fastembed 0.2.3__tar.gz → 0.2.5__tar.gz

{fastembed-0.2.3 → fastembed-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fastembed
-Version: 0.2.3
+Version: 0.2.5
 Summary: Fast, light, accurate library built for retrieval embedding generation
 Home-page: https://github.com/qdrant/fastembed
 License: Apache License

{fastembed-0.2.3 → fastembed-0.2.5}/fastembed/__init__.py

@@ -1,3 +1,6 @@
+import importlib.metadata
+
 from fastembed.text.text_embedding import TextEmbedding
 
+__version__ = importlib.metadata.version("fastembed")
 __all__ = ["TextEmbedding"]

{fastembed-0.2.3 → fastembed-0.2.5}/fastembed/sparse/sparse_text_embedding.py

@@ -48,7 +48,7 @@ class SparseTextEmbedding(SparseTextEmbeddingBase):
 
         for EMBEDDING_MODEL_TYPE in self.EMBEDDINGS_REGISTRY:
             supported_models = EMBEDDING_MODEL_TYPE.list_supported_models()
-            if any(model_name == model["model"] for model in supported_models):
+            if any(model_name.lower() == model["model"].lower() for model in supported_models):
                 self.model = EMBEDDING_MODEL_TYPE(model_name, cache_dir, threads, **kwargs)
                 return
 

{fastembed-0.2.3 → fastembed-0.2.5}/fastembed/sparse/splade_pp.py

@@ -8,7 +8,7 @@ from fastembed.sparse.sparse_embedding_base import SparseEmbedding, SparseTextEm
 
 supported_splade_models = [
     {
-        "model": "prithvida/SPLADE_PP_en_v1",
+        "model": "prithvida/Splade_PP_en_v1",
         "vocab_size": 30522,
         "description": "Independent Implementation of SPLADE++ Model for English",
         "size_in_GB": 0.532,
@@ -27,11 +27,10 @@ class SpladePP(SparseTextEmbeddingBase, OnnxModel[SparseEmbedding]):
 
         weighted_log = relu_log * np.expand_dims(attention_mask, axis=-1)
 
-        max_val = np.max(weighted_log, axis=1)
+        scores = np.max(weighted_log, axis=1)
 
         # Score matrix of shape (batch_size, vocab_size)
         # Most of the values are 0, only a few are non-zero
-        scores = np.squeeze(max_val)
         for row_scores in scores:
             indices = row_scores.nonzero()[0]
             scores = row_scores[indices]

{fastembed-0.2.3 → fastembed-0.2.5}/fastembed/text/text_embedding.py

@@ -55,7 +55,7 @@ class TextEmbedding(TextEmbeddingBase):
 
         for EMBEDDING_MODEL_TYPE in self.EMBEDDINGS_REGISTRY:
             supported_models = EMBEDDING_MODEL_TYPE.list_supported_models()
-            if any(model_name == model["model"] for model in supported_models):
+            if any(model_name.lower() == model["model"].lower() for model in supported_models):
                 self.model = EMBEDDING_MODEL_TYPE(model_name, cache_dir, threads, **kwargs)
                 return
 

{fastembed-0.2.3 → fastembed-0.2.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "fastembed"
-version = "0.2.3"
+version = "0.2.5"
 description = "Fast, light, accurate library built for retrieval embedding generation"
 authors = ["NirantK <nirant.bits@gmail.com>"]
 license = "Apache License"