vellum-ai 0.5.2__py3-none-any.whl → 0.6.0__py3-none-any.whl

vellum/types/instructor_vectorizer_config.py

@@ -0,0 +1,31 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+
+
+class InstructorVectorizerConfig(pydantic_v1.BaseModel):
+    """
+    Configuration for using an Instructor vectorizer.
+    """
+
+    instruction_domain: str
+    instruction_query_text_type: str
+    instruction_document_text_type: str
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/instructor_vectorizer_config_request.py

@@ -0,0 +1,31 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+
+
+class InstructorVectorizerConfigRequest(pydantic_v1.BaseModel):
+    """
+    Configuration for using an Instructor vectorizer.
+    """
+
+    instruction_domain: str
+    instruction_query_text_type: str
+    instruction_document_text_type: str
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/intfloat_multilingual_e_5_large_enum.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+IntfloatMultilingualE5LargeEnum = typing.Literal["intfloat/multilingual-e5-large"]

vellum/types/metric_enum.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+MetricEnum = typing.Literal["METRIC"]

vellum/types/{chat_history_variable_value.py → metric_node_result.py}

@@ -5,11 +5,12 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from ..core.pydantic_utilities import pydantic_v1
-from .chat_message import ChatMessage
 
 
-class ChatHistoryVariableValue(pydantic_v1.BaseModel):
-    value: typing.Optional[typing.List[ChatMessage]] = None
+class MetricNodeResult(pydantic_v1.BaseModel):
+    """
+    A Node Result Event emitted from a Metric Node.
+    """
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

vellum/types/named_test_case_function_call_variable_value.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from ..core.pydantic_utilities import pydantic_v1
-from .fulfilled_function_call import FulfilledFunctionCall
+from .function_call import FunctionCall
 
 
 class NamedTestCaseFunctionCallVariableValue(pydantic_v1.BaseModel):
@@ -13,7 +13,7 @@ class NamedTestCaseFunctionCallVariableValue(pydantic_v1.BaseModel):
     Named Test Case value that is of type FUNCTION_CALL
     """
 
-    value: typing.Optional[FulfilledFunctionCall] = None
+    value: typing.Optional[FunctionCall] = None
     name: str
 
     def json(self, **kwargs: typing.Any) -> str:

vellum/types/named_test_case_function_call_variable_value_request.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from ..core.pydantic_utilities import pydantic_v1
-from .fulfilled_function_call_request import FulfilledFunctionCallRequest
+from .function_call_request import FunctionCallRequest
 
 
 class NamedTestCaseFunctionCallVariableValueRequest(pydantic_v1.BaseModel):
@@ -13,7 +13,7 @@ class NamedTestCaseFunctionCallVariableValueRequest(pydantic_v1.BaseModel):
     Named Test Case value that is of type FUNCTION_CALL
     """
 
-    value: typing.Optional[FulfilledFunctionCallRequest] = None
+    value: typing.Optional[FunctionCallRequest] = None
     name: str
 
     def json(self, **kwargs: typing.Any) -> str:

vellum/types/node_output_compiled_array_value.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from ..core.pydantic_utilities import pydantic_v1
-from .array_variable_value_item import ArrayVariableValueItem
+from .array_vellum_value_item import ArrayVellumValueItem
 from .workflow_node_result_event_state import WorkflowNodeResultEventState
 
 
@@ -14,7 +14,7 @@ class NodeOutputCompiledArrayValue(pydantic_v1.BaseModel):
     An output returned by a node that is of type ARRAY.
     """
 
-    value: typing.Optional[typing.List[ArrayVariableValueItem]] = None
+    value: typing.Optional[typing.List[ArrayVellumValueItem]] = None
     node_output_id: str
     state: typing.Optional[WorkflowNodeResultEventState] = None
 

vellum/types/{search_results_variable_value.py → number_vellum_value.py}

@@ -5,11 +5,14 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from ..core.pydantic_utilities import pydantic_v1
-from .search_result import SearchResult
 
 
-class SearchResultsVariableValue(pydantic_v1.BaseModel):
-    value: typing.Optional[typing.List[SearchResult]] = None
+class NumberVellumValue(pydantic_v1.BaseModel):
+    """
+    A value representing a number.
+    """
+
+    value: typing.Optional[float] = None
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

vellum/types/open_ai_vectorizer_config.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .add_openai_api_key_enum import AddOpenaiApiKeyEnum
+
+
+class OpenAiVectorizerConfig(pydantic_v1.BaseModel):
+    """
+    Configuration for using an OpenAI vectorizer.
+    """
+
+    add_openai_api_key: typing.Optional[AddOpenaiApiKeyEnum] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/open_ai_vectorizer_config_request.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .add_openai_api_key_enum import AddOpenaiApiKeyEnum
+
+
+class OpenAiVectorizerConfigRequest(pydantic_v1.BaseModel):
+    """
+    Configuration for using an OpenAI vectorizer.
+    """
+
+    add_openai_api_key: typing.Optional[AddOpenaiApiKeyEnum] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/open_ai_vectorizer_text_embedding_3_large.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .open_ai_vectorizer_config import OpenAiVectorizerConfig
+
+
+class OpenAiVectorizerTextEmbedding3Large(pydantic_v1.BaseModel):
+    """
+    OpenAI vectorizer for text-embedding-3-large.
+    """
+
+    config: OpenAiVectorizerConfig
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/open_ai_vectorizer_text_embedding_3_large_request.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .open_ai_vectorizer_config_request import OpenAiVectorizerConfigRequest
+
+
+class OpenAiVectorizerTextEmbedding3LargeRequest(pydantic_v1.BaseModel):
+    """
+    OpenAI vectorizer for text-embedding-3-large.
+    """
+
+    config: OpenAiVectorizerConfigRequest
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/open_ai_vectorizer_text_embedding_3_small.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .open_ai_vectorizer_config import OpenAiVectorizerConfig
+
+
+class OpenAiVectorizerTextEmbedding3Small(pydantic_v1.BaseModel):
+    """
+    OpenAI vectorizer for text-embedding-3-small.
+    """
+
+    config: OpenAiVectorizerConfig
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/open_ai_vectorizer_text_embedding_3_small_request.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .open_ai_vectorizer_config_request import OpenAiVectorizerConfigRequest
+
+
+class OpenAiVectorizerTextEmbedding3SmallRequest(pydantic_v1.BaseModel):
+    """
+    OpenAI vectorizer for text-embedding-3-small.
+    """
+
+    config: OpenAiVectorizerConfigRequest
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/open_ai_vectorizer_text_embedding_ada_002.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .open_ai_vectorizer_config import OpenAiVectorizerConfig
+
+
+class OpenAiVectorizerTextEmbeddingAda002(pydantic_v1.BaseModel):
+    """
+    OpenAI vectorizer for text-embedding-ada-002.
+    """
+
+    config: OpenAiVectorizerConfig
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/open_ai_vectorizer_text_embedding_ada_002_request.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .open_ai_vectorizer_config_request import OpenAiVectorizerConfigRequest
+
+
+class OpenAiVectorizerTextEmbeddingAda002Request(pydantic_v1.BaseModel):
+    """
+    OpenAI vectorizer for text-embedding-ada-002.
+    """
+
+    config: OpenAiVectorizerConfigRequest
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/reducto_chunker_config.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+
+
+class ReductoChunkerConfig(pydantic_v1.BaseModel):
+    """
+    Configuration for Reducto chunking
+    """
+
+    character_limit: typing.Optional[int] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/reducto_chunker_config_request.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+
+
+class ReductoChunkerConfigRequest(pydantic_v1.BaseModel):
+    """
+    Configuration for Reducto chunking
+    """
+
+    character_limit: typing.Optional[int] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/reducto_chunker_enum.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ReductoChunkerEnum = typing.Literal["reducto-chunker"]

vellum/types/reducto_chunking.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .reducto_chunker_config import ReductoChunkerConfig
+
+
+class ReductoChunking(pydantic_v1.BaseModel):
+    """
+    Reducto chunking
+    """
+
+    chunker_config: typing.Optional[ReductoChunkerConfig] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/reducto_chunking_request.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .reducto_chunker_config_request import ReductoChunkerConfigRequest
+
+
+class ReductoChunkingRequest(pydantic_v1.BaseModel):
+    """
+    Reducto chunking
+    """
+
+    chunker_config: typing.Optional[ReductoChunkerConfigRequest] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/sentence_chunker_config.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+
+
+class SentenceChunkerConfig(pydantic_v1.BaseModel):
+    """
+    Configuration for sentence chunking
+    """
+
+    character_limit: typing.Optional[int] = None
+    min_overlap_ratio: typing.Optional[float] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/sentence_chunker_config_request.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+
+
+class SentenceChunkerConfigRequest(pydantic_v1.BaseModel):
+    """
+    Configuration for sentence chunking
+    """
+
+    character_limit: typing.Optional[int] = None
+    min_overlap_ratio: typing.Optional[float] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/sentence_chunker_enum.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+SentenceChunkerEnum = typing.Literal["sentence-chunker"]

vellum/types/sentence_chunking.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .sentence_chunker_config import SentenceChunkerConfig
+
+
+class SentenceChunking(pydantic_v1.BaseModel):
+    """
+    Sentence chunking
+    """
+
+    chunker_config: typing.Optional[SentenceChunkerConfig] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}