vectorize_client.models.ai_platform_config_schema

Vectorize API (Beta)

API for Vectorize services

The version of the OpenAPI document: 0.0.1 Generated by OpenAPI Generator (https://openapi-generator.tech)

Do not edit the class manually.

View Source

  1# coding: utf-8
  2
  3"""
  4    Vectorize API (Beta)
  5
  6    API for Vectorize services
  7
  8    The version of the OpenAPI document: 0.0.1
  9    Generated by OpenAPI Generator (https://openapi-generator.tech)
 10
 11    Do not edit the class manually.
 12"""  # noqa: E501
 13
 14
 15from __future__ import annotations
 16import pprint
 17import re  # noqa: F401
 18import json
 19
 20from pydantic import BaseModel, ConfigDict, Field, StrictStr, field_validator
 21from typing import Any, ClassVar, Dict, List, Optional
 22from typing_extensions import Annotated
 23from typing import Optional, Set
 24from typing_extensions import Self
 25
 26class AIPlatformConfigSchema(BaseModel):
 27    """
 28    AIPlatformConfigSchema
 29    """ # noqa: E501
 30    embedding_model: Optional[StrictStr] = Field(default=None, alias="embeddingModel")
 31    chunking_strategy: Optional[StrictStr] = Field(default=None, alias="chunkingStrategy")
 32    chunk_size: Optional[Annotated[int, Field(strict=True, ge=1)]] = Field(default=None, alias="chunkSize")
 33    chunk_overlap: Optional[Annotated[int, Field(strict=True, ge=0)]] = Field(default=None, alias="chunkOverlap")
 34    dimensions: Optional[Annotated[int, Field(strict=True, ge=1)]] = None
 35    extraction_strategy: Optional[StrictStr] = Field(default=None, alias="extractionStrategy")
 36    __properties: ClassVar[List[str]] = ["embeddingModel", "chunkingStrategy", "chunkSize", "chunkOverlap", "dimensions", "extractionStrategy"]
 37
 38    @field_validator('embedding_model')
 39    def embedding_model_validate_enum(cls, value):
 40        """Validates the enum"""
 41        if value is None:
 42            return value
 43
 44        if value not in set(['VECTORIZE_OPEN_AI_TEXT_EMBEDDING_2', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'VECTORIZE_VOYAGE_AI_2', 'VECTORIZE_VOYAGE_AI_3', 'VECTORIZE_VOYAGE_AI_3_LITE', 'VECTORIZE_VOYAGE_AI_3_LARGE', 'VECTORIZE_VOYAGE_AI_FINANCE_2', 'VECTORIZE_VOYAGE_AI_MULTILINGUAL_2', 'VECTORIZE_VOYAGE_AI_LAW_2', 'VECTORIZE_VOYAGE_AI_CODE_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_1', 'OPEN_AI_TEXT_EMBEDDING_2', 'OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VOYAGE_AI_2', 'VOYAGE_AI_3', 'VOYAGE_AI_3_LITE', 'VOYAGE_AI_3_LARGE', 'VOYAGE_AI_FINANCE_2', 'VOYAGE_AI_MULTILINGUAL_2', 'VOYAGE_AI_LAW_2', 'VOYAGE_AI_CODE_2', 'TITAN_TEXT_EMBEDDING_1', 'TITAN_TEXT_EMBEDDING_2', 'VERTEX_TEXT_EMBEDDING_4', 'VERTEX_TEXT_EMBEDDING_GECKO_3', 'VERTEX_GECKO_MULTILINGUAL_1', 'VERTEX_MULTILINGUAL_EMBEDDING_2']):
 45            raise ValueError("must be one of enum values ('VECTORIZE_OPEN_AI_TEXT_EMBEDDING_2', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'VECTORIZE_VOYAGE_AI_2', 'VECTORIZE_VOYAGE_AI_3', 'VECTORIZE_VOYAGE_AI_3_LITE', 'VECTORIZE_VOYAGE_AI_3_LARGE', 'VECTORIZE_VOYAGE_AI_FINANCE_2', 'VECTORIZE_VOYAGE_AI_MULTILINGUAL_2', 'VECTORIZE_VOYAGE_AI_LAW_2', 'VECTORIZE_VOYAGE_AI_CODE_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_1', 'OPEN_AI_TEXT_EMBEDDING_2', 'OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VOYAGE_AI_2', 'VOYAGE_AI_3', 'VOYAGE_AI_3_LITE', 'VOYAGE_AI_3_LARGE', 'VOYAGE_AI_FINANCE_2', 'VOYAGE_AI_MULTILINGUAL_2', 'VOYAGE_AI_LAW_2', 'VOYAGE_AI_CODE_2', 'TITAN_TEXT_EMBEDDING_1', 'TITAN_TEXT_EMBEDDING_2', 'VERTEX_TEXT_EMBEDDING_4', 'VERTEX_TEXT_EMBEDDING_GECKO_3', 'VERTEX_GECKO_MULTILINGUAL_1', 'VERTEX_MULTILINGUAL_EMBEDDING_2')")
 46        return value
 47
 48    @field_validator('chunking_strategy')
 49    def chunking_strategy_validate_enum(cls, value):
 50        """Validates the enum"""
 51        if value is None:
 52            return value
 53
 54        if value not in set(['FIXED', 'SENTENCE', 'PARAGRAPH', 'MARKDOWN']):
 55            raise ValueError("must be one of enum values ('FIXED', 'SENTENCE', 'PARAGRAPH', 'MARKDOWN')")
 56        return value
 57
 58    @field_validator('extraction_strategy')
 59    def extraction_strategy_validate_enum(cls, value):
 60        """Validates the enum"""
 61        if value is None:
 62            return value
 63
 64        if value not in set(['FAST', 'IRIS', 'MIXED']):
 65            raise ValueError("must be one of enum values ('FAST', 'IRIS', 'MIXED')")
 66        return value
 67
 68    model_config = ConfigDict(
 69        populate_by_name=True,
 70        validate_assignment=True,
 71        protected_namespaces=(),
 72    )
 73
 74
 75    def to_str(self) -> str:
 76        """Returns the string representation of the model using alias"""
 77        return pprint.pformat(self.model_dump(by_alias=True))
 78
 79    def to_json(self) -> str:
 80        """Returns the JSON representation of the model using alias"""
 81        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
 82        return json.dumps(self.to_dict())
 83
 84    @classmethod
 85    def from_json(cls, json_str: str) -> Optional[Self]:
 86        """Create an instance of AIPlatformConfigSchema from a JSON string"""
 87        return cls.from_dict(json.loads(json_str))
 88
 89    def to_dict(self) -> Dict[str, Any]:
 90        """Return the dictionary representation of the model using alias.
 91
 92        This has the following differences from calling pydantic's
 93        `self.model_dump(by_alias=True)`:
 94
 95        * `None` is only added to the output dict for nullable fields that
 96          were set at model initialization. Other fields with value `None`
 97          are ignored.
 98        """
 99        excluded_fields: Set[str] = set([
100        ])
101
102        _dict = self.model_dump(
103            by_alias=True,
104            exclude=excluded_fields,
105            exclude_none=True,
106        )
107        return _dict
108
109    @classmethod
110    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
111        """Create an instance of AIPlatformConfigSchema from a dict"""
112        if obj is None:
113            return None
114
115        if not isinstance(obj, dict):
116            return cls.model_validate(obj)
117
118        _obj = cls.model_validate({
119            "embeddingModel": obj.get("embeddingModel"),
120            "chunkingStrategy": obj.get("chunkingStrategy"),
121            "chunkSize": obj.get("chunkSize"),
122            "chunkOverlap": obj.get("chunkOverlap"),
123            "dimensions": obj.get("dimensions"),
124            "extractionStrategy": obj.get("extractionStrategy")
125        })
126        return _obj

class AIPlatformConfigSchema(pydantic.main.BaseModel): View Source

 27class AIPlatformConfigSchema(BaseModel):
 28    """
 29    AIPlatformConfigSchema
 30    """ # noqa: E501
 31    embedding_model: Optional[StrictStr] = Field(default=None, alias="embeddingModel")
 32    chunking_strategy: Optional[StrictStr] = Field(default=None, alias="chunkingStrategy")
 33    chunk_size: Optional[Annotated[int, Field(strict=True, ge=1)]] = Field(default=None, alias="chunkSize")
 34    chunk_overlap: Optional[Annotated[int, Field(strict=True, ge=0)]] = Field(default=None, alias="chunkOverlap")
 35    dimensions: Optional[Annotated[int, Field(strict=True, ge=1)]] = None
 36    extraction_strategy: Optional[StrictStr] = Field(default=None, alias="extractionStrategy")
 37    __properties: ClassVar[List[str]] = ["embeddingModel", "chunkingStrategy", "chunkSize", "chunkOverlap", "dimensions", "extractionStrategy"]
 38
 39    @field_validator('embedding_model')
 40    def embedding_model_validate_enum(cls, value):
 41        """Validates the enum"""
 42        if value is None:
 43            return value
 44
 45        if value not in set(['VECTORIZE_OPEN_AI_TEXT_EMBEDDING_2', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'VECTORIZE_VOYAGE_AI_2', 'VECTORIZE_VOYAGE_AI_3', 'VECTORIZE_VOYAGE_AI_3_LITE', 'VECTORIZE_VOYAGE_AI_3_LARGE', 'VECTORIZE_VOYAGE_AI_FINANCE_2', 'VECTORIZE_VOYAGE_AI_MULTILINGUAL_2', 'VECTORIZE_VOYAGE_AI_LAW_2', 'VECTORIZE_VOYAGE_AI_CODE_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_1', 'OPEN_AI_TEXT_EMBEDDING_2', 'OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VOYAGE_AI_2', 'VOYAGE_AI_3', 'VOYAGE_AI_3_LITE', 'VOYAGE_AI_3_LARGE', 'VOYAGE_AI_FINANCE_2', 'VOYAGE_AI_MULTILINGUAL_2', 'VOYAGE_AI_LAW_2', 'VOYAGE_AI_CODE_2', 'TITAN_TEXT_EMBEDDING_1', 'TITAN_TEXT_EMBEDDING_2', 'VERTEX_TEXT_EMBEDDING_4', 'VERTEX_TEXT_EMBEDDING_GECKO_3', 'VERTEX_GECKO_MULTILINGUAL_1', 'VERTEX_MULTILINGUAL_EMBEDDING_2']):
 46            raise ValueError("must be one of enum values ('VECTORIZE_OPEN_AI_TEXT_EMBEDDING_2', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'VECTORIZE_VOYAGE_AI_2', 'VECTORIZE_VOYAGE_AI_3', 'VECTORIZE_VOYAGE_AI_3_LITE', 'VECTORIZE_VOYAGE_AI_3_LARGE', 'VECTORIZE_VOYAGE_AI_FINANCE_2', 'VECTORIZE_VOYAGE_AI_MULTILINGUAL_2', 'VECTORIZE_VOYAGE_AI_LAW_2', 'VECTORIZE_VOYAGE_AI_CODE_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_1', 'OPEN_AI_TEXT_EMBEDDING_2', 'OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VOYAGE_AI_2', 'VOYAGE_AI_3', 'VOYAGE_AI_3_LITE', 'VOYAGE_AI_3_LARGE', 'VOYAGE_AI_FINANCE_2', 'VOYAGE_AI_MULTILINGUAL_2', 'VOYAGE_AI_LAW_2', 'VOYAGE_AI_CODE_2', 'TITAN_TEXT_EMBEDDING_1', 'TITAN_TEXT_EMBEDDING_2', 'VERTEX_TEXT_EMBEDDING_4', 'VERTEX_TEXT_EMBEDDING_GECKO_3', 'VERTEX_GECKO_MULTILINGUAL_1', 'VERTEX_MULTILINGUAL_EMBEDDING_2')")
 47        return value
 48
 49    @field_validator('chunking_strategy')
 50    def chunking_strategy_validate_enum(cls, value):
 51        """Validates the enum"""
 52        if value is None:
 53            return value
 54
 55        if value not in set(['FIXED', 'SENTENCE', 'PARAGRAPH', 'MARKDOWN']):
 56            raise ValueError("must be one of enum values ('FIXED', 'SENTENCE', 'PARAGRAPH', 'MARKDOWN')")
 57        return value
 58
 59    @field_validator('extraction_strategy')
 60    def extraction_strategy_validate_enum(cls, value):
 61        """Validates the enum"""
 62        if value is None:
 63            return value
 64
 65        if value not in set(['FAST', 'IRIS', 'MIXED']):
 66            raise ValueError("must be one of enum values ('FAST', 'IRIS', 'MIXED')")
 67        return value
 68
 69    model_config = ConfigDict(
 70        populate_by_name=True,
 71        validate_assignment=True,
 72        protected_namespaces=(),
 73    )
 74
 75
 76    def to_str(self) -> str:
 77        """Returns the string representation of the model using alias"""
 78        return pprint.pformat(self.model_dump(by_alias=True))
 79
 80    def to_json(self) -> str:
 81        """Returns the JSON representation of the model using alias"""
 82        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
 83        return json.dumps(self.to_dict())
 84
 85    @classmethod
 86    def from_json(cls, json_str: str) -> Optional[Self]:
 87        """Create an instance of AIPlatformConfigSchema from a JSON string"""
 88        return cls.from_dict(json.loads(json_str))
 89
 90    def to_dict(self) -> Dict[str, Any]:
 91        """Return the dictionary representation of the model using alias.
 92
 93        This has the following differences from calling pydantic's
 94        `self.model_dump(by_alias=True)`:
 95
 96        * `None` is only added to the output dict for nullable fields that
 97          were set at model initialization. Other fields with value `None`
 98          are ignored.
 99        """
100        excluded_fields: Set[str] = set([
101        ])
102
103        _dict = self.model_dump(
104            by_alias=True,
105            exclude=excluded_fields,
106            exclude_none=True,
107        )
108        return _dict
109
110    @classmethod
111    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
112        """Create an instance of AIPlatformConfigSchema from a dict"""
113        if obj is None:
114            return None
115
116        if not isinstance(obj, dict):
117            return cls.model_validate(obj)
118
119        _obj = cls.model_validate({
120            "embeddingModel": obj.get("embeddingModel"),
121            "chunkingStrategy": obj.get("chunkingStrategy"),
122            "chunkSize": obj.get("chunkSize"),
123            "chunkOverlap": obj.get("chunkOverlap"),
124            "dimensions": obj.get("dimensions"),
125            "extractionStrategy": obj.get("extractionStrategy")
126        })
127        return _obj

AIPlatformConfigSchema

embedding_model: Optional[Annotated[str, Strict(strict=True)]]

chunking_strategy: Optional[Annotated[str, Strict(strict=True)]]

chunk_size: Optional[Annotated[int, FieldInfo(annotation=NoneType, required=True, metadata=[Strict(strict=True), Ge(ge=1)])]]

chunk_overlap: Optional[Annotated[int, FieldInfo(annotation=NoneType, required=True, metadata=[Strict(strict=True), Ge(ge=0)])]]

dimensions: Optional[Annotated[int, FieldInfo(annotation=NoneType, required=True, metadata=[Strict(strict=True), Ge(ge=1)])]]

extraction_strategy: Optional[Annotated[str, Strict(strict=True)]]

@field_validator('embedding_model')

def embedding_model_validate_enum(cls, value): View Source

39    @field_validator('embedding_model')
40    def embedding_model_validate_enum(cls, value):
41        """Validates the enum"""
42        if value is None:
43            return value
44
45        if value not in set(['VECTORIZE_OPEN_AI_TEXT_EMBEDDING_2', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'VECTORIZE_VOYAGE_AI_2', 'VECTORIZE_VOYAGE_AI_3', 'VECTORIZE_VOYAGE_AI_3_LITE', 'VECTORIZE_VOYAGE_AI_3_LARGE', 'VECTORIZE_VOYAGE_AI_FINANCE_2', 'VECTORIZE_VOYAGE_AI_MULTILINGUAL_2', 'VECTORIZE_VOYAGE_AI_LAW_2', 'VECTORIZE_VOYAGE_AI_CODE_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_1', 'OPEN_AI_TEXT_EMBEDDING_2', 'OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VOYAGE_AI_2', 'VOYAGE_AI_3', 'VOYAGE_AI_3_LITE', 'VOYAGE_AI_3_LARGE', 'VOYAGE_AI_FINANCE_2', 'VOYAGE_AI_MULTILINGUAL_2', 'VOYAGE_AI_LAW_2', 'VOYAGE_AI_CODE_2', 'TITAN_TEXT_EMBEDDING_1', 'TITAN_TEXT_EMBEDDING_2', 'VERTEX_TEXT_EMBEDDING_4', 'VERTEX_TEXT_EMBEDDING_GECKO_3', 'VERTEX_GECKO_MULTILINGUAL_1', 'VERTEX_MULTILINGUAL_EMBEDDING_2']):
46            raise ValueError("must be one of enum values ('VECTORIZE_OPEN_AI_TEXT_EMBEDDING_2', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VECTORIZE_OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'VECTORIZE_VOYAGE_AI_2', 'VECTORIZE_VOYAGE_AI_3', 'VECTORIZE_VOYAGE_AI_3_LITE', 'VECTORIZE_VOYAGE_AI_3_LARGE', 'VECTORIZE_VOYAGE_AI_FINANCE_2', 'VECTORIZE_VOYAGE_AI_MULTILINGUAL_2', 'VECTORIZE_VOYAGE_AI_LAW_2', 'VECTORIZE_VOYAGE_AI_CODE_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_2', 'VECTORIZE_TITAN_TEXT_EMBEDDING_1', 'OPEN_AI_TEXT_EMBEDDING_2', 'OPEN_AI_TEXT_EMBEDDING_3_SMALL', 'OPEN_AI_TEXT_EMBEDDING_3_LARGE', 'VOYAGE_AI_2', 'VOYAGE_AI_3', 'VOYAGE_AI_3_LITE', 'VOYAGE_AI_3_LARGE', 'VOYAGE_AI_FINANCE_2', 'VOYAGE_AI_MULTILINGUAL_2', 'VOYAGE_AI_LAW_2', 'VOYAGE_AI_CODE_2', 'TITAN_TEXT_EMBEDDING_1', 'TITAN_TEXT_EMBEDDING_2', 'VERTEX_TEXT_EMBEDDING_4', 'VERTEX_TEXT_EMBEDDING_GECKO_3', 'VERTEX_GECKO_MULTILINGUAL_1', 'VERTEX_MULTILINGUAL_EMBEDDING_2')")
47        return value

Validates the enum

@field_validator('chunking_strategy')

def chunking_strategy_validate_enum(cls, value): View Source

49    @field_validator('chunking_strategy')
50    def chunking_strategy_validate_enum(cls, value):
51        """Validates the enum"""
52        if value is None:
53            return value
54
55        if value not in set(['FIXED', 'SENTENCE', 'PARAGRAPH', 'MARKDOWN']):
56            raise ValueError("must be one of enum values ('FIXED', 'SENTENCE', 'PARAGRAPH', 'MARKDOWN')")
57        return value

Validates the enum

@field_validator('extraction_strategy')

def extraction_strategy_validate_enum(cls, value): View Source

59    @field_validator('extraction_strategy')
60    def extraction_strategy_validate_enum(cls, value):
61        """Validates the enum"""
62        if value is None:
63            return value
64
65        if value not in set(['FAST', 'IRIS', 'MIXED']):
66            raise ValueError("must be one of enum values ('FAST', 'IRIS', 'MIXED')")
67        return value

Validates the enum

model_config = {'populate_by_name': True, 'validate_assignment': True, 'protected_namespaces': ()}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

def to_str(self) -> str: View Source

76    def to_str(self) -> str:
77        """Returns the string representation of the model using alias"""
78        return pprint.pformat(self.model_dump(by_alias=True))

Returns the string representation of the model using alias

def to_json(self) -> str: View Source

80    def to_json(self) -> str:
81        """Returns the JSON representation of the model using alias"""
82        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
83        return json.dumps(self.to_dict())

Returns the JSON representation of the model using alias

@classmethod

def from_json(cls, json_str: str) -> Optional[Self]: View Source

85    @classmethod
86    def from_json(cls, json_str: str) -> Optional[Self]:
87        """Create an instance of AIPlatformConfigSchema from a JSON string"""
88        return cls.from_dict(json.loads(json_str))

Create an instance of AIPlatformConfigSchema from a JSON string

def to_dict(self) -> Dict[str, Any]: View Source

 90    def to_dict(self) -> Dict[str, Any]:
 91        """Return the dictionary representation of the model using alias.
 92
 93        This has the following differences from calling pydantic's
 94        `self.model_dump(by_alias=True)`:
 95
 96        * `None` is only added to the output dict for nullable fields that
 97          were set at model initialization. Other fields with value `None`
 98          are ignored.
 99        """
100        excluded_fields: Set[str] = set([
101        ])
102
103        _dict = self.model_dump(
104            by_alias=True,
105            exclude=excluded_fields,
106            exclude_none=True,
107        )
108        return _dict

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.

@classmethod

def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]: View Source

110    @classmethod
111    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
112        """Create an instance of AIPlatformConfigSchema from a dict"""
113        if obj is None:
114            return None
115
116        if not isinstance(obj, dict):
117            return cls.model_validate(obj)
118
119        _obj = cls.model_validate({
120            "embeddingModel": obj.get("embeddingModel"),
121            "chunkingStrategy": obj.get("chunkingStrategy"),
122            "chunkSize": obj.get("chunkSize"),
123            "chunkOverlap": obj.get("chunkOverlap"),
124            "dimensions": obj.get("dimensions"),
125            "extractionStrategy": obj.get("extractionStrategy")
126        })
127        return _obj

Create an instance of AIPlatformConfigSchema from a dict