fastembed-haystack 0.1.0__tar.gz → 1.1.0__tar.gz

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: fastembed-haystack
-Version: 0.1.0
+Version: 1.1.0
 Summary: Haystack 2.x component to embed strings and Documents using fastembed embedding model
 Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/fastembed/README.md
@@ -9,6 +9,7 @@ Author-email: deepset GmbH <info@deepset.ai>
 License-Expression: Apache-2.0
 License-File: LICENSE.txt
 Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/pydoc/config.yml

@@ -18,7 +18,7 @@ processors:
   - type: smart
   - type: crossref
 renderer:
-  type: haystack_pydoc_tools.renderers.ReadmePreviewRenderer
+  type: haystack_pydoc_tools.renderers.ReadmeIntegrationRenderer
   excerpt: FastEmbed integration for Haystack
   category_slug: integrations-api
   title: FastEmbed

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/pyproject.toml

@@ -14,6 +14,7 @@ authors = [
   { name = "deepset GmbH", email = "info@deepset.ai" },
 ]
 classifiers = [
+  "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
   "Programming Language :: Python :: 3.8",

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/src/haystack_integrations/components/embedders/fastembed/embedding_backend/fastembed_backend.py

@@ -19,13 +19,16 @@ class _FastembedEmbeddingBackendFactory:
         model_name: str,
         cache_dir: Optional[str] = None,
         threads: Optional[int] = None,
+        local_files_only: bool = False,
     ):
         embedding_backend_id = f"{model_name}{cache_dir}{threads}"
 
         if embedding_backend_id in _FastembedEmbeddingBackendFactory._instances:
             return _FastembedEmbeddingBackendFactory._instances[embedding_backend_id]
 
-        embedding_backend = _FastembedEmbeddingBackend(model_name=model_name, cache_dir=cache_dir, threads=threads)
+        embedding_backend = _FastembedEmbeddingBackend(
+            model_name=model_name, cache_dir=cache_dir, threads=threads, local_files_only=local_files_only
+        )
         _FastembedEmbeddingBackendFactory._instances[embedding_backend_id] = embedding_backend
         return embedding_backend
 
@@ -40,8 +43,11 @@ class _FastembedEmbeddingBackend:
         model_name: str,
         cache_dir: Optional[str] = None,
         threads: Optional[int] = None,
+        local_files_only: bool = False,
     ):
-        self.model = TextEmbedding(model_name=model_name, cache_dir=cache_dir, threads=threads)
+        self.model = TextEmbedding(
+            model_name=model_name, cache_dir=cache_dir, threads=threads, local_files_only=local_files_only
+        )
 
     def embed(self, data: List[str], progress_bar=True, **kwargs) -> List[List[float]]:
         # the embed method returns a Iterable[np.ndarray], so we convert it to a list of lists
@@ -66,6 +72,7 @@ class _FastembedSparseEmbeddingBackendFactory:
         model_name: str,
         cache_dir: Optional[str] = None,
         threads: Optional[int] = None,
+        local_files_only: bool = False,
     ):
         embedding_backend_id = f"{model_name}{cache_dir}{threads}"
 
@@ -73,7 +80,7 @@ class _FastembedSparseEmbeddingBackendFactory:
             return _FastembedSparseEmbeddingBackendFactory._instances[embedding_backend_id]
 
         embedding_backend = _FastembedSparseEmbeddingBackend(
-            model_name=model_name, cache_dir=cache_dir, threads=threads
+            model_name=model_name, cache_dir=cache_dir, threads=threads, local_files_only=local_files_only
         )
         _FastembedSparseEmbeddingBackendFactory._instances[embedding_backend_id] = embedding_backend
         return embedding_backend
@@ -89,8 +96,11 @@ class _FastembedSparseEmbeddingBackend:
         model_name: str,
         cache_dir: Optional[str] = None,
         threads: Optional[int] = None,
+        local_files_only: bool = False,
     ):
-        self.model = SparseTextEmbedding(model_name=model_name, cache_dir=cache_dir, threads=threads)
+        self.model = SparseTextEmbedding(
+            model_name=model_name, cache_dir=cache_dir, threads=threads, local_files_only=local_files_only
+        )
 
     def embed(self, data: List[List[str]], progress_bar=True, **kwargs) -> List[SparseEmbedding]:
         # The embed method returns a Iterable[SparseEmbedding], so we convert to Haystack SparseEmbedding type.

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_document_embedder.py

@@ -29,14 +29,18 @@ class FastembedDocumentEmbedder:
     # Text taken from PubMed QA Dataset (https://huggingface.co/datasets/pubmed_qa)
     document_list = [
         Document(
-            content="Oxidative stress generated within inflammatory joints can produce autoimmune phenomena and joint destruction. Radical species with oxidative activity, including reactive nitrogen species, represent mediators of inflammation and cartilage damage.",
+            content=("Oxidative stress generated within inflammatory joints can produce autoimmune phenomena and joint "
+                     "destruction. Radical species with oxidative activity, including reactive nitrogen species, "
+                     "represent mediators of inflammation and cartilage damage."),
             meta={
                 "pubid": "25,445,628",
                 "long_answer": "yes",
             },
         ),
         Document(
-            content="Plasma levels of pancreatic polypeptide (PP) rise upon food intake. Although other pancreatic islet hormones, such as insulin and glucagon, have been extensively investigated, PP secretion and actions are still poorly understood.",
+            content=("Plasma levels of pancreatic polypeptide (PP) rise upon food intake. Although other pancreatic "
+                     "islet hormones, such as insulin and glucagon, have been extensively investigated, PP secretion "
+                     "and actions are still poorly understood."),
             meta={
                 "pubid": "25,445,712",
                 "long_answer": "yes",
@@ -49,7 +53,7 @@ class FastembedDocumentEmbedder:
     print(f"Document Embedding: {result['documents'][0].embedding}")
     print(f"Embedding Dimension: {len(result['documents'][0].embedding)}")
     ```
-    """  # noqa: E501
+    """
 
     def __init__(
         self,
@@ -61,6 +65,7 @@ class FastembedDocumentEmbedder:
         batch_size: int = 256,
         progress_bar: bool = True,
         parallel: Optional[int] = None,
+        local_files_only: bool = False,
         meta_fields_to_embed: Optional[List[str]] = None,
         embedding_separator: str = "\n",
     ):
@@ -76,11 +81,12 @@ class FastembedDocumentEmbedder:
         :param prefix: A string to add to the beginning of each text.
         :param suffix: A string to add to the end of each text.
         :param batch_size: Number of strings to encode at once.
-        :param progress_bar: If true, displays progress bar during embedding.
+        :param progress_bar: If `True`, displays progress bar during embedding.
         :param parallel:
                 If > 1, data-parallel encoding will be used, recommended for offline encoding of large datasets.
                 If 0, use all available cores.
                 If None, don't use data-parallel processing, use default onnxruntime threading instead.
+        :param local_files_only: If `True`, only use the model files in the `cache_dir`.
         :param meta_fields_to_embed: List of meta fields that should be embedded along with the Document content.
         :param embedding_separator: Separator used to concatenate the meta fields to the Document content.
         """
@@ -93,6 +99,7 @@ class FastembedDocumentEmbedder:
         self.batch_size = batch_size
         self.progress_bar = progress_bar
         self.parallel = parallel
+        self.local_files_only = local_files_only
         self.meta_fields_to_embed = meta_fields_to_embed or []
         self.embedding_separator = embedding_separator
 
@@ -112,6 +119,7 @@ class FastembedDocumentEmbedder:
             batch_size=self.batch_size,
             progress_bar=self.progress_bar,
             parallel=self.parallel,
+            local_files_only=self.local_files_only,
             meta_fields_to_embed=self.meta_fields_to_embed,
             embedding_separator=self.embedding_separator,
         )
@@ -122,7 +130,10 @@ class FastembedDocumentEmbedder:
         """
         if not hasattr(self, "embedding_backend"):
             self.embedding_backend = _FastembedEmbeddingBackendFactory.get_embedding_backend(
-                model_name=self.model_name, cache_dir=self.cache_dir, threads=self.threads
+                model_name=self.model_name,
+                cache_dir=self.cache_dir,
+                threads=self.threads,
+                local_files_only=self.local_files_only,
             )
 
     def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_document_embedder.py

@@ -12,30 +12,31 @@ class FastembedSparseDocumentEmbedder:
 
     Usage example:
     ```python
-    # To use this component, install the "fastembed-haystack" package.
-    # pip install fastembed-haystack
-
     from haystack_integrations.components.embedders.fastembed import FastembedSparseDocumentEmbedder
     from haystack.dataclasses import Document
 
-    doc_embedder = FastembedSparseDocumentEmbedder(
+    sparse_doc_embedder = FastembedSparseDocumentEmbedder(
         model="prithvida/Splade_PP_en_v1",
         batch_size=32,
     )
 
-    doc_embedder.warm_up()
+    sparse_doc_embedder.warm_up()
 
     # Text taken from PubMed QA Dataset (https://huggingface.co/datasets/pubmed_qa)
     document_list = [
         Document(
-            content="Oxidative stress generated within inflammatory joints can produce autoimmune phenomena and joint destruction. Radical species with oxidative activity, including reactive nitrogen species, represent mediators of inflammation and cartilage damage.",
+            content=("Oxidative stress generated within inflammatory joints can produce autoimmune phenomena and joint "
+                     "destruction. Radical species with oxidative activity, including reactive nitrogen species, "
+                     "represent mediators of inflammation and cartilage damage."),
             meta={
                 "pubid": "25,445,628",
                 "long_answer": "yes",
             },
         ),
         Document(
-            content="Plasma levels of pancreatic polypeptide (PP) rise upon food intake. Although other pancreatic islet hormones, such as insulin and glucagon, have been extensively investigated, PP secretion and actions are still poorly understood.",
+            content=("Plasma levels of pancreatic polypeptide (PP) rise upon food intake. Although other pancreatic "
+                     "islet hormones, such as insulin and glucagon, have been extensively investigated, PP secretion "
+                     "and actions are still poorly understood."),
             meta={
                 "pubid": "25,445,712",
                 "long_answer": "yes",
@@ -43,12 +44,12 @@ class FastembedSparseDocumentEmbedder:
         ),
     ]
 
-    result = doc_embedder.run(document_list)
+    result = sparse_doc_embedder.run(document_list)
     print(f"Document Text: {result['documents'][0].content}")
-    print(f"Document Embedding: {result['documents'][0].sparse_embedding}")
-    print(f"Embedding Dimension: {len(result['documents'][0].sparse_embedding)}")
+    print(f"Document Sparse Embedding: {result['documents'][0].sparse_embedding}")
+    print(f"Sparse Embedding Dimension: {len(result['documents'][0].sparse_embedding)}")
     ```
-    """  # noqa: E501
+    """
 
     def __init__(
         self,
@@ -58,6 +59,7 @@ class FastembedSparseDocumentEmbedder:
         batch_size: int = 32,
         progress_bar: bool = True,
         parallel: Optional[int] = None,
+        local_files_only: bool = False,
         meta_fields_to_embed: Optional[List[str]] = None,
         embedding_separator: str = "\n",
     ):
@@ -76,6 +78,7 @@ class FastembedSparseDocumentEmbedder:
                 If > 1, data-parallel encoding will be used, recommended for offline encoding of large datasets.
                 If 0, use all available cores.
                 If None, don't use data-parallel processing, use default onnxruntime threading instead.
+        :param local_files_only: If `True`, only use the model files in the `cache_dir`.
         :param meta_fields_to_embed: List of meta fields that should be embedded along with the Document content.
         :param embedding_separator: Separator used to concatenate the meta fields to the Document content.
         """
@@ -86,6 +89,7 @@ class FastembedSparseDocumentEmbedder:
         self.batch_size = batch_size
         self.progress_bar = progress_bar
         self.parallel = parallel
+        self.local_files_only = local_files_only
         self.meta_fields_to_embed = meta_fields_to_embed or []
         self.embedding_separator = embedding_separator
 
@@ -103,6 +107,7 @@ class FastembedSparseDocumentEmbedder:
             batch_size=self.batch_size,
             progress_bar=self.progress_bar,
             parallel=self.parallel,
+            local_files_only=self.local_files_only,
             meta_fields_to_embed=self.meta_fields_to_embed,
             embedding_separator=self.embedding_separator,
         )
@@ -113,7 +118,10 @@ class FastembedSparseDocumentEmbedder:
         """
         if not hasattr(self, "embedding_backend"):
             self.embedding_backend = _FastembedSparseEmbeddingBackendFactory.get_embedding_backend(
-                model_name=self.model_name, cache_dir=self.cache_dir, threads=self.threads
+                model_name=self.model_name,
+                cache_dir=self.cache_dir,
+                threads=self.threads,
+                local_files_only=self.local_files_only,
             )
 
     def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_text_embedder.py

@@ -13,30 +13,28 @@ class FastembedSparseTextEmbedder:
 
     Usage example:
     ```python
-    # To use this component, install the "fastembed-haystack" package.
-    # pip install fastembed-haystack
-
     from haystack_integrations.components.embedders.fastembed import FastembedSparseTextEmbedder
 
-    text = "It clearly says online this will work on a Mac OS system. The disk comes and it does not, only Windows. Do Not order this if you have a Mac!!"
+    text = ("It clearly says online this will work on a Mac OS system. "
+            "The disk comes and it does not, only Windows. Do Not order this if you have a Mac!!")
 
-    text_embedder = FastembedSparseTextEmbedder(
+    sparse_text_embedder = FastembedSparseTextEmbedder(
         model="prithvida/Splade_PP_en_v1"
     )
-    text_embedder.warm_up()
+    sparse_text_embedder.warm_up()
 
-    embedding = text_embedder.run(text)["embedding"]
+    sparse_embedding = sparse_text_embedder.run(text)["sparse_embedding"]
     ```
-    """  # noqa: E501
+    """
 
     def __init__(
         self,
         model: str = "prithvida/Splade_PP_en_v1",
         cache_dir: Optional[str] = None,
         threads: Optional[int] = None,
-        batch_size: int = 32,
         progress_bar: bool = True,
         parallel: Optional[int] = None,
+        local_files_only: bool = False,
     ):
         """
         Create a FastembedSparseTextEmbedder component.
@@ -46,20 +44,20 @@ class FastembedSparseTextEmbedder:
                 Can be set using the `FASTEMBED_CACHE_PATH` env variable.
                 Defaults to `fastembed_cache` in the system's temp directory.
         :param threads: The number of threads single onnxruntime session can use. Defaults to None.
-        :param batch_size: Number of strings to encode at once.
-        :param progress_bar: If true, displays progress bar during embedding.
+        :param progress_bar: If `True`, displays progress bar during embedding.
         :param parallel:
                 If > 1, data-parallel encoding will be used, recommended for offline encoding of large datasets.
                 If 0, use all available cores.
                 If None, don't use data-parallel processing, use default onnxruntime threading instead.
+        :param local_files_only: If `True`, only use the model files in the `cache_dir`.
         """
 
         self.model_name = model
         self.cache_dir = cache_dir
         self.threads = threads
-        self.batch_size = batch_size
         self.progress_bar = progress_bar
         self.parallel = parallel
+        self.local_files_only = local_files_only
 
     def to_dict(self) -> Dict[str, Any]:
         """
@@ -73,9 +71,9 @@ class FastembedSparseTextEmbedder:
             model=self.model_name,
             cache_dir=self.cache_dir,
             threads=self.threads,
-            batch_size=self.batch_size,
             progress_bar=self.progress_bar,
             parallel=self.parallel,
+            local_files_only=self.local_files_only,
         )
 
     def warm_up(self):
@@ -84,7 +82,10 @@ class FastembedSparseTextEmbedder:
         """
         if not hasattr(self, "embedding_backend"):
             self.embedding_backend = _FastembedSparseEmbeddingBackendFactory.get_embedding_backend(
-                model_name=self.model_name, cache_dir=self.cache_dir, threads=self.threads
+                model_name=self.model_name,
+                cache_dir=self.cache_dir,
+                threads=self.threads,
+                local_files_only=self.local_files_only,
             )
 
     @component.output_types(sparse_embedding=SparseEmbedding)
@@ -110,7 +111,6 @@ class FastembedSparseTextEmbedder:
 
         embedding = self.embedding_backend.embed(
             [text],
-            batch_size=self.batch_size,
             show_progress_bar=self.progress_bar,
             parallel=self.parallel,
         )[0]

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_text_embedder.py

@@ -12,12 +12,10 @@ class FastembedTextEmbedder:
 
     Usage example:
     ```python
-    # To use this component, install the "fastembed-haystack" package.
-    # pip install fastembed-haystack
-
     from haystack_integrations.components.embedders.fastembed import FastembedTextEmbedder
 
-    text = "It clearly says online this will work on a Mac OS system. The disk comes and it does not, only Windows. Do Not order this if you have a Mac!!"
+    text = ("It clearly says online this will work on a Mac OS system. "
+            "The disk comes and it does not, only Windows. Do Not order this if you have a Mac!!")
 
     text_embedder = FastembedTextEmbedder(
         model="BAAI/bge-small-en-v1.5"
@@ -26,7 +24,7 @@ class FastembedTextEmbedder:
 
     embedding = text_embedder.run(text)["embedding"]
     ```
-    """  # noqa: E501
+    """
 
     def __init__(
         self,
@@ -37,6 +35,7 @@ class FastembedTextEmbedder:
         suffix: str = "",
         progress_bar: bool = True,
         parallel: Optional[int] = None,
+        local_files_only: bool = False,
     ):
         """
         Create a FastembedTextEmbedder component.
@@ -48,11 +47,12 @@ class FastembedTextEmbedder:
         :param threads: The number of threads single onnxruntime session can use. Defaults to None.
         :param prefix: A string to add to the beginning of each text.
         :param suffix: A string to add to the end of each text.
-        :param progress_bar: If true, displays progress bar during embedding.
+        :param progress_bar: If `True`, displays progress bar during embedding.
         :param parallel:
                 If > 1, data-parallel encoding will be used, recommended for offline encoding of large datasets.
                 If 0, use all available cores.
                 If None, don't use data-parallel processing, use default onnxruntime threading instead.
+        :param local_files_only: If `True`, only use the model files in the `cache_dir`.
         """
 
         self.model_name = model
@@ -62,6 +62,7 @@ class FastembedTextEmbedder:
         self.suffix = suffix
         self.progress_bar = progress_bar
         self.parallel = parallel
+        self.local_files_only = local_files_only
 
     def to_dict(self) -> Dict[str, Any]:
         """
@@ -79,6 +80,7 @@ class FastembedTextEmbedder:
             suffix=self.suffix,
             progress_bar=self.progress_bar,
             parallel=self.parallel,
+            local_files_only=self.local_files_only,
         )
 
     def warm_up(self):
@@ -87,7 +89,10 @@ class FastembedTextEmbedder:
         """
         if not hasattr(self, "embedding_backend"):
             self.embedding_backend = _FastembedEmbeddingBackendFactory.get_embedding_backend(
-                model_name=self.model_name, cache_dir=self.cache_dir, threads=self.threads
+                model_name=self.model_name,
+                cache_dir=self.cache_dir,
+                threads=self.threads,
+                local_files_only=self.local_files_only,
             )
 
     @component.output_types(embedding=List[float])

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/tests/test_fastembed_backend.py

@@ -27,7 +27,9 @@ def test_model_initialization(mock_instructor):
     _FastembedEmbeddingBackendFactory.get_embedding_backend(
         model_name="BAAI/bge-small-en-v1.5",
     )
-    mock_instructor.assert_called_once_with(model_name="BAAI/bge-small-en-v1.5", cache_dir=None, threads=None)
+    mock_instructor.assert_called_once_with(
+        model_name="BAAI/bge-small-en-v1.5", cache_dir=None, threads=None, local_files_only=False
+    )
     # restore the factory state
     _FastembedEmbeddingBackendFactory._instances = {}
 

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/tests/test_fastembed_document_embedder.py

@@ -22,6 +22,7 @@ class TestFastembedDocumentEmbedder:
         assert embedder.batch_size == 256
         assert embedder.progress_bar is True
         assert embedder.parallel is None
+        assert not embedder.local_files_only
         assert embedder.meta_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
 
@@ -38,6 +39,7 @@ class TestFastembedDocumentEmbedder:
             batch_size=64,
             progress_bar=False,
             parallel=1,
+            local_files_only=True,
             meta_fields_to_embed=["test_field"],
             embedding_separator=" | ",
         )
@@ -49,6 +51,7 @@ class TestFastembedDocumentEmbedder:
         assert embedder.batch_size == 64
         assert embedder.progress_bar is False
         assert embedder.parallel == 1
+        assert embedder.local_files_only
         assert embedder.meta_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == " | "
 
@@ -69,6 +72,7 @@ class TestFastembedDocumentEmbedder:
                 "batch_size": 256,
                 "progress_bar": True,
                 "parallel": None,
+                "local_files_only": False,
                 "embedding_separator": "\n",
                 "meta_fields_to_embed": [],
             },
@@ -87,6 +91,7 @@ class TestFastembedDocumentEmbedder:
             batch_size=64,
             progress_bar=False,
             parallel=1,
+            local_files_only=True,
             meta_fields_to_embed=["test_field"],
             embedding_separator=" | ",
         )
@@ -102,6 +107,7 @@ class TestFastembedDocumentEmbedder:
                 "batch_size": 64,
                 "progress_bar": False,
                 "parallel": 1,
+                "local_files_only": True,
                 "meta_fields_to_embed": ["test_field"],
                 "embedding_separator": " | ",
             },
@@ -122,6 +128,7 @@ class TestFastembedDocumentEmbedder:
                 "batch_size": 256,
                 "progress_bar": True,
                 "parallel": None,
+                "local_files_only": False,
                 "meta_fields_to_embed": [],
                 "embedding_separator": "\n",
             },
@@ -135,6 +142,7 @@ class TestFastembedDocumentEmbedder:
         assert embedder.batch_size == 256
         assert embedder.progress_bar is True
         assert embedder.parallel is None
+        assert not embedder.local_files_only
         assert embedder.meta_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
 
@@ -153,6 +161,7 @@ class TestFastembedDocumentEmbedder:
                 "batch_size": 64,
                 "progress_bar": False,
                 "parallel": 1,
+                "local_files_only": True,
                 "meta_fields_to_embed": ["test_field"],
                 "embedding_separator": " | ",
             },
@@ -166,6 +175,7 @@ class TestFastembedDocumentEmbedder:
         assert embedder.batch_size == 64
         assert embedder.progress_bar is False
         assert embedder.parallel == 1
+        assert embedder.local_files_only
         assert embedder.meta_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == " | "
 
@@ -180,7 +190,7 @@ class TestFastembedDocumentEmbedder:
         mocked_factory.get_embedding_backend.assert_not_called()
         embedder.warm_up()
         mocked_factory.get_embedding_backend.assert_called_once_with(
-            model_name="BAAI/bge-small-en-v1.5", cache_dir=None, threads=None
+            model_name="BAAI/bge-small-en-v1.5", cache_dir=None, threads=None, local_files_only=False
         )
 
     @patch(

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/tests/test_fastembed_sparse_document_embedder.py

@@ -21,6 +21,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
         assert embedder.batch_size == 32
         assert embedder.progress_bar is True
         assert embedder.parallel is None
+        assert not embedder.local_files_only
         assert embedder.meta_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
 
@@ -35,6 +36,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
             batch_size=64,
             progress_bar=False,
             parallel=1,
+            local_files_only=True,
             meta_fields_to_embed=["test_field"],
             embedding_separator=" | ",
         )
@@ -44,6 +46,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
         assert embedder.batch_size == 64
         assert embedder.progress_bar is False
         assert embedder.parallel == 1
+        assert embedder.local_files_only
         assert embedder.meta_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == " | "
 
@@ -62,6 +65,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
                 "batch_size": 32,
                 "progress_bar": True,
                 "parallel": None,
+                "local_files_only": False,
                 "embedding_separator": "\n",
                 "meta_fields_to_embed": [],
             },
@@ -78,6 +82,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
             batch_size=64,
             progress_bar=False,
             parallel=1,
+            local_files_only=True,
             meta_fields_to_embed=["test_field"],
             embedding_separator=" | ",
         )
@@ -91,6 +96,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
                 "batch_size": 64,
                 "progress_bar": False,
                 "parallel": 1,
+                "local_files_only": True,
                 "meta_fields_to_embed": ["test_field"],
                 "embedding_separator": " | ",
             },
@@ -110,6 +116,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
                 "batch_size": 32,
                 "progress_bar": True,
                 "parallel": None,
+                "local_files_only": False,
                 "meta_fields_to_embed": [],
                 "embedding_separator": "\n",
             },
@@ -121,6 +128,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
         assert embedder.batch_size == 32
         assert embedder.progress_bar is True
         assert embedder.parallel is None
+        assert not embedder.local_files_only
         assert embedder.meta_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
 
@@ -138,6 +146,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
                 "batch_size": 64,
                 "progress_bar": False,
                 "parallel": 1,
+                "local_files_only": True,
                 "meta_fields_to_embed": ["test_field"],
                 "embedding_separator": " | ",
             },
@@ -149,6 +158,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
         assert embedder.batch_size == 64
         assert embedder.progress_bar is False
         assert embedder.parallel == 1
+        assert embedder.local_files_only
         assert embedder.meta_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == " | "
 
@@ -163,7 +173,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
         mocked_factory.get_embedding_backend.assert_not_called()
         embedder.warm_up()
         mocked_factory.get_embedding_backend.assert_called_once_with(
-            model_name="prithvida/Splade_PP_en_v1", cache_dir=None, threads=None
+            model_name="prithvida/Splade_PP_en_v1", cache_dir=None, threads=None, local_files_only=False
         )
 
     @patch(

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/tests/test_fastembed_sparse_text_embedder.py

@@ -18,7 +18,6 @@ class TestFastembedSparseTextEmbedder:
         assert embedder.model_name == "prithvida/Splade_PP_en_v1"
         assert embedder.cache_dir is None
         assert embedder.threads is None
-        assert embedder.batch_size == 32
         assert embedder.progress_bar is True
         assert embedder.parallel is None
 
@@ -30,14 +29,12 @@ class TestFastembedSparseTextEmbedder:
             model="prithvida/Splade_PP_en_v1",
             cache_dir="fake_dir",
             threads=2,
-            batch_size=64,
             progress_bar=False,
             parallel=1,
         )
         assert embedder.model_name == "prithvida/Splade_PP_en_v1"
         assert embedder.cache_dir == "fake_dir"
         assert embedder.threads == 2
-        assert embedder.batch_size == 64
         assert embedder.progress_bar is False
         assert embedder.parallel == 1
 
@@ -53,9 +50,9 @@ class TestFastembedSparseTextEmbedder:
                 "model": "prithvida/Splade_PP_en_v1",
                 "cache_dir": None,
                 "threads": None,
-                "batch_size": 32,
                 "progress_bar": True,
                 "parallel": None,
+                "local_files_only": False,
             },
         }
 
@@ -67,9 +64,9 @@ class TestFastembedSparseTextEmbedder:
             model="prithvida/Splade_PP_en_v1",
             cache_dir="fake_dir",
             threads=2,
-            batch_size=64,
             progress_bar=False,
             parallel=1,
+            local_files_only=True,
         )
         embedder_dict = embedder.to_dict()
         assert embedder_dict == {
@@ -78,9 +75,9 @@ class TestFastembedSparseTextEmbedder:
                 "model": "prithvida/Splade_PP_en_v1",
                 "cache_dir": "fake_dir",
                 "threads": 2,
-                "batch_size": 64,
                 "progress_bar": False,
                 "parallel": 1,
+                "local_files_only": True,
             },
         }
 
@@ -94,7 +91,6 @@ class TestFastembedSparseTextEmbedder:
                 "model": "prithvida/Splade_PP_en_v1",
                 "cache_dir": None,
                 "threads": None,
-                "batch_size": 32,
                 "progress_bar": True,
                 "parallel": None,
             },
@@ -103,7 +99,6 @@ class TestFastembedSparseTextEmbedder:
         assert embedder.model_name == "prithvida/Splade_PP_en_v1"
         assert embedder.cache_dir is None
         assert embedder.threads is None
-        assert embedder.batch_size == 32
         assert embedder.progress_bar is True
         assert embedder.parallel is None
 
@@ -117,7 +112,6 @@ class TestFastembedSparseTextEmbedder:
                 "model": "prithvida/Splade_PP_en_v1",
                 "cache_dir": "fake_dir",
                 "threads": 2,
-                "batch_size": 64,
                 "progress_bar": False,
                 "parallel": 1,
             },
@@ -126,7 +120,6 @@ class TestFastembedSparseTextEmbedder:
         assert embedder.model_name == "prithvida/Splade_PP_en_v1"
         assert embedder.cache_dir == "fake_dir"
         assert embedder.threads == 2
-        assert embedder.batch_size == 64
         assert embedder.progress_bar is False
         assert embedder.parallel == 1
 
@@ -141,7 +134,7 @@ class TestFastembedSparseTextEmbedder:
         mocked_factory.get_embedding_backend.assert_not_called()
         embedder.warm_up()
         mocked_factory.get_embedding_backend.assert_called_once_with(
-            model_name="prithvida/Splade_PP_en_v1", cache_dir=None, threads=None
+            model_name="prithvida/Splade_PP_en_v1", cache_dir=None, threads=None, local_files_only=False
         )
 
     @patch(

{fastembed_haystack-0.1.0 → fastembed_haystack-1.1.0}/tests/test_fastembed_text_embedder.py

@@ -59,6 +59,7 @@ class TestFastembedTextEmbedder:
                 "suffix": "",
                 "progress_bar": True,
                 "parallel": None,
+                "local_files_only": False,
             },
         }
 
@@ -74,6 +75,7 @@ class TestFastembedTextEmbedder:
             suffix="suffix",
             progress_bar=False,
             parallel=1,
+            local_files_only=True,
         )
         embedder_dict = embedder.to_dict()
         assert embedder_dict == {
@@ -86,6 +88,7 @@ class TestFastembedTextEmbedder:
                 "suffix": "suffix",
                 "progress_bar": False,
                 "parallel": 1,
+                "local_files_only": True,
             },
         }
 
@@ -150,7 +153,7 @@ class TestFastembedTextEmbedder:
         mocked_factory.get_embedding_backend.assert_not_called()
         embedder.warm_up()
         mocked_factory.get_embedding_backend.assert_called_once_with(
-            model_name="BAAI/bge-small-en-v1.5", cache_dir=None, threads=None
+            model_name="BAAI/bge-small-en-v1.5", cache_dir=None, threads=None, local_files_only=False
         )
 
     @patch(