hoops_ai.ml.embeddings.EmbeddingBatch

class hoops_ai.ml.embeddings.EmbeddingBatch(values, model, dim, ids=None, metadata=None)

Bases: object

Batch embedding result for multiple inputs.

Parameters:

  • values (np.ndarray) – Embedding matrix of shape (n, dim), dtype float32

  • model (str) – Model identifier (e.g., ‘hf:all-MiniLM-L6-v2’, ‘hoops:shape-v1’)

  • dim (int) – Dimensionality of each embedding vector

  • ids (Optional[List[str]]) – Optional identifiers for each embedding in the batch

  • metadata (Dict[str, Any]) – Optional batch-level diagnostics

classmethod from_arrays(embeddings, model='unknown', ids=None, metadata=None)

Create EmbeddingBatch from xarray or numpy arrays.

Parameters:

  • embeddings (Union[xr.DataArray, np.ndarray]) – Embedding matrix (xr.DataArray or np.ndarray) with shape (n, dim)

  • model (str) – Model identifier string

  • ids (Optional[Union[xr.DataArray, np.ndarray, List[str]]]) – Optional part IDs (xr.DataArray, np.ndarray, or List[str])

  • metadata (Optional[Dict[str, Any]]) – Optional batch-level metadata

Returns:

EmbeddingBatch instance

Raises:

  • TypeError – If arrays are not of supported types

  • ValueError – If embedding array is not 2D

Return type:

EmbeddingBatch

get(index)

Retrieve a single Embedding from the batch by index.

Parameters:

index (int) – Zero-based index into the batch.

Returns:

Embedding with a copy of the vector at the given index.

Raises:

IndexError – If index is out of range.

Return type:

Embedding

dim: int
ids: List[str] | None = None
metadata: Dict[str, Any] = None
model: str
values: np.ndarray