elasticsearch-haystack 5.1.0__py3-none-any.whl

elasticsearch_haystack-5.1.0.dist-info/METADATA

@@ -0,0 +1,41 @@
+Metadata-Version: 2.4
+Name: elasticsearch-haystack
+Version: 5.1.0
+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
+Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/elasticsearch
+Author-email: Silvano Cerza <silvanocerza@gmail.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.10
+Requires-Dist: aiohttp>=3.9.0
+Requires-Dist: elasticsearch<9,>=8
+Requires-Dist: haystack-ai>=2.22.0
+Description-Content-Type: text/markdown
+
+# elasticsearch-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/elasticsearch-haystack.svg)](https://pypi.org/project/elasticsearch-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/elasticsearch-haystack.svg)](https://pypi.org/project/elasticsearch-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/elasticsearch-document-store)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/elasticsearch/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
+
+To run integration tests locally, you need a Docker container running ElasticSearch.
+Use the provided `docker-compose.yml` file to start the container: `docker compose up -d`.

elasticsearch_haystack-5.1.0.dist-info/RECORD

@@ -0,0 +1,12 @@
+haystack_integrations/components/retrievers/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+haystack_integrations/components/retrievers/elasticsearch/__init__.py,sha256=cSJBsYjz_T4kK-M-auAHVUnYIcgUqqwwQe_hsF0_IG4,307
+haystack_integrations/components/retrievers/elasticsearch/bm25_retriever.py,sha256=ErMEQjzgg3-I2J8zOM_kDV0Y8UWtfqNHm89_vV-fOSo,7048
+haystack_integrations/components/retrievers/elasticsearch/embedding_retriever.py,sha256=gz5BnSG0u7QimzKJWDYVvrkURMGXnGv4gldyJFTAk5U,7351
+haystack_integrations/document_stores/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+haystack_integrations/document_stores/elasticsearch/__init__.py,sha256=YTfu94dtVUBogbJFr1aJrKuaI6-Bw9VuHfPoyU7M8os,207
+haystack_integrations/document_stores/elasticsearch/document_store.py,sha256=Wzn5kpcag2p75ySN788Uql9Q00RWj1CRXWmmmnuMLNU,65683
+haystack_integrations/document_stores/elasticsearch/filters.py,sha256=UmQ9zbITweR1QQnVbRKCbH46Dcdrj2rhMO90ll_sHT0,9747
+elasticsearch_haystack-5.1.0.dist-info/METADATA,sha256=VKvwAgwRGEqE3vUWFAskVqf9yMQuBQNeMvvRdyZF_D0,2057
+elasticsearch_haystack-5.1.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+elasticsearch_haystack-5.1.0.dist-info/licenses/LICENSE,sha256=_M2kulivnaiTHiW-5CRlZrPmH47tt04pBgAgeDvfYi4,11342
+elasticsearch_haystack-5.1.0.dist-info/RECORD,,

elasticsearch_haystack-5.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.28.0
+Root-Is-Purelib: true
+Tag: py3-none-any

elasticsearch_haystack-5.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2023 deepset GmbH
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

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"]

haystack_integrations/components/retrievers/elasticsearch/bm25_retriever.py

@@ -0,0 +1,166 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+from typing import Any
+
+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
+
+
+@component
+class ElasticsearchBM25Retriever:
+    """
+    ElasticsearchBM25Retriever retrieves documents from the ElasticsearchDocumentStore using BM25 algorithm to find the
+    most similar documents to a user's query.
+
+    This retriever is only compatible with ElasticsearchDocumentStore.
+
+    Usage example:
+    ```python
+    from haystack import Document
+    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)
+
+    # Add documents to DocumentStore
+    documents = [
+        Document(text="My name is Carla and I live in Berlin"),
+        Document(text="My name is Paul and I live in New York"),
+        Document(text="My name is Silvano and I live in Matera"),
+        Document(text="My name is Usagi Tsukino and I live in Tokyo"),
+    ]
+    document_store.write_documents(documents)
+
+    result = retriever.run(query="Who lives in Berlin?")
+    for doc in result["documents"]:
+        print(doc.content)
+    ```
+    """
+
+    def __init__(
+        self,
+        *,
+        document_store: ElasticsearchDocumentStore,
+        filters: dict[str, Any] | None = None,
+        fuzziness: str = "AUTO",
+        top_k: int = 10,
+        scale_score: bool = False,
+        filter_policy: str | FilterPolicy = FilterPolicy.REPLACE,
+    ):
+        """
+        Initialize ElasticsearchBM25Retriever with an instance ElasticsearchDocumentStore.
+
+        :param document_store: An instance of ElasticsearchDocumentStore.
+        :param filters: Filters applied to the retrieved Documents, for more info
+                        see `ElasticsearchDocumentStore.filter_documents`.
+        :param fuzziness: Fuzziness parameter passed to Elasticsearch. See the official
+            [documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/common-options.html#fuzziness)
+            for more details.
+        :param top_k: Maximum number of Documents to return.
+        :param scale_score: If `True` scales the Document`s scores between 0 and 1.
+        :param filter_policy: Policy to determine how filters are applied.
+        :raises ValueError: If `document_store` is not an instance of `ElasticsearchDocumentStore`.
+        """
+
+        if not isinstance(document_store, ElasticsearchDocumentStore):
+            msg = "document_store must be an instance of ElasticsearchDocumentStore"
+            raise ValueError(msg)
+
+        self._document_store = document_store
+        self._filters = filters or {}
+        self._fuzziness = fuzziness
+        self._top_k = top_k
+        self._scale_score = scale_score
+        self._filter_policy = FilterPolicy.from_str(filter_policy) if isinstance(filter_policy, str) else filter_policy
+
+    def to_dict(self) -> dict[str, Any]:
+        """
+        Serializes the component to a dictionary.
+
+        :returns:
+            Dictionary with serialized data.
+        """
+        return default_to_dict(
+            self,
+            filters=self._filters,
+            fuzziness=self._fuzziness,
+            top_k=self._top_k,
+            scale_score=self._scale_score,
+            filter_policy=self._filter_policy.value,
+            document_store=self._document_store.to_dict(),
+        )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "ElasticsearchBM25Retriever":
+        """
+        Deserializes the component from a dictionary.
+
+        :param data:
+            Dictionary to deserialize from.
+        :returns:
+            Deserialized component.
+        """
+        data["init_parameters"]["document_store"] = ElasticsearchDocumentStore.from_dict(
+            data["init_parameters"]["document_store"]
+        )
+        # Pipelines serialized with old versions of the component might not
+        # have the filter_policy field.
+        if filter_policy := data["init_parameters"].get("filter_policy"):
+            data["init_parameters"]["filter_policy"] = FilterPolicy.from_str(filter_policy)
+        return default_from_dict(cls, data)
+
+    @component.output_types(documents=list[Document])
+    def run(
+        self, query: str, filters: dict[str, Any] | None = None, top_k: int | None = None
+    ) -> dict[str, list[Document]]:
+        """
+        Retrieve documents using the BM25 keyword-based algorithm.
+
+        :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.
+        :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 = self._document_store._bm25_retrieval(
+            query=query,
+            filters=filters,
+            fuzziness=self._fuzziness,
+            top_k=top_k or self._top_k,
+            scale_score=self._scale_score,
+        )
+        return {"documents": docs}
+
+    @component.output_types(documents=list[Document])
+    async def run_async(
+        self, query: str, filters: dict[str, Any] | None = None, top_k: int | None = None
+    ) -> dict[str, list[Document]]:
+        """
+        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}

haystack_integrations/components/retrievers/elasticsearch/embedding_retriever.py

@@ -0,0 +1,164 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+from typing import Any
+
+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
+
+
+@component
+class ElasticsearchEmbeddingRetriever:
+    """
+    ElasticsearchEmbeddingRetriever retrieves documents from the ElasticsearchDocumentStore using vector similarity.
+
+    Usage example:
+    ```python
+    from haystack import Document
+    from haystack.components.embedders import SentenceTransformersTextEmbedder
+    from haystack_integrations.document_stores.elasticsearch import ElasticsearchDocumentStore
+    from haystack_integrations.components.retrievers.elasticsearch import ElasticsearchEmbeddingRetriever
+
+    document_store = ElasticsearchDocumentStore(hosts="http://localhost:9200")
+    retriever = ElasticsearchEmbeddingRetriever(document_store=document_store)
+
+    # Add documents to DocumentStore
+    documents = [
+        Document(text="My name is Carla and I live in Berlin"),
+        Document(text="My name is Paul and I live in New York"),
+        Document(text="My name is Silvano and I live in Matera"),
+        Document(text="My name is Usagi Tsukino and I live in Tokyo"),
+    ]
+    document_store.write_documents(documents)
+
+    te = SentenceTransformersTextEmbedder()
+    te.warm_up()
+    query_embeddings = te.run("Who lives in Berlin?")["embedding"]
+
+    result = retriever.run(query=query_embeddings)
+    for doc in result["documents"]:
+        print(doc.content)
+    ```
+    """
+
+    def __init__(
+        self,
+        *,
+        document_store: ElasticsearchDocumentStore,
+        filters: dict[str, Any] | None = None,
+        top_k: int = 10,
+        num_candidates: int | None = None,
+        filter_policy: str | FilterPolicy = FilterPolicy.REPLACE,
+    ):
+        """
+        Create the ElasticsearchEmbeddingRetriever component.
+
+        :param document_store: An instance of ElasticsearchDocumentStore.
+        :param filters: Filters applied to the retrieved Documents.
+            Filters are applied during the approximate KNN search to ensure that top_k matching documents are returned.
+        :param top_k: Maximum number of Documents to return.
+        :param num_candidates: Number of approximate nearest neighbor candidates on each shard. Defaults to top_k * 10.
+            Increasing this value will improve search accuracy at the cost of slower search speeds.
+            You can read more about it in the Elasticsearch
+            [documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/knn-search.html#tune-approximate-knn-for-speed-accuracy)
+        :param filter_policy: Policy to determine how filters are applied.
+        :raises ValueError: If `document_store` is not an instance of ElasticsearchDocumentStore.
+        """
+        if not isinstance(document_store, ElasticsearchDocumentStore):
+            msg = "document_store must be an instance of ElasticsearchDocumentStore"
+            raise ValueError(msg)
+
+        self._document_store = document_store
+        self._filters = filters or {}
+        self._top_k = top_k
+        self._num_candidates = num_candidates
+        self._filter_policy = FilterPolicy.from_str(filter_policy) if isinstance(filter_policy, str) else filter_policy
+
+    def to_dict(self) -> dict[str, Any]:
+        """
+        Serializes the component to a dictionary.
+
+        :returns:
+            Dictionary with serialized data.
+        """
+        return default_to_dict(
+            self,
+            filters=self._filters,
+            top_k=self._top_k,
+            num_candidates=self._num_candidates,
+            filter_policy=self._filter_policy.value,
+            document_store=self._document_store.to_dict(),
+        )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "ElasticsearchEmbeddingRetriever":
+        """
+        Deserializes the component from a dictionary.
+
+        :param data:
+            Dictionary to deserialize from.
+        :returns:
+            Deserialized component.
+        """
+        data["init_parameters"]["document_store"] = ElasticsearchDocumentStore.from_dict(
+            data["init_parameters"]["document_store"]
+        )
+        # Pipelines serialized with old versions of the component might not
+        # have the filter_policy field.
+        if filter_policy := data["init_parameters"].get("filter_policy"):
+            data["init_parameters"]["filter_policy"] = FilterPolicy.from_str(filter_policy)
+        return default_from_dict(cls, data)
+
+    @component.output_types(documents=list[Document])
+    def run(
+        self, query_embedding: list[float], filters: dict[str, Any] | None = None, top_k: int | None = None
+    ) -> dict[str, list[Document]]:
+        """
+        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 most similar to the given `query_embedding`
+        """
+        filters = apply_filter_policy(self._filter_policy, self._filters, filters)
+        docs = self._document_store._embedding_retrieval(
+            query_embedding=query_embedding,
+            filters=filters,
+            top_k=top_k or self._top_k,
+            num_candidates=self._num_candidates,
+        )
+        return {"documents": docs}
+
+    @component.output_types(documents=list[Document])
+    async def run_async(
+        self, query_embedding: list[float], filters: dict[str, Any] | None = None, top_k: int | None = None
+    ) -> dict[str, list[Document]]:
+        """
+        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}

haystack_integrations/document_stores/elasticsearch/__init__.py

@@ -0,0 +1,6 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+from .document_store import ElasticsearchDocumentStore
+
+__all__ = ["ElasticsearchDocumentStore"]