fastembed-haystack 1.4.1__tar.gz → 1.6.0__tar.gz

fastembed_haystack-1.6.0/CHANGELOG.md

@@ -0,0 +1,147 @@
+# Changelog
+
+## [integrations/fastembed-v1.5.0] - 2025-06-17
+
+### 🐛 Bug Fixes
+
+- Fix Fastembed types + add py.typed (#1954)
+
+### ⚙️ CI
+
+- Review testing workflows (#1541)
+
+### 🧹 Chores
+
+- Fix linting/isort (#1215)
+- Remove Python 3.8 support (#1421)
+- Align core-integrations Hatch scripts (#1898)
+
+
+## [integrations/fastembed-v1.4.1] - 2024-11-19
+
+### 🌀 Miscellaneous
+
+- Add new example with the ranker and fix the old ones (#1198)
+- Fix: Fastembed - Change default Sparse model as the used one is deprecated due to a typo (#1201)
+
+## [integrations/fastembed-v1.4.0] - 2024-11-13
+
+### ⚙️ CI
+
+- Adopt uv as installer (#1142)
+
+### 🌀 Miscellaneous
+
+- Chore: fastembed - pin `onnxruntime<1.20.0` (#1164)
+- Feat: Fastembed - add FastembedRanker (#1178)
+
+## [integrations/fastembed-v1.3.0] - 2024-10-07
+
+### 🚀 Features
+
+- Introduce `model_kwargs` in Sparse Embedders (can be used for BM25 parameters) (#1126)
+
+### 🧪 Testing
+
+- Do not retry tests in `hatch run test` command (#954)
+
+### ⚙️ CI
+
+- Retry tests to reduce flakyness (#836)
+
+### 🧹 Chores
+
+- Update ruff invocation to include check parameter (#853)
+- Update ruff linting scripts and settings (#1105)
+
+### 🌀 Miscellaneous
+
+- Ci: install `pytest-rerunfailures` where needed; add retry config to `test-cov` script (#845)
+- Typo on Sparse embedders. The parameter should be "progress_bar" … (#814)
+- Chore: fastembed - ruff update, don't ruff tests (#997)
+
+## [integrations/fastembed-v1.1.0] - 2024-05-15
+
+### 🌀 Miscellaneous
+
+- Chore: change the pydoc renderer class (#718)
+- Use the local_files_only option available as of fastembed==0.2.7. It … (#736)
+
+## [integrations/fastembed-v1.0.0] - 2024-05-06
+
+### 🌀 Miscellaneous
+
+- Chore: add license classifiers (#680)
+- `FastembedSparseTextEmbedder` - remove `batch_size` (#688)
+
+## [integrations/fastembed-v0.1.0] - 2024-04-10
+
+### 🚀 Features
+
+- *(FastEmbed)* Support for SPLADE Sparse Embedder (#579)
+
+### 📚 Documentation
+
+- Disable-class-def (#556)
+
+### 🌀 Miscellaneous
+
+- Remove references to Python 3.7 (#601)
+
+## [integrations/fastembed-v0.0.6] - 2024-03-07
+
+### 📚 Documentation
+
+- Review and normalize docstrings - `integrations.fastembed` (#519)
+- Small consistency improvements (#536)
+
+### 🌀 Miscellaneous
+
+- Docs: Fix `integrations.fastembed` API docs (#540)
+- Improvements to FastEmbed integration (#558)
+
+## [integrations/fastembed-v0.0.5] - 2024-02-20
+
+### 🐛 Bug Fixes
+
+- Fix order of API docs (#447)
+
+### 📚 Documentation
+
+- Update category slug (#442)
+
+### 🌀 Miscellaneous
+
+- Fastembed integration new parameters (#446)
+
+## [integrations/fastembed-v0.0.4] - 2024-02-16
+
+### 🌀 Miscellaneous
+
+- Fastembed integration: add example (#401)
+- Fastembed fix: add parallel (#403)
+
+## [integrations/fastembed-v0.0.3] - 2024-02-12
+
+### 🐛 Bug Fixes
+
+- From numpy float to float (#391)
+
+### 📚 Documentation
+
+- Update paths and titles (#397)
+
+## [integrations/fastembed-v0.0.2] - 2024-02-11
+
+### 🌀 Miscellaneous
+
+- Updated labeler and readme (#389)
+- Fastembed fix: added prefix and suffix (#390)
+
+## [integrations/fastembed-v0.0.1] - 2024-02-10
+
+### 🌀 Miscellaneous
+
+- Add Fastembed Embeddings integration (#383)
+
+<!-- generated by git-cliff -->

{fastembed_haystack-1.4.1 → fastembed_haystack-1.6.0}/LICENSE.txt

@@ -58,7 +58,7 @@ APPENDIX: How to apply the Apache License to your work.
 
 To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!)  The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives.
 
-Copyright [yyyy] [name of copyright owner]
+Copyright 2024 deepset GmbH
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.

fastembed_haystack-1.6.0/PKG-INFO

@@ -0,0 +1,38 @@
+Metadata-Version: 2.4
+Name: fastembed-haystack
+Version: 1.6.0
+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
+Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
+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 :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.9
+Requires-Dist: fastembed>=0.4.2
+Requires-Dist: haystack-ai>=2.0.1
+Description-Content-Type: text/markdown
+
+# fastembed-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/fastembed-haystack.svg)](https://pypi.org/project/fastembed-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/fastembed-haystack.svg)](https://pypi.org/project/fastembed-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/fastembed)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/fastembed/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

fastembed_haystack-1.6.0/README.md

@@ -0,0 +1,13 @@
+# fastembed-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/fastembed-haystack.svg)](https://pypi.org/project/fastembed-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/fastembed-haystack.svg)](https://pypi.org/project/fastembed-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/fastembed)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/fastembed/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

fastembed_haystack-1.6.0/pydoc/config_docusaurus.yml

@@ -0,0 +1,32 @@
+loaders:
+- ignore_when_discovered:
+  - __init__
+  modules:
+  - haystack_integrations.components.embedders.fastembed.fastembed_document_embedder
+  - haystack_integrations.components.embedders.fastembed.fastembed_text_embedder
+  - haystack_integrations.components.embedders.fastembed.fastembed_sparse_document_embedder
+  - haystack_integrations.components.embedders.fastembed.fastembed_sparse_text_embedder
+  - haystack_integrations.components.rankers.fastembed.ranker
+  search_path:
+  - ../src
+  type: haystack_pydoc_tools.loaders.CustomPythonLoader
+processors:
+- do_not_filter_modules: false
+  documented_only: true
+  expression: null
+  skip_empty_modules: true
+  type: filter
+- type: smart
+- type: crossref
+renderer:
+  description: FastEmbed integration for Haystack
+  id: fastembed-embedders
+  markdown:
+    add_member_class_prefix: false
+    add_method_class_prefix: true
+    classdef_code_block: false
+    descriptive_class_title: false
+    descriptive_module_title: true
+    filename: fastembed.md
+  title: FastEmbed
+  type: haystack_pydoc_tools.renderers.DocusaurusRenderer

{fastembed_haystack-1.4.1 → fastembed_haystack-1.6.0}/pyproject.toml

@@ -7,7 +7,7 @@ name = "fastembed-haystack"
 dynamic = ["version"]
 description = "Haystack 2.x component to embed strings and Documents using fastembed embedding model"
 readme = "README.md"
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 license = "Apache-2.0"
 keywords = []
 authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }]
@@ -15,11 +15,11 @@ classifiers = [
   "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
-  "Programming Language :: Python :: 3.8",
   "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
@@ -43,42 +43,39 @@ git_describe_command = 'git describe --tags --match="integrations/fastembed-v[0-
 
 [tool.hatch.envs.default]
 installer = "uv"
+dependencies = ["haystack-pydoc-tools", "ruff"]
+[tool.hatch.envs.default.scripts]
+docs = ["pydoc-markdown pydoc/config_docusaurus.yml"]
+fmt = "ruff check --fix {args}; ruff format {args}"
+fmt-check = "ruff check {args} && ruff format --check {args}"
+
+[tool.hatch.envs.test]
 dependencies = [
-  "coverage[toml]>=6.5",
-  "pytest",
-  "pytest-rerunfailures",
-  "ipython",
-  "haystack-pydoc-tools",
+    "pytest",
+    "pytest-asyncio",
+    "pytest-cov",
+    "pytest-rerunfailures",
+    "mypy",
+    "pip",
+    "ipython"
 ]
-[tool.hatch.envs.default.scripts]
-test = "pytest {args:tests}"
-test-cov = "coverage run -m pytest {args:tests}"
-test-cov-retry = "test-cov --reruns 3 --reruns-delay 30 -x"
-cov-report = ["- coverage combine", "coverage report"]
-cov = ["test-cov", "cov-report"]
-cov-retry = ["test-cov-retry", "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]
-installer = "uv"
-detached = true
-dependencies = ["pip", "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 check {args:.}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff check --fix {args:.}", "style"]
-all = ["style", "typing"]
-
-[tool.black]
-target-version = ["py38"]
-line-length = 120
-skip-string-normalization = true
+
+[tool.hatch.envs.test.scripts]
+unit = 'pytest -m "not integration" {args:tests}'
+integration = 'pytest -m "integration" {args:tests}'
+all = 'pytest {args:tests}'
+cov-retry = 'pytest --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x {args:tests}'
+types = """mypy -p haystack_integrations.components.embedders.fastembed \
+-p haystack_integrations.components.rankers.fastembed {args}"""
+
+[tool.mypy]
+install_types = true
+non_interactive = true
+check_untyped_defs = true
+disallow_incomplete_defs = true
 
 [tool.ruff]
-target-version = "py38"
+target-version = "py39"
 line-length = 120
 
 [tool.ruff.lint]
@@ -156,14 +153,5 @@ exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
 
 [tool.pytest.ini_options]
 minversion = "6.0"
-markers = ["unit: unit tests", "integration: integration tests"]
-
-[[tool.mypy.overrides]]
-module = [
-  "haystack.*",
-  "haystack_integrations.*",
-  "fastembed.*",
-  "pytest.*",
-  "numpy.*",
-]
-ignore_missing_imports = true
+markers = ["integration: integration tests"]
+

{fastembed_haystack-1.4.1 → fastembed_haystack-1.6.0}/src/haystack_integrations/components/embedders/fastembed/__init__.py

@@ -1,6 +1,7 @@
 # SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
+
 from .fastembed_document_embedder import FastembedDocumentEmbedder
 from .fastembed_sparse_document_embedder import FastembedSparseDocumentEmbedder
 from .fastembed_sparse_text_embedder import FastembedSparseTextEmbedder
@@ -8,7 +9,7 @@ from .fastembed_text_embedder import FastembedTextEmbedder
 
 __all__ = [
     "FastembedDocumentEmbedder",
-    "FastembedTextEmbedder",
     "FastembedSparseDocumentEmbedder",
     "FastembedSparseTextEmbedder",
+    "FastembedTextEmbedder",
 ]

{fastembed_haystack-1.4.1 → fastembed_haystack-1.6.0}/src/haystack_integrations/components/embedders/fastembed/embedding_backend/fastembed_backend.py

@@ -1,4 +1,4 @@
-from typing import Any, ClassVar, Dict, List, Optional
+from typing import Any, ClassVar, Optional
 
 from haystack.dataclasses.sparse_embedding import SparseEmbedding
 from tqdm import tqdm
@@ -12,7 +12,7 @@ class _FastembedEmbeddingBackendFactory:
     Factory class to create instances of fastembed embedding backends.
     """
 
-    _instances: ClassVar[Dict[str, "_FastembedEmbeddingBackend"]] = {}
+    _instances: ClassVar[dict[str, "_FastembedEmbeddingBackend"]] = {}
 
     @staticmethod
     def get_embedding_backend(
@@ -20,7 +20,7 @@ class _FastembedEmbeddingBackendFactory:
         cache_dir: Optional[str] = None,
         threads: Optional[int] = None,
         local_files_only: bool = False,
-    ):
+    ) -> "_FastembedEmbeddingBackend":
         embedding_backend_id = f"{model_name}{cache_dir}{threads}"
 
         if embedding_backend_id in _FastembedEmbeddingBackendFactory._instances:
@@ -49,7 +49,7 @@ class _FastembedEmbeddingBackend:
             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]]:
+    def embed(self, data: list[str], progress_bar: bool = True, **kwargs: Any) -> list[list[float]]:
         # the embed method returns a Iterable[np.ndarray], so we convert it to a list of lists
         embeddings = []
         embeddings_iterable = self.model.embed(data, **kwargs)
@@ -65,7 +65,7 @@ class _FastembedSparseEmbeddingBackendFactory:
     Factory class to create instances of fastembed sparse embedding backends.
     """
 
-    _instances: ClassVar[Dict[str, "_FastembedSparseEmbeddingBackend"]] = {}
+    _instances: ClassVar[dict[str, "_FastembedSparseEmbeddingBackend"]] = {}
 
     @staticmethod
     def get_embedding_backend(
@@ -73,8 +73,8 @@ class _FastembedSparseEmbeddingBackendFactory:
         cache_dir: Optional[str] = None,
         threads: Optional[int] = None,
         local_files_only: bool = False,
-        model_kwargs: Optional[Dict[str, Any]] = None,
-    ):
+        model_kwargs: Optional[dict[str, Any]] = None,
+    ) -> "_FastembedSparseEmbeddingBackend":
         embedding_backend_id = f"{model_name}{cache_dir}{threads}{local_files_only}{model_kwargs}"
 
         if embedding_backend_id in _FastembedSparseEmbeddingBackendFactory._instances:
@@ -102,7 +102,7 @@ class _FastembedSparseEmbeddingBackend:
         cache_dir: Optional[str] = None,
         threads: Optional[int] = None,
         local_files_only: bool = False,
-        model_kwargs: Optional[Dict[str, Any]] = None,
+        model_kwargs: Optional[dict[str, Any]] = None,
     ):
         model_kwargs = model_kwargs or {}
 
@@ -114,7 +114,7 @@ class _FastembedSparseEmbeddingBackend:
             **model_kwargs,
         )
 
-    def embed(self, data: List[List[str]], progress_bar=True, **kwargs) -> List[SparseEmbedding]:
+    def embed(self, data: list[str], progress_bar: bool = True, **kwargs: Any) -> list[SparseEmbedding]:
         # The embed method returns a Iterable[SparseEmbedding], so we convert to Haystack SparseEmbedding type.
         # Each SparseEmbedding contains an `indices` key containing a list of int and
         # an `values` key containing a list of floats.

{fastembed_haystack-1.4.1 → fastembed_haystack-1.6.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_document_embedder.py

@@ -1,8 +1,13 @@
-from typing import Any, Dict, List, Optional
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from dataclasses import replace
+from typing import Any, Optional
 
 from haystack import Document, component, default_to_dict
 
-from .embedding_backend.fastembed_backend import _FastembedEmbeddingBackendFactory
+from .embedding_backend.fastembed_backend import _FastembedEmbeddingBackend, _FastembedEmbeddingBackendFactory
 
 
 @component
@@ -66,9 +71,9 @@ class FastembedDocumentEmbedder:
         progress_bar: bool = True,
         parallel: Optional[int] = None,
         local_files_only: bool = False,
-        meta_fields_to_embed: Optional[List[str]] = None,
+        meta_fields_to_embed: Optional[list[str]] = None,
         embedding_separator: str = "\n",
-    ):
+    ) -> None:
         """
         Create an FastembedDocumentEmbedder component.
 
@@ -102,8 +107,9 @@ class FastembedDocumentEmbedder:
         self.local_files_only = local_files_only
         self.meta_fields_to_embed = meta_fields_to_embed or []
         self.embedding_separator = embedding_separator
+        self.embedding_backend: Optional[_FastembedEmbeddingBackend] = None
 
-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
         """
         Serializes the component to a dictionary.
         :returns:
@@ -124,11 +130,11 @@ class FastembedDocumentEmbedder:
             embedding_separator=self.embedding_separator,
         )
 
-    def warm_up(self):
+    def warm_up(self) -> None:
         """
         Initializes the component.
         """
-        if not hasattr(self, "embedding_backend"):
+        if self.embedding_backend is None:
             self.embedding_backend = _FastembedEmbeddingBackendFactory.get_embedding_backend(
                 model_name=self.model_name,
                 cache_dir=self.cache_dir,
@@ -136,7 +142,7 @@ class FastembedDocumentEmbedder:
                 local_files_only=self.local_files_only,
             )
 
-    def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:
+    def _prepare_texts_to_embed(self, documents: list[Document]) -> list[str]:
         texts_to_embed = []
         for doc in documents:
             meta_values_to_embed = [
@@ -149,34 +155,36 @@ class FastembedDocumentEmbedder:
             texts_to_embed.append(text_to_embed)
         return texts_to_embed
 
-    @component.output_types(documents=List[Document])
-    def run(self, documents: List[Document]):
+    @component.output_types(documents=list[Document])
+    def run(self, documents: list[Document]) -> dict[str, list[Document]]:
         """
         Embeds a list of Documents.
 
         :param documents: List of Documents to embed.
         :returns: A dictionary with the following keys:
             - `documents`: List of Documents with each Document's `embedding` field set to the computed embeddings.
+        :raises TypeError: If the input is not a list of Documents.
         """
-        if not isinstance(documents, list) or documents and not isinstance(documents[0], Document):
+        if not isinstance(documents, list) or (documents and not isinstance(documents[0], Document)):
             msg = (
                 "FastembedDocumentEmbedder expects a list of Documents as input. "
                 "In case you want to embed a list of strings, please use the FastembedTextEmbedder."
             )
             raise TypeError(msg)
-        if not hasattr(self, "embedding_backend"):
-            msg = "The embedding model has not been loaded. Please call warm_up() before running."
-            raise RuntimeError(msg)
+
+        if self.embedding_backend is None:
+            self.warm_up()
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
-        embeddings = self.embedding_backend.embed(
+        embeddings = self.embedding_backend.embed(  # type: ignore[union-attr]
             texts_to_embed,
             batch_size=self.batch_size,
             progress_bar=self.progress_bar,
             parallel=self.parallel,
         )
 
+        new_documents = []
         for doc, emb in zip(documents, embeddings):
-            doc.embedding = emb
+            new_documents.append(replace(doc, embedding=emb))
 
-        return {"documents": documents}
+        return {"documents": new_documents}

{fastembed_haystack-1.4.1 → fastembed_haystack-1.6.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_document_embedder.py

@@ -1,8 +1,16 @@
-from typing import Any, Dict, List, Optional
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from dataclasses import replace
+from typing import Any, Optional
 
 from haystack import Document, component, default_to_dict
 
-from .embedding_backend.fastembed_backend import _FastembedSparseEmbeddingBackendFactory
+from .embedding_backend.fastembed_backend import (
+    _FastembedSparseEmbeddingBackend,
+    _FastembedSparseEmbeddingBackendFactory,
+)
 
 
 @component
@@ -60,10 +68,10 @@ class FastembedSparseDocumentEmbedder:
         progress_bar: bool = True,
         parallel: Optional[int] = None,
         local_files_only: bool = False,
-        meta_fields_to_embed: Optional[List[str]] = None,
+        meta_fields_to_embed: Optional[list[str]] = None,
         embedding_separator: str = "\n",
-        model_kwargs: Optional[Dict[str, Any]] = None,
-    ):
+        model_kwargs: Optional[dict[str, Any]] = None,
+    ) -> None:
         """
         Create an FastembedDocumentEmbedder component.
 
@@ -95,8 +103,9 @@ class FastembedSparseDocumentEmbedder:
         self.meta_fields_to_embed = meta_fields_to_embed or []
         self.embedding_separator = embedding_separator
         self.model_kwargs = model_kwargs
+        self.embedding_backend: Optional[_FastembedSparseEmbeddingBackend] = None
 
-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
         """
         Serializes the component to a dictionary.
         :returns:
@@ -116,11 +125,11 @@ class FastembedSparseDocumentEmbedder:
             model_kwargs=self.model_kwargs,
         )
 
-    def warm_up(self):
+    def warm_up(self) -> None:
         """
         Initializes the component.
         """
-        if not hasattr(self, "embedding_backend"):
+        if self.embedding_backend is None:
             self.embedding_backend = _FastembedSparseEmbeddingBackendFactory.get_embedding_backend(
                 model_name=self.model_name,
                 cache_dir=self.cache_dir,
@@ -129,7 +138,7 @@ class FastembedSparseDocumentEmbedder:
                 model_kwargs=self.model_kwargs,
             )
 
-    def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:
+    def _prepare_texts_to_embed(self, documents: list[Document]) -> list[str]:
         texts_to_embed = []
         for doc in documents:
             meta_values_to_embed = [
@@ -140,8 +149,8 @@ class FastembedSparseDocumentEmbedder:
             texts_to_embed.append(text_to_embed)
         return texts_to_embed
 
-    @component.output_types(documents=List[Document])
-    def run(self, documents: List[Document]):
+    @component.output_types(documents=list[Document])
+    def run(self, documents: list[Document]) -> dict[str, list[Document]]:
         """
         Embeds a list of Documents.
 
@@ -149,25 +158,28 @@ class FastembedSparseDocumentEmbedder:
         :returns: A dictionary with the following keys:
             - `documents`: List of Documents with each Document's `sparse_embedding`
                             field set to the computed embeddings.
+        :raises TypeError: If the input is not a list of Documents.
         """
-        if not isinstance(documents, list) or documents and not isinstance(documents[0], Document):
+        if not isinstance(documents, list) or (documents and not isinstance(documents[0], Document)):
             msg = (
                 "FastembedSparseDocumentEmbedder expects a list of Documents as input. "
                 "In case you want to embed a list of strings, please use the FastembedTextEmbedder."
             )
             raise TypeError(msg)
-        if not hasattr(self, "embedding_backend"):
-            msg = "The embedding model has not been loaded. Please call warm_up() before running."
-            raise RuntimeError(msg)
+
+        if self.embedding_backend is None:
+            self.warm_up()
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
-        embeddings = self.embedding_backend.embed(
+        embeddings = self.embedding_backend.embed(  # type: ignore[union-attr]
             texts_to_embed,
             batch_size=self.batch_size,
             progress_bar=self.progress_bar,
             parallel=self.parallel,
         )
 
+        new_documents = []
         for doc, emb in zip(documents, embeddings):
-            doc.sparse_embedding = emb
-        return {"documents": documents}
+            new_documents.append(replace(doc, sparse_embedding=emb))
+
+        return {"documents": new_documents}