orca_sdk.embedding_model

PretrainedEmbeddingModel

Bases: _EmbeddingModel

A pretrained embedding model

Models:

OrcaCloud supports a select number of small to medium sized embedding models that perform well on the Hugging Face MTEB Leaderboard. These can be accessed as class attributes. We currently support:

• CDE_SMALL: Context-aware CDE small model from Hugging Face (jxm/cde-small-v1)
• CLIP_BASE: Multi-modal CLIP model from Hugging Face (sentence-transformers/clip-ViT-L-14)
• GTE_BASE: Alibaba’s GTE model from Hugging Face (Alibaba-NLP/gte-base-en-v1.5)

Examples:

>>> PretrainedEmbeddingModel.CDE_SMALL
PretrainedEmbeddingModel({name: CDE_SMALL, embedding_dim: 768, max_seq_length: 512})

Attributes:

• name –

  Name of the pretrained embedding model

• embedding_dim –

  Dimension of the embeddings that are generated by the model

• max_seq_length –

  Maximum input length (in tokens not characters) that this model can process. Inputs that are longer will be truncated during the embedding process

• uses_context –

  Whether the pretrained embedding model uses context

all classmethod

all()

List all pretrained embedding models in the OrcaCloud

Returns:

• list[PretrainedEmbeddingModel] –

  A list of all pretrained embedding models available in the OrcaCloud

exists classmethod

exists(name)

Check if a pretrained embedding model exists by name

Parameters:

• name (str) –

  The name of the pretrained embedding model

Returns:

• bool –

  True if the pretrained embedding model exists, False otherwise

finetune

finetune(
    name,
    train_datasource,
    *,
    eval_datasource=None,
    label_column="label",
    value_column="value",
    training_method=EmbeddingFinetuningMethod.CLASSIFICATION,
    training_args=None,
    if_exists="error"
)

Finetune an embedding model

Parameters:

• name (str) –

  Name of the finetuned embedding model

• train_datasource (Datasource | LabeledMemoryset) –

  Data to train on

• eval_datasource (Datasource | None, default: None ) –

  Optionally provide data to evaluate on

• label_column (str, default: 'label' ) –

  Column name of the label

• value_column (str, default: 'value' ) –

  Column name of the value

• training_method (EmbeddingFinetuningMethod | str, default: CLASSIFICATION ) –

  Training method to use

• training_args (dict | None, default: None ) –

  Optional override for Hugging Face TrainingArguments. If not provided, reasonable training arguments will be used for the specified training method

• if_exists (CreateMode, default: 'error' ) –

  What to do if a finetuned embedding model with the same name already exists, defaults to "error". Other option is "open" to open the existing finetuned embedding model.

Returns:

• FinetunedEmbeddingModel –

  The finetuned embedding model

Raises:

• ValueError –

  If the finetuned embedding model already exists and if_exists is "error" or if it is "open" but the base model param does not match the existing model

Examples:

>>> datasource = Datasource.open("my_datasource")
>>> model = PretrainedEmbeddingModel.CLIP_BASE
>>> model.finetune("my_finetuned_model", datasource)

FinetunedEmbeddingModel

Bases: _EmbeddingModel

A finetuned embedding model in the OrcaCloud

Attributes:

• name –

  Name of the finetuned embedding model

• embedding_dim –

  Dimension of the embeddings that are generated by the model

• max_seq_length –

  Maximum input length (in tokens not characters) that this model can process. Inputs that are longer will be truncated during the embedding process

• uses_context –

  Whether the model uses the memoryset to contextualize embeddings (acts akin to inverse document frequency in TFIDF features)

• id (str) –

  Unique identifier of the finetuned embedding model

• base_model (PretrainedEmbeddingModel) –

  Base model the finetuned embedding model was trained on

• created_at (datetime) –

  When the model was finetuned

base_model property

base_model

Pretrained model the finetuned embedding model was based on

all classmethod

all()

List all finetuned embedding model handles in the OrcaCloud

Returns:

• list[FinetunedEmbeddingModel] –

  A list of all finetuned embedding model handles in the OrcaCloud

open classmethod

open(name)

Get a handle to a finetuned embedding model in the OrcaCloud

Parameters:

• name (str) –

  The name or unique identifier of a finetuned embedding model

Returns:

• FinetunedEmbeddingModel –

  A handle to the finetuned embedding model in the OrcaCloud

Raises:

• LookupError –

  If the finetuned embedding model does not exist

exists classmethod

exists(name_or_id)

Check if a finetuned embedding model with the given name or id exists.

Parameters:

• name_or_id (str) –

  The name or id of the finetuned embedding model

Returns:

• bool –

  True if the finetuned embedding model exists, False otherwise

drop classmethod

drop(name_or_id, *, if_not_exists='error')

Delete the finetuned embedding model from the OrcaCloud

Parameters:

• name_or_id (str) –

  The name or id of the finetuned embedding model

Raises:

• LookupError –

  If the finetuned embedding model does not exist and if_not_exists is "error"