luplo.core.embedding.local
==========================

.. py:module:: luplo.core.embedding.local

.. autoapi-nested-parse::

   Local embedding backend using sentence-transformers (BGE-M3).

   Requires the ``luplo[vector-local]`` extra::

       uv pip install 'luplo[vector-local]'



Classes
-------

.. autoapisummary::

   luplo.core.embedding.local.LocalEmbedding


Module Contents
---------------

.. py:class:: LocalEmbedding(model_name: str = 'BAAI/bge-m3')

   Embedding backend backed by a local sentence-transformers model.

   :param model_name: HuggingFace model ID (default ``BAAI/bge-m3``).


   .. py:method:: embed(texts: list[str]) -> list[list[float] | None]
      :async:


      Embed texts using the local model.

      Note: sentence-transformers is synchronous; this call blocks.
      For production use, consider wrapping in ``asyncio.to_thread``.