gotenberg-haystack 0.1.0__py3-none-any.whl

gotenberg_haystack-0.1.0.dist-info/METADATA

@@ -0,0 +1,48 @@
+Metadata-Version: 2.5
+Name: gotenberg-haystack
+Version: 0.1.0
+Summary: Gotenberg document to PDF converter integration for Haystack
+Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/gotenberg#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/gotenberg
+Author: Max Swain
+Author-email: deepset GmbH <info@deepset.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
+Keywords: document-conversion,gotenberg,haystack,libreoffice,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
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.10
+Requires-Dist: haystack-ai
+Requires-Dist: httpx2>=2.12.0
+Description-Content-Type: text/markdown
+
+# gotenberg-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/gotenberg-haystack.svg)](https://pypi.org/project/gotenberg-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/gotenberg-haystack.svg)](https://pypi.org/project/gotenberg-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/gotenberg)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/gotenberg/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
+
+The integration tests require a local Gotenberg service. Start the provided Gotenberg v8 container from this directory:
+
+```bash
+docker compose up -d --wait
+```
+
+Then run the integration tests with `hatch run test:integration`. Stop the service afterward with `docker compose down`.

gotenberg_haystack-0.1.0.dist-info/RECORD

@@ -0,0 +1,7 @@
+haystack_integrations/components/converters/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+haystack_integrations/components/converters/gotenberg/__init__.py,sha256=OYlaE8SFJdynvQMi8mBnAz_3gOpCkyx9UxJ5jnWLElM,248
+haystack_integrations/components/converters/gotenberg/converter.py,sha256=lJv3qKfAbPhM7uDbGmBlL12ClpyHdk2ZpUCmDOjJ73M,24519
+gotenberg_haystack-0.1.0.dist-info/METADATA,sha256=tPiv4yjgWwnei-u3Rpn72Qc8DHH-gBQIg0CS-S1XNMw,2212
+gotenberg_haystack-0.1.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+gotenberg_haystack-0.1.0.dist-info/licenses/LICENSE.txt,sha256=OrAtTu4aPmrTjKDSTzkSPgo_ji6NOMWO2N9JOTFyAzM,11350
+gotenberg_haystack-0.1.0.dist-info/RECORD,,

gotenberg_haystack-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.32.4
+Root-Is-Purelib: true
+Tag: py3-none-any

gotenberg_haystack-0.1.0.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/converters/gotenberg/__init__.py

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

haystack_integrations/components/converters/gotenberg/converter.py

@@ -0,0 +1,581 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import asyncio
+import mimetypes
+import re
+from pathlib import Path
+from typing import Any, Literal
+
+import httpx2
+from haystack import component, default_from_dict, default_to_dict
+from haystack.components.converters.utils import normalize_metadata
+from haystack.dataclasses import ByteStream
+from httpx2._types import FileTypes, RequestFiles
+from typing_extensions import Self
+
+_Route = Literal["libreoffice", "html", "markdown", "url"]
+# Supported Gotenberg LibreOffice conversion input formats:
+# https://gotenberg.dev/docs/convert-with-libreoffice/convert-to-pdf
+_LIBREOFFICE_EXTENSIONS = frozenset(
+    {
+        ".123",
+        ".602",
+        ".abw",
+        ".bib",
+        ".bmp",
+        ".cdr",
+        ".cgm",
+        ".cmx",
+        ".csv",
+        ".cwk",
+        ".dbf",
+        ".dif",
+        ".doc",
+        ".docm",
+        ".docx",
+        ".dot",
+        ".dotm",
+        ".dotx",
+        ".dxf",
+        ".emf",
+        ".eps",
+        ".epub",
+        ".fodg",
+        ".fodp",
+        ".fods",
+        ".fodt",
+        ".fopd",
+        ".gif",
+        ".htm",
+        ".html",
+        ".hwp",
+        ".jpeg",
+        ".jpg",
+        ".key",
+        ".ltx",
+        ".lwp",
+        ".mcw",
+        ".met",
+        ".mml",
+        ".mw",
+        ".numbers",
+        ".odd",
+        ".odg",
+        ".odm",
+        ".odp",
+        ".ods",
+        ".odt",
+        ".otg",
+        ".oth",
+        ".otp",
+        ".ots",
+        ".ott",
+        ".pages",
+        ".pbm",
+        ".pcd",
+        ".pct",
+        ".pcx",
+        ".pdb",
+        ".pdf",
+        ".pgm",
+        ".png",
+        ".pot",
+        ".potm",
+        ".potx",
+        ".ppm",
+        ".pps",
+        ".ppsm",
+        ".ppsx",
+        ".ppt",
+        ".pptm",
+        ".pptx",
+        ".psd",
+        ".psw",
+        ".pub",
+        ".pwp",
+        ".pxl",
+        ".ras",
+        ".rtf",
+        ".sda",
+        ".sdc",
+        ".sdd",
+        ".sdp",
+        ".sdw",
+        ".sgl",
+        ".slk",
+        ".smf",
+        ".stc",
+        ".std",
+        ".sti",
+        ".stw",
+        ".svg",
+        ".svm",
+        ".swf",
+        ".sxc",
+        ".sxd",
+        ".sxg",
+        ".sxi",
+        ".sxm",
+        ".sxw",
+        ".tga",
+        ".tif",
+        ".tiff",
+        ".txt",
+        ".uof",
+        ".uop",
+        ".uos",
+        ".uot",
+        ".vdx",
+        ".vor",
+        ".vsd",
+        ".vsdm",
+        ".vsdx",
+        ".wb2",
+        ".wk1",
+        ".wks",
+        ".wmf",
+        ".wpd",
+        ".wpg",
+        ".wps",
+        ".xbm",
+        ".xhtml",
+        ".xls",
+        ".xlsb",
+        ".xlsm",
+        ".xlsx",
+        ".xlt",
+        ".xltm",
+        ".xltx",
+        ".xlw",
+        ".xml",
+        ".xpm",
+        ".zabw",
+    }
+)
+_MIME_TYPE_EXTENSIONS = {
+    "application/epub+zip": ".epub",
+    "application/msword": ".doc",
+    "application/pdf": ".pdf",
+    "application/postscript": ".eps",
+    "application/rtf": ".rtf",
+    "application/vnd.apple.keynote": ".key",
+    "application/vnd.apple.numbers": ".numbers",
+    "application/vnd.apple.pages": ".pages",
+    "application/vnd.ms-excel": ".xls",
+    "application/vnd.ms-excel.sheet.binary.macroenabled.12": ".xlsb",
+    "application/vnd.ms-excel.sheet.macroenabled.12": ".xlsm",
+    "application/vnd.ms-excel.template.macroenabled.12": ".xltm",
+    "application/vnd.ms-powerpoint": ".ppt",
+    "application/vnd.ms-powerpoint.presentation.macroenabled.12": ".pptm",
+    "application/vnd.ms-powerpoint.slideshow.macroenabled.12": ".ppsm",
+    "application/vnd.ms-powerpoint.template.macroenabled.12": ".potm",
+    "application/vnd.ms-word.document.macroenabled.12": ".docm",
+    "application/vnd.ms-word.template.macroenabled.12": ".dotm",
+    "application/vnd.oasis.opendocument.graphics": ".odg",
+    "application/vnd.oasis.opendocument.graphics-template": ".otg",
+    "application/vnd.oasis.opendocument.presentation": ".odp",
+    "application/vnd.oasis.opendocument.presentation-template": ".otp",
+    "application/vnd.oasis.opendocument.spreadsheet": ".ods",
+    "application/vnd.oasis.opendocument.spreadsheet-template": ".ots",
+    "application/vnd.oasis.opendocument.text": ".odt",
+    "application/vnd.oasis.opendocument.text-master": ".odm",
+    "application/vnd.oasis.opendocument.text-template": ".ott",
+    "application/vnd.oasis.opendocument.text-web": ".oth",
+    "application/vnd.openxmlformats-officedocument.presentationml.presentation": ".pptx",
+    "application/vnd.openxmlformats-officedocument.presentationml.slideshow": ".ppsx",
+    "application/vnd.openxmlformats-officedocument.presentationml.template": ".potx",
+    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
+    "application/vnd.openxmlformats-officedocument.spreadsheetml.template": ".xltx",
+    "application/vnd.openxmlformats-officedocument.wordprocessingml.document": ".docx",
+    "application/vnd.openxmlformats-officedocument.wordprocessingml.template": ".dotx",
+    "application/vnd.stardivision.calc": ".sdc",
+    "application/vnd.stardivision.draw": ".sda",
+    "application/vnd.stardivision.impress": ".sdd",
+    "application/vnd.stardivision.math": ".smf",
+    "application/vnd.stardivision.writer": ".sdw",
+    "application/vnd.sun.xml.calc": ".sxc",
+    "application/vnd.sun.xml.draw": ".sxd",
+    "application/vnd.sun.xml.impress": ".sxi",
+    "application/vnd.sun.xml.math": ".sxm",
+    "application/vnd.sun.xml.writer": ".sxw",
+    "application/vnd.sun.xml.writer.global": ".sxg",
+    "application/vnd.uof.presentation": ".uop",
+    "application/vnd.uof.spreadsheet": ".uos",
+    "application/vnd.uof.text": ".uot",
+    "application/vnd.wordperfect": ".wpd",
+    "application/xml": ".xml",
+    "image/pict": ".pct",
+    "image/svg+xml": ".svg",
+    "text/csv": ".csv",
+    "text/plain": ".txt",
+    "text/rtf": ".rtf",
+    "text/xml": ".xml",
+}
+
+
+def _resources(resources: list[Path] | None) -> list[Path]:
+    """Validate resource paths once and return the normalized list."""
+    paths = resources or []
+    names: set[str] = set()
+    for resource in paths:
+        if not isinstance(resource, Path):
+            msg = f"Unsupported resource type: {type(resource).__name__}; expected Path"
+            raise TypeError(msg)
+        if not resource.is_file():
+            msg = f"Resource does not exist or is not a file: {resource}"
+            raise FileNotFoundError(msg)
+        if resource.name in names:
+            msg = f"Resource filenames must be unique: {resource.name!r}"
+            raise ValueError(msg)
+        if resource.name == "index.html":
+            msg = "A resource cannot be named 'index.html'; that name is reserved by Gotenberg"
+            raise ValueError(msg)
+        names.add(resource.name)
+    return paths
+
+
+def _source_metadata(source: str | Path | ByteStream) -> dict[str, Any]:
+    """Return metadata inherited from the source."""
+    if isinstance(source, ByteStream):
+        return source.meta
+    if isinstance(source, Path) or "://" not in source:
+        return {"file_path": str(source)}
+    return {}
+
+
+def _is_url_source(source: str) -> bool:
+    """Return whether a string is an HTTP(S) URL, rejecting malformed or unsupported URLs."""
+    if "://" not in source:
+        return False
+    try:
+        parsed = httpx2.URL(url=source)
+    except httpx2.InvalidURL as error:
+        msg = f"Malformed HTTP(S) URL source: {source!r}"
+        raise ValueError(msg) from error
+    if parsed.scheme not in {"http", "https"}:
+        msg = f"Unsupported URL scheme {parsed.scheme!r}; only HTTP(S) URLs are supported"
+        raise ValueError(msg)
+
+    if not parsed.host:
+        msg = f"Malformed HTTP(S) URL source: {source!r}; expected a valid host"
+        raise ValueError(msg)
+    return True
+
+
+@component
+class GotenbergFileConverter:
+    """
+    Automatically route local files, typed byte streams, and web URLs to Gotenberg and return ordered PDFs.
+
+    Local Markdown files use Gotenberg's Markdown route, local HTML files use its Chromium HTML route, and every
+    other supported local file uses its LibreOffice route. HTTP(S) strings use the Chromium URL route. `ByteStream`
+    sources are routed by their MIME type. Resources are validated for every batch but uploaded only with HTML and
+    Markdown sources. Output metadata preserves local source paths under `file_path` and metadata from `ByteStream`
+    sources; explicit metadata takes precedence.
+
+    ### Usage example
+
+    ```python
+    from pathlib import Path
+
+    from haystack_integrations.components.converters.gotenberg import GotenbergFileConverter
+
+    converter = GotenbergFileConverter()
+    result = converter.run(sources=[Path("report.docx"), "https://haystack.deepset.ai"])
+    pdfs = result["output"]
+    ```
+    """
+
+    def __init__(
+        self,
+        url: str = "http://localhost:3000",
+        timeout: float = 30.0,
+        concurrency_limit: int = 5,
+    ) -> None:
+        """
+        Create a Gotenberg file converter.
+
+        :param url: The URL of the Gotenberg service.
+        :param timeout: The request timeout in seconds.
+        :param concurrency_limit: Maximum number of Gotenberg requests in flight during `run_async`. Has no
+            effect on synchronous `run`, which converts one source at a time.
+        """
+        try:
+            parsed_url = httpx2.URL(url=url)
+        except httpx2.InvalidURL as error:
+            msg = "url must be a valid HTTP(S) Gotenberg service URL"
+            raise ValueError(msg) from error
+        if parsed_url.scheme not in {"http", "https"} or not parsed_url.host:
+            msg = "url must be a valid HTTP(S) Gotenberg service URL"
+            raise ValueError(msg)
+        if timeout <= 0:
+            msg = "timeout must be greater than zero"
+            raise ValueError(msg)
+        self.url = url.rstrip("/")
+        self.timeout = timeout
+        self.concurrency_limit = concurrency_limit
+
+    def to_dict(self) -> dict[str, Any]:
+        """Serialize this component to a dictionary."""
+        return default_to_dict(
+            obj=self,
+            url=self.url,
+            timeout=self.timeout,
+            concurrency_limit=self.concurrency_limit,
+        )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> Self:
+        """Deserialize this component from a dictionary."""
+        return default_from_dict(cls=cls, data=data)
+
+    @staticmethod
+    def _pdf(response: httpx2.Response, meta: dict[str, Any]) -> ByteStream:
+        """Validate a Gotenberg response and convert it to a PDF byte stream."""
+        response.raise_for_status()
+        content_type = response.headers.get("content-type", "").split(";", maxsplit=1)[0].strip().lower()
+        if content_type in {"application/zip", "application/x-zip-compressed"}:
+            msg = "Gotenberg unexpectedly returned a ZIP archive instead of one PDF"
+            raise RuntimeError(msg)
+        return ByteStream(data=bytes(response.content), meta=meta, mime_type="application/pdf")
+
+    @staticmethod
+    def _local_route(source: Path) -> _Route:
+        """Validate a local source and return its route from the file suffix."""
+        if not source.is_file():
+            msg = f"Local source file does not exist or is not a file: {source}"
+            raise FileNotFoundError(msg)
+        suffix = source.suffix.lower()
+        if not suffix:
+            msg = f"Local source filename is missing a file extension: {source.name!r}"
+            raise ValueError(msg)
+        if suffix in {".md", ".markdown"}:
+            return "markdown"
+        if suffix in {".html", ".htm", ".xhtml"}:
+            return "html"
+        if suffix in _LIBREOFFICE_EXTENSIONS:
+            return "libreoffice"
+        msg = f"Unsupported local source suffix: {suffix!r}"
+        raise ValueError(msg)
+
+    @staticmethod
+    def _byte_stream_route(source: ByteStream) -> tuple[_Route, str]:
+        """Classify a byte stream by its normalized MIME type and return its authoritative suffix."""
+        mime_type = (source.mime_type or "").split(";", maxsplit=1)[0].strip().lower()
+        if not mime_type:
+            msg = "ByteStream sources require a non-empty mime_type"
+            raise ValueError(msg)
+        if mime_type in {"text/html", "application/xhtml+xml"}:
+            return "html", ".html"
+        if mime_type in {"text/markdown", "text/x-markdown"}:
+            return "markdown", ".md"
+
+        suffix = _MIME_TYPE_EXTENSIONS.get(mime_type) or mimetypes.guess_extension(type=mime_type, strict=False)
+        if suffix is None or suffix.lower() not in _LIBREOFFICE_EXTENSIONS:
+            msg = f"Unsupported ByteStream MIME type: {mime_type!r}"
+            raise ValueError(msg)
+        return "libreoffice", suffix.lower()
+
+    @staticmethod
+    def _safe_stem(filename: str | None) -> str:
+        """Return a filesystem-safe source filename stem."""
+        stem = re.sub(pattern=r"[^A-Za-z0-9_.-]", repl="_", string=Path(filename or "document").stem)
+        return "document" if stem in {"", ".", ".."} else stem
+
+    def _prepare(
+        self,
+        sources: list[str | Path | ByteStream],
+        resources: list[Path] | None,
+    ) -> list[tuple[str, RequestFiles]]:
+        """Validate inputs and build direct multipart requests in input order."""
+        if not sources:
+            msg = "sources must contain at least one source"
+            raise ValueError(msg)
+        resource_paths = _resources(resources=resources)
+        resource_names = {resource.name for resource in resource_paths}
+        resource_files: list[tuple[str, FileTypes]] = [
+            (
+                "files",
+                (
+                    resource.name,
+                    resource.read_bytes(),
+                    mimetypes.guess_type(resource.name.lower(), strict=False)[0] or "application/octet-stream",
+                ),
+            )
+            for resource in resource_paths
+        ]
+        requests: list[tuple[str, RequestFiles]] = []
+        for index, source in enumerate(sources):
+            if isinstance(source, str) and _is_url_source(source=source):
+                requests.append(("/forms/chromium/convert/url", [("url", (None, source))]))
+                continue
+
+            filename: str | None
+            suffix: str | None = None
+            if isinstance(source, (Path, str)):
+                source_path = Path(source)
+                kind = self._local_route(source=source_path)
+                data, filename = source_path.read_bytes(), source_path.name
+            elif isinstance(source, ByteStream):
+                kind, suffix = self._byte_stream_route(source=source)
+                file_path = source.meta.get("file_path")
+                filename = Path(file_path).name if file_path else None
+                data = source.data
+            else:
+                msg = f"Unsupported source type: {type(source).__name__}; expected str, Path, or ByteStream"
+                raise TypeError(msg)
+
+            if kind == "libreoffice":
+                upload_filename = filename or f"{index}-document{suffix or ''}"
+                if suffix is not None:
+                    upload_filename = f"{index}-{self._safe_stem(filename)}{suffix}"
+                content_type = (
+                    mimetypes.guess_type(upload_filename.lower(), strict=False)[0] or "application/octet-stream"
+                )
+                requests.append(("/forms/libreoffice/convert", [("files", (upload_filename, data, content_type))]))
+                continue
+            try:
+                text = data.decode("utf-8")
+            except UnicodeDecodeError as error:
+                msg = f"{kind.upper() if kind == 'html' else kind.title()} sources must contain UTF-8 text"
+                raise ValueError(msg) from error
+            if kind == "html":
+                requests.append(
+                    ("/forms/chromium/convert/html", [("files", ("index.html", text, "text/html")), *resource_files])
+                )
+                continue
+
+            markdown_filename = f"{self._safe_stem(filename=filename)}.md"
+            if markdown_filename in resource_names:
+                msg = f"A resource conflicts with the Markdown source filename: {markdown_filename!r}"
+                raise ValueError(msg)
+            head = '<!doctype html><html><head><meta charset="utf-8"></head>'
+            template = f'{head}<body>{{{{ toHTML "{markdown_filename}" }}}}</body></html>'
+            requests.append(
+                (
+                    "/forms/chromium/convert/markdown",
+                    [
+                        ("files", ("index.html", template, "text/html")),
+                        ("files", (markdown_filename, text, "text/markdown")),
+                        *resource_files,
+                    ],
+                )
+            )
+        return requests
+
+    @component.output_types(output=list[ByteStream])
+    def run(
+        self,
+        sources: list[str | Path | ByteStream],
+        meta: dict[str, Any] | list[dict[str, Any]] | None = None,
+        *,
+        resources: list[Path] | None = None,
+    ) -> dict[str, list[ByteStream]]:
+        """
+        Convert automatically routed sources to PDF.
+
+        Each source is classified independently and converted using the corresponding Gotenberg route:
+
+        - A string containing `://` is treated as a URL. It must be an HTTP(S) URL, and Gotenberg's Chromium URL
+          route navigates to that URL and prints the resulting page to PDF.
+        - A string without `://`, or a `Path`, is treated as a local file. Markdown files (`.md` and `.markdown`) use
+          the Chromium Markdown route, HTML files (`.html`, `.htm`, and `.xhtml`) use the Chromium HTML route, and
+          other supported file extensions use the LibreOffice route.
+        - A `ByteStream` is classified by its MIME type. HTML MIME types use the Chromium HTML route, Markdown MIME
+          types use the Chromium Markdown route, and other supported MIME types use the LibreOffice route. For
+          LibreOffice conversion, the MIME type determines the staged file extension. MIME parameters such as
+          `charset=utf-8` are ignored when classifying the stream.
+
+        HTML and Markdown inputs are uploaded to Gotenberg together with `resources`, while URL inputs are fetched by
+        Gotenberg and LibreOffice inputs are uploaded as files. A mixed batch can contain any combination of these
+        source types. Routes are executed in input order, and one PDF is produced for each source. HTML and Markdown
+        `ByteStream` content must be UTF-8 text.
+
+        :param sources: Sources to convert. Strings, `Path` objects, and `ByteStream` objects are supported as
+            described above.
+        :param meta: Optional metadata to attach to the output PDFs. A single dictionary is applied to every output. A
+            list of dictionaries must have the same length as `sources` and is applied to corresponding outputs.
+            Metadata on a source `ByteStream` is preserved, with values from this parameter taking precedence.
+        :param resources: Optional local resources for HTML and Markdown conversion. Resources are validated once and
+            uploaded only with those routes. Filenames must be unique and cannot be `index.html`; a resource also
+            cannot have the same filename as a staged Markdown source.
+        :returns: A dictionary containing an `"output"` list with one PDF `ByteStream` per source, in input order.
+        :raises TypeError: If a source or resource has an unsupported type.
+        :raises FileNotFoundError: If a local source or resource does not exist or is not a file.
+        :raises ValueError: If sources, metadata, URLs, suffixes, MIME types, resources, or text contents are invalid.
+        :raises RuntimeError: If Gotenberg returns a ZIP archive instead of a PDF.
+        """
+        meta_list = normalize_metadata(meta=meta, sources_count=len(sources))
+        requests = self._prepare(sources=sources, resources=resources)
+        with httpx2.Client(base_url=self.url, timeout=self.timeout) as client:
+            output = [
+                self._pdf(
+                    response=client.post(path, files=files),
+                    meta={**_source_metadata(source=source), **source_meta},
+                )
+                for source, (path, files), source_meta in zip(sources, requests, meta_list, strict=True)
+            ]
+        return {"output": output}
+
+    @component.output_types(output=list[ByteStream])
+    async def run_async(
+        self,
+        sources: list[str | Path | ByteStream],
+        meta: dict[str, Any] | list[dict[str, Any]] | None = None,
+        *,
+        resources: list[Path] | None = None,
+    ) -> dict[str, list[ByteStream]]:
+        """
+        Asynchronously convert automatically routed sources to PDF.
+
+        This is the asynchronous equivalent of `run()` and uses the same source classification and routing rules. Each
+        source is classified independently and converted using the corresponding Gotenberg route:
+
+        - A string containing `://` is treated as a valid HTTP(S) URL and converted by Gotenberg's Chromium URL route.
+        - A string without `://`, or a `Path`, is treated as a local file. Markdown files (`.md` and `.markdown`) use
+          the Chromium Markdown route, HTML files (`.html`, `.htm`, and `.xhtml`) use the Chromium HTML route, and
+          other supported file extensions use the LibreOffice route.
+        - A `ByteStream` is classified by its MIME type: HTML MIME types use the Chromium HTML route, Markdown MIME
+          types use the Chromium Markdown route, and other supported MIME types use the LibreOffice route. The MIME
+          type determines the staged file extension for LibreOffice conversion, without its parameters (for example,
+          `charset=utf-8`).
+
+        HTML and Markdown inputs are uploaded with `resources`, URL inputs are fetched by Gotenberg, and LibreOffice
+        inputs are uploaded as files. A mixed batch can contain any combination of these source types. Routes are
+        executed in input order, and one PDF is produced for each source. HTML and Markdown `ByteStream` content must
+        be UTF-8 text.
+
+        :param sources: Sources to convert. Strings, `Path` objects, and `ByteStream` objects are supported as
+            described above.
+        :param meta: Optional metadata to attach to the output PDFs. A single dictionary is applied to every output. A
+            list of dictionaries must have the same length as `sources` and is applied to corresponding outputs.
+            Metadata on a source `ByteStream` is preserved, with values from this parameter taking precedence.
+        :param resources: Optional local resources for HTML and Markdown conversion. Resources are validated once and
+            uploaded only with those routes. Filenames must be unique and cannot be `index.html`; a resource also
+            cannot have the same filename as a staged Markdown source.
+        :returns: A dictionary containing an `"output"` list with one PDF `ByteStream` per source, in input order.
+        :raises TypeError: If a source or resource has an unsupported type.
+        :raises FileNotFoundError: If a local source or resource does not exist or is not a file.
+        :raises ValueError: If sources, metadata, URLs, suffixes, MIME types, resources, or text contents are invalid.
+        :raises RuntimeError: If Gotenberg returns a ZIP archive instead of a PDF.
+        """
+        meta_list = normalize_metadata(meta=meta, sources_count=len(sources))
+        requests = self._prepare(sources=sources, resources=resources)
+        semaphore = asyncio.Semaphore(max(1, self.concurrency_limit))
+
+        async def _runner(path: str, files: RequestFiles) -> httpx2.Response:
+            async with semaphore:
+                return await client.post(path, files=files)
+
+        async with httpx2.AsyncClient(base_url=self.url, timeout=self.timeout) as client:
+            responses = await asyncio.gather(*(_runner(path, files) for path, files in requests))
+        output = [
+            self._pdf(
+                response=response,
+                meta={**_source_metadata(source=source), **source_meta},
+            )
+            for source, response, source_meta in zip(sources, responses, meta_list, strict=True)
+        ]
+        return {"output": output}