| Name | Type | Description |
|---|---|---|
model_name | str | Default: 'Qdrant/bm25'The name of the model to use. |
batch_size | int | Default: 256Batch size for encoding. |
cache_dir | str | Default: NoneThe path to the model cache directory. Can also be set using the |
threads | int | Default: None |
providers | Sequence[Any] | Default: None |
kwargs | Any | Default: {} |
An interface for sparse embedding models to use with Qdrant.
The number of threads onnxruntime session can use.
List of ONNX execution providers. parallel (int, optional): If >1, data-parallel encoding will be used, r Recommended for encoding of large datasets. If 0, use all available cores. If None, don't use data-parallel processing, use default onnxruntime threading instead.
Additional options to pass to fastembed.SparseTextEmbedding
