qdrant_client.fastembed_common module

class FastEmbedMisc

Bases: object

classmethod import_fastembed() → None

classmethod is_installed() → bool

classmethod is_supported_image_model(model_name: str) → bool

Checks if the model is supported by fastembed.

Parameters:

model_name (str) – The name of the model to check.

Returns:

bool – True if the model is supported, False otherwise.

classmethod is_supported_late_interaction_multimodal_model(model_name: str) → bool

Checks if the model is supported by fastembed.

Parameters:

model_name (str) – The name of the model to check.

Returns:

bool – True if the model is supported, False otherwise.

classmethod is_supported_late_interaction_text_model(model_name: str) → bool

Checks if the model is supported by fastembed.

Parameters:

model_name (str) – The name of the model to check.

Returns:

bool – True if the model is supported, False otherwise.

classmethod is_supported_sparse_model(model_name: str) → bool

Checks if the model is supported by fastembed.

Parameters:

model_name (str) – The name of the model to check.

Returns:

bool – True if the model is supported, False otherwise.

classmethod is_supported_text_model(model_name: str) → bool

Checks if the model is supported by fastembed.

Parameters:

model_name (str) – The name of the model to check.

Returns:

bool – True if the model is supported, False otherwise.

classmethod list_image_models() → dict[str, tuple[int, Distance]]

Lists the supported image dense models.

Custom image models are not supported yet, but calls to ImageEmbedding.list_supported_models() is done each time in order for preserving the same style as with TextEmbedding.

Returns:

dict[str, tuple[int, models.Distance]] – A dict of model names, their dimensions and distance metrics.

classmethod list_late_interaction_multimodal_models() → dict[str, tuple[int, Distance]]

Lists the supported late interaction multimodal models.

Custom late interaction multimodal models are not supported yet, but calls to LateInteractionMultimodalEmbedding.list_supported_models() is done each time in order for preserving the same style as with TextEmbedding.

Returns:

dict[str, tuple[int, models.Distance]] – A dict of model names, their dimensions and distance metrics.

classmethod list_late_interaction_text_models() → dict[str, tuple[int, Distance]]

Lists the supported late interaction text models.

Custom late interaction models are not supported yet, but calls to LateInteractionTextEmbedding.list_supported_models() is done each time in order for preserving the same style as with TextEmbedding.

Returns:

dict[str, tuple[int, models.Distance]] – A dict of model names, their dimensions and distance metrics.

classmethod list_sparse_models() → dict[str, dict[str, Any]]

Lists the supported sparse models.

Custom sparse models are not supported yet, but calls to SparseTextEmbedding.list_supported_models() is done each time in order for preserving the same style as with TextEmbedding.

Returns:

dict[str, dict[str, Any]] – A dict of model names and their descriptions.

classmethod list_text_models() → dict[str, tuple[int, Distance]]

Lists the supported dense text models.

Requires invocation of TextEmbedding.list_supported_models() to support custom models.

Returns:

dict[str, tuple[int, models.Distance]] – A dict of model names, their dimensions and distance metrics.

IS_INSTALLED: bool = False

class QueryResponse(*, id: str | int, embedding: list[float] | None, sparse_embedding: SparseVector | None = None, metadata: dict[str, Any], document: str, score: float)

Bases: BaseModel

document: str

embedding: list[float] | None

id: str | int

metadata: dict[str, Any]

model_config: ClassVar[ConfigDict] = {'extra': 'forbid'}

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

score: float

sparse_embedding: SparseVector | None