elasticsearch-haystack 0.7.1__tar.gz → 1.0.1__tar.gz

{elasticsearch_haystack-0.7.1 → elasticsearch_haystack-1.0.1}/CHANGELOG.md

@@ -1,10 +1,25 @@
 # Changelog
 
-## [unreleased]
+## [integrations/elasticsearch-v1.0.0] - 2024-09-12
 
 ### 🚀 Features
 
 - Defer the database connection to when it's needed (#766)
+- Add filter_policy to elasticsearch integration (#825)
+
+### 🐛 Bug Fixes
+
+- `ElasticSearch` - Fallback to default filter policy when deserializing retrievers without the init parameter (#898)
+
+### 🧪 Testing
+
+- Do not retry tests in `hatch run test` command (#954)
+
+### ⚙️ Miscellaneous Tasks
+
+- Retry tests to reduce flakyness (#836)
+- Update ruff invocation to include check parameter (#853)
+- ElasticSearch - remove legacy filters elasticsearch (#1078)
 
 ## [integrations/elasticsearch-v0.5.0] - 2024-05-24
 

{elasticsearch_haystack-0.7.1 → elasticsearch_haystack-1.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: elasticsearch-haystack
-Version: 0.7.1
+Version: 1.0.1
 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-0.7.1 → elasticsearch_haystack-1.0.1}/pyproject.toml

@@ -41,6 +41,7 @@ root = "../.."
 git_describe_command = 'git describe --tags --match="integrations/elasticsearch-v[0-9]*"'
 
 [tool.hatch.envs.default]
+installer = "uv"
 dependencies = [
   "coverage[toml]>=6.5",
   "pytest",
@@ -49,22 +50,25 @@ dependencies = [
   "haystack-pydoc-tools",
 ]
 [tool.hatch.envs.default.scripts]
-test = "pytest --reruns 3 --reruns-delay 30 -x {args:tests}"
-test-cov = "coverage run -m pytest --reruns 3 --reruns-delay 30 -x {args:tests}"
+test = "pytest {args:tests}"
+test-cov = "coverage run -m pytest {args:tests}"
+test-cov-retry = "test-cov --reruns 3 --reruns-delay 30 -x"
 cov-report = ["- coverage combine", "coverage report"]
 cov = ["test-cov", "cov-report"]
+cov-retry = ["test-cov-retry", "cov-report"]
 docs = ["pydoc-markdown pydoc/config.yml"]
 
 [[tool.hatch.envs.all.matrix]]
 python = ["3.8", "3.9", "3.10", "3.11"]
 
 [tool.hatch.envs.lint]
+installer = "uv"
 detached = true
-dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
+dependencies = ["pip", "black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = ["ruff check {args:.}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
+style = ["ruff check {args:}", "black --check --diff {args:.}"]
+fmt = ["black {args:.}", "ruff check --fix {args:}", "style"]
 all = ["style", "typing"]
 
 [tool.hatch.metadata]
@@ -78,6 +82,8 @@ skip-string-normalization = true
 [tool.ruff]
 target-version = "py38"
 line-length = 120
+
+[tool.ruff.lint]
 select = [
   "A",
   "ARG",
@@ -126,13 +132,13 @@ unfixable = [
   "F401",
 ]
 
-[tool.ruff.isort]
-known-first-party = ["src"]
+[tool.ruff.lint.isort]
+known-first-party = ["haystack_integrations"]
 
-[tool.ruff.flake8-tidy-imports]
+[tool.ruff.lint.flake8-tidy-imports]
 ban-relative-imports = "parents"
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
 "tests/**/*" = ["PLR2004", "S101", "TID252"]
 

{elasticsearch_haystack-0.7.1 → elasticsearch_haystack-1.0.1}/src/haystack_integrations/components/retrievers/elasticsearch/bm25_retriever.py

@@ -7,6 +7,7 @@ from haystack import component, default_from_dict, default_to_dict
 from haystack.dataclasses import Document
 from haystack.document_stores.types import FilterPolicy
 from haystack.document_stores.types.filter_policy import apply_filter_policy
+
 from haystack_integrations.document_stores.elasticsearch.document_store import ElasticsearchDocumentStore
 
 

{elasticsearch_haystack-0.7.1 → elasticsearch_haystack-1.0.1}/src/haystack_integrations/components/retrievers/elasticsearch/embedding_retriever.py

@@ -7,6 +7,7 @@ from haystack import component, default_from_dict, default_to_dict
 from haystack.dataclasses import Document
 from haystack.document_stores.types import FilterPolicy
 from haystack.document_stores.types.filter_policy import apply_filter_policy
+
 from haystack_integrations.document_stores.elasticsearch.document_store import ElasticsearchDocumentStore
 
 

{elasticsearch_haystack-0.7.1 → elasticsearch_haystack-1.0.1}/src/haystack_integrations/document_stores/elasticsearch/document_store.py

@@ -12,7 +12,6 @@ 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]
@@ -106,9 +105,12 @@ class ElasticsearchDocumentStore:
     @property
     def client(self) -> Elasticsearch:
         if self._client is None:
+            headers = self._kwargs.pop("headers", {})
+            headers["user-agent"] = f"haystack-py-ds/{haystack_version}"
+
             client = Elasticsearch(
                 self._hosts,
-                headers={"user-agent": f"haystack-py-ds/{haystack_version}"},
+                headers=headers,
                 **self._kwargs,
             )
             # Check client connection, this will raise if not connected
@@ -224,7 +226,8 @@ class ElasticsearchDocumentStore:
         :returns: List of `Document`s that match the filters.
         """
         if filters and "operator" not in filters and "conditions" not in filters:
-            filters = convert(filters)
+            msg = "Invalid filter syntax. See https://docs.haystack.deepset.ai/docs/metadata-filtering for details."
+            raise ValueError(msg)
 
         query = {"bool": {"filter": _normalize_filters(filters)}} if filters else None
         documents = self._search_documents(query=query)

{elasticsearch_haystack-0.7.1 → elasticsearch_haystack-1.0.1}/tests/test_bm25_retriever.py

@@ -6,6 +6,7 @@ from unittest.mock import Mock, patch
 import pytest
 from haystack.dataclasses import Document
 from haystack.document_stores.types import FilterPolicy
+
 from haystack_integrations.components.retrievers.elasticsearch import ElasticsearchBM25Retriever
 from haystack_integrations.document_stores.elasticsearch import ElasticsearchDocumentStore
 

{elasticsearch_haystack-0.7.1 → elasticsearch_haystack-1.0.1}/tests/test_document_store.py

@@ -12,6 +12,7 @@ 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 haystack_integrations.document_stores.elasticsearch import ElasticsearchDocumentStore
 
 
@@ -21,6 +22,20 @@ def test_init_is_lazy(_mock_es_client):
     _mock_es_client.assert_not_called()
 
 
+@patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
+def test_headers_are_supported(_mock_es_client):
+    _ = ElasticsearchDocumentStore(hosts="testhost", headers={"header1": "value1", "header2": "value2"}).client
+
+    assert _mock_es_client.call_count == 1
+    _, kwargs = _mock_es_client.call_args
+
+    headers_found = kwargs["headers"]
+    assert headers_found["header1"] == "value1"
+    assert headers_found["header2"] == "value2"
+
+    assert headers_found["user-agent"].startswith("haystack-py-ds/")
+
+
 @patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
 def test_to_dict(_mock_elasticsearch_client):
     document_store = ElasticsearchDocumentStore(hosts="some hosts")

{elasticsearch_haystack-0.7.1 → elasticsearch_haystack-1.0.1}/tests/test_embedding_retriever.py

@@ -6,6 +6,7 @@ from unittest.mock import Mock, patch
 import pytest
 from haystack.dataclasses import Document
 from haystack.document_stores.types import FilterPolicy
+
 from haystack_integrations.components.retrievers.elasticsearch import ElasticsearchEmbeddingRetriever
 from haystack_integrations.document_stores.elasticsearch import ElasticsearchDocumentStore
 

{elasticsearch_haystack-0.7.1 → elasticsearch_haystack-1.0.1}/tests/test_filters.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 import pytest
 from haystack.errors import FilterError
+
 from haystack_integrations.document_stores.elasticsearch.filters import _normalize_filters, _normalize_ranges
 
 filters_data = [