
 
 from langchain.chains.llm import LLMChain
 from langchain.memory.chat_memory import BaseChatMemory

langchain/memory/vectorstore.py

@@ -3,8 +3,8 @@
 from typing import Any, Dict, List, Optional, Sequence, Union
 
 from langchain_core.documents import Document
-from langchain_core.pydantic_v1 import Field
 from langchain_core.vectorstores import VectorStoreRetriever
+from pydantic import Field
 
 from langchain.memory.chat_memory import BaseMemory
 from langchain.memory.utils import get_prompt_input_key

langchain/memory/vectorstore_token_buffer_memory.py

@@ -13,8 +13,8 @@ from typing import Any, Dict, List
 
 from langchain_core.messages import BaseMessage
 from langchain_core.prompts.chat import SystemMessagePromptTemplate
-from langchain_core.pydantic_v1 import Field, PrivateAttr
 from langchain_core.vectorstores import VectorStoreRetriever
+from pydantic import Field, PrivateAttr
 
 from langchain.memory import ConversationTokenBufferMemory, VectorStoreRetrieverMemory
 from langchain.memory.chat_memory import BaseChatMemory

langchain/output_parsers/fix.py

@@ -1,11 +1,12 @@
 from __future__ import annotations
 
-from typing import Any, TypeVar, Union
+from typing import Annotated, Any, TypeVar, Union
 
 from langchain_core.exceptions import OutputParserException
 from langchain_core.output_parsers import BaseOutputParser, StrOutputParser
 from langchain_core.prompts import BasePromptTemplate
 from langchain_core.runnables import Runnable, RunnableSerializable
+from pydantic import SkipValidation
 from typing_extensions import TypedDict
 
 from langchain.output_parsers.prompts import NAIVE_FIX_PROMPT
@@ -26,7 +27,7 @@ class OutputFixingParser(BaseOutputParser[T]):
     def is_lc_serializable(cls) -> bool:
         return True
 
-    parser: BaseOutputParser[T]
+    parser: Annotated[BaseOutputParser[T], SkipValidation()]
     """The parser to use to parse the output."""
     # Should be an LLMChain but we want to avoid top-level imports from langchain.chains
     retry_chain: Union[

langchain/output_parsers/pandas_dataframe.py

@@ -3,7 +3,7 @@ from typing import Any, Dict, List, Tuple, Union
 
 from langchain_core.exceptions import OutputParserException
 from langchain_core.output_parsers.base import BaseOutputParser
-from langchain_core.pydantic_v1 import validator
+from pydantic import field_validator
 
 from langchain.output_parsers.format_instructions import (
     PANDAS_DATAFRAME_FORMAT_INSTRUCTIONS,
@@ -16,7 +16,8 @@ class PandasDataFrameOutputParser(BaseOutputParser[Dict[str, Any]]):
     """The Pandas DataFrame to parse."""
     dataframe: Any
 
-    @validator("dataframe")
+    @field_validator("dataframe")
+    @classmethod
     def validate_dataframe(cls, val: Any) -> Any:
         import pandas as pd
 

langchain/output_parsers/retry.py

@@ -8,7 +8,8 @@ from langchain_core.output_parsers import BaseOutputParser, StrOutputParser
 from langchain_core.prompt_values import PromptValue
 from langchain_core.prompts import BasePromptTemplate, PromptTemplate
 from langchain_core.runnables import RunnableSerializable
-from typing_extensions import TypedDict
+from pydantic import SkipValidation
+from typing_extensions import Annotated, TypedDict
 
 NAIVE_COMPLETION_RETRY = """Prompt:
 {prompt}
@@ -53,7 +54,7 @@ class RetryOutputParser(BaseOutputParser[T]):
     LLM, and telling it the completion did not satisfy criteria in the prompt.
     """
 
-    parser: BaseOutputParser[T]
+    parser: Annotated[BaseOutputParser[T], SkipValidation()]
     """The parser to use to parse the output."""
     # Should be an LLMChain but we want to avoid top-level imports from langchain.chains
     retry_chain: Union[RunnableSerializable[RetryOutputParserRetryChainInput, str], Any]
@@ -183,7 +184,7 @@ class RetryWithErrorOutputParser(BaseOutputParser[T]):
     LLM, which in theory should give it more information on how to fix it.
     """
 
-    parser: BaseOutputParser[T]
+    parser: Annotated[BaseOutputParser[T], SkipValidation()]
     """The parser to use to parse the output."""
     # Should be an LLMChain but we want to avoid top-level imports from langchain.chains
     retry_chain: Union[

langchain/output_parsers/structured.py

@@ -4,7 +4,7 @@ from typing import Any, Dict, List
 
 from langchain_core.output_parsers import BaseOutputParser
 from langchain_core.output_parsers.json import parse_and_check_json_markdown
-from langchain_core.pydantic_v1 import BaseModel
+from pydantic import BaseModel
 
 from langchain.output_parsers.format_instructions import (
     STRUCTURED_FORMAT_INSTRUCTIONS,

langchain/output_parsers/yaml.py

@@ -5,7 +5,7 @@ from typing import Type, TypeVar
 import yaml
 from langchain_core.exceptions import OutputParserException
 from langchain_core.output_parsers import BaseOutputParser
-from langchain_core.pydantic_v1 import BaseModel, ValidationError
+from pydantic import BaseModel, ValidationError
 
 from langchain.output_parsers.format_instructions import YAML_FORMAT_INSTRUCTIONS
 
@@ -35,7 +35,10 @@ class YamlOutputParser(BaseOutputParser[T]):
                 yaml_str = text
 
             json_object = yaml.safe_load(yaml_str)
-            return self.pydantic_object.parse_obj(json_object)
+            if hasattr(self.pydantic_object, "model_validate"):
+                return self.pydantic_object.model_validate(json_object)
+            else:
+                return self.pydantic_object.parse_obj(json_object)
 
         except (yaml.YAMLError, ValidationError) as e:
             name = self.pydantic_object.__name__

langchain/pydantic_v1/__init__.py

@@ -1,5 +1,7 @@
 from importlib import metadata
 
+from langchain_core._api import warn_deprecated
+
 ## 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.
@@ -21,3 +23,21 @@ try:
     _PYDANTIC_MAJOR_VERSION: int = int(metadata.version("pydantic").split(".")[0])
 except metadata.PackageNotFoundError:
     _PYDANTIC_MAJOR_VERSION = 0
+
+warn_deprecated(
+    "0.3.0",
+    removal="1.0.0",
+    alternative="pydantic.v1 or pydantic",
+    message=(
+        "As of langchain-core 0.3.0, LangChain uses pydantic v2 internally. "
+        "The langchain.pydantic_v1 module was a "
+        "compatibility shim for pydantic v1, and should no longer be used. "
+        "Please update the code to import from Pydantic directly.\n\n"
+        "For example, replace imports like: "
+        "`from langchain.pydantic_v1 import BaseModel`\n"
+        "with: `from pydantic import BaseModel`\n"
+        "or the v1 compatibility namespace if you are working in a code base "
+        "that has not been fully upgraded to pydantic 2 yet. "
+        "\tfrom pydantic.v1 import BaseModel\n"
+    ),
+)

langchain/pydantic_v1/dataclasses.py

@@ -1,4 +1,24 @@
+from langchain_core._api import warn_deprecated
+
 try:
     from pydantic.v1.dataclasses import *  # noqa: F403
 except ImportError:
     from pydantic.dataclasses import *  # type: ignore # noqa: F403
+
+warn_deprecated(
+    "0.3.0",
+    removal="1.0.0",
+    alternative="pydantic.v1 or pydantic",
+    message=(
+        "As of langchain-core 0.3.0, LangChain uses pydantic v2 internally. "
+        "The langchain.pydantic_v1 module was a "
+        "compatibility shim for pydantic v1, and should no longer be used. "
+        "Please update the code to import from Pydantic directly.\n\n"
+        "For example, replace imports like: "
+        "`from langchain.pydantic_v1 import BaseModel`\n"
+        "with: `from pydantic import BaseModel`\n"
+        "or the v1 compatibility namespace if you are working in a code base "
+        "that has not been fully upgraded to pydantic 2 yet. "
+        "\tfrom pydantic.v1 import BaseModel\n"
+    ),
+)

langchain/pydantic_v1/main.py

@@ -1,4 +1,24 @@
+from langchain_core._api import warn_deprecated
+
 try:
     from pydantic.v1.main import *  # noqa: F403
 except ImportError:
     from pydantic.main import *  # type: ignore # noqa: F403
+
+warn_deprecated(
+    "0.3.0",
+    removal="1.0.0",
+    alternative="pydantic.v1 or pydantic",
+    message=(
+        "As of langchain-core 0.3.0, LangChain uses pydantic v2 internally. "
+        "The langchain.pydantic_v1 module was a "
+        "compatibility shim for pydantic v1, and should no longer be used. "
+        "Please update the code to import from Pydantic directly.\n\n"
+        "For example, replace imports like: "
+        "`from langchain.pydantic_v1 import BaseModel`\n"
+        "with: `from pydantic import BaseModel`\n"
+        "or the v1 compatibility namespace if you are working in a code base "
+        "that has not been fully upgraded to pydantic 2 yet. "
+        "\tfrom pydantic.v1 import BaseModel\n"
+    ),
+)

langchain/retrievers/contextual_compression.py

@@ -6,6 +6,7 @@ from langchain_core.callbacks import (
 )
 from langchain_core.documents import Document
 from langchain_core.retrievers import BaseRetriever, RetrieverLike
+from pydantic import ConfigDict
 
 from langchain.retrievers.document_compressors.base import (
     BaseDocumentCompressor,
@@ -21,8 +22,9 @@ class ContextualCompressionRetriever(BaseRetriever):
     base_retriever: RetrieverLike
     """Base Retriever to use for getting relevant documents."""
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+    )
 
     def _get_relevant_documents(
         self,

langchain/retrievers/document_compressors/base.py

@@ -7,6 +7,7 @@ from langchain_core.documents import (
     BaseDocumentTransformer,
     Document,
 )
+from pydantic import ConfigDict
 
 
 class DocumentCompressorPipeline(BaseDocumentCompressor):
@@ -15,8 +16,9 @@ class DocumentCompressorPipeline(BaseDocumentCompressor):
     transformers: List[Union[BaseDocumentTransformer, BaseDocumentCompressor]]
     """List of document filters that are chained together and run in sequence."""
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+    )
 
     def compress_documents(
         self,

langchain/retrievers/document_compressors/chain_extract.py

@@ -11,6 +11,7 @@ from langchain_core.language_models import BaseLanguageModel
 from langchain_core.output_parsers import BaseOutputParser, StrOutputParser
 from langchain_core.prompts import PromptTemplate
 from langchain_core.runnables import Runnable
+from pydantic import ConfigDict
 
 from langchain.chains.llm import LLMChain
 from langchain.retrievers.document_compressors.base import BaseDocumentCompressor
@@ -56,8 +57,9 @@ class LLMChainExtractor(BaseDocumentCompressor):
     get_input: Callable[[str, Document], dict] = default_get_input
     """Callable for constructing the chain input from the query and a Document."""
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+    )
 
     def compress_documents(
         self,

langchain/retrievers/document_compressors/chain_filter.py

@@ -9,6 +9,7 @@ from langchain_core.output_parsers import StrOutputParser
 from langchain_core.prompts import BasePromptTemplate, PromptTemplate
 from langchain_core.runnables import Runnable
 from langchain_core.runnables.config import RunnableConfig
+from pydantic import ConfigDict
 
 from langchain.chains import LLMChain
 from langchain.output_parsers.boolean import BooleanOutputParser
@@ -41,8 +42,9 @@ class LLMChainFilter(BaseDocumentCompressor):
     get_input: Callable[[str, Document], dict] = default_get_input
     """Callable for constructing the chain input from the query and a Document."""
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+    )
 
     def compress_documents(
         self,

langchain/retrievers/document_compressors/cohere_rerank.py

@@ -6,8 +6,8 @@ from typing import Any, Dict, List, Optional, Sequence, Union
 from langchain_core._api.deprecation import deprecated
 from langchain_core.callbacks.manager import Callbacks
 from langchain_core.documents import 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
 
 from langchain.retrievers.document_compressors.base import BaseDocumentCompressor
 
@@ -30,12 +30,14 @@ class CohereRerank(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 and python package exists in environment."""
         if not values.get("client"):
             try:

langchain/retrievers/document_compressors/cross_encoder_rerank.py

@@ -5,6 +5,7 @@ from typing import Optional, Sequence
 
 from langchain_core.callbacks import Callbacks
 from langchain_core.documents import BaseDocumentCompressor, Document
+from pydantic import ConfigDict
 
 from langchain.retrievers.document_compressors.cross_encoder import BaseCrossEncoder
 
@@ -18,9 +19,10 @@ class CrossEncoderReranker(BaseDocumentCompressor):
     top_n: int = 3
     """Number of documents to return."""
 
-    class Config:
-        arbitrary_types_allowed = True
-        extra = "forbid"
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+        extra="forbid",
+    )
 
     def compress_documents(
         self,

langchain/retrievers/document_compressors/embeddings_filter.py

@@ -4,8 +4,8 @@ import numpy as np
 from langchain_core.callbacks.manager import Callbacks
 from langchain_core.documents import Document
 from langchain_core.embeddings import Embeddings
-from langchain_core.pydantic_v1 import Field
 from langchain_core.utils import pre_init
+from pydantic import ConfigDict, Field
 
 from langchain.retrievers.document_compressors.base import (
     BaseDocumentCompressor,
@@ -36,13 +36,14 @@ class EmbeddingsFilter(BaseDocumentCompressor):
     k: Optional[int] = 20
     """The number of relevant documents to return. Can be set to None, in which case
     `similarity_threshold` must be specified. Defaults to 20."""
-    similarity_threshold: Optional[float]
+    similarity_threshold: Optional[float] = None
     """Threshold for determining when two documents are similar enough
     to be considered redundant. Defaults to None, must be specified if `k` is set
     to None."""
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+    )
 
     @pre_init
     def validate_params(cls, values: Dict) -> Dict:

langchain/retrievers/document_compressors/listwise_rerank.py

@@ -6,8 +6,8 @@ from langchain_core.callbacks import Callbacks
 from langchain_core.documents import BaseDocumentCompressor, Document
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.prompts import BasePromptTemplate, ChatPromptTemplate
-from langchain_core.pydantic_v1 import BaseModel, Field
 from langchain_core.runnables import Runnable, RunnableLambda, RunnablePassthrough
+from pydantic import BaseModel, ConfigDict, Field
 
 _default_system_tmpl = """{context}
 
@@ -76,8 +76,9 @@ class LLMListwiseRerank(BaseDocumentCompressor):
     top_n: int = 3
     """Number of documents to return."""
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+    )
 
     def compress_documents(
         self,