cayu.embeddings

Public Cayu API. Definitions are grouped by their public source module, and definitions from private implementation modules appear on their package’s page; adding a symbol does not move existing links. The import shown at each entry is a supported public namespace. Read the Python API overview and install the required extra.

TextEmbedding

from cayu import TextEmbedding

One embedding vector returned by a provider.

Bases: BaseModel.

Fields and attributes

Defaults below are source expressions; Field(...) includes schema/validation settings and default_factory creates a fresh value. Inherited declarations are included. Constructor behavior follows the model or dataclass shown in the bases/decorators.

Name	Type	Default
index	int	required
vector	list[float]	required

validate_index (method)

TextEmbedding.validate_index(value: int, info) -> int

validate_vector (method)

TextEmbedding.validate_vector(value: list[float], info) -> list[float]

Release source · Runtime guarantees · Capability guides

TextEmbeddingProvider

from cayu import TextEmbeddingProvider

Provider-neutral text embedding contract.

Bases: ABC.

Fields and attributes

Defaults below are source expressions; Field(...) includes schema/validation settings and default_factory creates a fresh value. Inherited declarations are included. Constructor behavior follows the model or dataclass shown in the bases/decorators.

Name	Type	Default
name	str	required

embed_texts (method)

async TextEmbeddingProvider.embed_texts(request: TextEmbeddingRequest) -> TextEmbeddingResult

Embed text inputs and return one vector for each input.

Release source · Runtime guarantees · Capability guides

TextEmbeddingRequest

from cayu import TextEmbeddingRequest

Provider-neutral request to embed one or more text inputs.

Bases: BaseModel.

Fields and attributes

Defaults below are source expressions; Field(...) includes schema/validation settings and default_factory creates a fresh value. Inherited declarations are included. Constructor behavior follows the model or dataclass shown in the bases/decorators.

Name	Type	Default
model	str	required
texts	list[str]	required
dimensions	int | None	None
options	dict[str, Any]	Field(default_factory=dict)

validate_model (method)

TextEmbeddingRequest.validate_model(value: str, info) -> str

validate_texts (method)

TextEmbeddingRequest.validate_texts(value: list[str], info) -> list[str]

validate_dimensions (method)

TextEmbeddingRequest.validate_dimensions(value: int | None, info) -> int | None

copy_options (method)

TextEmbeddingRequest.copy_options(value: dict[str, Any]) -> dict[str, Any]

Release source · Runtime guarantees · Capability guides

TextEmbeddingResult

from cayu import TextEmbeddingResult

Provider-neutral embedding response.

Bases: BaseModel.

Fields and attributes

Defaults below are source expressions; Field(...) includes schema/validation settings and default_factory creates a fresh value. Inherited declarations are included. Constructor behavior follows the model or dataclass shown in the bases/decorators.

Name	Type	Default
model	str	required
embeddings	list[TextEmbedding]	required
usage	TextEmbeddingUsage | None	None
metadata	dict[str, Any]	Field(default_factory=dict)

validate_model (method)

TextEmbeddingResult.validate_model(value: str, info) -> str

copy_embeddings (method)

TextEmbeddingResult.copy_embeddings(value: list[TextEmbedding]) -> list[TextEmbedding]

copy_usage (method)

TextEmbeddingResult.copy_usage(value: TextEmbeddingUsage | None) -> TextEmbeddingUsage | None

copy_metadata (method)

TextEmbeddingResult.copy_metadata(value: dict[str, Any]) -> dict[str, Any]

validate_embeddings (method)

TextEmbeddingResult.validate_embeddings() -> TextEmbeddingResult

Release source · Runtime guarantees · Capability guides

TextEmbeddingUsage

from cayu import TextEmbeddingUsage

Provider-reported token usage for an embedding request when available.

Bases: BaseModel.

Fields and attributes

Defaults below are source expressions; Field(...) includes schema/validation settings and default_factory creates a fresh value. Inherited declarations are included. Constructor behavior follows the model or dataclass shown in the bases/decorators.

Name	Type	Default
input_tokens	int | None	Field(default=None, ge=0)
total_tokens	int | None	Field(default=None, ge=0)
metadata	dict[str, Any]	Field(default_factory=dict)

validate_token_count (method)

TextEmbeddingUsage.validate_token_count(value: int | None, info) -> int | None

copy_metadata (method)

TextEmbeddingUsage.copy_metadata(value: dict[str, Any]) -> dict[str, Any]

Release source · Runtime guarantees · Capability guides