weaviate-haystack 4.0.0__tar.gz → 4.0.2__tar.gz

{weaviate_haystack-4.0.0 → weaviate_haystack-4.0.2}/CHANGELOG.md

@@ -1,10 +1,19 @@
 # Changelog
 
-## [integrations/weaviate-v3.0.0] - 2024-09-12
+## [integrations/weaviate-v4.0.1] - 2024-11-11
+
+## [integrations/weaviate-v4.0.0] - 2024-10-18
+
+### 🐛 Bug Fixes
+
+- Compatibility with Weaviate 4.9.0 (#1143)
 
 ### ⚙️ Miscellaneous Tasks
 
 - Weaviate - remove legacy filter support (#1070)
+- Update changelog after removing legacy filters (#1083)
+- Update ruff linting scripts and settings (#1105)
+- Adopt uv as installer (#1142)
 
 ## [integrations/weaviate-v2.2.1] - 2024-09-07
 
@@ -58,8 +67,6 @@
 This PR will also push the docs to Readme
 - Fix weaviate auth tests (#488)
 
-
-
 ### 📚 Documentation
 
 - Update category slug (#442)

{weaviate_haystack-4.0.0 → weaviate_haystack-4.0.2}/PKG-INFO

@@ -1,13 +1,12 @@
 Metadata-Version: 2.3
 Name: weaviate-haystack
-Version: 4.0.0
+Version: 4.0.2
 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
 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
+License: Apache-2.0
 Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
@@ -20,7 +19,6 @@ Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: >=3.9
 Requires-Dist: haystack-ai
-Requires-Dist: haystack-pydoc-tools
 Requires-Dist: python-dateutil
 Requires-Dist: weaviate-client>=4.9
 Description-Content-Type: text/markdown

{weaviate_haystack-4.0.0 → weaviate_haystack-4.0.2}/pyproject.toml

@@ -26,7 +26,6 @@ classifiers = [
 dependencies = [
   "haystack-ai",
   "weaviate-client>=4.9",
-  "haystack-pydoc-tools",
   "python-dateutil",
 ]
 
@@ -48,7 +47,7 @@ git_describe_command = 'git describe --tags --match="integrations/weaviate-v[0-9
 
 [tool.hatch.envs.default]
 installer = "uv"
-dependencies = ["coverage[toml]>=6.5", "pytest", "pytest-rerunfailures", "ipython"]
+dependencies = ["coverage[toml]>=6.5", "pytest", "pytest-rerunfailures", "ipython", "haystack-pydoc-tools"]
 [tool.hatch.envs.default.scripts]
 test = "pytest {args:tests}"
 test-cov = "coverage run -m pytest {args:tests}"

{weaviate_haystack-4.0.0 → weaviate_haystack-4.0.2}/src/haystack_integrations/document_stores/weaviate/document_store.py

@@ -286,6 +286,14 @@ class WeaviateDocumentStore:
         # The embedding vector is stored separately from the rest of the data
         del data["embedding"]
 
+        # _split_overlap meta field is unsupported because of a bug
+        # https://github.com/deepset-ai/haystack-core-integrations/issues/1172
+        if "_split_overlap" in data:
+            data.pop("_split_overlap")
+            logger.warning(
+                "Document %s has the unsupported `_split_overlap` meta field. It will be ignored.", data["_original_id"]
+            )
+
         if "sparse_embedding" in data:
             sparse_embedding = data.pop("sparse_embedding", None)
             if sparse_embedding:

{weaviate_haystack-4.0.0 → weaviate_haystack-4.0.2}/tests/test_document_store.py

@@ -508,6 +508,30 @@ class TestWeaviateDocumentStore(CountDocumentsTest, WriteDocumentsTest, DeleteDo
     def test_comparison_not_equal_with_dataframe(self, document_store, filterable_docs):
         return super().test_comparison_not_equal_with_dataframe(document_store, filterable_docs)
 
+    def test_meta_split_overlap_is_skipped(self, document_store):
+        doc = Document(
+            content="The moonlight shimmered ",
+            meta={
+                "source_id": "62049ba1d1e1d5ebb1f6230b0b00c5356b8706c56e0b9c36b1dfc86084cd75f0",
+                "page_number": 1,
+                "split_id": 0,
+                "split_idx_start": 0,
+                "_split_overlap": [
+                    {"doc_id": "68ed48ba830048c5d7815874ed2de794722e6d10866b6c55349a914fd9a0df65", "range": (0, 20)}
+                ],
+            },
+        )
+        document_store.write_documents([doc])
+
+        written_doc = document_store.filter_documents()[0]
+
+        assert written_doc.content == "The moonlight shimmered "
+        assert written_doc.meta["source_id"] == "62049ba1d1e1d5ebb1f6230b0b00c5356b8706c56e0b9c36b1dfc86084cd75f0"
+        assert written_doc.meta["page_number"] == 1.0
+        assert written_doc.meta["split_id"] == 0.0
+        assert written_doc.meta["split_idx_start"] == 0.0
+        assert "_split_overlap" not in written_doc.meta
+
     def test_bm25_retrieval(self, document_store):
         document_store.write_documents(
             [