fastembed 0.3.2__tar.gz → 0.3.3__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {fastembed-0.3.2 → fastembed-0.3.3}/PKG-INFO +1 -1
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/sparse/bm25.py +2 -2
- {fastembed-0.3.2 → fastembed-0.3.3}/pyproject.toml +1 -1
- {fastembed-0.3.2 → fastembed-0.3.3}/LICENSE +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/README.md +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/__init__.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/common/__init__.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/common/model_management.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/common/onnx_model.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/common/preprocessor_utils.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/common/types.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/common/utils.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/image/__init__.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/image/image_embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/image/image_embedding_base.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/image/onnx_embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/image/onnx_image_model.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/image/transform/functional.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/image/transform/operators.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/late_interaction/__init__.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/late_interaction/colbert.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/late_interaction/late_interaction_embedding_base.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/late_interaction/late_interaction_text_embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/parallel_processor.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/sparse/__init__.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/sparse/bm42.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/sparse/sparse_embedding_base.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/sparse/sparse_text_embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/sparse/splade_pp.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/sparse/utils/tokenizer.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/text/__init__.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/text/clip_embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/text/e5_onnx_embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/text/jina_onnx_embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/text/mini_lm_embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/text/onnx_embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/text/onnx_text_model.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/text/text_embedding.py +0 -0
- {fastembed-0.3.2 → fastembed-0.3.3}/fastembed/text/text_embedding_base.py +0 -0
|
@@ -250,8 +250,8 @@ class Bm25(SparseTextEmbeddingBase):
|
|
|
250
250
|
tokens = self.tokenizer.tokenize(text)
|
|
251
251
|
stemmed_tokens = self._stem(tokens)
|
|
252
252
|
token_ids = np.array(
|
|
253
|
-
|
|
254
|
-
dtype=np.
|
|
253
|
+
list(set(self.compute_token_id(token) for token in stemmed_tokens)),
|
|
254
|
+
dtype=np.int32,
|
|
255
255
|
)
|
|
256
256
|
values = np.ones_like(token_ids)
|
|
257
257
|
yield SparseEmbedding(indices=token_ids, values=values)
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[tool.poetry]
|
|
2
2
|
name = "fastembed"
|
|
3
|
-
version = "0.3.
|
|
3
|
+
version = "0.3.3"
|
|
4
4
|
description = "Fast, light, accurate library built for retrieval embedding generation"
|
|
5
5
|
authors = ["Qdrant Team <info@qdrant.tech>", "NirantK <nirant.bits@gmail.com>"]
|
|
6
6
|
license = "Apache License"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{fastembed-0.3.2 → fastembed-0.3.3}/fastembed/late_interaction/late_interaction_embedding_base.py
RENAMED
|
File without changes
|
{fastembed-0.3.2 → fastembed-0.3.3}/fastembed/late_interaction/late_interaction_text_embedding.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|