elasticsearch-haystack 0.4.0__py3-none-any.whl → 0.5.0__py3-none-any.whl

{elasticsearch_haystack-0.4.0.dist-info → elasticsearch_haystack-0.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: elasticsearch-haystack
-Version: 0.4.0
+Version: 0.5.0
 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
@@ -9,6 +9,7 @@ Author-email: Silvano Cerza <silvanocerza@gmail.com>
 License-Expression: Apache-2.0
 License-File: LICENSE
 Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9

{elasticsearch_haystack-0.4.0.dist-info → elasticsearch_haystack-0.5.0.dist-info}/RECORD

@@ -2,9 +2,9 @@ haystack_integrations/components/retrievers/elasticsearch/__init__.py,sha256=cSJ
 haystack_integrations/components/retrievers/elasticsearch/bm25_retriever.py,sha256=fFx554MTcUHnQZa2SgC0PzIR85YVbqAdMNOiXKkVSu8,4849
 haystack_integrations/components/retrievers/elasticsearch/embedding_retriever.py,sha256=RcIbSMELiKIJsD-8F_u76J33YRt5bLr6lHnoX-hVQ1M,4990
 haystack_integrations/document_stores/elasticsearch/__init__.py,sha256=YTfu94dtVUBogbJFr1aJrKuaI6-Bw9VuHfPoyU7M8os,207
-haystack_integrations/document_stores/elasticsearch/document_store.py,sha256=m_NvCRt0xQhVuTdkfxaqql4sB7qVDyYc8f9LaWMoLyA,17688
+haystack_integrations/document_stores/elasticsearch/document_store.py,sha256=XMbrn-dsRw0HS8mPMreGCO3cRQnwwU_UA3OzWb3pi_4,18304
 haystack_integrations/document_stores/elasticsearch/filters.py,sha256=L1tN7YCIDuNdhGrBQdPoqXFk37x__2-K038xZ6PRdNQ,9923
-elasticsearch_haystack-0.4.0.dist-info/METADATA,sha256=sHF3d2RaJjZ8DQ8W7Vm1e8iZN01W8BjlsPIUkrpF8yg,2105
-elasticsearch_haystack-0.4.0.dist-info/WHEEL,sha256=uNdcs2TADwSd5pVaP0Z_kcjcvvTUklh2S7bxZMF8Uj0,87
-elasticsearch_haystack-0.4.0.dist-info/licenses/LICENSE,sha256=_M2kulivnaiTHiW-5CRlZrPmH47tt04pBgAgeDvfYi4,11342
-elasticsearch_haystack-0.4.0.dist-info/RECORD,,
+elasticsearch_haystack-0.5.0.dist-info/METADATA,sha256=bKt2Am26Ey5iq0ZQw7JOeBSu_Em7-e9iDdl1eHqCt08,2168
+elasticsearch_haystack-0.5.0.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+elasticsearch_haystack-0.5.0.dist-info/licenses/LICENSE,sha256=_M2kulivnaiTHiW-5CRlZrPmH47tt04pBgAgeDvfYi4,11342
+elasticsearch_haystack-0.5.0.dist-info/RECORD,,

{elasticsearch_haystack-0.4.0.dist-info → elasticsearch_haystack-0.5.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.22.4
+Generator: hatchling 1.24.2
 Root-Is-Purelib: true
 Tag: py3-none-any

haystack_integrations/document_stores/elasticsearch/document_store.py

@@ -63,6 +63,7 @@ class ElasticsearchDocumentStore:
         self,
         *,
         hosts: Optional[Hosts] = None,
+        custom_mapping: Optional[Dict[str, Any]] = None,
         index: str = "default",
         embedding_similarity_function: Literal["cosine", "dot_product", "l2_norm", "max_inner_product"] = "cosine",
         **kwargs,
@@ -82,6 +83,7 @@ class ElasticsearchDocumentStore:
         [reference](https://elasticsearch-py.readthedocs.io/en/stable/api.html#module-elasticsearch)
 
         :param hosts: List of hosts running the Elasticsearch client.
+        :param custom_mapping: Custom mapping for the index. If not provided, a default mapping will be used.
         :param index: Name of index in Elasticsearch.
         :param embedding_similarity_function: The similarity function used to compare Documents embeddings.
             This parameter only takes effect if the index does not yet exist and is created.
@@ -98,29 +100,37 @@ class ElasticsearchDocumentStore:
         )
         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()
 
-        # configure mapping for the embedding field
-        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",
-                        },
+        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",
+                            },
+                        }
                     }
-                }
-            ],
-        }
+                ],
+            }
 
         # Create the index if it doesn't exist
         if not self._client.indices.exists(index=index):
@@ -139,6 +149,7 @@ class ElasticsearchDocumentStore:
         return default_to_dict(
             self,
             hosts=self._hosts,
+            custom_mapping=self._custom_mapping,
             index=self._index,
             embedding_similarity_function=self._embedding_similarity_function,
             **self._kwargs,