KnowledgeBaseCreateRequest¶

pydantic model openapi_client.models.knowledge_base_create_request.KnowledgeBaseCreateRequest¶

KnowledgeBaseCreateRequest

Fields:

data_store_type (str | None)
description (str | None)
embedding_model (str | None)
guard_rails (List[openapi_client.models.guardrail.Guardrail] | None)
keywords (List[str] | None)
knowledgebase_name (str)
knowledgebase_type (str | None)
smart_chunking (bool | None)
tenant_name (str | None)

field knowledgebase_name: Annotated[str, Field(min_length=3, strict=True, max_length=120)] [Required] (alias 'KnowledgebaseName')¶

Unique knowledge base name. Must start with a letter and be 3-120 alphanumeric or underscore characters. Structured knowledge bases are limited to 32 characters.

Constraints:

strict = True
min_length = 3
max_length = 120

field description: Optional[Annotated[str, Field(strict=True, max_length=200)]] = None (alias 'Description')¶: Optional description of the knowledge base. Maximum 200 characters.

field embedding_model: Optional[StrictStr] = None (alias 'EmbeddingModel')¶: Embedding model ID enabled for knowledge bases. Required for unstructured knowledge bases (KnowledgebaseType unstructured or omitted). Ignored for structured knowledge bases.

field guard_rails: Optional[List[Guardrail]] = None (alias 'GuardRails')¶: Guard rails to attach. Each item requires Id and Version. If omitted or empty, the default guard rail is applied.

field keywords: Optional[List[StrictStr]] = None (alias 'Keywords')¶: Optional keywords associated with the knowledge base.

field knowledgebase_type: Optional[StrictStr] = None (alias 'KnowledgebaseType')¶: Knowledge base type. Defaults to unstructured if omitted. Use unstructured or structured. The handler treats any value other than structured as unstructured.

field data_store_type: Optional[StrictStr] = None (alias 'DataStoreType')¶: Structured datastore. Required when KnowledgebaseType is structured. Ignored for unstructured knowledge bases.

field tenant_name: Optional[StrictStr] = None (alias 'TenantName')¶: Tenant database name. Required when DataStoreType is redshift and multi-tenancy is enabled. Ignored for unstructured and s3athena.

field smart_chunking: Optional[StrictBool] = False (alias 'SmartChunking')¶: When true, run LLM-assisted contextual chunking during unstructured ingestion. Improves retrieval quality; increases indexing cost and latency. Defaults to false. Stored only for unstructured knowledge bases.

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 KnowledgeBaseCreateRequest 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 KnowledgeBaseCreateRequest from a dict

Return type:: Optional[Self]