fastembed-haystack 1.5.0__tar.gz → 1.6.0__tar.gz

{fastembed_haystack-1.5.0 → fastembed_haystack-1.6.0}/CHANGELOG.md

@@ -1,5 +1,22 @@
 # 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

{fastembed_haystack-1.5.0 → 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-1.5.0 → fastembed_haystack-1.6.0}/pyproject.toml

@@ -45,8 +45,8 @@ git_describe_command = 'git describe --tags --match="integrations/fastembed-v[0-
 installer = "uv"
 dependencies = ["haystack-pydoc-tools", "ruff"]
 [tool.hatch.envs.default.scripts]
-docs = ["pydoc-markdown pydoc/config.yml"]
-fmt = "ruff check --fix {args} && ruff format {args}"
+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]
@@ -64,7 +64,7 @@ dependencies = [
 unit = 'pytest -m "not integration" {args:tests}'
 integration = 'pytest -m "integration" {args:tests}'
 all = 'pytest {args:tests}'
-cov-retry = 'all --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x'
+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}"""
 
@@ -74,13 +74,8 @@ non_interactive = true
 check_untyped_defs = true
 disallow_incomplete_defs = true
 
-[tool.black]
-target-version = ["py38"]
-line-length = 120
-skip-string-normalization = true
-
 [tool.ruff]
-target-version = "py38"
+target-version = "py39"
 line-length = 120
 
 [tool.ruff.lint]

{fastembed_haystack-1.5.0 → 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

{fastembed_haystack-1.5.0 → 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(
@@ -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: bool = True, **kwargs: Any) -> 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(
@@ -73,7 +73,7 @@ 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}"
 
@@ -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[str], progress_bar: bool = True, **kwargs: Any) -> 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-1.5.0 → 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 = [
@@ -149,14 +155,15 @@ 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]) -> Dict[str, 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)):
             msg = (
@@ -164,19 +171,20 @@ class FastembedDocumentEmbedder:
                 "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-1.5.0 → 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]) -> Dict[str, List[Document]]:
+    @component.output_types(documents=list[Document])
+    def run(self, documents: list[Document]) -> dict[str, list[Document]]:
         """
         Embeds a list of Documents.
 
@@ -149,6 +158,7 @@ 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)):
             msg = (
@@ -156,18 +166,20 @@ class FastembedSparseDocumentEmbedder:
                 "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}

{fastembed_haystack-1.5.0 → fastembed_haystack-1.6.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_text_embedder.py

@@ -1,9 +1,16 @@
-from typing import Any, Dict, Optional
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from typing import Any, Optional
 
 from haystack import component, default_to_dict
 from haystack.dataclasses.sparse_embedding import SparseEmbedding
 
-from .embedding_backend.fastembed_backend import _FastembedSparseEmbeddingBackendFactory
+from .embedding_backend.fastembed_backend import (
+    _FastembedSparseEmbeddingBackend,
+    _FastembedSparseEmbeddingBackendFactory,
+)
 
 
 @component
@@ -35,8 +42,8 @@ class FastembedSparseTextEmbedder:
         progress_bar: bool = True,
         parallel: Optional[int] = None,
         local_files_only: bool = False,
-        model_kwargs: Optional[Dict[str, Any]] = None,
-    ):
+        model_kwargs: Optional[dict[str, Any]] = None,
+    ) -> None:
         """
         Create a FastembedSparseTextEmbedder component.
 
@@ -61,8 +68,9 @@ class FastembedSparseTextEmbedder:
         self.parallel = parallel
         self.local_files_only = local_files_only
         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.
 
@@ -80,11 +88,11 @@ class FastembedSparseTextEmbedder:
             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,
@@ -94,7 +102,7 @@ class FastembedSparseTextEmbedder:
             )
 
     @component.output_types(sparse_embedding=SparseEmbedding)
-    def run(self, text: str) -> Dict[str, SparseEmbedding]:
+    def run(self, text: str) -> dict[str, SparseEmbedding]:
         """
         Embeds text using the Fastembed model.
 
@@ -102,7 +110,6 @@ class FastembedSparseTextEmbedder:
         :returns: A dictionary with the following keys:
             - `embedding`: A list of floats representing the embedding of the input text.
         :raises TypeError: If the input is not a string.
-        :raises RuntimeError: If the embedding model has not been loaded.
         """
         if not isinstance(text, str):
             msg = (
@@ -110,11 +117,11 @@ class FastembedSparseTextEmbedder:
                 "In case you want to embed a list of Documents, please use the FastembedDocumentEmbedder."
             )
             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)
 
-        embedding = self.embedding_backend.embed(
+        if self.embedding_backend is None:
+            self.warm_up()
+
+        embedding = self.embedding_backend.embed(  # type: ignore[union-attr]
             [text],
             progress_bar=self.progress_bar,
             parallel=self.parallel,

{fastembed_haystack-1.5.0 → fastembed_haystack-1.6.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_text_embedder.py

@@ -1,8 +1,12 @@
-from typing import Any, Dict, List, Optional
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from typing import Any, Optional
 
 from haystack import component, default_to_dict
 
-from .embedding_backend.fastembed_backend import _FastembedEmbeddingBackendFactory
+from .embedding_backend.fastembed_backend import _FastembedEmbeddingBackend, _FastembedEmbeddingBackendFactory
 
 
 @component
@@ -36,7 +40,7 @@ class FastembedTextEmbedder:
         progress_bar: bool = True,
         parallel: Optional[int] = None,
         local_files_only: bool = False,
-    ):
+    ) -> None:
         """
         Create a FastembedTextEmbedder component.
 
@@ -63,8 +67,9 @@ class FastembedTextEmbedder:
         self.progress_bar = progress_bar
         self.parallel = parallel
         self.local_files_only = local_files_only
+        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.
 
@@ -83,11 +88,11 @@ class FastembedTextEmbedder:
             local_files_only=self.local_files_only,
         )
 
-    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,
@@ -95,8 +100,8 @@ class FastembedTextEmbedder:
                 local_files_only=self.local_files_only,
             )
 
-    @component.output_types(embedding=List[float])
-    def run(self, text: str) -> Dict[str, List[float]]:
+    @component.output_types(embedding=list[float])
+    def run(self, text: str) -> dict[str, list[float]]:
         """
         Embeds text using the Fastembed model.
 
@@ -104,7 +109,6 @@ class FastembedTextEmbedder:
         :returns: A dictionary with the following keys:
             - `embedding`: A list of floats representing the embedding of the input text.
         :raises TypeError: If the input is not a string.
-        :raises RuntimeError: If the embedding model has not been loaded.
         """
         if not isinstance(text, str):
             msg = (
@@ -112,13 +116,13 @@ class FastembedTextEmbedder:
                 "In case you want to embed a list of Documents, please use the FastembedDocumentEmbedder."
             )
             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()
 
         text_to_embed = [self.prefix + text + self.suffix]
         embedding = list(
-            self.embedding_backend.embed(
+            self.embedding_backend.embed(  # type: ignore[union-attr]
                 text_to_embed,
                 progress_bar=self.progress_bar,
                 parallel=self.parallel,

fastembed_haystack-1.6.0/src/haystack_integrations/components/rankers/fastembed/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from .ranker import FastembedRanker
+
+__all__ = ["FastembedRanker"]

{fastembed_haystack-1.5.0 → fastembed_haystack-1.6.0}/src/haystack_integrations/components/rankers/fastembed/ranker.py

@@ -1,4 +1,8 @@
-from typing import Any, Dict, List, Optional
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from typing import Any, Optional
 
 from haystack import Document, component, default_from_dict, default_to_dict, logging
 
@@ -40,7 +44,7 @@ class FastembedRanker:
         batch_size: int = 64,
         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,
         meta_data_separator: str = "\n",
     ):
         """
@@ -78,7 +82,7 @@ class FastembedRanker:
         self.meta_data_separator = meta_data_separator
         self._model: Optional[TextCrossEncoder] = None
 
-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
         """
         Serializes the component to a dictionary.
 
@@ -99,7 +103,7 @@ class FastembedRanker:
         )
 
     @classmethod
-    def from_dict(cls, data: Dict[str, Any]) -> "FastembedRanker":
+    def from_dict(cls, data: dict[str, Any]) -> "FastembedRanker":
         """
         Deserializes the component from a dictionary.
 
@@ -122,7 +126,7 @@ class FastembedRanker:
                 local_files_only=self.local_files_only,
             )
 
-    def _prepare_fastembed_input_docs(self, documents: List[Document]) -> List[str]:
+    def _prepare_fastembed_input_docs(self, documents: list[Document]) -> list[str]:
         """
         Prepare the input by concatenating the document text with the metadata fields specified.
         :param documents: The list of Document objects.
@@ -139,8 +143,8 @@ class FastembedRanker:
 
         return concatenated_input_list
 
-    @component.output_types(documents=List[Document])
-    def run(self, query: str, documents: List[Document], top_k: Optional[int] = None) -> Dict[str, List[Document]]:
+    @component.output_types(documents=list[Document])
+    def run(self, query: str, documents: list[Document], top_k: Optional[int] = None) -> dict[str, list[Document]]:
         """
         Returns a list of documents ranked by their similarity to the given query, using FastEmbed.
 

{fastembed_haystack-1.5.0 → fastembed_haystack-1.6.0}/tests/test_fastembed_backend.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from unittest.mock import patch
 
 from haystack_integrations.components.embedders.fastembed.embedding_backend.fastembed_backend import (

{fastembed_haystack-1.5.0 → fastembed_haystack-1.6.0}/tests/test_fastembed_document_embedder.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from unittest.mock import MagicMock, patch
 
 import numpy as np
@@ -237,13 +241,13 @@ class TestFastembedDocumentEmbedder:
 
         with pytest.raises(
             TypeError,
-            match="FastembedDocumentEmbedder expects a list of Documents as input.",
+            match=r"FastembedDocumentEmbedder expects a list of Documents as input\.",
         ):
             embedder.run(documents=string_input)
 
         with pytest.raises(
             TypeError,
-            match="FastembedDocumentEmbedder expects a list of Documents as input.",
+            match=r"FastembedDocumentEmbedder expects a list of Documents as input\.",
         ):
             embedder.run(documents=list_integers_input)
 

{fastembed_haystack-1.5.0 → fastembed_haystack-1.6.0}/tests/test_fastembed_ranker.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from unittest.mock import MagicMock
 
 import pytest
@@ -189,13 +193,13 @@ class TestFastembedRanker:
 
         with pytest.raises(
             TypeError,
-            match="FastembedRanker expects a list of Documents as input.",
+            match=r"FastembedRanker expects a list of Documents as input\.",
         ):
             ranker.run(query=query, documents=string_input)
 
         with pytest.raises(
             TypeError,
-            match="FastembedRanker expects a list of Documents as input.",
+            match=r"FastembedRanker expects a list of Documents as input\.",
         ):
             ranker.run(query=query, documents=list_integers_input)
 
@@ -211,20 +215,6 @@ class TestFastembedRanker:
         ):
             ranker.run(query=query, documents=list_document, top_k=-3)
 
-    def test_run_no_warmup(self):
-        """
-        Test for checking error when calling without a warmup.
-        """
-        ranker = FastembedRanker(model_name="Xenova/ms-marco-MiniLM-L-12-v2")
-
-        query = "query"
-        list_document = [Document("Document 1")]
-
-        with pytest.raises(
-            RuntimeError,
-        ):
-            ranker.run(query=query, documents=list_document)
-
     def test_run_empty_document_list(self):
         """
         Test for no error when sending no documents.

{fastembed_haystack-1.5.0 → fastembed_haystack-1.6.0}/tests/test_fastembed_sparse_document_embedder.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from unittest.mock import MagicMock, patch
 
 import numpy as np
@@ -242,13 +246,13 @@ class TestFastembedSparseDocumentEmbedderDoc:
 
         with pytest.raises(
             TypeError,
-            match="FastembedSparseDocumentEmbedder expects a list of Documents as input.",
+            match=r"FastembedSparseDocumentEmbedder expects a list of Documents as input\.",
         ):
             embedder.run(documents=string_input)
 
         with pytest.raises(
             TypeError,
-            match="FastembedSparseDocumentEmbedder expects a list of Documents as input.",
+            match=r"FastembedSparseDocumentEmbedder expects a list of Documents as input\.",
         ):
             embedder.run(documents=list_integers_input)
 

{fastembed_haystack-1.5.0 → fastembed_haystack-1.6.0}/tests/test_fastembed_sparse_text_embedder.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from unittest.mock import MagicMock, patch
 
 import numpy as np

{fastembed_haystack-1.5.0 → fastembed_haystack-1.6.0}/tests/test_fastembed_text_embedder.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from unittest.mock import MagicMock, patch
 
 import numpy as np

fastembed_haystack-1.5.0/PKG-INFO

@@ -1,125 +0,0 @@
-Metadata-Version: 2.4
-Name: fastembed-haystack
-Version: 1.5.0
-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)
-
------
-
-**Table of Contents**
-
-- [Installation](#installation)
-- [Usage](#Usage)
-- [License](#license)
-
-## Installation
-
-```console
-pip install fastembed-haystack
-```
-
-## Usage
-
-You can use `FastembedTextEmbedder` and `FastembedDocumentEmbedder` by importing as:
-
-```python
-from haystack_integrations.components.embedders.fastembed import FastembedTextEmbedder
-
-text = "fastembed is supported by and maintained by Qdrant."
-text_embedder = FastembedTextEmbedder(
-    model="BAAI/bge-small-en-v1.5"
-)
-text_embedder.warm_up()
-embedding = text_embedder.run(text)["embedding"]
-```
-
-```python
-from haystack_integrations.components.embedders.fastembed import FastembedDocumentEmbedder
-from haystack import Document
-
-embedder = FastembedDocumentEmbedder(
-    model="BAAI/bge-small-en-v1.5",
-)
-embedder.warm_up()
-doc = Document(content="fastembed is supported by and maintained by Qdrant.", meta={"long_answer": "no",})
-result = embedder.run(documents=[doc])
-```
-
-You can use `FastembedSparseTextEmbedder` and `FastembedSparseDocumentEmbedder` by importing as:
-
-```python
-from haystack_integrations.components.embedders.fastembed import FastembedSparseTextEmbedder
-
-text = "fastembed is supported by and maintained by Qdrant."
-text_embedder = FastembedSparseTextEmbedder(
-    model="prithivida/Splade_PP_en_v1"
-)
-text_embedder.warm_up()
-embedding = text_embedder.run(text)["sparse_embedding"]
-```
-
-```python
-from haystack_integrations.components.embedders.fastembed import FastembedSparseDocumentEmbedder
-from haystack import Document
-
-embedder = FastembedSparseDocumentEmbedder(
-    model="prithivida/Splade_PP_en_v1",
-)
-embedder.warm_up()
-doc = Document(content="fastembed is supported by and maintained by Qdrant.", meta={"long_answer": "no",})
-result = embedder.run(documents=[doc])
-```
-
-You can use `FastembedRanker` by importing as:
-
-```python
-from haystack import Document
-
-from haystack_integrations.components.rankers.fastembed import FastembedRanker
-
-query = "Who is maintaining Qdrant?"
-documents = [
-    Document(
-        content="This is built to be faster and lighter than other embedding libraries e.g. Transformers, Sentence-Transformers, etc."
-    ),
-    Document(content="fastembed is supported by and maintained by Qdrant."),
-]
-
-ranker = FastembedRanker(model_name="Xenova/ms-marco-MiniLM-L-6-v2")
-ranker.warm_up()
-reranked_documents = ranker.run(query=query, documents=documents)["documents"]
-
-print(reranked_documents[0])
-
-# Document(id=...,
-#  content: 'fastembed is supported by and maintained by Qdrant.',
-#  score: 5.472434997558594..)
-```
-
-## License
-
-`fastembed-haystack` is distributed under the terms of the [Apache-2.0](https://spdx.org/licenses/Apache-2.0.html) license.

fastembed_haystack-1.5.0/README.md

@@ -1,100 +0,0 @@
-# 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)
-
------
-
-**Table of Contents**
-
-- [Installation](#installation)
-- [Usage](#Usage)
-- [License](#license)
-
-## Installation
-
-```console
-pip install fastembed-haystack
-```
-
-## Usage
-
-You can use `FastembedTextEmbedder` and `FastembedDocumentEmbedder` by importing as:
-
-```python
-from haystack_integrations.components.embedders.fastembed import FastembedTextEmbedder
-
-text = "fastembed is supported by and maintained by Qdrant."
-text_embedder = FastembedTextEmbedder(
-    model="BAAI/bge-small-en-v1.5"
-)
-text_embedder.warm_up()
-embedding = text_embedder.run(text)["embedding"]
-```
-
-```python
-from haystack_integrations.components.embedders.fastembed import FastembedDocumentEmbedder
-from haystack import Document
-
-embedder = FastembedDocumentEmbedder(
-    model="BAAI/bge-small-en-v1.5",
-)
-embedder.warm_up()
-doc = Document(content="fastembed is supported by and maintained by Qdrant.", meta={"long_answer": "no",})
-result = embedder.run(documents=[doc])
-```
-
-You can use `FastembedSparseTextEmbedder` and `FastembedSparseDocumentEmbedder` by importing as:
-
-```python
-from haystack_integrations.components.embedders.fastembed import FastembedSparseTextEmbedder
-
-text = "fastembed is supported by and maintained by Qdrant."
-text_embedder = FastembedSparseTextEmbedder(
-    model="prithivida/Splade_PP_en_v1"
-)
-text_embedder.warm_up()
-embedding = text_embedder.run(text)["sparse_embedding"]
-```
-
-```python
-from haystack_integrations.components.embedders.fastembed import FastembedSparseDocumentEmbedder
-from haystack import Document
-
-embedder = FastembedSparseDocumentEmbedder(
-    model="prithivida/Splade_PP_en_v1",
-)
-embedder.warm_up()
-doc = Document(content="fastembed is supported by and maintained by Qdrant.", meta={"long_answer": "no",})
-result = embedder.run(documents=[doc])
-```
-
-You can use `FastembedRanker` by importing as:
-
-```python
-from haystack import Document
-
-from haystack_integrations.components.rankers.fastembed import FastembedRanker
-
-query = "Who is maintaining Qdrant?"
-documents = [
-    Document(
-        content="This is built to be faster and lighter than other embedding libraries e.g. Transformers, Sentence-Transformers, etc."
-    ),
-    Document(content="fastembed is supported by and maintained by Qdrant."),
-]
-
-ranker = FastembedRanker(model_name="Xenova/ms-marco-MiniLM-L-6-v2")
-ranker.warm_up()
-reranked_documents = ranker.run(query=query, documents=documents)["documents"]
-
-print(reranked_documents[0])
-
-# Document(id=...,
-#  content: 'fastembed is supported by and maintained by Qdrant.',
-#  score: 5.472434997558594..)
-```
-
-## License
-
-`fastembed-haystack` is distributed under the terms of the [Apache-2.0](https://spdx.org/licenses/Apache-2.0.html) license.

fastembed_haystack-1.5.0/pydoc/config.yml

@@ -1,34 +0,0 @@
-loaders:
-  - type: haystack_pydoc_tools.loaders.CustomPythonLoader
-    search_path: [../src]
-    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"
-      ]
-    ignore_when_discovered: ["__init__"]
-processors:
-  - type: filter
-    expression:
-    documented_only: true
-    do_not_filter_modules: false
-    skip_empty_modules: true
-  - type: smart
-  - type: crossref
-renderer:
-  type: haystack_pydoc_tools.renderers.ReadmeIntegrationRenderer
-  excerpt: FastEmbed integration for Haystack
-  category_slug: integrations-api
-  title: FastEmbed
-  slug: fastembed-embedders
-  order: 80
-  markdown:
-    descriptive_class_title: false
-    classdef_code_block: false
-    descriptive_module_title: true
-    add_method_class_prefix: true
-    add_member_class_prefix: false
-    filename: _readme_fastembed.md

fastembed_haystack-1.5.0/src/haystack_integrations/components/rankers/fastembed/__init__.py

@@ -1,3 +0,0 @@
-from .ranker import FastembedRanker
-
-__all__ = ["FastembedRanker"]