elasticsearch-haystack 0.5.0__tar.gz → 0.6.0__tar.gz

{elasticsearch_haystack-0.5.0 → elasticsearch_haystack-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: elasticsearch-haystack
-Version: 0.5.0
+Version: 0.6.0
 Summary: Haystack 2.x Document Store for ElasticSearch
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/elasticsearch#readme
 Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues

{elasticsearch_haystack-0.5.0 → elasticsearch_haystack-0.6.0}/src/haystack_integrations/document_stores/elasticsearch/document_store.py

@@ -93,48 +93,60 @@ class ElasticsearchDocumentStore:
         :param **kwargs: Optional arguments that `Elasticsearch` takes.
         """
         self._hosts = hosts
-        self._client = Elasticsearch(
-            hosts,
-            headers={"user-agent": f"haystack-py-ds/{haystack_version}"},
-            **kwargs,
-        )
+        self._client = None
         self._index = index
         self._embedding_similarity_function = embedding_similarity_function
         self._custom_mapping = custom_mapping
         self._kwargs = kwargs
 
-        # Check client connection, this will raise if not connected
-        self._client.info()
-
         if self._custom_mapping and not isinstance(self._custom_mapping, Dict):
             msg = "custom_mapping must be a dictionary"
             raise ValueError(msg)
 
-        if self._custom_mapping:
-            mappings = self._custom_mapping
-        else:
-            # Configure mapping for the embedding field if none is provided
-            mappings = {
-                "properties": {
-                    "embedding": {"type": "dense_vector", "index": True, "similarity": embedding_similarity_function},
-                    "content": {"type": "text"},
-                },
-                "dynamic_templates": [
-                    {
-                        "strings": {
-                            "path_match": "*",
-                            "match_mapping_type": "string",
-                            "mapping": {
-                                "type": "keyword",
-                            },
+    @property
+    def client(self) -> Elasticsearch:
+        if self._client is None:
+            client = Elasticsearch(
+                self._hosts,
+                headers={"user-agent": f"haystack-py-ds/{haystack_version}"},
+                **self._kwargs,
+            )
+            # Check client connection, this will raise if not connected
+            client.info()
+
+            if self._custom_mapping:
+                mappings = self._custom_mapping
+            else:
+                # Configure mapping for the embedding field if none is provided
+                mappings = {
+                    "properties": {
+                        "embedding": {
+                            "type": "dense_vector",
+                            "index": True,
+                            "similarity": self._embedding_similarity_function,
+                        },
+                        "content": {"type": "text"},
+                    },
+                    "dynamic_templates": [
+                        {
+                            "strings": {
+                                "path_match": "*",
+                                "match_mapping_type": "string",
+                                "mapping": {
+                                    "type": "keyword",
+                                },
+                            }
                         }
-                    }
-                ],
-            }
+                    ],
+                }
+
+            # Create the index if it doesn't exist
+            if not client.indices.exists(index=self._index):
+                client.indices.create(index=self._index, mappings=mappings)
+
+            self._client = client
 
-        # Create the index if it doesn't exist
-        if not self._client.indices.exists(index=index):
-            self._client.indices.create(index=index, mappings=mappings)
+        return self._client
 
     def to_dict(self) -> Dict[str, Any]:
         """
@@ -172,7 +184,7 @@ class ElasticsearchDocumentStore:
         Returns how many documents are present in the document store.
         :returns: Number of documents in the document store.
         """
-        return self._client.count(index=self._index)["count"]
+        return self.client.count(index=self._index)["count"]
 
     def _search_documents(self, **kwargs) -> List[Document]:
         """
@@ -187,7 +199,7 @@ class ElasticsearchDocumentStore:
         from_ = 0
         # Handle pagination
         while True:
-            res = self._client.search(
+            res = self.client.search(
                 index=self._index,
                 from_=from_,
                 **kwargs,
@@ -261,7 +273,7 @@ class ElasticsearchDocumentStore:
             )
 
         documents_written, errors = helpers.bulk(
-            client=self._client,
+            client=self.client,
             actions=elasticsearch_actions,
             refresh="wait_for",
             index=self._index,
@@ -317,7 +329,7 @@ class ElasticsearchDocumentStore:
         """
 
         helpers.bulk(
-            client=self._client,
+            client=self.client,
             actions=({"_op_type": "delete", "_id": id_} for id_ in document_ids),
             refresh="wait_for",
             index=self._index,

{elasticsearch_haystack-0.5.0 → elasticsearch_haystack-0.6.0}/tests/test_document_store.py

@@ -15,6 +15,12 @@ from haystack.testing.document_store import DocumentStoreBaseTests
 from haystack_integrations.document_stores.elasticsearch import ElasticsearchDocumentStore
 
 
+@patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
+def test_init_is_lazy(_mock_es_client):
+    ElasticsearchDocumentStore(hosts="testhost")
+    _mock_es_client.assert_not_called()
+
+
 @patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
 def test_to_dict(_mock_elasticsearch_client):
     document_store = ElasticsearchDocumentStore(hosts="some hosts")
@@ -73,7 +79,7 @@ class TestDocumentStore(DocumentStoreBaseTests):
             hosts=hosts, index=index, embedding_similarity_function=embedding_similarity_function
         )
         yield store
-        store._client.options(ignore_status=[400, 404]).indices.delete(index=index)
+        store.client.options(ignore_status=[400, 404]).indices.delete(index=index)
 
     def assert_documents_are_equal(self, received: List[Document], expected: List[Document]):
         """
@@ -101,7 +107,7 @@ class TestDocumentStore(DocumentStoreBaseTests):
         super().assert_documents_are_equal(received, expected)
 
     def test_user_agent_header(self, document_store: ElasticsearchDocumentStore):
-        assert document_store._client._headers["user-agent"].startswith("haystack-py-ds/")
+        assert document_store.client._headers["user-agent"].startswith("haystack-py-ds/")
 
     def test_write_documents(self, document_store: ElasticsearchDocumentStore):
         docs = [Document(id="1")]
@@ -308,7 +314,7 @@ class TestDocumentStore(DocumentStoreBaseTests):
         )
         mock_elasticsearch.return_value = mock_client
 
-        ElasticsearchDocumentStore(hosts="some hosts", custom_mapping=custom_mapping)
+        _ = ElasticsearchDocumentStore(hosts="some hosts", custom_mapping=custom_mapping).client
         mock_client.indices.create.assert_called_once_with(
             index="default",
             mappings=custom_mapping,