elasticsearch-haystack 0.1.3__py3-none-any.whl → 0.3.0__py3-none-any.whl

{elasticsearch_haystack-0.1.3.dist-info → elasticsearch_haystack-0.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: elasticsearch-haystack
-Version: 0.1.3
+Version: 0.3.0
 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-0.3.0.dist-info/RECORD

@@ -0,0 +1,10 @@
+haystack_integrations/components/retrievers/elasticsearch/__init__.py,sha256=cSJBsYjz_T4kK-M-auAHVUnYIcgUqqwwQe_hsF0_IG4,307
+haystack_integrations/components/retrievers/elasticsearch/bm25_retriever.py,sha256=qu67WxyTjh1DbEEqg1_IcOkNl0BHtedLFjQVDC0bONE,4398
+haystack_integrations/components/retrievers/elasticsearch/embedding_retriever.py,sha256=6HhfAzOjec9R2PnjWT2hLcIWVEe6-bZuWhULu18gJCE,3513
+haystack_integrations/document_stores/elasticsearch/__init__.py,sha256=YTfu94dtVUBogbJFr1aJrKuaI6-Bw9VuHfPoyU7M8os,207
+haystack_integrations/document_stores/elasticsearch/document_store.py,sha256=qFe9BmXaT6vNOF5EYZ8PNhC6Z1bZVzBoAZ5J2agwcZI,15586
+haystack_integrations/document_stores/elasticsearch/filters.py,sha256=L1tN7YCIDuNdhGrBQdPoqXFk37x__2-K038xZ6PRdNQ,9923
+elasticsearch_haystack-0.3.0.dist-info/METADATA,sha256=P5KpaBuMowYSFu5pf88YxHfyZI0oHJZ-4Z5-tdj7AwE,2105
+elasticsearch_haystack-0.3.0.dist-info/WHEEL,sha256=TJPnKdtrSue7xZ_AVGkp9YXcvDrobsjBds1du3Nx6dc,87
+elasticsearch_haystack-0.3.0.dist-info/licenses/LICENSE,sha256=_M2kulivnaiTHiW-5CRlZrPmH47tt04pBgAgeDvfYi4,11342
+elasticsearch_haystack-0.3.0.dist-info/RECORD,,

{elasticsearch_haystack-0.1.3.dist-info → elasticsearch_haystack-0.3.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.21.0
+Generator: hatchling 1.21.1
 Root-Is-Purelib: true
 Tag: py3-none-any

haystack_integrations/components/retrievers/elasticsearch/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+from .bm25_retriever import ElasticsearchBM25Retriever
+from .embedding_retriever import ElasticsearchEmbeddingRetriever
+
+__all__ = ["ElasticsearchBM25Retriever", "ElasticsearchEmbeddingRetriever"]

{elasticsearch_haystack → haystack_integrations/components/retrievers/elasticsearch}/bm25_retriever.py

@@ -5,8 +5,7 @@ from typing import Any, Dict, List, Optional
 
 from haystack import component, default_from_dict, default_to_dict
 from haystack.dataclasses import Document
-
-from elasticsearch_haystack.document_store import ElasticsearchDocumentStore
+from haystack_integrations.document_stores.elasticsearch.document_store import ElasticsearchDocumentStore
 
 
 @component
@@ -19,8 +18,8 @@ class ElasticsearchBM25Retriever:
     Usage example:
     ```python
     from haystack import Document
-    from elasticsearch_haystack.document_store import ElasticsearchDocumentStore
-    from elasticsearch_haystack.bm25_retriever import ElasticsearchBM25Retriever
+    from haystack_integrations.document_stores.elasticsearch import ElasticsearchDocumentStore
+    from haystack_integrations.components.retrievers.elasticsearch import ElasticsearchBM25Retriever
 
     document_store = ElasticsearchDocumentStore(hosts="http://localhost:9200")
     retriever = ElasticsearchBM25Retriever(document_store=document_store)
@@ -90,17 +89,18 @@ class ElasticsearchBM25Retriever:
         return default_from_dict(cls, data)
 
     @component.output_types(documents=List[Document])
-    def run(self, query: str, top_k: Optional[int] = None):
+    def run(self, query: str, filters: Optional[Dict[str, Any]] = None, top_k: Optional[int] = None):
         """
         Retrieve documents using the BM25 keyword-based algorithm.
 
         :param query: String to search in Documents' text.
+        :param filters: Filters applied to the retrieved Documents.
         :param top_k: Maximum number of Documents to return.
         :return: List of Documents that match the query.
         """
         docs = self._document_store._bm25_retrieval(
             query=query,
-            filters=self._filters,
+            filters=filters or self._filters,
             fuzziness=self._fuzziness,
             top_k=top_k or self._top_k,
             scale_score=self._scale_score,

{elasticsearch_haystack → haystack_integrations/components/retrievers/elasticsearch}/embedding_retriever.py

@@ -5,8 +5,7 @@ from typing import Any, Dict, List, Optional
 
 from haystack import component, default_from_dict, default_to_dict
 from haystack.dataclasses import Document
-
-from elasticsearch_haystack.document_store import ElasticsearchDocumentStore
+from haystack_integrations.document_stores.elasticsearch.document_store import ElasticsearchDocumentStore
 
 
 @component
@@ -64,17 +63,18 @@ class ElasticsearchEmbeddingRetriever:
         return default_from_dict(cls, data)
 
     @component.output_types(documents=List[Document])
-    def run(self, query_embedding: List[float], top_k: Optional[int] = None):
+    def run(self, query_embedding: List[float], filters: Optional[Dict[str, Any]] = None, top_k: Optional[int] = None):
         """
         Retrieve documents using a vector similarity metric.
 
         :param query_embedding: Embedding of the query.
+        :param filters: Filters applied to the retrieved Documents.
         :param top_k: Maximum number of Documents to return.
         :return: List of Documents similar to `query_embedding`.
         """
         docs = self._document_store._embedding_retrieval(
             query_embedding=query_embedding,
-            filters=self._filters,
+            filters=filters or self._filters,
             top_k=top_k or self._top_k,
             num_candidates=self._num_candidates,
         )

{elasticsearch_haystack → haystack_integrations/document_stores/elasticsearch}/__init__.py

@@ -1,6 +1,6 @@
 # SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
-from elasticsearch_haystack.document_store import ElasticsearchDocumentStore
+from .document_store import ElasticsearchDocumentStore
 
 __all__ = ["ElasticsearchDocumentStore"]

{elasticsearch_haystack → haystack_integrations/document_stores/elasticsearch}/document_store.py

@@ -8,14 +8,16 @@ import numpy as np
 
 # There are no import stubs for elastic_transport and elasticsearch so mypy fails
 from elastic_transport import NodeConfig  # type: ignore[import-not-found]
-from elasticsearch import Elasticsearch, helpers  # type: ignore[import-not-found]
 from haystack import default_from_dict, default_to_dict
 from haystack.dataclasses import Document
 from haystack.document_stores.errors import DocumentStoreError, DuplicateDocumentError
 from haystack.document_stores.types import DuplicatePolicy
 from haystack.utils.filters import convert
+from haystack.version import __version__ as haystack_version
+
+from elasticsearch import Elasticsearch, helpers  # type: ignore[import-not-found]
 
-from elasticsearch_haystack.filters import _normalize_filters
+from .filters import _normalize_filters
 
 logger = logging.getLogger(__name__)
 
@@ -89,7 +91,11 @@ class ElasticsearchDocumentStore:
         :param **kwargs: Optional arguments that ``Elasticsearch`` takes.
         """
         self._hosts = hosts
-        self._client = Elasticsearch(hosts, **kwargs)
+        self._client = Elasticsearch(
+            hosts,
+            headers={"user-agent": f"haystack-py-ds/{haystack_version}"},
+            **kwargs,
+        )
         self._index = index
         self._embedding_similarity_function = embedding_similarity_function
         self._kwargs = kwargs

elasticsearch_haystack-0.1.3.dist-info/RECORD

@@ -1,9 +0,0 @@
-elasticsearch_haystack/__init__.py,sha256=g4FvBDxgCM32ZF9JwRne61b3yhs5-KA9qLta-YtMCQE,229
-elasticsearch_haystack/bm25_retriever.py,sha256=eL_vUy8SYl5_LJytbgCbQH-jCmYjLEcw9YJnvV-IHcE,4215
-elasticsearch_haystack/document_store.py,sha256=rHCQ3mSYOJDqXN4ghiL0hqIXzpBPySL2xwffX1cLfmA,15437
-elasticsearch_haystack/embedding_retriever.py,sha256=C4su5erlQINxNqnPxnshUkvnwT1J1rs94jHTPA2VU68,3364
-elasticsearch_haystack/filters.py,sha256=L1tN7YCIDuNdhGrBQdPoqXFk37x__2-K038xZ6PRdNQ,9923
-elasticsearch_haystack-0.1.3.dist-info/METADATA,sha256=gRoQqQJcXhG7Emrx4yg7cR84PRlB3sTHttAT40PAJuc,2105
-elasticsearch_haystack-0.1.3.dist-info/WHEEL,sha256=mRYSEL3Ih6g5a_CVMIcwiF__0Ae4_gLYh01YFNwiq1k,87
-elasticsearch_haystack-0.1.3.dist-info/licenses/LICENSE,sha256=_M2kulivnaiTHiW-5CRlZrPmH47tt04pBgAgeDvfYi4,11342
-elasticsearch_haystack-0.1.3.dist-info/RECORD,,