fastembed-haystack 1.0.0__tar.gz → 1.2.0__tar.gz

{fastembed_haystack-1.0.0 → fastembed_haystack-1.2.0}/.gitignore

@@ -135,3 +135,12 @@ dmypy.json
 # Docs generation artifacts
 _readme_*.md
 .idea
+
+# macOS
+.DS_Store
+
+# http cache (requests-cache)
+**/http_cache.sqlite
+
+# ruff
+.ruff_cache

{fastembed_haystack-1.0.0 → fastembed_haystack-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: fastembed-haystack
-Version: 1.0.0
+Version: 1.2.0
 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

{fastembed_haystack-1.0.0 → fastembed_haystack-1.2.0}/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-1.0.0 → fastembed_haystack-1.2.0}/pyproject.toml

@@ -10,9 +10,7 @@ readme = "README.md"
 requires-python = ">=3.8"
 license = "Apache-2.0"
 keywords = []
-authors = [
-  { name = "deepset GmbH", email = "info@deepset.ai" },
-]
+authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }]
 classifiers = [
   "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
@@ -25,10 +23,7 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = [
-"haystack-ai>=2.0.1",
-"fastembed>=0.2.5",
-]
+dependencies = ["haystack-ai>=2.0.1", "fastembed>=0.2.5"]
 
 [project.urls]
 Source = "https://github.com/deepset-ai/haystack-core-integrations"
@@ -50,50 +45,28 @@ git_describe_command = 'git describe --tags --match="integrations/fastembed-v[0-
 dependencies = [
   "coverage[toml]>=6.5",
   "pytest",
+  "pytest-rerunfailures",
   "ipython",
   "haystack-pydoc-tools",
 ]
 [tool.hatch.envs.default.scripts]
-test = "pytest {args:tests}"
-test-cov = "coverage run -m pytest {args:tests}"
-cov-report = [
-  "- coverage combine",
-  "coverage report",
-]
-cov = [
-  "test-cov",
-  "cov-report",
-]
-docs = [
-  "pydoc-markdown pydoc/config.yml"
-]
+test = "pytest --reruns 3 --reruns-delay 30 -x {args:tests}"
+test-cov = "coverage run -m pytest --reruns 3 --reruns-delay 30 -x {args:tests}"
+cov-report = ["- coverage combine", "coverage report"]
+cov = ["test-cov", "cov-report"]
+docs = ["pydoc-markdown pydoc/config.yml"]
 
 [[tool.hatch.envs.all.matrix]]
 python = ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
 [tool.hatch.envs.lint]
 detached = true
-dependencies = [
-  "black>=23.1.0",
-  "mypy>=1.0.0",
-  "ruff>=0.0.243",
-  "numpy"
-]
+dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243", "numpy"]
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = [
-  "ruff {args:.}",
-  "black --check --diff {args:.}",
-]
-fmt = [
-  "black {args:.}",
-  "ruff --fix {args:.}",
-  "style",
-]
-all = [
-  "style",
-  "typing",
-]
+style = ["ruff check {args:.}", "black --check --diff {args:.}"]
+fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
+all = ["style", "typing"]
 
 [tool.black]
 target-version = ["py38"]
@@ -135,11 +108,18 @@ ignore = [
   "B027",
   # Allow boolean positional values in function calls, like `dict.get(... True)`
   "FBT003",
-  "FBT001", "FBT002",
+  "FBT001",
+  "FBT002",
   # Ignore checks for possible passwords
-  "S105", "S106", "S107",
+  "S105",
+  "S106",
+  "S107",
   # Ignore complexity
-  "C901", "PLR0911", "PLR0912", "PLR0913", "PLR0915",
+  "C901",
+  "PLR0911",
+  "PLR0912",
+  "PLR0913",
+  "PLR0915",
 ]
 unfixable = [
   # Don't touch unused imports
@@ -165,12 +145,8 @@ parallel = false
 
 [tool.coverage.report]
 omit = ["*/tests/*", "*/__init__.py"]
-show_missing=true
-exclude_lines = [
-  "no cov",
-  "if __name__ == .__main__.:",
-  "if TYPE_CHECKING:",
-]
+show_missing = true
+exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
 
 [[tool.mypy.overrides]]
 module = [
@@ -178,6 +154,6 @@ module = [
   "haystack_integrations.*",
   "fastembed.*",
   "pytest.*",
-  "numpy.*"
+  "numpy.*",
 ]
 ignore_missing_imports = true

{fastembed_haystack-1.0.0 → fastembed_haystack-1.2.0}/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-1.0.0 → fastembed_haystack-1.2.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_document_embedder.py

@@ -65,6 +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",
     ):
@@ -80,11 +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.
         """
@@ -97,6 +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
 
@@ -116,6 +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,
         )
@@ -126,7 +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-1.0.0 → fastembed_haystack-1.2.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_document_embedder.py

@@ -59,6 +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",
     ):
@@ -77,6 +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.
         """
@@ -87,6 +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
 
@@ -104,6 +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,
         )
@@ -114,7 +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]:
@@ -152,7 +159,7 @@ class FastembedSparseDocumentEmbedder:
         embeddings = self.embedding_backend.embed(
             texts_to_embed,
             batch_size=self.batch_size,
-            show_progress_bar=self.progress_bar,
+            progress_bar=self.progress_bar,
             parallel=self.parallel,
         )
 

{fastembed_haystack-1.0.0 → fastembed_haystack-1.2.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_text_embedder.py

@@ -34,6 +34,7 @@ class FastembedSparseTextEmbedder:
         threads: Optional[int] = None,
         progress_bar: bool = True,
         parallel: Optional[int] = None,
+        local_files_only: bool = False,
     ):
         """
         Create a FastembedSparseTextEmbedder component.
@@ -43,11 +44,12 @@ 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 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
@@ -55,6 +57,7 @@ class FastembedSparseTextEmbedder:
         self.threads = threads
         self.progress_bar = progress_bar
         self.parallel = parallel
+        self.local_files_only = local_files_only
 
     def to_dict(self) -> Dict[str, Any]:
         """
@@ -70,6 +73,7 @@ class FastembedSparseTextEmbedder:
             threads=self.threads,
             progress_bar=self.progress_bar,
             parallel=self.parallel,
+            local_files_only=self.local_files_only,
         )
 
     def warm_up(self):
@@ -78,7 +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)
@@ -104,7 +111,7 @@ class FastembedSparseTextEmbedder:
 
         embedding = self.embedding_backend.embed(
             [text],
-            show_progress_bar=self.progress_bar,
+            progress_bar=self.progress_bar,
             parallel=self.parallel,
         )[0]
         return {"sparse_embedding": embedding}

{fastembed_haystack-1.0.0 → fastembed_haystack-1.2.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_text_embedder.py

@@ -35,6 +35,7 @@ class FastembedTextEmbedder:
         suffix: str = "",
         progress_bar: bool = True,
         parallel: Optional[int] = None,
+        local_files_only: bool = False,
     ):
         """
         Create a FastembedTextEmbedder component.
@@ -46,11 +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
@@ -60,6 +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]:
         """
@@ -77,6 +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):
@@ -85,7 +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-1.0.0 → fastembed_haystack-1.2.0}/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-1.0.0 → fastembed_haystack-1.2.0}/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-1.0.0 → fastembed_haystack-1.2.0}/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(
@@ -260,7 +270,7 @@ class TestFastembedSparseDocumentEmbedderDoc:
                 "meta_value 4\ndocument-number 4",
             ],
             batch_size=32,
-            show_progress_bar=True,
+            progress_bar=True,
             parallel=None,
         )
 

{fastembed_haystack-1.0.0 → fastembed_haystack-1.2.0}/tests/test_fastembed_sparse_text_embedder.py

@@ -52,6 +52,7 @@ class TestFastembedSparseTextEmbedder:
                 "threads": None,
                 "progress_bar": True,
                 "parallel": None,
+                "local_files_only": False,
             },
         }
 
@@ -65,6 +66,7 @@ class TestFastembedSparseTextEmbedder:
             threads=2,
             progress_bar=False,
             parallel=1,
+            local_files_only=True,
         )
         embedder_dict = embedder.to_dict()
         assert embedder_dict == {
@@ -75,6 +77,7 @@ class TestFastembedSparseTextEmbedder:
                 "threads": 2,
                 "progress_bar": False,
                 "parallel": 1,
+                "local_files_only": True,
             },
         }
 
@@ -131,7 +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-1.0.0 → fastembed_haystack-1.2.0}/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(