weaviate-haystack 2.1.2__tar.gz → 2.2.0__tar.gz

{weaviate_haystack-2.1.2 → weaviate_haystack-2.2.0}/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## [unreleased]
 
+### 🚀 Features
+
+- Add filter_policy to weaviate integration (#824)
+
 ### 🐛 Bug Fixes
 
 - Weaviate filter error (#811)
@@ -10,6 +14,7 @@
 ### ⚙️ Miscellaneous Tasks
 
 - Retry tests to reduce flakyness (#836)
+- Update ruff invocation to include check parameter (#853)
 
 ## [integrations/weaviate-v2.1.0] - 2024-06-10
 

{weaviate_haystack-2.1.2 → weaviate_haystack-2.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: weaviate-haystack
-Version: 2.1.2
+Version: 2.2.0
 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

{weaviate_haystack-2.1.2 → weaviate_haystack-2.2.0}/src/haystack_integrations/components/retrievers/weaviate/bm25_retriever.py

@@ -80,7 +80,11 @@ class WeaviateBM25Retriever:
         data["init_parameters"]["document_store"] = WeaviateDocumentStore.from_dict(
             data["init_parameters"]["document_store"]
         )
-        data["init_parameters"]["filter_policy"] = FilterPolicy.from_str(data["init_parameters"]["filter_policy"])
+        # Pipelines serialized with old versions of the component might not
+        # have the filter_policy field.
+        if filter_policy := data["init_parameters"].get("filter_policy"):
+            data["init_parameters"]["filter_policy"] = FilterPolicy.from_str(filter_policy)
+
         return default_from_dict(cls, data)
 
     @component.output_types(documents=List[Document])

{weaviate_haystack-2.1.2 → weaviate_haystack-2.2.0}/src/haystack_integrations/components/retrievers/weaviate/embedding_retriever.py

@@ -90,7 +90,11 @@ class WeaviateEmbeddingRetriever:
             data["init_parameters"]["document_store"]
         )
 
-        data["init_parameters"]["filter_policy"] = FilterPolicy.from_str(data["init_parameters"]["filter_policy"])
+        # Pipelines serialized with old versions of the component might not
+        # have the filter_policy field.
+        if filter_policy := data["init_parameters"].get("filter_policy"):
+            data["init_parameters"]["filter_policy"] = FilterPolicy.from_str(filter_policy)
+
         return default_from_dict(cls, data)
 
     @component.output_types(documents=List[Document])

{weaviate_haystack-2.1.2 → weaviate_haystack-2.2.0}/src/haystack_integrations/document_stores/weaviate/document_store.py

@@ -203,7 +203,7 @@ class WeaviateDocumentStore:
         self._client.connect()
 
         # Test connection, it will raise an exception if it fails.
-        self._client.collections._get_all(simple=True)
+        self._client.collections.list_all(simple=True)
         if not self._client.collections.exists(self._collection_settings["class"]):
             self._client.collections.create_from_dict(self._collection_settings)
 

{weaviate_haystack-2.1.2 → weaviate_haystack-2.2.0}/tests/test_bm25_retriever.py

@@ -100,6 +100,45 @@ def test_from_dict(_mock_weaviate):
     assert retriever._top_k == 10
 
 
+@patch("haystack_integrations.document_stores.weaviate.document_store.weaviate")
+def test_from_dict_no_filter_policy(_mock_weaviate):
+    retriever = WeaviateBM25Retriever.from_dict(
+        {
+            "type": "haystack_integrations.components.retrievers.weaviate.bm25_retriever.WeaviateBM25Retriever",
+            "init_parameters": {
+                "filters": {},
+                "top_k": 10,
+                "document_store": {
+                    "type": "haystack_integrations.document_stores.weaviate.document_store.WeaviateDocumentStore",
+                    "init_parameters": {
+                        "url": None,
+                        "collection_settings": {
+                            "class": "Default",
+                            "invertedIndexConfig": {"indexNullState": True},
+                            "properties": [
+                                {"name": "_original_id", "dataType": ["text"]},
+                                {"name": "content", "dataType": ["text"]},
+                                {"name": "dataframe", "dataType": ["text"]},
+                                {"name": "blob_data", "dataType": ["blob"]},
+                                {"name": "blob_mime_type", "dataType": ["text"]},
+                                {"name": "score", "dataType": ["number"]},
+                            ],
+                        },
+                        "auth_client_secret": None,
+                        "additional_headers": None,
+                        "embedded_options": None,
+                        "additional_config": None,
+                    },
+                },
+            },
+        }
+    )
+    assert retriever._document_store
+    assert retriever._filters == {}
+    assert retriever._top_k == 10
+    assert retriever._filter_policy == FilterPolicy.REPLACE
+
+
 @patch("haystack_integrations.components.retrievers.weaviate.bm25_retriever.WeaviateDocumentStore")
 def test_run(mock_document_store):
     retriever = WeaviateBM25Retriever(document_store=mock_document_store)

{weaviate_haystack-2.1.2 → weaviate_haystack-2.2.0}/tests/test_embedding_retriever.py

@@ -114,6 +114,49 @@ def test_from_dict(_mock_weaviate):
     assert retriever._certainty is None
 
 
+@patch("haystack_integrations.document_stores.weaviate.document_store.weaviate")
+def test_from_dict_no_filter_policy(_mock_weaviate):
+    retriever = WeaviateEmbeddingRetriever.from_dict(
+        {
+            "type": "haystack_integrations.components.retrievers.weaviate.embedding_retriever.WeaviateEmbeddingRetriever",  # noqa: E501
+            "init_parameters": {
+                "filters": {},
+                "top_k": 10,
+                "distance": None,
+                "certainty": None,
+                "document_store": {
+                    "type": "haystack_integrations.document_stores.weaviate.document_store.WeaviateDocumentStore",
+                    "init_parameters": {
+                        "url": None,
+                        "collection_settings": {
+                            "class": "Default",
+                            "invertedIndexConfig": {"indexNullState": True},
+                            "properties": [
+                                {"name": "_original_id", "dataType": ["text"]},
+                                {"name": "content", "dataType": ["text"]},
+                                {"name": "dataframe", "dataType": ["text"]},
+                                {"name": "blob_data", "dataType": ["blob"]},
+                                {"name": "blob_mime_type", "dataType": ["text"]},
+                                {"name": "score", "dataType": ["number"]},
+                            ],
+                        },
+                        "auth_client_secret": None,
+                        "additional_headers": None,
+                        "embedded_options": None,
+                        "additional_config": None,
+                    },
+                },
+            },
+        }
+    )
+    assert retriever._document_store
+    assert retriever._filters == {}
+    assert retriever._top_k == 10
+    assert retriever._distance is None
+    assert retriever._certainty is None
+    assert retriever._filter_policy == FilterPolicy.REPLACE  # defaults to REPLACE
+
+
 @patch("haystack_integrations.components.retrievers.weaviate.bm25_retriever.WeaviateDocumentStore")
 def test_run(mock_document_store):
     retriever = WeaviateEmbeddingRetriever(document_store=mock_document_store)