elasticsearch-haystack 3.0.1__tar.gz → 3.1.0__tar.gz

{elasticsearch_haystack-3.0.1 → elasticsearch_haystack-3.1.0}/CHANGELOG.md

@@ -1,7 +1,19 @@
 # Changelog
 
+## [integrations/elasticsearch-v3.0.1] - 2025-05-27
+
+
+### ⚙️ CI
+
+- Review testing workflows (#1541)
+
+### 🌀 Miscellaneous
+
+- Pining lower versions of haystack and `aiohttp` for `ElasticSearch` (#1827)
+
 ## [integrations/elasticsearch-v3.0.0] - 2025-03-11
 
+
 ### 🧹 Chores
 
 - Use Haystack logging across integrations (#1484)
@@ -21,9 +33,6 @@
 
 - Remove Python 3.8 support (#1421)
 
-### 🌀 Miscellaneous
-
-- Docs: update changelog for integrations/elasticsearch (#1400)
 
 ## [integrations/elasticsearch-v2.0.0] - 2025-02-14
 

{elasticsearch_haystack-3.0.1 → elasticsearch_haystack-3.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: elasticsearch-haystack
-Version: 3.0.1
+Version: 3.1.0
 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
@@ -50,7 +50,7 @@ docker-compose up
 Then run tests:
 
 ```console
-hatch run test
+hatch run test:all
 ```
 
 ## License

{elasticsearch_haystack-3.0.1 → elasticsearch_haystack-3.1.0}/README.md

@@ -24,7 +24,7 @@ docker-compose up
 Then run tests:
 
 ```console
-hatch run test
+hatch run test:all
 ```
 
 ## License

{elasticsearch_haystack-3.0.1 → elasticsearch_haystack-3.1.0}/pyproject.toml

@@ -47,33 +47,37 @@ git_describe_command = 'git describe --tags --match="integrations/elasticsearch-
 
 [tool.hatch.envs.default]
 installer = "uv"
-dependencies = [
-  "coverage[toml]>=6.5",
-  "pytest",
-  "pytest-asyncio",
-  "pytest-rerunfailures",
-  "pytest-xdist",
-  "haystack-pydoc-tools",
-]
+dependencies = ["haystack-pydoc-tools", "ruff"]
+
 [tool.hatch.envs.default.scripts]
-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"]
+fmt = "ruff check --fix {args} && ruff format {args}"
+fmt-check = "ruff check {args} && ruff format --check {args}"
 
-[tool.hatch.envs.lint]
-installer = "uv"
-detached = true
-dependencies = ["pip", "black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
+[tool.hatch.envs.test]
+dependencies = [
+    "pytest",
+    "pytest-asyncio",
+    "pytest-cov",
+    "pytest-rerunfailures",
+    "mypy",
+    "pip"
+]
+
+[tool.hatch.envs.test.scripts]
+unit = 'pytest -m "not integration" {args:tests}'
+integration = 'pytest -m "integration" {args:tests}'
+all = 'pytest {args:tests}'
+cov-retry = 'all --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x'
+
+types = """mypy -p haystack_integrations.document_stores.elasticsearch \
+-p haystack_integrations.components.retrievers.elasticsearch {args}"""
 
-[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 check --fix {args:}", "style"]
-all = ["style", "typing"]
+[tool.mypy]
+install_types = true
+non_interactive = true
+check_untyped_defs = true
+disallow_incomplete_defs = true
 
 [tool.hatch.metadata]
 allow-direct-references = true
@@ -164,6 +168,3 @@ markers = ["unit: unit tests", "integration: integration tests"]
 asyncio_mode = "auto"
 asyncio_default_fixture_loop_scope = "class"
 
-[[tool.mypy.overrides]]
-module = ["haystack.*", "haystack_integrations.*", "numpy.*", "pytest.*"]
-ignore_missing_imports = true

{elasticsearch_haystack-3.0.1 → elasticsearch_haystack-3.1.0}/src/haystack_integrations/components/retrievers/elasticsearch/bm25_retriever.py

@@ -116,7 +116,9 @@ class ElasticsearchBM25Retriever:
         return default_from_dict(cls, data)
 
     @component.output_types(documents=List[Document])
-    def run(self, query: str, filters: Optional[Dict[str, Any]] = None, top_k: Optional[int] = None):
+    def run(
+        self, query: str, filters: Optional[Dict[str, Any]] = None, top_k: Optional[int] = None
+    ) -> Dict[str, List[Document]]:
         """
         Retrieve documents using the BM25 keyword-based algorithm.
 
@@ -139,7 +141,9 @@ class ElasticsearchBM25Retriever:
         return {"documents": docs}
 
     @component.output_types(documents=List[Document])
-    async def run_async(self, query: str, filters: Optional[Dict[str, Any]] = None, top_k: Optional[int] = None):
+    async def run_async(
+        self, query: str, filters: Optional[Dict[str, Any]] = None, top_k: Optional[int] = None
+    ) -> Dict[str, List[Document]]:
         """
         Asynchronously retrieve documents using the BM25 keyword-based algorithm.
 

{elasticsearch_haystack-3.0.1 → elasticsearch_haystack-3.1.0}/src/haystack_integrations/components/retrievers/elasticsearch/embedding_retriever.py

@@ -114,7 +114,9 @@ class ElasticsearchEmbeddingRetriever:
         return default_from_dict(cls, data)
 
     @component.output_types(documents=List[Document])
-    def run(self, query_embedding: List[float], filters: Optional[Dict[str, Any]] = None, top_k: Optional[int] = None):
+    def run(
+        self, query_embedding: List[float], filters: Optional[Dict[str, Any]] = None, top_k: Optional[int] = None
+    ) -> Dict[str, List[Document]]:
         """
         Retrieve documents using a vector similarity metric.
 
@@ -139,7 +141,7 @@ class ElasticsearchEmbeddingRetriever:
     @component.output_types(documents=List[Document])
     async def run_async(
         self, query_embedding: List[float], filters: Optional[Dict[str, Any]] = None, top_k: Optional[int] = None
-    ):
+    ) -> Dict[str, List[Document]]:
         """
         Asynchronously retrieve documents using a vector similarity metric.
 

{elasticsearch_haystack-3.0.1 → elasticsearch_haystack-3.1.0}/src/haystack_integrations/document_stores/elasticsearch/document_store.py

@@ -5,16 +5,14 @@ from collections.abc import Mapping
 from typing import Any, Dict, List, Literal, Optional, Union
 
 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 elastic_transport import NodeConfig
 from haystack import default_from_dict, default_to_dict, logging
 from haystack.dataclasses import Document
 from haystack.document_stores.errors import DocumentStoreError, DuplicateDocumentError
 from haystack.document_stores.types import DuplicatePolicy
 from haystack.version import __version__ as haystack_version
 
-from elasticsearch import AsyncElasticsearch, Elasticsearch, helpers  # type: ignore[import-not-found]
+from elasticsearch import AsyncElasticsearch, Elasticsearch, helpers
 
 from .filters import _normalize_filters
 
@@ -66,7 +64,7 @@ class ElasticsearchDocumentStore:
         custom_mapping: Optional[Dict[str, Any]] = None,
         index: str = "default",
         embedding_similarity_function: Literal["cosine", "dot_product", "l2_norm", "max_inner_product"] = "cosine",
-        **kwargs,
+        **kwargs: Any,
     ):
         """
         Creates a new ElasticsearchDocumentStore instance.
@@ -93,8 +91,8 @@ class ElasticsearchDocumentStore:
         :param **kwargs: Optional arguments that `Elasticsearch` takes.
         """
         self._hosts = hosts
-        self._client = None
-        self._async_client = None
+        self._client: Optional[Elasticsearch] = None
+        self._async_client: Optional[AsyncElasticsearch] = None
         self._index = index
         self._embedding_similarity_function = embedding_similarity_function
         self._custom_mapping = custom_mapping
@@ -166,6 +164,7 @@ class ElasticsearchDocumentStore:
         Returns the synchronous Elasticsearch client, initializing it if necessary.
         """
         self._ensure_initialized()
+        assert self._client is not None  # noqa: S101
         return self._client
 
     @property
@@ -174,6 +173,7 @@ class ElasticsearchDocumentStore:
         Returns the asynchronous Elasticsearch client, initializing it if necessary.
         """
         self._ensure_initialized()
+        assert self._async_client is not None  # noqa: S101
         return self._async_client
 
     def to_dict(self) -> Dict[str, Any]:
@@ -226,7 +226,7 @@ class ElasticsearchDocumentStore:
         result = await self._async_client.count(index=self._index)  # type: ignore
         return result["count"]
 
-    def _search_documents(self, **kwargs) -> List[Document]:
+    def _search_documents(self, **kwargs: Any) -> List[Document]:
         """
         Calls the Elasticsearch client's search method and handles pagination.
         """
@@ -253,7 +253,7 @@ class ElasticsearchDocumentStore:
                 break
         return documents
 
-    async def _search_documents_async(self, **kwargs) -> List[Document]:
+    async def _search_documents_async(self, **kwargs: Any) -> List[Document]:
         """
         Asynchronously calls the Elasticsearch client's search method and handles pagination.
         """
@@ -379,9 +379,12 @@ class ElasticsearchDocumentStore:
             refresh="wait_for",
             index=self._index,
             raise_on_error=False,
+            stats_only=False,
         )
 
         if errors:
+            # with stats_only=False, errors is guaranteed to be a list of dicts
+            assert isinstance(errors, list)  # noqa: S101
             duplicate_errors_ids = []
             other_errors = []
             for e in errors:
@@ -451,13 +454,16 @@ class ElasticsearchDocumentStore:
 
         try:
             success, failed = await helpers.async_bulk(
-                client=self._async_client,
+                client=self.async_client,
                 actions=actions,
                 index=self._index,
                 refresh=True,
                 raise_on_error=False,
+                stats_only=False,
             )
             if failed:
+                # with stats_only=False, failed is guaranteed to be a list of dicts
+                assert isinstance(failed, list)  # noqa: S101
                 if policy == DuplicatePolicy.FAIL:
                     for error in failed:
                         if "create" in error and error["create"]["status"] == DOC_ALREADY_EXISTS:
@@ -494,7 +500,7 @@ class ElasticsearchDocumentStore:
 
         try:
             await helpers.async_bulk(
-                client=self._async_client,
+                client=self.async_client,
                 actions=({"_op_type": "delete", "_id": id_} for id_ in document_ids),
                 index=self._index,
                 refresh=True,
@@ -551,6 +557,8 @@ class ElasticsearchDocumentStore:
 
         if scale_score:
             for doc in documents:
+                if doc.score is None:
+                    continue
                 doc.score = float(1 / (1 + np.exp(-np.asarray(doc.score / BM25_SCALING_FACTOR))))
 
         return documents

{elasticsearch_haystack-3.0.1 → elasticsearch_haystack-3.1.0}/tests/test_document_store.py

@@ -342,7 +342,6 @@ class TestDocumentStore(DocumentStoreBaseTests):
 
 @pytest.mark.integration
 class TestElasticsearchDocumentStoreAsync:
-
     @pytest.fixture
     async def document_store(self, request):
         """
@@ -410,7 +409,6 @@ class TestElasticsearchDocumentStoreAsync:
 
     @pytest.mark.asyncio
     async def test_embedding_retrieval_async(self, document_store):
-
         # init document store
         docs = [
             Document(content="Most similar document", embedding=[1.0, 1.0, 1.0, 1.0]),