elasticsearch-haystack 2.1.0__tar.gz → 3.0.0__tar.gz

{elasticsearch_haystack-2.1.0 → elasticsearch_haystack-3.0.0}/CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## [integrations/elasticsearch-v2.1.0] - 2025-02-26
+
+### 🚀 Features
+
+- Adding async support to ElasticSearch retrievers and document store (#1429)
+
+### 🧹 Chores
+
+- Remove Python 3.8 support (#1421)
+
+### 🌀 Miscellaneous
+
+- Docs: update changelog for integrations/elasticsearch (#1400)
+
 ## [integrations/elasticsearch-v2.0.0] - 2025-02-14
 
 ### 🧹 Chores

{elasticsearch_haystack-2.1.0 → elasticsearch_haystack-3.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: elasticsearch-haystack
-Version: 2.1.0
+Version: 3.0.0
 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
@@ -17,8 +17,9 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: >=3.9
+Requires-Dist: aiohttp
 Requires-Dist: elasticsearch<9,>=8
-Requires-Dist: haystack-ai
+Requires-Dist: haystack-ai>=2.11.0
 Description-Content-Type: text/markdown
 
 [![test](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/elasticsearch.yml/badge.svg)](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/elasticsearch.yml)

{elasticsearch_haystack-2.1.0 → elasticsearch_haystack-3.0.0}/pyproject.toml

@@ -21,7 +21,11 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai", "elasticsearch>=8,<9"]
+dependencies = [
+                "haystack-ai>=2.11.0",
+                "elasticsearch>=8,<9",
+                "aiohttp" # for async support https://elasticsearch-py.readthedocs.io/en/latest/async.html#valueerror-when-initializing-asyncelasticsearch
+                ]
 
 [project.urls]
 Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/elasticsearch#readme"

{elasticsearch_haystack-2.1.0 → elasticsearch_haystack-3.0.0}/src/haystack_integrations/document_stores/elasticsearch/document_store.py

@@ -1,7 +1,6 @@
 # SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
-import logging
 from collections.abc import Mapping
 from typing import Any, Dict, List, Literal, Optional, Union
 
@@ -9,7 +8,7 @@ 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 haystack import default_from_dict, default_to_dict
+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
@@ -36,7 +35,7 @@ DOC_ALREADY_EXISTS = 409
 
 class ElasticsearchDocumentStore:
     """
-    ElasticsearchDocumentStore is a Document Store for Elasticsearch. It can be used with Elastic Cloud or your own
+    An ElasticsearchDocumentStore instance that works with Elastic Cloud or your own
     Elasticsearch cluster.
 
     Usage example (Elastic Cloud):
@@ -329,15 +328,6 @@ class ElasticsearchDocumentStore:
             data["metadata"]["highlighted"] = hit["highlight"]
         data["score"] = hit["_score"]
 
-        if "dataframe" in data:
-            dataframe = data.pop("dataframe")
-            if dataframe:
-                logger.warning(
-                    "Document %s has the `dataframe` field set,"
-                    "ElasticsearchDocumentStore no longer supports dataframes and this field will be ignored. "
-                    "The `dataframe` field will soon be removed from Haystack Document.",
-                    data["id"],
-                )
         return Document.from_dict(data)
 
     def write_documents(self, documents: List[Document], policy: DuplicatePolicy = DuplicatePolicy.NONE) -> int:
@@ -365,23 +355,15 @@ class ElasticsearchDocumentStore:
         elasticsearch_actions = []
         for doc in documents:
             doc_dict = doc.to_dict()
-            if "dataframe" in doc_dict:
-                dataframe = doc_dict.pop("dataframe")
-                if dataframe:
-                    logger.warning(
-                        "Document %s has the `dataframe` field set,"
-                        "ElasticsearchDocumentStore no longer supports dataframes and this field will be ignored. "
-                        "The `dataframe` field will soon be removed from Haystack Document.",
-                        doc.id,
-                    )
+
             if "sparse_embedding" in doc_dict:
                 sparse_embedding = doc_dict.pop("sparse_embedding", None)
                 if sparse_embedding:
                     logger.warning(
-                        "Document %s has the `sparse_embedding` field set,"
+                        "Document {doc_id} has the `sparse_embedding` field set,"
                         "but storing sparse embeddings in Elasticsearch is not currently supported."
                         "The `sparse_embedding` field will be ignored.",
-                        doc.id,
+                        doc_id=doc.id,
                     )
             elasticsearch_actions.append(
                 {
@@ -449,23 +431,15 @@ class ElasticsearchDocumentStore:
         actions = []
         for doc in documents:
             doc_dict = doc.to_dict()
-            if "dataframe" in doc_dict:
-                dataframe = doc_dict.pop("dataframe")
-                if dataframe:
-                    logger.warning(
-                        "Document {id} has the `dataframe` field set,"
-                        "ElasticsearchDocumentStore no longer supports dataframes and this field will be ignored. "
-                        "The `dataframe` field will soon be removed from Haystack Document.",
-                    )
 
             if "sparse_embedding" in doc_dict:
                 sparse_embedding = doc_dict.pop("sparse_embedding", None)
                 if sparse_embedding:
                     logger.warning(
-                        "Document %s has the `sparse_embedding` field set,"
+                        "Document {doc_id} has the `sparse_embedding` field set,"
                         "but storing sparse embeddings in Elasticsearch is not currently supported."
                         "The `sparse_embedding` field will be ignored.",
-                        doc.id,
+                        doc_id=doc.id,
                     )
 
             action = {

{elasticsearch_haystack-2.1.0 → elasticsearch_haystack-3.0.0}/tests/test_document_store.py

@@ -13,7 +13,6 @@ from haystack.dataclasses.sparse_embedding import SparseEmbedding
 from haystack.document_stores.errors import DocumentStoreError, DuplicateDocumentError
 from haystack.document_stores.types import DuplicatePolicy
 from haystack.testing.document_store import DocumentStoreBaseTests
-from pandas import DataFrame
 
 from haystack_integrations.document_stores.elasticsearch import ElasticsearchDocumentStore
 
@@ -135,27 +134,6 @@ class TestDocumentStore(DocumentStoreBaseTests):
         with pytest.raises(DuplicateDocumentError):
             document_store.write_documents(docs, DuplicatePolicy.FAIL)
 
-    def test_write_documents_dataframe_ignored(self, document_store: ElasticsearchDocumentStore):
-        doc = Document(id="1", content="test")
-        doc.dataframe = DataFrame({"a": [1, 2, 3]})
-        document_store.write_documents([doc])
-        res = document_store.filter_documents()
-        assert len(res) == 1
-        assert res[0].id == "1"
-        assert res[0].content == "test"
-        assert not hasattr(res[0], "dataframe") or res[0].dataframe is None
-
-    def test_deserialize_document_dataframe_ignored(self, document_store: ElasticsearchDocumentStore):
-        hit = {
-            "_source": {"id": "1", "content": "test", "dataframe": {"a": [1, 2, 3]}},
-            "_score": 1.0,
-        }
-        doc = document_store._deserialize_document(hit)
-        assert doc.id == "1"
-        assert doc.content == "test"
-        assert doc.score == 1.0
-        assert not hasattr(doc, "dataframe") or doc.dataframe is None
-
     def test_bm25_retrieval(self, document_store: ElasticsearchDocumentStore):
         document_store.write_documents(
             [
@@ -499,19 +477,6 @@ class TestElasticsearchDocumentStoreAsync:
         with pytest.raises(ValueError, match="param 'documents' must contain a list of objects of type Document"):
             await document_store.write_documents_async(invalid_docs)
 
-    @pytest.mark.asyncio
-    async def test_write_documents_async_with_dataframe_warning(self, document_store, caplog):
-        """Test write_documents with document containing dataframe field"""
-        doc = Document(id="1", content="test", dataframe=DataFrame({"col": [1, 2, 3]}))
-
-        await document_store.write_documents_async([doc])
-        assert "ElasticsearchDocumentStore no longer supports dataframes" in caplog.text
-
-        results = await document_store.filter_documents_async()
-        assert len(results) == 1
-        assert results[0].id == "1"
-        assert not hasattr(results[0], "dataframe") or results[0].dataframe is None
-
     @pytest.mark.asyncio
     async def test_write_documents_async_with_sparse_embedding_warning(self, document_store, caplog):
         """Test write_documents with document containing sparse_embedding field"""