hoops_ai.ml.embeddings.Embedding

class hoops_ai.ml.embeddings.Embedding(values, model, dim, id=None, metadata=None)

Bases: object

Single embedding result.

Parameters:

  • values (ndarray) – Embedding vector of shape (dim,), dtype float32

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

  • dim (int) – Dimensionality of the embedding vector

  • id (str | None) – Optional identifier for this embedding (e.g., file path, part ID)

  • metadata (Dict[str, Any]) – Optional diagnostics (tokens, timings, processing info, etc.)

dim: int
id: str | None = None
metadata: Dict[str, Any] = None
model: str
values: ndarray