elasticsearch-haystack 0.1.3__tar.gz → 0.3.0__tar.gz

{elasticsearch_haystack-0.1.3 → elasticsearch_haystack-0.3.0}/PKG-INFO

@@ -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/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-0.1.3 → elasticsearch_haystack-0.3.0}/pyproject.toml

@@ -33,6 +33,9 @@ Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/m
 Issues = "https://github.com/deepset-ai/haystack-core-integrations/issues"
 Source = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/elasticsearch"
 
+[tool.hatch.build.targets.wheel]
+packages = ["src/haystack_integrations"]
+
 [tool.hatch.version]
 source = "vcs"
 tag-pattern = 'integrations\/elasticsearch-v(?P<version>.*)'
@@ -46,6 +49,7 @@ dependencies = [
   "coverage[toml]>=6.5",
   "pytest",
   "pytest-xdist",
+  "haystack-pydoc-tools",
 ]
 [tool.hatch.envs.default.scripts]
 test = "pytest {args:tests}"
@@ -58,6 +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"]
@@ -70,7 +77,7 @@ dependencies = [
   "ruff>=0.0.243",
 ]
 [tool.hatch.envs.lint.scripts]
-typing = "mypy --install-types --non-interactive {args:src/elasticsearch_haystack tests}"
+typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
 style = [
   "ruff {args:.}",
   "black --check --diff {args:.}",
@@ -139,26 +146,23 @@ unfixable = [
 ]
 
 [tool.ruff.isort]
-known-first-party = ["elasticsearch_haystack"]
+known-first-party = ["src"]
 
 [tool.ruff.flake8-tidy-imports]
-ban-relative-imports = "all"
+ban-relative-imports = "parents"
 
 [tool.ruff.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
 "tests/**/*" = ["PLR2004", "S101", "TID252"]
 
 [tool.coverage.run]
-source_pkgs = ["elasticsearch_haystack", "tests"]
+source_pkgs = ["src", "tests"]
 branch = true
 parallel = true
-omit = [
-  "src/elasticsearch_haystack/__about__.py",
-]
 
 [tool.coverage.paths]
-elasticsearch_haystack = ["src/elasticsearch_haystack", "*/elasticsearch-haystack/src/elasticsearch_haystack"]
-tests = ["tests", "*/elasticsearch-haystack/tests"]
+elasticsearch_haystack = ["src/haystack_integrations", "*/elasticsearch/src/haystack_integrations"]
+tests = ["tests", "*/elasticsearch/src/tests"]
 
 [tool.coverage.report]
 exclude_lines = [
@@ -177,6 +181,7 @@ markers = [
 [[tool.mypy.overrides]]
 module = [
   "haystack.*",
+  "haystack_integrations.*",
   "pytest.*"
 ]
 ignore_missing_imports = true

elasticsearch_haystack-0.3.0/src/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-0.1.3/src/elasticsearch_haystack → elasticsearch_haystack-0.3.0/src/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-0.1.3/src/elasticsearch_haystack → elasticsearch_haystack-0.3.0/src/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-0.1.3/src/elasticsearch_haystack → elasticsearch_haystack-0.3.0/src/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-0.1.3/src/elasticsearch_haystack → elasticsearch_haystack-0.3.0/src/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 → elasticsearch_haystack-0.3.0}/tests/test_bm25_retriever.py

@@ -4,9 +4,8 @@
 from unittest.mock import Mock, patch
 
 from haystack.dataclasses import Document
-
-from elasticsearch_haystack.bm25_retriever import ElasticsearchBM25Retriever
-from elasticsearch_haystack.document_store import ElasticsearchDocumentStore
+from haystack_integrations.components.retrievers.elasticsearch import ElasticsearchBM25Retriever
+from haystack_integrations.document_stores.elasticsearch import ElasticsearchDocumentStore
 
 
 def test_init_default():
@@ -18,13 +17,13 @@ def test_init_default():
     assert not retriever._scale_score
 
 
-@patch("elasticsearch_haystack.document_store.Elasticsearch")
+@patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
 def test_to_dict(_mock_elasticsearch_client):
     document_store = ElasticsearchDocumentStore(hosts="some fake host")
     retriever = ElasticsearchBM25Retriever(document_store=document_store)
     res = retriever.to_dict()
     assert res == {
-        "type": "elasticsearch_haystack.bm25_retriever.ElasticsearchBM25Retriever",
+        "type": "haystack_integrations.components.retrievers.elasticsearch.bm25_retriever.ElasticsearchBM25Retriever",
         "init_parameters": {
             "document_store": {
                 "init_parameters": {
@@ -32,7 +31,7 @@ def test_to_dict(_mock_elasticsearch_client):
                     "index": "default",
                     "embedding_similarity_function": "cosine",
                 },
-                "type": "elasticsearch_haystack.document_store.ElasticsearchDocumentStore",
+                "type": "haystack_integrations.document_stores.elasticsearch.document_store.ElasticsearchDocumentStore",
             },
             "filters": {},
             "fuzziness": "AUTO",
@@ -42,14 +41,14 @@ def test_to_dict(_mock_elasticsearch_client):
     }
 
 
-@patch("elasticsearch_haystack.document_store.Elasticsearch")
+@patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
 def test_from_dict(_mock_elasticsearch_client):
     data = {
-        "type": "elasticsearch_haystack.bm25_retriever.ElasticsearchBM25Retriever",
+        "type": "haystack_integrations.components.retrievers.elasticsearch.bm25_retriever.ElasticsearchBM25Retriever",
         "init_parameters": {
             "document_store": {
                 "init_parameters": {"hosts": "some fake host", "index": "default"},
-                "type": "elasticsearch_haystack.document_store.ElasticsearchDocumentStore",
+                "type": "haystack_integrations.document_stores.elasticsearch.document_store.ElasticsearchDocumentStore",
             },
             "filters": {},
             "fuzziness": "AUTO",

{elasticsearch_haystack-0.1.3 → elasticsearch_haystack-0.3.0}/tests/test_document_store.py

@@ -12,10 +12,10 @@ from haystack.dataclasses.document import Document
 from haystack.document_stores.errors import DocumentStoreError, DuplicateDocumentError
 from haystack.document_stores.types import DuplicatePolicy
 from haystack.testing.document_store import DocumentStoreBaseTests
-
-from elasticsearch_haystack.document_store import ElasticsearchDocumentStore
+from haystack_integrations.document_stores.elasticsearch import ElasticsearchDocumentStore
 
 
+@pytest.mark.integration
 class TestDocumentStore(DocumentStoreBaseTests):
     """
     Common test cases will be provided by `DocumentStoreBaseTests` but
@@ -67,12 +67,12 @@ class TestDocumentStore(DocumentStoreBaseTests):
 
         super().assert_documents_are_equal(received, expected)
 
-    @patch("elasticsearch_haystack.document_store.Elasticsearch")
+    @patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
     def test_to_dict(self, _mock_elasticsearch_client):
         document_store = ElasticsearchDocumentStore(hosts="some hosts")
         res = document_store.to_dict()
         assert res == {
-            "type": "elasticsearch_haystack.document_store.ElasticsearchDocumentStore",
+            "type": "haystack_integrations.document_stores.elasticsearch.document_store.ElasticsearchDocumentStore",
             "init_parameters": {
                 "hosts": "some hosts",
                 "index": "default",
@@ -80,10 +80,10 @@ class TestDocumentStore(DocumentStoreBaseTests):
             },
         }
 
-    @patch("elasticsearch_haystack.document_store.Elasticsearch")
+    @patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
     def test_from_dict(self, _mock_elasticsearch_client):
         data = {
-            "type": "elasticsearch_haystack.document_store.ElasticsearchDocumentStore",
+            "type": "haystack_integrations.document_stores.elasticsearch.document_store.ElasticsearchDocumentStore",
             "init_parameters": {
                 "hosts": "some hosts",
                 "index": "default",
@@ -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

{elasticsearch_haystack-0.1.3 → elasticsearch_haystack-0.3.0}/tests/test_embedding_retriever.py

@@ -4,9 +4,8 @@
 from unittest.mock import Mock, patch
 
 from haystack.dataclasses import Document
-
-from elasticsearch_haystack.document_store import ElasticsearchDocumentStore
-from elasticsearch_haystack.embedding_retriever import ElasticsearchEmbeddingRetriever
+from haystack_integrations.components.retrievers.elasticsearch import ElasticsearchEmbeddingRetriever
+from haystack_integrations.document_stores.elasticsearch import ElasticsearchDocumentStore
 
 
 def test_init_default():
@@ -18,13 +17,14 @@ def test_init_default():
     assert retriever._num_candidates is None
 
 
-@patch("elasticsearch_haystack.document_store.Elasticsearch")
+@patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
 def test_to_dict(_mock_elasticsearch_client):
     document_store = ElasticsearchDocumentStore(hosts="some fake host")
     retriever = ElasticsearchEmbeddingRetriever(document_store=document_store)
     res = retriever.to_dict()
+    t = "haystack_integrations.components.retrievers.elasticsearch.embedding_retriever.ElasticsearchEmbeddingRetriever"
     assert res == {
-        "type": "elasticsearch_haystack.embedding_retriever.ElasticsearchEmbeddingRetriever",
+        "type": t,
         "init_parameters": {
             "document_store": {
                 "init_parameters": {
@@ -32,7 +32,7 @@ def test_to_dict(_mock_elasticsearch_client):
                     "index": "default",
                     "embedding_similarity_function": "cosine",
                 },
-                "type": "elasticsearch_haystack.document_store.ElasticsearchDocumentStore",
+                "type": "haystack_integrations.document_stores.elasticsearch.document_store.ElasticsearchDocumentStore",
             },
             "filters": {},
             "top_k": 10,
@@ -41,14 +41,15 @@ def test_to_dict(_mock_elasticsearch_client):
     }
 
 
-@patch("elasticsearch_haystack.document_store.Elasticsearch")
+@patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
 def test_from_dict(_mock_elasticsearch_client):
+    t = "haystack_integrations.components.retrievers.elasticsearch.embedding_retriever.ElasticsearchEmbeddingRetriever"
     data = {
-        "type": "elasticsearch_haystack.embedding_retriever.ElasticsearchEmbeddingRetriever",
+        "type": t,
         "init_parameters": {
             "document_store": {
                 "init_parameters": {"hosts": "some fake host", "index": "default"},
-                "type": "elasticsearch_haystack.document_store.ElasticsearchDocumentStore",
+                "type": "haystack_integrations.document_stores.elasticsearch.document_store.ElasticsearchDocumentStore",
             },
             "filters": {},
             "top_k": 10,

{elasticsearch_haystack-0.1.3 → elasticsearch_haystack-0.3.0}/tests/test_filters.py

@@ -3,8 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 import pytest
 from haystack.errors import FilterError
-
-from elasticsearch_haystack.filters import _normalize_filters, _normalize_ranges
+from haystack_integrations.document_stores.elasticsearch.filters import _normalize_filters, _normalize_ranges
 
 filters_data = [
     (