ResourceAdditionRequestChunkingConfiguration

pydantic model openapi_client.models.resource_addition_request_chunking_configuration.ResourceAdditionRequestChunkingConfiguration

Optional chunking config for unstructured knowledge bases. Defaults to ChunkingStrategy NONE if omitted. Ignored for structured knowledge bases. Only strategy-specific fields for the chosen ChunkingStrategy are allowed.

Fields:

• breakpoint_percentile_threshold (int | None)

• buffer_size (int | None)

• chunking_strategy (str | None)

• max_token_layer1 (int | None)

• max_token_layer2 (int | None)

• max_tokens (int | None)

• overlap_percentage (int | None)

• overlap_tokens (int | None)

field chunking_strategy: Optional[StrictStr] = 'NONE' (alias 'ChunkingStrategy')

Chunking strategy. Defaults to NONE if omitted.

field max_tokens: Optional[Annotated[int, Field(strict=True, ge=1)]] = None (alias 'MaxTokens')

Max tokens for FIXED_SIZE or SEMANTIC chunking. Default 300. Must be an integer >= 1.

field overlap_percentage: Optional[Annotated[int, Field(le=99, strict=True, ge=1)]] = None (alias 'OverlapPercentage')

Overlap percentage for FIXED_SIZE chunking. Default 10. Range 1-99.

field max_token_layer2: Optional[Annotated[int, Field(le=8192, strict=True, ge=1)]] = None (alias 'MaxTokenLayer2')

Max tokens for hierarchical layer 2. Default 300. Range 1-8192. Must be less than or equal to MaxTokenLayer1.

field max_token_layer1: Optional[Annotated[int, Field(le=8192, strict=True, ge=1)]] = None (alias 'MaxTokenLayer1')

Max tokens for hierarchical layer 1. Default 512. Range 1-8192. Must be greater than or equal to MaxTokenLayer2.

field overlap_tokens: Optional[Annotated[int, Field(strict=True, ge=1)]] = None (alias 'OverlapTokens')

Overlap tokens for hierarchical chunking. Default 10. Must be >= 1 and less than or equal to MaxTokenLayer2.

field buffer_size: Optional[StrictInt] = None (alias 'BufferSize')

Buffer size for SEMANTIC chunking. Default 1.

field breakpoint_percentile_threshold: Optional[Annotated[int, Field(le=99, strict=True, ge=50)]] = None (alias 'BreakpointPercentileThreshold')

Breakpoint percentile for SEMANTIC chunking. Default 95. Range 50-99.

to_str()

Returns the string representation of the model using alias

Return type:

str

to_json()

Returns the JSON representation of the model using alias

Return type:

str

classmethod from_json(json_str)

Create an instance of ResourceAdditionRequestChunkingConfiguration from a JSON string

Return type:

Optional[Self]

to_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.

Return type:

Dict[str, Any]

classmethod from_dict(obj)

Create an instance of ResourceAdditionRequestChunkingConfiguration from a dict

Return type:

Optional[Self]