elasticsearch-haystack 1.0.1__tar.gz → 2.1.0__tar.gz

elasticsearch_haystack-2.1.0/CHANGELOG.md

@@ -0,0 +1,152 @@
+# Changelog
+
+## [integrations/elasticsearch-v2.0.0] - 2025-02-14
+
+### 🧹 Chores
+
+- Inherit from `FilterDocumentsTestWithDataframe` in Document Stores (#1290)
+- [**breaking**] Elasticsearch - remove dataframe support (#1377)
+
+
+## [integrations/elasticsearch-v1.0.1] - 2024-10-28
+
+### ⚙️ CI
+
+- Adopt uv as installer (#1142)
+
+### 🧹 Chores
+
+- Update changelog after removing legacy filters (#1083)
+- Update ruff linting scripts and settings (#1105)
+
+### 🌀 Miscellaneous
+
+- Fix: Elasticsearch - allow passing headers (#1156)
+
+## [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)
+
+### ⚙️ CI
+
+- Retry tests to reduce flakyness (#836)
+
+### 🧹 Chores
+
+- Update ruff invocation to include check parameter (#853)
+- ElasticSearch - remove legacy filters elasticsearch (#1078)
+
+### 🌀 Miscellaneous
+
+- Ci: install `pytest-rerunfailures` where needed; add retry config to `test-cov` script (#845)
+- Chore: Minor retriever pydoc fix (#884)
+- Chore: elasticsearch - ruff update, don't ruff tests (#999)
+
+## [integrations/elasticsearch-v0.5.0] - 2024-05-24
+
+### 🐛 Bug Fixes
+
+- Add support for custom mapping in ElasticsearchDocumentStore (#721)
+
+### 🌀 Miscellaneous
+
+- Chore: add license classifiers (#680)
+- Chore: change the pydoc renderer class (#718)
+
+## [integrations/elasticsearch-v0.4.0] - 2024-04-03
+
+### 📚 Documentation
+
+- Docstring update  (#525)
+- Review Elastic (#541)
+- Disable-class-def (#556)
+
+### 🌀 Miscellaneous
+
+- Make tests show coverage (#566)
+- Refactor tests (#574)
+- Remove references to Python 3.7 (#601)
+- Make Document Stores initially skip `SparseEmbedding` (#606)
+- [Elasticsearch] fix: Filters not working with metadata that contain a space or capitalization (#639)
+
+## [integrations/elasticsearch-v0.3.0] - 2024-02-23
+
+### 🐛 Bug Fixes
+
+- Fix order of API docs (#447)
+
+### 📚 Documentation
+
+- Update category slug (#442)
+
+### 🌀 Miscellaneous
+
+- Generate api docs (#322)
+- Add filters to run function in retrievers of elasticsearch (#440)
+- Add user-agent header (#457)
+
+## [integrations/elasticsearch-v0.2.0] - 2024-01-19
+
+### 🌀 Miscellaneous
+
+- Mount import paths under haystack_integrations (#244)
+
+## [integrations/elasticsearch-v0.1.3] - 2024-01-18
+
+### 🌀 Miscellaneous
+
+- Added top_k argument in the run function of ElasticSearcBM25Retriever (#130)
+- Add more docstrings for `ElasticsearchDocumentStore` and `ElasticsearchBM25Retriever` (#184)
+- Elastic - update imports for beta5 (#238)
+
+## [integrations/elasticsearch-v0.1.2] - 2023-12-20
+
+### 🐛 Bug Fixes
+
+- Fix project URLs (#96)
+
+### 🚜 Refactor
+
+- Use `hatch_vcs` to manage integrations versioning (#103)
+
+### 🌀 Miscellaneous
+
+- Update elasticsearch test badge (#79)
+- [Elasticsearch] - BM25 retrieval: not all terms must mandatorily match (#125)
+
+## [integrations/elasticsearch-v0.1.1] - 2023-12-05
+
+### 🐛 Bug Fixes
+
+- Document Stores: fix protocol import (#77)
+
+## [integrations/elasticsearch-v0.1.0] - 2023-12-04
+
+### 🐛 Bug Fixes
+
+- Fix license headers
+
+### 🌀 Miscellaneous
+
+- Remove Document Store decorator (#76)
+
+## [integrations/elasticsearch-v0.0.2] - 2023-11-29
+
+### 🌀 Miscellaneous
+
+- Reorganize repository (#62)
+- Update `ElasticSearchDocumentStore` to use latest `haystack-ai` version (#63)
+- Bump elasticsearch_haystack to 0.0.2
+
+<!-- generated by git-cliff -->

{elasticsearch_haystack-1.0.1 → elasticsearch_haystack-2.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: elasticsearch-haystack
-Version: 1.0.1
+Version: 2.1.0
 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
@@ -11,13 +11,12 @@ License-File: LICENSE
 Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
-Requires-Python: >=3.8
+Requires-Python: >=3.9
 Requires-Dist: elasticsearch<9,>=8
 Requires-Dist: haystack-ai
 Description-Content-Type: text/markdown

{elasticsearch_haystack-1.0.1 → elasticsearch_haystack-2.1.0}/pyproject.toml

@@ -7,7 +7,7 @@ name = "elasticsearch-haystack"
 dynamic = ["version"]
 description = 'Haystack 2.x Document Store for ElasticSearch'
 readme = "README.md"
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 license = "Apache-2.0"
 keywords = []
 authors = [{ name = "Silvano Cerza", email = "silvanocerza@gmail.com" }]
@@ -15,7 +15,6 @@ classifiers = [
   "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
-  "Programming Language :: Python :: 3.8",
   "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
@@ -45,6 +44,7 @@ installer = "uv"
 dependencies = [
   "coverage[toml]>=6.5",
   "pytest",
+  "pytest-asyncio",
   "pytest-rerunfailures",
   "pytest-xdist",
   "haystack-pydoc-tools",
@@ -59,12 +59,13 @@ 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"]
+python = [ "3.9", "3.10", "3.11"]
 
 [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.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
 style = ["ruff check {args:}", "black --check --diff {args:.}"]
@@ -157,7 +158,9 @@ exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
 [tool.pytest.ini_options]
 minversion = "6.0"
 markers = ["unit: unit tests", "integration: integration tests"]
+asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "class"
 
 [[tool.mypy.overrides]]
-module = ["haystack.*", "haystack_integrations.*", "pytest.*"]
+module = ["haystack.*", "haystack_integrations.*", "numpy.*", "pytest.*"]
 ignore_missing_imports = true

{elasticsearch_haystack-1.0.1 → elasticsearch_haystack-2.1.0}/src/haystack_integrations/components/retrievers/elasticsearch/bm25_retriever.py

@@ -120,7 +120,7 @@ class ElasticsearchBM25Retriever:
         """
         Retrieve documents using the BM25 keyword-based algorithm.
 
-        :param query: String to search in `Document`s' text.
+        :param query: String to search in the `Document`s text.
         :param filters: Filters applied to the retrieved Documents. The way runtime filters are applied depends on
                         the `filter_policy` chosen at retriever initialization. See init method docstring for more
                         details.
@@ -137,3 +137,26 @@ class ElasticsearchBM25Retriever:
             scale_score=self._scale_score,
         )
         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):
+        """
+        Asynchronously retrieve documents using the BM25 keyword-based algorithm.
+
+        :param query: String to search in the `Document` text.
+        :param filters: Filters applied to the retrieved Documents. The way runtime filters are applied depends on
+                        the `filter_policy` chosen at retriever initialization. See init method docstring for more
+                        details.
+        :param top_k: Maximum number of `Document` to return.
+        :returns: A dictionary with the following keys:
+            - `documents`: List of `Document`s that match the query.
+        """
+        filters = apply_filter_policy(self._filter_policy, self._filters, filters)
+        docs = await self._document_store._bm25_retrieval_async(
+            query=query,
+            filters=filters,
+            fuzziness=self._fuzziness,
+            top_k=top_k or self._top_k,
+            scale_score=self._scale_score,
+        )
+        return {"documents": docs}

{elasticsearch_haystack-1.0.1 → elasticsearch_haystack-2.1.0}/src/haystack_integrations/components/retrievers/elasticsearch/embedding_retriever.py

@@ -119,10 +119,11 @@ class ElasticsearchEmbeddingRetriever:
         Retrieve documents using a vector similarity metric.
 
         :param query_embedding: Embedding of the query.
-        :param filters: Filters applied to the retrieved Documents. The way runtime filters are applied depends on
-                        the `filter_policy` chosen at retriever initialization. See init method docstring for more
-                        details.
-        :param top_k: Maximum number of `Document`s to return.
+        :param filters: Filters applied when fetching documents from the Document Store.
+            Filters are applied during the approximate kNN search to ensure the Retriever returns
+              `top_k` matching documents.
+            The way runtime filters are applied depends on the `filter_policy` selected when initializing the Retriever.
+        :param top_k: Maximum number of documents to return.
         :returns: A dictionary with the following keys:
             - `documents`: List of `Document`s most similar to the given `query_embedding`
         """
@@ -134,3 +135,28 @@ class ElasticsearchEmbeddingRetriever:
             num_candidates=self._num_candidates,
         )
         return {"documents": docs}
+
+    @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
+    ):
+        """
+        Asynchronously retrieve documents using a vector similarity metric.
+
+        :param query_embedding: Embedding of the query.
+        :param filters: Filters applied when fetching documents from the Document Store.
+            Filters are applied during the approximate kNN search to ensure the Retriever returns
+              `top_k` matching documents.
+            The way runtime filters are applied depends on the `filter_policy` selected when initializing the Retriever.
+        :param top_k: Maximum number of documents to return.
+        :returns: A dictionary with the following keys:
+            - `documents`: List of `Document`s that match the query.
+        """
+        filters = apply_filter_policy(self._filter_policy, self._filters, filters)
+        docs = await self._document_store._embedding_retrieval_async(
+            query_embedding=query_embedding,
+            filters=filters,
+            top_k=top_k or self._top_k,
+            num_candidates=self._num_candidates,
+        )
+        return {"documents": docs}