LaBSEmbedding

DenseEmbedding

DashAI.back.models.RAG.embeddings.dense.LaBSEmbedding

---

Dense embeddings using the LaBSE multilingual model (109 languages).

Wraps :class:_SentenceTransformerEmbedding (mean pooling, L2 normalisation forced on) and exposes it as a DashAI component with a configurable schema (:class:LaBSEmbeddingSchema).

Parameters

model_name : string, default=sentence-transformers/LaBSE

LaBSE model for multilingual embedding generation (109 languages).

overflow_strategy : string, default=truncate

Strategy for chunks exceeding model max sequence length.

device : string, default=cpu

Device to run the model on.

Methods

batch_encode(self, texts: List[str])

Defined on LaBSEmbedding

Encode a batch of texts into dense embeddings.

encode(self, text: str)

Defined on LaBSEmbedding

Encode a single text into a dense embedding.

load(self)

Defined on LaBSEmbedding

Load the LaBSE model and tokenizer.

get_credential(self, name: str)

Defined on ConfigObject

Resolve a registered credential component by name.

Parameters

name : str

Credential component class name (e.g. "HuggingFaceCredential").

Returns

BaseCredential

An instance of the requested credential component.

get_schema(cls) -> dict

Defined on ConfigObject

Generates the component related Json Schema.

Returns

dict

Dictionary representing the Json Schema of the component.

validate_and_transform(self, raw_data: dict) -> dict

Defined on ConfigObject

It takes the data given by the user to initialize the model and returns it with all the objects that the model needs to work.

Parameters

raw_data : dict

A dictionary with the data provided by the user to initialize the model.

Returns

dict

A validated dictionary with the necessary objects.