fix wheel

integrations/instructor-embedders/instructor_embedders_haystack/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+from instructor_embedders_haystack.instructor_document_embedder import InstructorDocumentEmbedder
+from instructor_embedders_haystack.instructor_text_embedder import InstructorTextEmbedder
+
+__all__ = ["InstructorDocumentEmbedder", "InstructorTextEmbedder"]

integrations/instructor-embedders/instructor_embedders/instructor_document_embedder.py → integrations/instructor-embedders/instructor_embedders_haystack/instructor_document_embedder.py

@@ -5,7 +5,7 @@
 
 from haystack import Document, component, default_from_dict, default_to_dict
 
-from instructor_embedders.embedding_backend.instructor_backend import _InstructorEmbeddingBackendFactory
+from instructor_embedders_haystack.embedding_backend.instructor_backend import _InstructorEmbeddingBackendFactory
 
 
 @component
@@ -19,7 +19,7 @@ class InstructorDocumentEmbedder:
     # To use this component, install the "instructor-embedders-haystack" package.
     # pip install instructor-embedders-haystack
 
-    from instructor_embedders.instructor_document_embedder import InstructorDocumentEmbedder
+    from instructor_embedders_haystack.instructor_document_embedder import InstructorDocumentEmbedder
     from haystack.dataclasses import Document
 
 

integrations/instructor-embedders/instructor_embedders/instructor_text_embedder.py → integrations/instructor-embedders/instructor_embedders_haystack/instructor_text_embedder.py

@@ -5,7 +5,7 @@
 
 from haystack import component, default_from_dict, default_to_dict
 
-from instructor_embedders.embedding_backend.instructor_backend import _InstructorEmbeddingBackendFactory
+from instructor_embedders_haystack.embedding_backend.instructor_backend import _InstructorEmbeddingBackendFactory
 
 
 @component
@@ -18,7 +18,7 @@ class InstructorTextEmbedder:
     # To use this component, install the "instructor-embedders-haystack" package.
     # pip install instructor-embedders-haystack
 
-    from instructor_embedders.instructor_text_embedder import InstructorTextEmbedder
+    from instructor_embedders_haystack.instructor_text_embedder import InstructorTextEmbedder
 
     text = "It clearly says online this will work on a Mac OS system. The disk comes and it does not, only Windows. Do Not order this if you have a Mac!!"
     instruction = (

integrations/instructor-embedders/pyproject.toml

@@ -50,22 +50,46 @@ dependencies = [
 dev = ["pytest"]
 
 [project.urls]
-Documentation = "https://github.com/deepset-ai/haystack-extras/tree/main/components/instructor-embedders#readme"
-Issues = "https://github.com/deepset-ai/haystack-extras/issues"
-Source = "https://github.com/deepset-ai/haystack-extras/tree/main/components/instructor-embedders"
+Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/components/instructor-embedders#readme"
+Issues = "https://github.com/deepset-ai/haystack-core-integrations/issues"
+Source = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/components/instructor-embedders"
 
 [tool.hatch.version]
-path = "instructor_embedders/__about__.py"
+path = "instructor_embedders_haystack/__about__.py"
 
 [tool.hatch.envs.default]
 dependencies = ["pytest", "pytest-cov"]
 
 [tool.hatch.envs.default.scripts]
 cov = "pytest --cov-report=term-missing --cov-config=pyproject.toml --cov=instructor-embedders --cov=tests"
 no-cov = "cov --no-cov"
+test = "pytest {args:tests}"
 
 [[tool.hatch.envs.test.matrix]]
-python = ["37", "38", "39", "310", "311"]
+python = ["38", "39", "310", "311"]
+
+[tool.hatch.envs.lint]
+detached = true
+dependencies = [
+  "black>=23.1.0",
+  "mypy>=1.0.0",
+  "ruff>=0.0.243",
+]
+[tool.hatch.envs.lint.scripts]
+typing = "mypy --install-types --non-interactive {args:instructor_embedders_haystack tests}"
+style = [
+  "ruff {args:.}",
+  "black --check --diff {args:.}",
+]
+fmt = [
+  "black {args:.}",
+  "ruff --fix {args:.}",
+  "style",
+]
+all = [
+  "style",
+  "typing",
+]
 
 [tool.coverage.run]
 branch = true
@@ -76,7 +100,7 @@ omit = ["instructor_embedders/__about__.py"]
 exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
 
 [tool.ruff]
-target-version = "py37"
+target-version = "py38"
 line-length = 120
 select = [
   "A",
@@ -132,8 +156,18 @@ ban-relative-imports = "all"
 [tool.pytest.ini_options]
 minversion = "6.0"
 addopts = "--strict-markers"
-markers = ["integration: integration tests", "unit: unit tests"]
+markers = ["integration: integration tests"]
 log_cli = true
 
 [tool.black]
 line-length = 120
+
+[[tool.mypy.overrides]]
+module = [
+  "instructor_embedders_haystack.*",
+  "InstructorEmbedding.*",
+  "haystack.*",
+  "pytest.*",
+  "numpy.*",
+]
+ignore_missing_imports = true

integrations/instructor-embedders/tests/test_instructor_backend.py

@@ -1,12 +1,10 @@
 from unittest.mock import patch
 
-import pytest
 
-from instructor_embedders.embedding_backend.instructor_backend import _InstructorEmbeddingBackendFactory
+from instructor_embedders_haystack.embedding_backend.instructor_backend import _InstructorEmbeddingBackendFactory
 
 
-@pytest.mark.unit
-@patch("instructor_embedders.embedding_backend.instructor_backend.INSTRUCTOR")
+@patch("instructor_embedders_haystack.embedding_backend.instructor_backend.INSTRUCTOR")
 def test_factory_behavior(mock_instructor):  # noqa: ARG001
     embedding_backend = _InstructorEmbeddingBackendFactory.get_embedding_backend(
         model_name_or_path="hkunlp/instructor-large", device="cpu"
@@ -19,20 +17,23 @@ def test_factory_behavior(mock_instructor):  # noqa: ARG001
     assert same_embedding_backend is embedding_backend
     assert another_embedding_backend is not embedding_backend
 
+    # restore the factory state
+    _InstructorEmbeddingBackendFactory._instances = {}
 
-@pytest.mark.unit
-@patch("instructor_embedders.embedding_backend.instructor_backend.INSTRUCTOR")
+
+@patch("instructor_embedders_haystack.embedding_backend.instructor_backend.INSTRUCTOR")
 def test_model_initialization(mock_instructor):
     _InstructorEmbeddingBackendFactory.get_embedding_backend(
         model_name_or_path="hkunlp/instructor-base", device="cpu", use_auth_token="huggingface_auth_token"
     )
     mock_instructor.assert_called_once_with(
         model_name_or_path="hkunlp/instructor-base", device="cpu", use_auth_token="huggingface_auth_token"
     )
+    # restore the factory state
+    _InstructorEmbeddingBackendFactory._instances = {}
 
 
-@pytest.mark.unit
-@patch("instructor_embedders.embedding_backend.instructor_backend.INSTRUCTOR")
+@patch("instructor_embedders_haystack.embedding_backend.instructor_backend.INSTRUCTOR")
 def test_embedding_function_with_kwargs(mock_instructor):  # noqa: ARG001
     embedding_backend = _InstructorEmbeddingBackendFactory.get_embedding_backend(
         model_name_or_path="hkunlp/instructor-base"
@@ -42,3 +43,5 @@ def test_embedding_function_with_kwargs(mock_instructor):  # noqa: ARG001
     embedding_backend.embed(data=data, normalize_embeddings=True)
 
     embedding_backend.model.encode.assert_called_once_with(data, normalize_embeddings=True)
+    # restore the factory state
+    _InstructorEmbeddingBackendFactory._instances = {}

integrations/instructor-embedders/tests/test_instructor_document_embedder.py

@@ -4,11 +4,10 @@
 import pytest
 from haystack import Document
 
-from instructor_embedders.instructor_document_embedder import InstructorDocumentEmbedder
+from instructor_embedders_haystack.instructor_document_embedder import InstructorDocumentEmbedder
 
 
 class TestInstructorDocumentEmbedder:
-    @pytest.mark.unit
     def test_init_default(self):
         """
         Test default initialization parameters for InstructorDocumentEmbedder.
@@ -24,7 +23,6 @@ def test_init_default(self):
         assert embedder.metadata_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
 
-    @pytest.mark.unit
     def test_init_with_parameters(self):
         """
         Test custom initialization parameters for InstructorDocumentEmbedder.
@@ -50,15 +48,14 @@ def test_init_with_parameters(self):
         assert embedder.metadata_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == " | "
 
-    @pytest.mark.unit
     def test_to_dict(self):
         """
         Test serialization of InstructorDocumentEmbedder to a dictionary, using default initialization parameters.
         """
         embedder = InstructorDocumentEmbedder(model_name_or_path="hkunlp/instructor-base")
         embedder_dict = embedder.to_dict()
         assert embedder_dict == {
-            "type": "instructor_embedders.instructor_document_embedder.InstructorDocumentEmbedder",
+            "type": "instructor_embedders_haystack.instructor_document_embedder.InstructorDocumentEmbedder",
             "init_parameters": {
                 "model_name_or_path": "hkunlp/instructor-base",
                 "device": "cpu",
@@ -72,7 +69,6 @@ def test_to_dict(self):
             },
         }
 
-    @pytest.mark.unit
     def test_to_dict_with_custom_init_parameters(self):
         """
         Test serialization of InstructorDocumentEmbedder to a dictionary, using custom initialization parameters.
@@ -90,7 +86,7 @@ def test_to_dict_with_custom_init_parameters(self):
         )
         embedder_dict = embedder.to_dict()
         assert embedder_dict == {
-            "type": "instructor_embedders.instructor_document_embedder.InstructorDocumentEmbedder",
+            "type": "instructor_embedders_haystack.instructor_document_embedder.InstructorDocumentEmbedder",
             "init_parameters": {
                 "model_name_or_path": "hkunlp/instructor-base",
                 "device": "cuda",
@@ -104,13 +100,12 @@ def test_to_dict_with_custom_init_parameters(self):
             },
         }
 
-    @pytest.mark.unit
     def test_from_dict(self):
         """
         Test deserialization of InstructorDocumentEmbedder from a dictionary, using default initialization parameters.
         """
         embedder_dict = {
-            "type": "instructor_embedders.instructor_document_embedder.InstructorDocumentEmbedder",
+            "type": "instructor_embedders_haystack.instructor_document_embedder.InstructorDocumentEmbedder",
             "init_parameters": {
                 "model_name_or_path": "hkunlp/instructor-base",
                 "device": "cpu",
@@ -134,13 +129,12 @@ def test_from_dict(self):
         assert embedder.metadata_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
 
-    @pytest.mark.unit
     def test_from_dict_with_custom_init_parameters(self):
         """
         Test deserialization of InstructorDocumentEmbedder from a dictionary, using custom initialization parameters.
         """
         embedder_dict = {
-            "type": "instructor_embedders.instructor_document_embedder.InstructorDocumentEmbedder",
+            "type": "instructor_embedders_haystack.instructor_document_embedder.InstructorDocumentEmbedder",
             "init_parameters": {
                 "model_name_or_path": "hkunlp/instructor-base",
                 "device": "cuda",
@@ -164,8 +158,7 @@ def test_from_dict_with_custom_init_parameters(self):
         assert embedder.metadata_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == " | "
 
-    @pytest.mark.unit
-    @patch("instructor_embedders.instructor_document_embedder._InstructorEmbeddingBackendFactory")
+    @patch("instructor_embedders_haystack.instructor_document_embedder._InstructorEmbeddingBackendFactory")
     def test_warmup(self, mocked_factory):
         """
         Test for checking embedder instances after warm-up.
@@ -177,8 +170,7 @@ def test_warmup(self, mocked_factory):
             model_name_or_path="hkunlp/instructor-base", device="cpu", use_auth_token=None
         )
 
-    @pytest.mark.unit
-    @patch("instructor_embedders.instructor_document_embedder._InstructorEmbeddingBackendFactory")
+    @patch("instructor_embedders_haystack.instructor_document_embedder._InstructorEmbeddingBackendFactory")
     def test_warmup_does_not_reload(self, mocked_factory):
         """
         Test for checking backend instances after multiple warm-ups.
@@ -189,7 +181,6 @@ def test_warmup_does_not_reload(self, mocked_factory):
         embedder.warm_up()
         mocked_factory.get_embedding_backend.assert_called_once()
 
-    @pytest.mark.unit
     def test_embed(self):
         """
         Test for checking output dimensions and embedding dimensions.
@@ -209,7 +200,6 @@ def test_embed(self):
             assert isinstance(doc.embedding, list)
             assert isinstance(doc.embedding[0], float)
 
-    @pytest.mark.unit
     def test_embed_incorrect_input_format(self):
         """
         Test for checking incorrect input format when creating embedding.
@@ -225,7 +215,6 @@ def test_embed_incorrect_input_format(self):
         with pytest.raises(TypeError, match="InstructorDocumentEmbedder expects a list of Documents as input."):
             embedder.run(documents=list_integers_input)
 
-    @pytest.mark.unit
     def test_embed_metadata(self):
         """
         Test for checking output dimensions and embedding dimensions for documents