azure-form-recognizer-haystack 1.0.0__py3-none-any.whl

azure_form_recognizer_haystack-1.0.0.dist-info/METADATA

@@ -0,0 +1,41 @@
+Metadata-Version: 2.4
+Name: azure-form-recognizer-haystack
+Version: 1.0.0
+Summary: Haystack integration for Azure Document Intelligence using the Form Recognizer SDK
+Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/azure_form_recognizer#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/azure_form_recognizer
+Author-email: deepset GmbH <info@deepset.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: Azure,Document Converter,Document Intelligence,Form Recognizer,Haystack,OCR,PDF
+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
+Requires-Python: >=3.10
+Requires-Dist: azure-ai-formrecognizer>=3.3.0
+Requires-Dist: haystack-ai>=2.22.0
+Requires-Dist: pandas>=2.3.3
+Description-Content-Type: text/markdown
+
+# azure-form-recognizer-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/azure-form-recognizer-haystack.svg)](https://pypi.org/project/azure-form-recognizer-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/azure-form-recognizer-haystack.svg)](https://pypi.org/project/azure-form-recognizer-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/azure-form-recognizer)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/azure_form_recognizer/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 to export the `CORE_AZURE_CS_ENDPOINT` and `CORE_AZURE_CS_API_KEY` environment variables.

azure_form_recognizer_haystack-1.0.0.dist-info/RECORD

@@ -0,0 +1,7 @@
+haystack_integrations/components/converters/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+haystack_integrations/components/converters/azure_form_recognizer/__init__.py,sha256=Kq-E_vkkr-r2ugYAgo4U8xZEkD_jDegDcFzhJmBNIGM,201
+haystack_integrations/components/converters/azure_form_recognizer/converter.py,sha256=bm631hypNhSFgEFwFlrz7KiF1hOXG7y10zMunmHL-yM,23501
+azure_form_recognizer_haystack-1.0.0.dist-info/METADATA,sha256=jdafihojmavWR1CM0FlkGo93v0TSsFGgXtv4p9Nl7sc,2191
+azure_form_recognizer_haystack-1.0.0.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+azure_form_recognizer_haystack-1.0.0.dist-info/licenses/LICENSE,sha256=_M2kulivnaiTHiW-5CRlZrPmH47tt04pBgAgeDvfYi4,11342
+azure_form_recognizer_haystack-1.0.0.dist-info/RECORD,,

azure_form_recognizer_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

azure_form_recognizer_haystack-1.0.0.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/converters/azure_form_recognizer/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from .converter import AzureOCRDocumentConverter
+
+__all__ = ["AzureOCRDocumentConverter"]

haystack_integrations/components/converters/azure_form_recognizer/converter.py

@@ -0,0 +1,477 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import copy
+import os
+from collections import defaultdict
+from pathlib import Path
+from typing import Any, Literal
+
+import networkx as nx
+from azure.ai.formrecognizer import AnalyzeResult, DocumentAnalysisClient, DocumentLine, DocumentParagraph
+from azure.core.credentials import AzureKeyCredential
+from haystack import Document, component, default_from_dict, default_to_dict, logging
+from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
+from haystack.dataclasses import ByteStream
+from haystack.utils import Secret, deserialize_secrets_inplace
+from pandas import DataFrame
+
+logger = logging.getLogger(__name__)
+
+
+@component
+class AzureOCRDocumentConverter:
+    """
+    Converts files to documents using Azure's Document Intelligence service.
+
+    Supported file formats are: PDF, JPEG, PNG, BMP, TIFF, DOCX, XLSX, PPTX, and HTML.
+
+    To use this component, you need an active Azure account
+    and a Document Intelligence or Cognitive Services resource. For help with setting up your resource, see
+    [Azure documentation](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/quickstarts/get-started-sdks-rest-api).
+
+    ### Usage example
+    ```python
+    import os
+    from datetime import datetime
+    from haystack_integrations.components.converters.azure_form_recognizer import AzureOCRDocumentConverter
+    from haystack.utils import Secret
+
+    converter = AzureOCRDocumentConverter(
+        endpoint=os.environ["CORE_AZURE_CS_ENDPOINT"],
+        api_key=Secret.from_env_var("CORE_AZURE_CS_API_KEY"),
+    )
+    results = converter.run(
+        sources=["test/test_files/pdf/react_paper.pdf"],
+        meta={"date_added": datetime.now().isoformat()},
+    )
+    documents = results["documents"]
+    print(documents[0].content)
+    # 'This is a text from the PDF file.'
+    ```
+    """
+
+    def __init__(
+        self,
+        endpoint: str,
+        api_key: Secret = Secret.from_env_var("AZURE_AI_API_KEY"),
+        model_id: str = "prebuilt-read",
+        preceding_context_len: int = 3,
+        following_context_len: int = 3,
+        merge_multiple_column_headers: bool = True,
+        page_layout: Literal["natural", "single_column"] = "natural",
+        threshold_y: float | None = 0.05,
+        store_full_path: bool = False,
+    ) -> None:
+        """
+        Creates an AzureOCRDocumentConverter component.
+
+        :param endpoint:
+            The endpoint of your Azure resource.
+        :param api_key:
+            The API key of your Azure resource.
+        :param model_id:
+            The ID of the model you want to use. For a list of available models, see [Azure documentation]
+            (https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/choose-model-feature).
+        :param preceding_context_len: Number of lines before a table to include as preceding context
+            (this will be added to the metadata).
+        :param following_context_len: Number of lines after a table to include as subsequent context (
+            this will be added to the metadata).
+        :param merge_multiple_column_headers: If `True`, merges multiple column header rows into a single row.
+        :param page_layout: The type reading order to follow. Possible options:
+            - `natural`: Uses the natural reading order determined by Azure.
+            - `single_column`: Groups all lines with the same height on the page based on a threshold
+            determined by `threshold_y`.
+        :param threshold_y: Only relevant if `single_column` is set to `page_layout`.
+            The threshold, in inches, to determine if two recognized PDF elements are grouped into a
+            single line. This is crucial for section headers or numbers which may be spatially separated
+            from the remaining text on the horizontal axis.
+        :param store_full_path:
+            If True, the full path of the file is stored in the metadata of the document.
+            If False, only the file name is stored.
+        """
+        self.document_analysis_client = DocumentAnalysisClient(
+            endpoint=endpoint, credential=AzureKeyCredential(api_key.resolve_value() or "")
+        )
+        self.endpoint = endpoint
+        self.model_id = model_id
+        self.api_key = api_key
+        self.preceding_context_len = preceding_context_len
+        self.following_context_len = following_context_len
+        self.merge_multiple_column_headers = merge_multiple_column_headers
+        self.page_layout = page_layout
+        self.threshold_y = threshold_y
+        self.store_full_path = store_full_path
+        if self.page_layout == "single_column" and self.threshold_y is None:
+            self.threshold_y = 0.05
+
+    @component.output_types(documents=list[Document], raw_azure_response=list[dict])
+    def run(
+        self, sources: list[str | Path | ByteStream], meta: dict[str, Any] | list[dict[str, Any]] | None = None
+    ) -> dict[str, Any]:
+        """
+        Convert a list of files to Documents using Azure's Document Intelligence service.
+
+        :param sources:
+            List of file paths or ByteStream objects.
+        :param meta:
+            Optional metadata to attach to the Documents.
+            This value can be either a list of dictionaries or a single dictionary.
+            If it's a single dictionary, its content is added to the metadata of all produced Documents.
+            If it's a list, the length of the list must match the number of sources, because the two lists will be
+            zipped. If `sources` contains ByteStream objects, their `meta` will be added to the output Documents.
+
+        :returns:
+            A dictionary with the following keys:
+            - `documents`: List of created Documents
+            - `raw_azure_response`: List of raw Azure responses used to create the Documents
+        """
+        documents = []
+        azure_output = []
+        meta_list: list[dict[str, Any]] = normalize_metadata(meta=meta, sources_count=len(sources))
+        for source, metadata in zip(sources, meta_list, strict=True):
+            try:
+                bytestream = get_bytestream_from_source(source=source)
+            except Exception as e:
+                logger.warning("Could not read {source}. Skipping it. Error: {error}", source=source, error=e)
+                continue
+
+            poller = self.document_analysis_client.begin_analyze_document(
+                model_id=self.model_id, document=bytestream.data
+            )
+            result = poller.result()
+            azure_output.append(result.to_dict())
+
+            merged_metadata = {**bytestream.meta, **metadata}
+
+            if not self.store_full_path and (file_path := bytestream.meta.get("file_path")):
+                merged_metadata["file_path"] = os.path.basename(file_path)
+            docs = self._convert_tables_and_text(result=result, meta=merged_metadata)
+            documents.extend(docs)
+
+        return {"documents": documents, "raw_azure_response": azure_output}
+
+    def to_dict(self) -> dict[str, Any]:
+        """
+        Serializes the component to a dictionary.
+
+        :returns:
+            Dictionary with serialized data.
+        """
+        return default_to_dict(
+            self,
+            api_key=self.api_key.to_dict(),
+            endpoint=self.endpoint,
+            model_id=self.model_id,
+            preceding_context_len=self.preceding_context_len,
+            following_context_len=self.following_context_len,
+            merge_multiple_column_headers=self.merge_multiple_column_headers,
+            page_layout=self.page_layout,
+            threshold_y=self.threshold_y,
+            store_full_path=self.store_full_path,
+        )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "AzureOCRDocumentConverter":
+        """
+        Deserializes the component from a dictionary.
+
+        :param data:
+            The dictionary to deserialize from.
+        :returns:
+            The deserialized component.
+        """
+        deserialize_secrets_inplace(data["init_parameters"], keys=["api_key"])
+        return default_from_dict(cls, data)
+
+    def _convert_tables_and_text(self, result: AnalyzeResult, meta: dict[str, Any] | None) -> list[Document]:
+        """
+        Converts the tables and text extracted by Azure's Document Intelligence service into Haystack Documents.
+
+        :param result: The AnalyzeResult object returned by the `begin_analyze_document` method. Docs on Analyze result
+            can be found [here](https://azuresdkdocs.blob.core.windows.net/$web/python/azure-ai-formrecognizer/3.3.0/azure.ai.formrecognizer.html?highlight=read#azure.ai.formrecognizer.AnalyzeResult).
+        :param meta: Optional dictionary with metadata that shall be attached to all resulting documents.
+            Can be any custom keys and values.
+        :returns: List of Documents containing the tables and text extracted from the AnalyzeResult object.
+        """
+        tables = self._convert_tables(result=result, meta=meta)
+        if self.page_layout == "natural":
+            text = self._convert_to_natural_text(result=result, meta=meta)
+        else:
+            threshold_y = self.threshold_y if self.threshold_y is not None else 0.05
+            text = self._convert_to_single_column_text(result=result, meta=meta, threshold_y=threshold_y)
+        return [*tables, text]
+
+    def _convert_tables(self, result: AnalyzeResult, meta: dict[str, Any] | None) -> list[Document]:
+        """
+        Converts the tables extracted by Azure's Document Intelligence service into Haystack Documents.
+
+        :param result: The AnalyzeResult Azure object
+        :param meta: Optional dictionary with metadata that shall be attached to all resulting documents.
+
+        :returns: List of Documents containing the tables extracted from the AnalyzeResult object.
+        """
+        converted_tables: list[Document] = []
+
+        if not result.tables:
+            return converted_tables
+
+        for table in result.tables:
+            # Initialize table with empty cells
+            table_list = [[""] * table.column_count for _ in range(table.row_count)]
+            additional_column_header_rows = set()
+            caption = ""
+            row_idx_start = 0
+
+            for idx, cell in enumerate(table.cells):
+                # Remove ':selected:'/':unselected:' tags from cell's content
+                cell.content = cell.content.replace(":selected:", "")
+                cell.content = cell.content.replace(":unselected:", "")
+
+                # Check if first row is a merged cell spanning whole table
+                # -> exclude this row and use as a caption
+                if idx == 0 and cell.column_span == table.column_count:
+                    caption = cell.content
+                    row_idx_start = 1
+                    table_list.pop(0)
+                    continue
+
+                column_span = cell.column_span if cell.column_span else 0
+                for c in range(column_span):
+                    row_span = cell.row_span if cell.row_span else 0
+                    for r in range(row_span):
+                        if (
+                            self.merge_multiple_column_headers
+                            and cell.kind == "columnHeader"
+                            and cell.row_index > row_idx_start
+                        ):
+                            # More than one row serves as column header
+                            table_list[0][cell.column_index + c] += f"\n{cell.content}"
+                            additional_column_header_rows.add(cell.row_index - row_idx_start)
+                        else:
+                            table_list[cell.row_index + r - row_idx_start][cell.column_index + c] = cell.content
+
+            # Remove additional column header rows, as these got attached to the first row
+            for row_idx in sorted(additional_column_header_rows, reverse=True):
+                del table_list[row_idx]
+
+            # Get preceding context of table
+            if table.bounding_regions:
+                table_beginning_page = next(
+                    page for page in result.pages if page.page_number == table.bounding_regions[0].page_number
+                )
+            else:
+                table_beginning_page = None
+            table_start_offset = table.spans[0].offset
+            if table_beginning_page and table_beginning_page.lines:
+                preceding_lines = [
+                    line.content for line in table_beginning_page.lines if line.spans[0].offset < table_start_offset
+                ]
+            else:
+                preceding_lines = []
+            preceding_context = "\n".join(preceding_lines[-self.preceding_context_len :]) + f"\n{caption}"
+            preceding_context = preceding_context.strip()
+
+            # Get following context
+            if table.bounding_regions and len(table.bounding_regions) == 1:
+                table_end_page = table_beginning_page
+            elif table.bounding_regions:
+                table_end_page = next(
+                    page for page in result.pages if page.page_number == table.bounding_regions[-1].page_number
+                )
+            else:
+                table_end_page = None
+
+            table_end_offset = table_start_offset + table.spans[0].length
+            if table_end_page and table_end_page.lines:
+                following_lines = [
+                    line.content for line in table_end_page.lines if line.spans[0].offset > table_end_offset
+                ]
+            else:
+                following_lines = []
+            following_context = "\n".join(following_lines[: self.following_context_len])
+
+            table_meta = copy.deepcopy(meta)
+
+            if isinstance(table_meta, dict):
+                table_meta["preceding_context"] = preceding_context
+                table_meta["following_context"] = following_context
+            else:
+                table_meta = {"preceding_context": preceding_context, "following_context": following_context}
+
+            if table.bounding_regions:
+                table_meta["page"] = table.bounding_regions[0].page_number
+
+            # Convert table to CSV
+            table_df = DataFrame(data=table_list)
+            table_content = table_df.to_csv(header=False, index=False, lineterminator="\n")
+            converted_tables.append(Document(content=table_content, meta=table_meta))
+
+        return converted_tables
+
+    def _convert_to_natural_text(self, result: AnalyzeResult, meta: dict[str, Any] | None) -> Document:
+        """
+        This converts the `AnalyzeResult` object into a single document.
+
+        We add "\f" separators between to differentiate between the text on separate pages. This is the expected format
+        for the PreProcessor.
+
+        :param result: The AnalyzeResult object returned by the `begin_analyze_document` method. Docs on Analyze result
+            can be found [here](https://azuresdkdocs.blob.core.windows.net/$web/python/azure-ai-formrecognizer/3.3.0/azure.ai.formrecognizer.html?highlight=read#azure.ai.formrecognizer.AnalyzeResult).
+        :param meta: Optional dictionary with metadata that shall be attached to all resulting documents.
+            Can be any custom keys and values.
+        :returns: A single Document containing all the text extracted from the AnalyzeResult object.
+        """
+        table_spans_by_page = self._collect_table_spans(result=result)
+
+        texts = []
+        if result.paragraphs:
+            paragraphs_to_pages: dict[int, str] = defaultdict(str)
+            for paragraph in result.paragraphs:
+                if paragraph.bounding_regions:
+                    # If paragraph spans multiple pages we group it with the first page number
+                    page_numbers = [b.page_number for b in paragraph.bounding_regions]
+                else:
+                    # If page_number is not available we put the paragraph onto an existing page
+                    current_last_page_number = sorted(paragraphs_to_pages.keys())[-1] if paragraphs_to_pages else 1
+                    page_numbers = [current_last_page_number]
+                tables_on_page = table_spans_by_page[page_numbers[0]]
+                # Check if paragraph is part of a table and if so skip
+                if self._check_if_in_table(tables_on_page, line_or_paragraph=paragraph):
+                    continue
+                paragraphs_to_pages[page_numbers[0]] += paragraph.content + "\n"
+
+            max_page_number: int = max(paragraphs_to_pages)
+            for page_idx in range(1, max_page_number + 1):
+                # We add empty strings for missing pages so the preprocessor can still extract the correct page number
+                # from the original PDF.
+                page_text = paragraphs_to_pages.get(page_idx, "")
+                texts.append(page_text)
+        else:
+            logger.warning("No text paragraphs were detected by the OCR conversion.")
+
+        all_text = "\f".join(texts)
+        return Document(content=all_text, meta=meta if meta else {})
+
+    def _convert_to_single_column_text(
+        self, result: AnalyzeResult, meta: dict[str, str] | None, threshold_y: float = 0.05
+    ) -> Document:
+        """
+        This converts the `AnalyzeResult` object into a single Haystack Document.
+
+        We add "\f" separators between to differentiate between the text on separate pages. This is the expected format
+        for the PreProcessor.
+
+        :param result: The AnalyzeResult object returned by the `begin_analyze_document` method. Docs on Analyze result
+            can be found [here](https://azuresdkdocs.blob.core.windows.net/$web/python/azure-ai-formrecognizer/3.3.0/azure.ai.formrecognizer.html?highlight=read#azure.ai.formrecognizer.AnalyzeResult).
+        :param meta: Optional dictionary with metadata that shall be attached to all resulting documents.
+            Can be any custom keys and values.
+        :param threshold_y: height threshold in inches for PDF and pixels for images
+        :returns: A single Document containing all the text extracted from the AnalyzeResult object.
+        """
+        table_spans_by_page = self._collect_table_spans(result=result)
+
+        # Find all pairs of lines that should be grouped together based on the y-value of the upper left coordinate
+        # of their bounding box
+        pairs_by_page = defaultdict(list)
+        for page_idx, page in enumerate(result.pages):
+            lines = page.lines if page.lines else []
+            # Only works if polygons is available
+            if all(line.polygon is not None for line in lines):
+                for i in range(len(lines)):
+                    # left_upi, right_upi, right_lowi, left_lowi = lines[i].polygon
+                    left_upi, _, _, _ = lines[i].polygon
+                    pairs_by_page[page_idx].append([i, i])
+                    for j in range(i + 1, len(lines)):
+                        left_upj, _, _, _ = lines[j].polygon
+                        close_on_y_axis = abs(left_upi[1] - left_upj[1]) < threshold_y
+                        if close_on_y_axis:
+                            pairs_by_page[page_idx].append([i, j])
+            # Default if polygon is not available
+            else:
+                logger.info(
+                    "Polygon information for lines on page {page_idx} is not available so it is not possible "
+                    "to enforce a single column page layout.",
+                    page_idx=page_idx,
+                )
+                for i in range(len(lines)):
+                    pairs_by_page[page_idx].append([i, i])
+
+        # merged the line pairs that are connected by page
+        merged_pairs_by_page = {}
+        for page_idx in pairs_by_page:
+            graph = nx.Graph()
+            graph.add_edges_from(pairs_by_page[page_idx])
+            merged_pairs_by_page[page_idx] = [list(a) for a in list(nx.connected_components(graph))]
+
+        # Convert line indices to the DocumentLine objects
+        merged_lines_by_page = {}
+        for page_idx, page in enumerate(result.pages):
+            rows = []
+            lines = page.lines if page.lines else []
+            # We use .get(page_idx, []) since the page could be empty
+            for row_of_lines in merged_pairs_by_page.get(page_idx, []):
+                lines_in_row = [lines[line_idx] for line_idx in row_of_lines]
+                rows.append(lines_in_row)
+            merged_lines_by_page[page_idx] = rows
+
+        # Sort the merged pairs in each row by the x-value of the upper left bounding box coordinate
+        x_sorted_lines_by_page = {}
+        for page_idx, _ in enumerate(result.pages):
+            sorted_rows = []
+            for row_of_lines in merged_lines_by_page[page_idx]:
+                sorted_rows.append(sorted(row_of_lines, key=lambda x: x.polygon[0][0]))
+            x_sorted_lines_by_page[page_idx] = sorted_rows
+
+        # Sort each row within the page by the y-value of the upper left bounding box coordinate
+        y_sorted_lines_by_page = {}
+        for page_idx, _ in enumerate(result.pages):
+            sorted_rows = sorted(x_sorted_lines_by_page[page_idx], key=lambda x: x[0].polygon[0][1])
+            y_sorted_lines_by_page[page_idx] = sorted_rows
+
+        # Construct the text to write
+        texts = []
+        for page_idx, page in enumerate(result.pages):
+            tables_on_page = table_spans_by_page[page.page_number]
+            page_text = ""
+            for row_of_lines in y_sorted_lines_by_page[page_idx]:
+                # Check if line is part of a table and if so skip
+                if any(self._check_if_in_table(tables_on_page, line_or_paragraph=line) for line in row_of_lines):
+                    continue
+                page_text += " ".join(line.content for line in row_of_lines)
+                page_text += "\n"
+            texts.append(page_text)
+        all_text = "\f".join(texts)
+        return Document(content=all_text, meta=meta if meta else {})
+
+    def _collect_table_spans(self, result: AnalyzeResult) -> dict:
+        """
+        Collect the spans of all tables by page number.
+
+        :param result: The AnalyzeResult object returned by the `begin_analyze_document` method.
+        :returns: A dictionary with the page number as key and a list of table spans as value.
+        """
+        table_spans_by_page = defaultdict(list)
+        tables = result.tables if result.tables else []
+        for table in tables:
+            if not table.bounding_regions:
+                continue
+            table_spans_by_page[table.bounding_regions[0].page_number].append(table.spans[0])
+        return table_spans_by_page
+
+    def _check_if_in_table(self, tables_on_page: dict, line_or_paragraph: DocumentLine | DocumentParagraph) -> bool:
+        """
+        Check if a line or paragraph is part of a table.
+
+        :param tables_on_page: A dictionary with the page number as key and a list of table spans as value.
+        :param line_or_paragraph: The line or paragraph to check.
+        :returns: True if the line or paragraph is part of a table, False otherwise.
+        """
+        in_table = False
+        # Check if line is part of a table
+        for table in tables_on_page:
+            if table.offset <= line_or_paragraph.spans[0].offset <= table.offset + table.length:
+                in_table = True
+                break
+        return in_table