elasticsearch-haystack 0.2.0__tar.gz → 0.3.0__tar.gz

{elasticsearch_haystack-0.2.0 → elasticsearch_haystack-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: elasticsearch-haystack
-Version: 0.2.0
+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/pydoc/config.yml

@@ -0,0 +1,31 @@
+loaders:
+  - type: haystack_pydoc_tools.loaders.CustomPythonLoader
+    search_path: [../src]
+    modules: [
+      "haystack_integrations.components.retrievers.elasticsearch.bm25_retriever",
+      "haystack_integrations.components.retrievers.elasticsearch.embedding_retriever",
+      "haystack_integrations.document_stores.elasticsearch.document_store",
+      "haystack_integrations.document_stores.elasticsearch.filters",
+    ]
+    ignore_when_discovered: ["__init__"]
+processors:
+  - type: filter
+    expression:
+    documented_only: true
+    do_not_filter_modules: false
+    skip_empty_modules: true
+  - type: smart
+  - type: crossref
+renderer:
+  type: haystack_pydoc_tools.renderers.ReadmePreviewRenderer
+  excerpt: Elasticsearch integration for Haystack
+  category_slug: integrations-api
+  title: Elasticsearch
+  slug: integrations-elasticsearch
+  order: 70
+  markdown:
+    descriptive_class_title: false
+    descriptive_module_title: true
+    add_method_class_prefix: true
+    add_member_class_prefix: false
+    filename: _readme_elasticsearch.md

{elasticsearch_haystack-0.2.0 → elasticsearch_haystack-0.3.0}/pyproject.toml

@@ -49,6 +49,7 @@ dependencies = [
   "coverage[toml]>=6.5",
   "pytest",
   "pytest-xdist",
+  "haystack-pydoc-tools",
 ]
 [tool.hatch.envs.default.scripts]
 test = "pytest {args:tests}"
@@ -61,6 +62,9 @@ cov = [
   "test-cov",
   "cov-report",
 ]
+docs = [
+  "pydoc-markdown pydoc/config.yml"
+]
 
 [[tool.hatch.envs.all.matrix]]
 python = ["3.8", "3.9", "3.10", "3.11"]

{elasticsearch_haystack-0.2.0 → elasticsearch_haystack-0.3.0}/src/haystack_integrations/components/retrievers/elasticsearch/bm25_retriever.py

@@ -89,17 +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-0.2.0 → elasticsearch_haystack-0.3.0}/src/haystack_integrations/components/retrievers/elasticsearch/embedding_retriever.py

@@ -63,17 +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-0.2.0 → elasticsearch_haystack-0.3.0}/src/haystack_integrations/document_stores/elasticsearch/document_store.py

@@ -13,6 +13,7 @@ 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]
 
@@ -90,7 +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-0.2.0 → elasticsearch_haystack-0.3.0}/tests/test_document_store.py

@@ -95,6 +95,9 @@ class TestDocumentStore(DocumentStoreBaseTests):
         assert document_store._index == "default"
         assert document_store._embedding_similarity_function == "cosine"
 
+    def test_user_agent_header(self, document_store: ElasticsearchDocumentStore):
+        assert document_store._client._headers["user-agent"].startswith("haystack-py-ds/")
+
     def test_write_documents(self, document_store: ElasticsearchDocumentStore):
         docs = [Document(id="1")]
         assert document_store.write_documents(docs) == 1