arangodb-haystack 1.0.0__py3-none-any.whl

arangodb_haystack-1.0.0.dist-info/METADATA

@@ -0,0 +1,40 @@
+Metadata-Version: 2.4
+Name: arangodb-haystack
+Version: 1.0.0
+Summary: Haystack integration for arangodb
+Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/arangodb#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/arangodb
+Author-email: deepset GmbH <info@deepset.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
+Keywords: arangodb,document-store,haystack,llm,rag,vector-search
+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 :: 3.14
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.10
+Requires-Dist: haystack-ai
+Requires-Dist: python-arango>=8.0.0
+Description-Content-Type: text/markdown
+
+# arangodb-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/arangodb-haystack.svg)](https://pypi.org/project/arangodb-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/arangodb-haystack.svg)](https://pypi.org/project/arangodb-haystack)
+
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/arangodb/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 ArangoDB. Use the provided `docker-compose.yml` file to start the container: `docker compose up -d`.

arangodb_haystack-1.0.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+haystack_integrations/components/retrievers/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+haystack_integrations/components/retrievers/arangodb/__init__.py,sha256=mSbwLeMVNwjwqUYGdKUi18dkNhoOqpXIIgwCArMBI1A,261
+haystack_integrations/components/retrievers/arangodb/embedding_retriever.py,sha256=SE7xm1Mjx3NTM_wutEJZnkYTKgv789FsNfcU2xSWLRE,3667
+haystack_integrations/document_stores/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+haystack_integrations/document_stores/arangodb/__init__.py,sha256=jL_VQoXqdP33_1WD5tN9eAykDM4I0vaGkkInTPO7o3k,240
+haystack_integrations/document_stores/arangodb/document_store.py,sha256=qUctFBPP-skCaGZgCJ1IKeAGdztQI5bo18JiA12-xDs,13749
+haystack_integrations/document_stores/arangodb/filters.py,sha256=rGd31XfHMfRNH1mTLw-Wf7VMllMzdLy_uzIzSvztr-Y,3983
+arangodb_haystack-1.0.0.dist-info/METADATA,sha256=RUq0Tkf_KemAL-JtmJPGTUDEteaQ_mqlHEuebWAFSOg,1979
+arangodb_haystack-1.0.0.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+arangodb_haystack-1.0.0.dist-info/licenses/LICENSE.txt,sha256=OrAtTu4aPmrTjKDSTzkSPgo_ji6NOMWO2N9JOTFyAzM,11350
+arangodb_haystack-1.0.0.dist-info/RECORD,,

arangodb_haystack-1.0.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.30.1
+Root-Is-Purelib: true
+Tag: py3-none-any

arangodb_haystack-1.0.0.dist-info/licenses/LICENSE.txt

@@ -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-present 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/arangodb/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from haystack_integrations.components.retrievers.arangodb.embedding_retriever import ArangoEmbeddingRetriever
+
+__all__ = ["ArangoEmbeddingRetriever"]

haystack_integrations/components/retrievers/arangodb/embedding_retriever.py

@@ -0,0 +1,102 @@
+# 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_integrations.document_stores.arangodb.document_store import ArangoDocumentStore
+
+
+@component
+class ArangoEmbeddingRetriever:
+    """
+    Retrieves documents from an `ArangoDocumentStore` using vector similarity on embeddings.
+
+    The similarity function is configured on the `ArangoDocumentStore` (cosine, dot product, or L2).
+
+    Example usage:
+
+    ```python
+    from haystack_integrations.document_stores.arangodb import ArangoDocumentStore
+    from haystack_integrations.components.retrievers.arangodb import ArangoEmbeddingRetriever
+
+    store = ArangoDocumentStore(host="http://localhost:8529", database="haystack",
+                                username="root", collection_name="docs", embedding_dimension=768)
+    retriever = ArangoEmbeddingRetriever(document_store=store, top_k=5)
+    result = retriever.run(query_embedding=[0.1, 0.2, ...])
+    ```
+    """
+
+    def __init__(
+        self,
+        *,
+        document_store: ArangoDocumentStore,
+        top_k: int = 10,
+        filters: dict[str, Any] | None = None,
+    ) -> None:
+        """
+        Creates a new ArangoEmbeddingRetriever.
+
+        :param document_store: The `ArangoDocumentStore` to retrieve documents from.
+        :param top_k: Maximum number of documents to return.
+        :param filters: Optional Haystack metadata filters applied at retrieval time.
+        """
+        if not isinstance(document_store, ArangoDocumentStore):
+            msg = f"document_store must be an ArangoDocumentStore, got {type(document_store)}"
+            raise ValueError(msg)
+        self.document_store = document_store
+        self.top_k = top_k
+        self.filters = filters
+
+    @component.output_types(documents=list[Document])
+    def run(
+        self,
+        query_embedding: list[float],
+        top_k: int | None = None,
+        filters: dict[str, Any] | None = None,
+    ) -> dict[str, list[Document]]:
+        """
+        Retrieves documents most similar to `query_embedding`.
+
+        :param query_embedding: The query vector.
+        :param top_k: Overrides the instance-level `top_k` for this call.
+        :param filters: Overrides the instance-level `filters` for this call.
+        :returns: A dictionary with `documents` — a list of `Document` objects sorted by score.
+        """
+        top_k = top_k if top_k is not None else self.top_k
+        filters = filters if filters is not None else self.filters
+        docs = self.document_store._embedding_retrieval(
+            query_embedding=query_embedding,
+            top_k=top_k,
+            filters=filters,
+        )
+        return {"documents": docs}
+
+    def to_dict(self) -> dict[str, Any]:
+        """
+        Serializes the component to a dictionary.
+
+        :returns: Dictionary with serialized data.
+        """
+        return default_to_dict(
+            self,
+            document_store=self.document_store.to_dict(),
+            top_k=self.top_k,
+            filters=self.filters,
+        )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "ArangoEmbeddingRetriever":
+        """
+        Deserializes the component from a dictionary.
+
+        :param data: Dictionary to deserialize from.
+        :returns: Deserialized component.
+        """
+        data["init_parameters"]["document_store"] = ArangoDocumentStore.from_dict(
+            data["init_parameters"]["document_store"]
+        )
+        return default_from_dict(cls, data)

haystack_integrations/document_stores/arangodb/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from haystack_integrations.document_stores.arangodb.document_store import ArangoDocumentStore
+
+__all__ = ["ArangoDocumentStore"]

haystack_integrations/document_stores/arangodb/document_store.py

@@ -0,0 +1,350 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import dataclasses
+from typing import Any, Literal, cast
+
+from arango import ArangoClient
+from arango.collection import StandardCollection
+from arango.cursor import Cursor
+from arango.database import StandardDatabase
+from haystack import default_from_dict, default_to_dict, logging
+from haystack.dataclasses import Document
+from haystack.document_stores.errors import DuplicateDocumentError
+from haystack.document_stores.types import DuplicatePolicy
+from haystack.utils.auth import Secret, deserialize_secrets_inplace
+
+from .filters import _convert_filters
+
+logger = logging.getLogger(__name__)
+
+# Maps the configured similarity function to the AQL vector function, its sort order,
+# and the metric name used when creating the vector index.
+_SIMILARITY_AQL: dict[str, tuple[str, str, str]] = {
+    "cosine": ("APPROX_NEAR_COSINE", "DESC", "cosine"),
+    "dot_product": ("APPROX_NEAR_INNER_PRODUCT", "DESC", "innerProduct"),
+    "l2": ("APPROX_NEAR_L2", "ASC", "l2"),
+}
+
+_VECTOR_INDEX_NAME = "haystack_vector_index"
+
+
+def _doc_to_arango(doc: Document) -> dict[str, Any]:
+    d = doc.to_dict(flatten=False)
+    d["_key"] = d.pop("id")
+    return d
+
+
+def _arango_to_doc(record: dict[str, Any]) -> Document:
+    record = dict(record)
+    record["id"] = record.pop("_key")
+    record.pop("_id", None)
+    record.pop("_rev", None)
+    return Document.from_dict(record)
+
+
+class ArangoDocumentStore:
+    """
+    A Haystack DocumentStore backed by [ArangoDB](https://www.arangodb.com/).
+
+    Documents are stored in an ArangoDB collection and support vector similarity search
+    via AQL vector functions (requires ArangoDB 3.12+).
+
+    Example usage:
+
+    ```python
+    from haystack_integrations.document_stores.arangodb import ArangoDocumentStore
+    from haystack.utils import Secret
+
+    store = ArangoDocumentStore(
+        host="http://localhost:8529",
+        database="haystack",
+        username=Secret.from_env_var("ARANGO_USERNAME", strict=False),
+        password=Secret.from_env_var("ARANGO_PASSWORD"),
+        collection_name="documents",
+        embedding_dimension=768,
+    )
+    ```
+    """
+
+    def __init__(
+        self,
+        *,
+        host: str = "http://localhost:8529",
+        database: str = "haystack",
+        username: Secret = Secret.from_env_var("ARANGO_USERNAME", strict=False),
+        password: Secret = Secret.from_env_var("ARANGO_PASSWORD"),
+        collection_name: str = "haystack_documents",
+        embedding_dimension: int = 768,
+        recreate_collection: bool = False,
+        similarity_function: Literal["cosine", "dot_product", "l2"] = "cosine",
+    ) -> None:
+        """
+        Creates a new ArangoDocumentStore instance.
+
+        :param host: ArangoDB server URL, e.g. `http://localhost:8529`.
+        :param database: Name of the ArangoDB database to use. Created if it does not exist.
+        :param username: ArangoDB username as a `Secret`. Defaults to `ARANGO_USERNAME` env var,
+            falling back to `root` if the variable is not set.
+        :param password: ArangoDB password as a `Secret`. Defaults to `ARANGO_PASSWORD` env var.
+        :param collection_name: Name of the collection to store documents in.
+        :param embedding_dimension: Dimensionality of document embeddings.
+        :param recreate_collection: If `True`, drop and recreate the collection on startup.
+        :param similarity_function: Vector similarity function to use for embedding retrieval.
+            One of `"cosine"` (default), `"dot_product"`, or `"l2"`.
+        """
+        self.host = host
+        self.database = database
+        self.username = username
+        self.password = password
+        self.collection_name = collection_name
+        self.embedding_dimension = embedding_dimension
+        self.recreate_collection = recreate_collection
+        self.similarity_function = similarity_function
+        self._db: StandardDatabase | None = None
+        self._col: StandardCollection | None = None
+
+    def _ensure_connected(self) -> None:
+        if self._db is not None and self._col is not None:
+            return
+        username = self.username.resolve_value() or "root"
+        pwd = self.password.resolve_value() or ""
+        client = ArangoClient(hosts=self.host)
+        sys_db = client.db("_system", username=username, password=pwd)
+        if not sys_db.has_database(self.database):
+            sys_db.create_database(self.database)
+        db = client.db(self.database, username=username, password=pwd)
+        if self.recreate_collection and db.has_collection(self.collection_name):
+            db.delete_collection(self.collection_name)
+        if not db.has_collection(self.collection_name):
+            db.create_collection(self.collection_name)
+        self._db = db
+        self._col = db.collection(self.collection_name)
+
+    def _ensure_vector_index(self) -> None:
+        """
+        Lazily creates the FAISS vector index used by the `APPROX_NEAR_*` functions.
+
+        The index is created on first retrieval rather than at write time because ArangoDB
+        requires the collection to already contain training documents with non-null embeddings,
+        and `nLists` must be `<=` the number of such documents. We use `nLists=1`, which
+        probes the single Voronoi cell (a full scan) and therefore returns exact, complete results.
+
+        If a vector index already exists on the `embedding` field, its `metric` and `dimension`
+        must match this store's configuration; otherwise a `ValueError` is raised, since an
+        incompatible index would make `APPROX_NEAR_*` fail or silently return wrong results.
+
+        :raises ValueError: If an incompatible vector index already exists on the collection.
+        """
+        col = cast(StandardCollection, self._col)
+        _, _, metric = _SIMILARITY_AQL[self.similarity_function]
+        existing = cast("list[dict[str, Any]]", col.indexes())
+        for index in existing:
+            if index.get("type") != "vector" or index.get("fields") != ["embedding"]:
+                continue
+            params = index.get("params") or {}
+            if params.get("metric") == metric and params.get("dimension") == self.embedding_dimension:
+                return
+            msg = (
+                f"Collection '{self.collection_name}' already has a vector index on 'embedding' "
+                f"with metric={params.get('metric')!r} and dimension={params.get('dimension')}, "
+                f"which is incompatible with this store's configuration "
+                f"(metric={metric!r}, dimension={self.embedding_dimension}). "
+                f"Use a different collection or set recreate_collection=True to rebuild it."
+            )
+            raise ValueError(msg)
+        col.add_index(
+            {
+                "type": "vector",
+                "name": _VECTOR_INDEX_NAME,
+                "fields": ["embedding"],
+                "params": {
+                    "metric": metric,
+                    "dimension": self.embedding_dimension,
+                    "nLists": 1,
+                },
+            }
+        )
+
+    def count_documents(self) -> int:
+        """
+        Returns the number of documents in the store.
+
+        :returns: Document count.
+        """
+        self._ensure_connected()
+        return cast(int, cast(StandardCollection, self._col).count())
+
+    def filter_documents(self, filters: dict[str, Any] | None = None) -> list[Document]:
+        """
+        Returns documents matching the provided filters.
+
+        :param filters: Haystack metadata filters. If `None`, all documents are returned.
+        :returns: List of matching `Document` objects.
+        """
+        self._ensure_connected()
+        db = cast(StandardDatabase, self._db)
+
+        aql = f"FOR doc IN {self.collection_name}"
+        bind_vars: dict[str, Any] = {}
+
+        if filters:
+            expr, bind_vars = _convert_filters(filters)
+            aql += f" FILTER {expr}"
+
+        aql += " RETURN doc"
+
+        cursor = cast(Cursor, db.aql.execute(aql, bind_vars=bind_vars))
+        return [_arango_to_doc(r) for r in cursor]
+
+    def write_documents(self, documents: list[Document], policy: DuplicatePolicy = DuplicatePolicy.NONE) -> int:
+        """
+        Writes documents to the store.
+
+        :param documents: Documents to write.
+        :param policy: How to handle duplicates — `OVERWRITE`, `SKIP`, or `FAIL` (default).
+        :raises ValueError: If `documents` contains non-`Document` objects.
+        :raises DuplicateDocumentError: If a duplicate is found and policy is `FAIL`.
+        :returns: Number of documents written.
+        """
+        if not documents:
+            return 0
+        if not isinstance(documents[0], Document):
+            msg = "param 'documents' must contain a list of objects of type Document"
+            raise ValueError(msg)
+
+        if policy == DuplicatePolicy.NONE:
+            policy = DuplicatePolicy.FAIL
+
+        self._ensure_connected()
+        col = cast(StandardCollection, self._col)
+
+        arango_docs = [_doc_to_arango(doc) for doc in documents]
+        overwrite = policy == DuplicatePolicy.OVERWRITE
+        raw = col.insert_many(arango_docs, overwrite=overwrite, silent=False)
+        results = raw if isinstance(raw, list) else []
+
+        written = 0
+        for i, result in enumerate(results):
+            if isinstance(result, Exception):
+                if policy == DuplicatePolicy.FAIL:
+                    msg = f"Document with id '{documents[i].id}' already exists."
+                    raise DuplicateDocumentError(msg)
+                # SKIP: just move on
+            else:
+                written += 1
+
+        return written
+
+    def delete_documents(self, document_ids: list[str]) -> None:
+        """
+        Deletes documents by their IDs.
+
+        :param document_ids: List of document IDs to delete.
+        """
+        if not document_ids:
+            return
+        self._ensure_connected()
+        col = cast(StandardCollection, self._col)
+        col.delete_many([{"_key": doc_id} for doc_id in document_ids])
+
+    def _embedding_retrieval(
+        self,
+        query_embedding: list[float],
+        *,
+        top_k: int = 10,
+        filters: dict[str, Any] | None = None,
+    ) -> list[Document]:
+        """
+        Retrieves documents most similar to the query embedding using cosine similarity.
+
+        This method is used internally by `ArangoEmbeddingRetriever`.
+
+        :param query_embedding: The query vector.
+        :param top_k: Number of top results to return.
+        :param filters: Optional metadata filters.
+        :returns: List of `Document` objects sorted by descending similarity score.
+        """
+        if not query_embedding:
+            msg = "query_embedding must be a non-empty list of floats"
+            raise ValueError(msg)
+
+        self._ensure_connected()
+        db = cast(StandardDatabase, self._db)
+        col = cast(StandardCollection, self._col)
+        doc_count = col.count()
+        if doc_count == 0:
+            return []
+
+        self._ensure_vector_index()
+
+        aql_func, sort_order, _ = _SIMILARITY_AQL[self.similarity_function]
+        bind_vars: dict[str, Any] = {"query_vec": query_embedding, "top_k": top_k}
+
+        # ArangoDB only uses the vector index when the `APPROX_NEAR_*` call is followed
+        # directly by `SORT` + `LIMIT` with no preceding `FILTER`. Metadata filters are
+        # therefore applied *after* the vector search.
+        if filters:
+            expr, fvars = _convert_filters(filters)
+            bind_vars.update(fvars)
+            bind_vars["candidates"] = doc_count
+            aql = f"""
+            FOR doc IN (
+                FOR d IN {self.collection_name}
+                    LET score = {aql_func}(d.embedding, @query_vec)
+                    SORT score {sort_order}
+                    LIMIT @candidates
+                    RETURN MERGE(d, {{score: score}})
+            )
+                FILTER {expr}
+                LIMIT @top_k
+                RETURN doc
+            """
+        else:
+            aql = f"""
+            FOR doc IN {self.collection_name}
+                LET score = {aql_func}(doc.embedding, @query_vec)
+                SORT score {sort_order}
+                LIMIT @top_k
+                RETURN MERGE(doc, {{score: score}})
+            """
+
+        cursor = cast(Cursor, db.aql.execute(aql, bind_vars=bind_vars))
+        docs = []
+        for record in cursor:
+            score = record.pop("score", None)
+            d = _arango_to_doc(record)
+            if score is not None:
+                d = dataclasses.replace(d, score=score)
+            docs.append(d)
+        return docs
+
+    def to_dict(self) -> dict[str, Any]:
+        """
+        Serializes the component to a dictionary.
+
+        :returns: Dictionary with serialized data.
+        """
+        return default_to_dict(
+            self,
+            host=self.host,
+            database=self.database,
+            username=self.username.to_dict(),
+            password=self.password.to_dict(),
+            collection_name=self.collection_name,
+            embedding_dimension=self.embedding_dimension,
+            recreate_collection=self.recreate_collection,
+            similarity_function=self.similarity_function,
+        )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "ArangoDocumentStore":
+        """
+        Deserializes the component from a dictionary.
+
+        :param data: Dictionary to deserialize from.
+        :returns: Deserialized component.
+        """
+        deserialize_secrets_inplace(data["init_parameters"], ["password", "username"])
+        return default_from_dict(cls, data)

haystack_integrations/document_stores/arangodb/filters.py

@@ -0,0 +1,128 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from datetime import datetime
+from typing import Any
+
+from haystack.errors import FilterError
+
+
+def _is_iso_date(value: str) -> bool:
+    try:
+        datetime.fromisoformat(value)
+        return True
+    except ValueError:
+        return False
+
+
+def _field_to_aql(field: str) -> str:
+    """Maps a Haystack field name to an AQL document field reference."""
+    if field == "id":
+        return "doc._key"
+    if field == "content":
+        return "doc.content"
+    if field == "embedding":
+        return "doc.embedding"
+    if field.startswith("meta."):
+        key = field[5:]
+        return f"doc.meta.`{key}`"
+    return f"doc.`{field}`"
+
+
+def _convert_filters(filters: dict[str, Any]) -> tuple[str, dict[str, Any]]:
+    """
+    Converts a Haystack filter dict to an AQL FILTER expression and bind vars.
+
+    :param filters: Haystack filter dict.
+    :returns: Tuple of (aql_filter_string, bind_vars).
+    """
+    bind_vars: dict[str, Any] = {}
+    expr = _parse_filter(filters, bind_vars, counter=[0])
+    return expr, bind_vars
+
+
+def _parse_filter(node: dict[str, Any], bind_vars: dict[str, Any], counter: list[int]) -> str:
+    if "operator" in node and "conditions" in node:
+        op = node["operator"].upper()
+        parts = [_parse_filter(c, bind_vars, counter) for c in node["conditions"]]
+        if op == "NOT":
+            inner = " AND ".join(parts)
+            return f"(NOT ({inner}))"
+        joiner = " AND " if op == "AND" else " OR "
+        inner = joiner.join(parts)
+        return f"({inner})"
+
+    if "field" in node and "operator" in node and "value" in node:
+        return _parse_comparison(node, bind_vars, counter)
+
+    if "NOT" in node:
+        inner = _parse_filter(node["NOT"], bind_vars, counter)
+        return f"(NOT {inner})"
+
+    msg = f"Unsupported filter structure: {node}"
+    raise FilterError(msg)
+
+
+_COMPARISON_OPS = {">", ">=", "<", "<="}
+
+
+def _parse_comparison(node: dict[str, Any], bind_vars: dict[str, Any], counter: list[int]) -> str:
+    field = _field_to_aql(node["field"])
+    op = node["operator"]
+    value = node["value"]
+
+    if op in _COMPARISON_OPS:
+        if value is None:
+            return "false"
+        if isinstance(value, list):
+            msg = f"Filter operator '{op}' does not support list values."
+            raise FilterError(msg)
+        if isinstance(value, str) and not _is_iso_date(value):
+            msg = f"Filter operator '{op}' does not support non-date string values."
+            raise FilterError(msg)
+        idx = counter[0]
+        counter[0] += 1
+        var = f"fv{idx}"
+        bind_vars[var] = value
+        return f"({field} != null AND {field} {op} @{var})"
+
+    if op == "==":
+        if value is None:
+            idx = counter[0]
+            counter[0] += 1
+            var = f"fv{idx}"
+            bind_vars[var] = value
+            return f"({field} == null OR {field} == @{var})"
+        idx = counter[0]
+        counter[0] += 1
+        var = f"fv{idx}"
+        bind_vars[var] = value
+        return f"{field} == @{var}"
+
+    if op == "!=":
+        if value is None:
+            idx = counter[0]
+            counter[0] += 1
+            var = f"fv{idx}"
+            bind_vars[var] = value
+            return f"({field} != null AND {field} != @{var})"
+        idx = counter[0]
+        counter[0] += 1
+        var = f"fv{idx}"
+        bind_vars[var] = value
+        return f"{field} != @{var}"
+
+    if op in ("in", "not in"):
+        if not isinstance(value, list):
+            msg = f"Filter operator '{op}' requires a list value, got {type(value).__name__}."
+            raise FilterError(msg)
+        idx = counter[0]
+        counter[0] += 1
+        var = f"fv{idx}"
+        bind_vars[var] = value
+        aql_op = "IN" if op == "in" else "NOT IN"
+        return f"{field} {aql_op} @{var}"
+
+    msg = f"Unsupported filter operator: {op}"
+    raise FilterError(msg)