fastembed-haystack 1.4.1__tar.gz → 1.5.0__tar.gz

{fastembed_haystack-1.4.1 → fastembed_haystack-1.5.0}/CHANGELOG.md

@@ -1,11 +1,23 @@
 # Changelog
 
+## [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
 
-### ⚙️ Miscellaneous Tasks
+### ⚙️ 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
@@ -16,20 +28,35 @@
 
 - Do not retry tests in `hatch run test` command (#954)
 
-### ⚙️ Miscellaneous Tasks
+### ⚙️ CI
 
 - Retry tests to reduce flakyness (#836)
+
+### 🧹 Chores
+
 - Update ruff invocation to include check parameter (#853)
 - Update ruff linting scripts and settings (#1105)
 
-### Fix
+### 🌀 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
@@ -40,6 +67,10 @@
 
 - Disable-class-def (#556)
 
+### 🌀 Miscellaneous
+
+- Remove references to Python 3.7 (#601)
+
 ## [integrations/fastembed-v0.0.6] - 2024-03-07
 
 ### 📚 Documentation
@@ -47,20 +78,32 @@
 - 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)
 
-This PR will also push the docs to Readme
-
 ### 📚 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
@@ -73,6 +116,15 @@ This PR will also push the docs to Readme
 
 ## [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-1.5.0}/PKG-INFO

@@ -1,23 +1,24 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: fastembed-haystack
-Version: 1.4.1
+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: Apache-2.0
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
 Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 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: >=3.8
+Requires-Python: >=3.9
 Requires-Dist: fastembed>=0.4.2
 Requires-Dist: haystack-ai>=2.0.1
 Description-Content-Type: text/markdown

{fastembed_haystack-1.4.1 → fastembed_haystack-1.5.0}/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",
 ]
@@ -43,34 +43,36 @@ git_describe_command = 'git describe --tags --match="integrations/fastembed-v[0-
 
 [tool.hatch.envs.default]
 installer = "uv"
-dependencies = [
-  "coverage[toml]>=6.5",
-  "pytest",
-  "pytest-rerunfailures",
-  "ipython",
-  "haystack-pydoc-tools",
-]
+dependencies = ["haystack-pydoc-tools", "ruff"]
 [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"]
+fmt = "ruff check --fix {args} && ruff format {args}"
+fmt-check = "ruff check {args} && ruff format --check {args}"
+
+[tool.hatch.envs.test]
+dependencies = [
+    "pytest",
+    "pytest-asyncio",
+    "pytest-cov",
+    "pytest-rerunfailures",
+    "mypy",
+    "pip",
+    "ipython"
+]
 
-[[tool.hatch.envs.all.matrix]]
-python = ["3.8", "3.9", "3.10", "3.11", "3.12"]
+[tool.hatch.envs.test.scripts]
+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'
+types = """mypy -p haystack_integrations.components.embedders.fastembed \
+-p haystack_integrations.components.rankers.fastembed {args}"""
 
-[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.mypy]
+install_types = true
+non_interactive = true
+check_untyped_defs = true
+disallow_incomplete_defs = true
 
 [tool.black]
 target-version = ["py38"]
@@ -156,14 +158,5 @@ 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-1.5.0}/src/haystack_integrations/components/embedders/fastembed/embedding_backend/fastembed_backend.py

@@ -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)
@@ -74,7 +74,7 @@ class _FastembedSparseEmbeddingBackendFactory:
         threads: Optional[int] = None,
         local_files_only: bool = False,
         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:
@@ -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-1.5.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_document_embedder.py

@@ -150,7 +150,7 @@ class FastembedDocumentEmbedder:
         return texts_to_embed
 
     @component.output_types(documents=List[Document])
-    def run(self, documents: List[Document]):
+    def run(self, documents: List[Document]) -> Dict[str, List[Document]]:
         """
         Embeds a list of Documents.
 
@@ -158,7 +158,7 @@ class FastembedDocumentEmbedder:
         :returns: A dictionary with the following keys:
             - `documents`: List of Documents with each Document's `embedding` field set to the computed embeddings.
         """
-        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."

{fastembed_haystack-1.4.1 → fastembed_haystack-1.5.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_document_embedder.py

@@ -141,7 +141,7 @@ class FastembedSparseDocumentEmbedder:
         return texts_to_embed
 
     @component.output_types(documents=List[Document])
-    def run(self, documents: List[Document]):
+    def run(self, documents: List[Document]) -> Dict[str, List[Document]]:
         """
         Embeds a list of Documents.
 
@@ -150,7 +150,7 @@ class FastembedSparseDocumentEmbedder:
             - `documents`: List of Documents with each Document's `sparse_embedding`
                             field set to the computed embeddings.
         """
-        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."

{fastembed_haystack-1.4.1 → fastembed_haystack-1.5.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_text_embedder.py

@@ -94,7 +94,7 @@ class FastembedSparseTextEmbedder:
             )
 
     @component.output_types(sparse_embedding=SparseEmbedding)
-    def run(self, text: str):
+    def run(self, text: str) -> Dict[str, SparseEmbedding]:
         """
         Embeds text using the Fastembed model.
 

{fastembed_haystack-1.4.1 → fastembed_haystack-1.5.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_text_embedder.py

@@ -96,7 +96,7 @@ class FastembedTextEmbedder:
             )
 
     @component.output_types(embedding=List[float])
-    def run(self, text: str):
+    def run(self, text: str) -> Dict[str, List[float]]:
         """
         Embeds text using the Fastembed model.
 

{fastembed_haystack-1.4.1 → fastembed_haystack-1.5.0}/src/haystack_integrations/components/rankers/fastembed/ranker.py

@@ -76,7 +76,7 @@ class FastembedRanker:
         self.local_files_only = local_files_only
         self.meta_fields_to_embed = meta_fields_to_embed or []
         self.meta_data_separator = meta_data_separator
-        self._model = None
+        self._model: Optional[TextCrossEncoder] = None
 
     def to_dict(self) -> Dict[str, Any]:
         """
@@ -140,7 +140,7 @@ 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):
+    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.
 
@@ -157,7 +157,7 @@ class FastembedRanker:
 
         :raises ValueError: If `top_k` is not > 0.
         """
-        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 = "FastembedRanker expects a list of Documents as input. "
             raise TypeError(msg)
         if query == "":

{fastembed_haystack-1.4.1 → fastembed_haystack-1.5.0}/src/haystack_integrations/components/embedders/fastembed/__init__.py

@@ -8,7 +8,7 @@ from .fastembed_text_embedder import FastembedTextEmbedder
 
 __all__ = [
     "FastembedDocumentEmbedder",
-    "FastembedTextEmbedder",
     "FastembedSparseDocumentEmbedder",
     "FastembedSparseTextEmbedder",
+    "FastembedTextEmbedder",
 ]