weaviate-haystack 2.2.0__tar.gz → 3.0.0__tar.gz

{weaviate_haystack-2.2.0 → weaviate_haystack-3.0.0}/CHANGELOG.md

@@ -1,6 +1,6 @@
 # Changelog
 
-## [unreleased]
+## [integrations/weaviate-v2.2.1] - 2024-09-07
 
 ### 🚀 Features
 
@@ -10,6 +10,12 @@
 
 - Weaviate filter error (#811)
 - Fix connection to Weaviate Cloud Service (#624)
+- Pin weaviate-client (#1046)
+- Weaviate - fix connection issues with some WCS URLs (#1058)
+
+### 🧪 Testing
+
+- Do not retry tests in `hatch run test` command (#954)
 
 ### ⚙️ Miscellaneous Tasks
 

{weaviate_haystack-2.2.0 → weaviate_haystack-3.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: weaviate-haystack
-Version: 2.2.0
+Version: 3.0.0
 Summary: An integration of Weaviate vector database with Haystack
 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/weaviate/README.md
@@ -22,7 +22,7 @@ Requires-Python: >=3.8
 Requires-Dist: haystack-ai
 Requires-Dist: haystack-pydoc-tools
 Requires-Dist: python-dateutil
-Requires-Dist: weaviate-client
+Requires-Dist: weaviate-client>=4.0
 Description-Content-Type: text/markdown
 
 # weaviate-haystack

{weaviate_haystack-2.2.0 → weaviate_haystack-3.0.0}/pyproject.toml

@@ -25,7 +25,7 @@ classifiers = [
 ]
 dependencies = [
   "haystack-ai",
-  "weaviate-client",
+  "weaviate-client>=4.0",
   "haystack-pydoc-tools",
   "python-dateutil",
 ]
@@ -49,10 +49,12 @@ git_describe_command = 'git describe --tags --match="integrations/weaviate-v[0-9
 [tool.hatch.envs.default]
 dependencies = ["coverage[toml]>=6.5", "pytest", "pytest-rerunfailures", "ipython"]
 [tool.hatch.envs.default.scripts]
-test = "pytest --reruns 3 --reruns-delay 30 -x {args:tests}"
-test-cov = "coverage run -m pytest --reruns 3 --reruns-delay 30 -x {args:tests}"
+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]]
@@ -63,8 +65,8 @@ 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 --explicit-package-bases {args:src/ tests}"
-style = ["ruff check {args:.}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
+style = ["ruff check {args:. --exclude tests/}", "black --check --diff {args:.}"]
+fmt = ["black {args:.}", "ruff --fix {args:. --exclude tests/}", "style"]
 all = ["style", "typing"]
 
 [tool.black]

{weaviate_haystack-2.2.0 → weaviate_haystack-3.0.0}/src/haystack_integrations/components/retrievers/weaviate/bm25_retriever.py

@@ -7,6 +7,7 @@ from typing import Any, Dict, List, Optional, Union
 from haystack import Document, component, default_from_dict, default_to_dict
 from haystack.document_stores.types import FilterPolicy
 from haystack.document_stores.types.filter_policy import apply_filter_policy
+
 from haystack_integrations.document_stores.weaviate import WeaviateDocumentStore
 
 

{weaviate_haystack-2.2.0 → weaviate_haystack-3.0.0}/src/haystack_integrations/components/retrievers/weaviate/embedding_retriever.py

@@ -7,6 +7,7 @@ from typing import Any, Dict, List, Optional, Union
 from haystack import Document, component, default_from_dict, default_to_dict
 from haystack.document_stores.types import FilterPolicy
 from haystack.document_stores.types.filter_policy import apply_filter_policy
+
 from haystack_integrations.document_stores.weaviate import WeaviateDocumentStore
 
 

{weaviate_haystack-2.2.0 → weaviate_haystack-3.0.0}/src/haystack_integrations/document_stores/weaviate/document_store.py

@@ -12,7 +12,6 @@ from haystack.core.serialization import default_from_dict, default_to_dict
 from haystack.dataclasses.document import Document
 from haystack.document_stores.errors import DocumentStoreError, DuplicateDocumentError
 from haystack.document_stores.types.policy import DuplicatePolicy
-from haystack.utils.filters import convert
 
 import weaviate
 from weaviate.collections.classes.data import DataObject
@@ -68,7 +67,7 @@ class WeaviateDocumentStore:
     from haystack_integrations.document_stores.weaviate.auth import AuthApiKey
     from haystack_integrations.document_stores.weaviate.document_store import WeaviateDocumentStore
 
-    os.environ["WEAVIATE_API_KEY"] = "MY_API_KEY
+    os.environ["WEAVIATE_API_KEY"] = "MY_API_KEY"
 
     document_store = WeaviateDocumentStore(
         url="rAnD0mD1g1t5.something.weaviate.cloud",
@@ -172,17 +171,18 @@ class WeaviateDocumentStore:
         if self._client:
             return self._client
 
-        if self._url and self._url.startswith("http") and self._url.endswith(".weaviate.network"):
-            # We use this utility function instead of using WeaviateClient directly like in other cases
-            # otherwise we'd have to parse the URL to get some information about the connection.
-            # This utility function does all that for us.
-            self._client = weaviate.connect_to_wcs(
+        if self._url and self._url.endswith((".weaviate.network", ".weaviate.cloud")):
+            # If we detect that the URL is a Weaviate Cloud URL, we use the utility function to connect
+            # instead of using WeaviateClient directly like in other cases.
+            # Among other things, the utility function takes care of parsing the URL.
+            self._client = weaviate.connect_to_weaviate_cloud(
                 self._url,
                 auth_credentials=self._auth_client_secret.resolve_value() if self._auth_client_secret else None,
                 headers=self._additional_headers,
                 additional_config=self._additional_config,
             )
         else:
+            # Embedded, local Docker deployment or custom connection.
             # proxies, timeout_config, trust_env are part of additional_config now
             # startup_period has been removed
             self._client = weaviate.WeaviateClient(
@@ -387,7 +387,8 @@ class WeaviateDocumentStore:
         :returns: A list of Documents that match the given filters.
         """
         if filters and "operator" not in filters and "conditions" not in filters:
-            filters = convert(filters)
+            msg = "Invalid filter syntax. See https://docs.haystack.deepset.ai/docs/metadata-filtering for details."
+            raise ValueError(msg)
 
         result = []
         if filters:

{weaviate_haystack-2.2.0 → weaviate_haystack-3.0.0}/tests/test_auth.py

@@ -2,6 +2,11 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
+from weaviate.auth import AuthApiKey as WeaviateAuthApiKey
+from weaviate.auth import AuthBearerToken as WeaviateAuthBearerToken
+from weaviate.auth import AuthClientCredentials as WeaviateAuthClientCredentials
+from weaviate.auth import AuthClientPassword as WeaviateAuthClientPassword
+
 from haystack_integrations.document_stores.weaviate.auth import (
     AuthApiKey,
     AuthBearerToken,
@@ -9,10 +14,6 @@ from haystack_integrations.document_stores.weaviate.auth import (
     AuthClientPassword,
     AuthCredentials,
 )
-from weaviate.auth import AuthApiKey as WeaviateAuthApiKey
-from weaviate.auth import AuthBearerToken as WeaviateAuthBearerToken
-from weaviate.auth import AuthClientCredentials as WeaviateAuthClientCredentials
-from weaviate.auth import AuthClientPassword as WeaviateAuthClientPassword
 
 
 class TestAuthApiKey:

{weaviate_haystack-2.2.0 → weaviate_haystack-3.0.0}/tests/test_bm25_retriever.py

@@ -6,6 +6,7 @@ from unittest.mock import Mock, patch
 
 import pytest
 from haystack.document_stores.types import FilterPolicy
+
 from haystack_integrations.components.retrievers.weaviate import WeaviateBM25Retriever
 from haystack_integrations.document_stores.weaviate import WeaviateDocumentStore
 

{weaviate_haystack-2.2.0 → weaviate_haystack-3.0.0}/tests/test_document_store.py

@@ -22,11 +22,6 @@ from haystack.testing.document_store import (
     WriteDocumentsTest,
 )
 from haystack.utils.auth import Secret
-from haystack_integrations.document_stores.weaviate.auth import AuthApiKey
-from haystack_integrations.document_stores.weaviate.document_store import (
-    DOCUMENT_COLLECTION_PROPERTIES,
-    WeaviateDocumentStore,
-)
 from numpy import array as np_array
 from numpy import array_equal as np_array_equal
 from numpy import float32 as np_float32
@@ -41,6 +36,12 @@ from weaviate.embedded import (
     EmbeddedOptions,
 )
 
+from haystack_integrations.document_stores.weaviate.auth import AuthApiKey
+from haystack_integrations.document_stores.weaviate.document_store import (
+    DOCUMENT_COLLECTION_PROPERTIES,
+    WeaviateDocumentStore,
+)
+
 
 @patch("haystack_integrations.document_stores.weaviate.document_store.weaviate.WeaviateClient")
 def test_init_is_lazy(_mock_client):
@@ -659,15 +660,6 @@ class TestWeaviateDocumentStore(CountDocumentsTest, WriteDocumentsTest, DeleteDo
         with pytest.raises(ValueError):
             document_store._embedding_retrieval(query_embedding=[], distance=0.1, certainty=0.1)
 
-    def test_filter_documents_with_legacy_filters(self, document_store):
-        docs = []
-        for index in range(10):
-            docs.append(Document(content="This is some content", meta={"index": index}))
-        document_store.write_documents(docs)
-        result = document_store.filter_documents({"content": {"$eq": "This is some content"}})
-
-        assert len(result) == 10
-
     def test_filter_documents_below_default_limit(self, document_store):
         docs = []
         for index in range(9998):

{weaviate_haystack-2.2.0 → weaviate_haystack-3.0.0}/tests/test_embedding_retriever.py

@@ -6,6 +6,7 @@ from unittest.mock import Mock, patch
 
 import pytest
 from haystack.document_stores.types import FilterPolicy
+
 from haystack_integrations.components.retrievers.weaviate import WeaviateEmbeddingRetriever
 from haystack_integrations.document_stores.weaviate import WeaviateDocumentStore