feat: Add DocumentWriter v2 (#5435)

* add draft of WriteToStore and basic test

* add DocumentWriter implementation

* draft unit and integration tests

* add release note

* mock Store in unit tests

* pylint

* Update haystack/preview/components/writers/document_writer.py

Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>

* Remove unnecessary test

* Rework DocumentWriter to support new Component I/O definition

---------

Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
Co-authored-by: Silvano Cerza <silvanocerza@gmail.com>

haystack/preview/components/__init__.py

@@ -2,3 +2,4 @@ from haystack.preview.components.audio.whisper_local import LocalWhisperTranscri
 from haystack.preview.components.audio.whisper_remote import RemoteWhisperTranscriber
 from haystack.preview.components.file_converters import TextFileToDocument
 from haystack.preview.components.classifiers import FileExtensionClassifier
+from haystack.preview.components.writers.document_writer import DocumentWriter

haystack/preview/components/writers/document_writer.py

@@ -0,0 +1,42 @@
+from typing import List, Optional
+
+from haystack.preview import component, Document
+from haystack.preview.document_stores import DocumentStoreAwareMixin, DocumentStore, DuplicatePolicy
+
+
+@component
+class DocumentWriter(DocumentStoreAwareMixin):
+    """
+    A component for writing documents to a DocumentStore.
+    """
+
+    supported_document_stores = [DocumentStore]  # type: ignore
+
+    def __init__(self, policy: DuplicatePolicy = DuplicatePolicy.FAIL):
+        """
+        Create a DocumentWriter component.
+
+        :param policy: The policy to use when encountering duplicate documents (default is DuplicatePolicy.FAIL).
+        """
+        self.policy = policy
+
+    def run(self, documents: List[Document], policy: Optional[DuplicatePolicy] = None):
+        """
+        Run DocumentWriter on the given input data.
+
+        :param documents: A list of documents to write to the store.
+        :param policy: The policy to use when encountering duplicate documents.
+        :return: None
+
+        :raises ValueError: If the specified document store is not found.
+        """
+        if not self.document_store:
+            raise ValueError(
+                "DocumentWriter needs a DocumentStore to run: set the DocumentStore instance to the self.document_store attribute."
+            )
+
+        if policy is None:
+            policy = self.policy
+
+        self.document_store.write_documents(documents=documents, policy=policy)
+        return {}

releasenotes/notes/document-writer-v2-bbe0a62b3066f9cf.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    Added new DocumentWriter component to Haystack v2 preview so that documents can be written to stores.

test/preview/components/writers/document_writer.py

@@ -0,0 +1,36 @@
+from unittest.mock import MagicMock
+
+import pytest
+
+from haystack.preview import Document
+from haystack.preview.components.writers.document_writer import DocumentWriter
+from haystack.preview.document_stores import DuplicatePolicy
+from test.preview.components.base import BaseTestComponent
+
+
+class TestDocumentWriter(BaseTestComponent):
+    @pytest.mark.unit
+    def test_run(self):
+        writer = DocumentWriter()
+        documents = [
+            Document(content="This is the text of a document."),
+            Document(content="This is the text of another document."),
+        ]
+
+        mocked_document_store = MagicMock()
+        mocked_document_store.__haystack_document_store__ = True
+        writer.document_store = mocked_document_store
+        writer.run(documents=documents)
+
+        mocked_document_store.write_documents.assert_called_once_with(documents=documents, policy=DuplicatePolicy.FAIL)
+
+    @pytest.mark.unit
+    def test_run_without_store(self):
+        writer = DocumentWriter()
+        documents = [Document(content="test")]
+        with pytest.raises(
+            ValueError,
+            match="DocumentWriter needs a DocumentStore to run: set the DocumentStore instance to the "
+            "self.document_store attribute",
+        ):
+            writer.run(documents=documents)