# coding: utf-8
"""
Amorphic Data Platform
Amorphic Data Platform - API Definition documentation
The version of the OpenAPI document: 0.3.0
Generated by OpenAPI Generator (https://openapi-generator.tech)
Do not edit the class manually.
""" # noqa: E501
from __future__ import annotations
import pprint
import re # noqa: F401
import json
from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr, field_validator
from typing import Any, ClassVar, Dict, List, Optional
from typing import Optional, Set
from typing_extensions import Self
[docs]
class ResourceAdditionRequestChunkingConfiguration(BaseModel):
"""
Configuration for chunking strategy.
""" # noqa: E501
chunking_strategy: Optional[StrictStr] = Field(default=None, description="The chunking strategy to use.", alias="ChunkingStrategy")
max_tokens: Optional[StrictInt] = Field(default=None, description="The maximum number of tokens to use for fixed size chunking.", alias="MaxTokens")
overlap_percentage: Optional[StrictInt] = Field(default=None, description="The overlap percentage to use for fixed size chunking.", alias="OverlapPercentage")
max_token_layer2: Optional[StrictInt] = Field(default=None, description="The maximum number of tokens to use for hierarchical chunking layer 2.", alias="MaxTokenLayer2")
max_token_layer1: Optional[StrictInt] = Field(default=None, description="The maximum number of tokens to use for hierarchical chunking layer 1.", alias="MaxTokenLayer1")
overlap_tokens: Optional[StrictInt] = Field(default=None, description="The overlap tokens between the 2 layers used for hierarchical chunking.", alias="OverlapTokens")
buffer_size: Optional[StrictInt] = Field(default=None, description="The buffer size to use for semantic chunking.", alias="BufferSize")
breakpoint_percentile_threshold: Optional[StrictInt] = Field(default=None, description="The breakpoint percentile threshold to use for semantic chunking.", alias="BreakpointPercentileThreshold")
__properties: ClassVar[List[str]] = ["ChunkingStrategy", "MaxTokens", "OverlapPercentage", "MaxTokenLayer2", "MaxTokenLayer1", "OverlapTokens", "BufferSize", "BreakpointPercentileThreshold"]
[docs]
@field_validator('chunking_strategy')
def chunking_strategy_validate_enum(cls, value):
"""Validates the enum"""
if value is None:
return value
if value not in set(['NONE', 'FIXED_SIZE', 'HIERARCHICAL', 'SEMANTIC']):
raise ValueError("must be one of enum values ('NONE', 'FIXED_SIZE', 'HIERARCHICAL', 'SEMANTIC')")
return value
model_config = ConfigDict(
populate_by_name=True,
validate_assignment=True,
protected_namespaces=(),
)
[docs]
def to_str(self) -> str:
"""Returns the string representation of the model using alias"""
return pprint.pformat(self.model_dump(by_alias=True))
[docs]
def to_json(self) -> str:
"""Returns the JSON representation of the model using alias"""
# TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
return json.dumps(self.to_dict())
[docs]
@classmethod
def from_json(cls, json_str: str) -> Optional[Self]:
"""Create an instance of ResourceAdditionRequestChunkingConfiguration from a JSON string"""
return cls.from_dict(json.loads(json_str))
[docs]
def to_dict(self) -> Dict[str, Any]:
"""Return the dictionary representation of the model using alias.
This has the following differences from calling pydantic's
`self.model_dump(by_alias=True)`:
* `None` is only added to the output dict for nullable fields that
were set at model initialization. Other fields with value `None`
are ignored.
"""
excluded_fields: Set[str] = set([
])
_dict = self.model_dump(
by_alias=True,
exclude=excluded_fields,
exclude_none=True,
)
return _dict
[docs]
@classmethod
def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
"""Create an instance of ResourceAdditionRequestChunkingConfiguration from a dict"""
if obj is None:
return None
if not isinstance(obj, dict):
return cls.model_validate(obj)
_obj = cls.model_validate({
"ChunkingStrategy": obj.get("ChunkingStrategy"),
"MaxTokens": obj.get("MaxTokens"),
"OverlapPercentage": obj.get("OverlapPercentage"),
"MaxTokenLayer2": obj.get("MaxTokenLayer2"),
"MaxTokenLayer1": obj.get("MaxTokenLayer1"),
"OverlapTokens": obj.get("OverlapTokens"),
"BufferSize": obj.get("BufferSize"),
"BreakpointPercentileThreshold": obj.get("BreakpointPercentileThreshold")
})
return _obj