Add DOCX file parsing support to FileParserBlock (#4710)

Co-authored-by: Suchintan Singh <suchintan@skyvern.com>

pyproject.toml

@@ -67,6 +67,7 @@ dependencies = [
     "azure-keyvault-secrets>=4.2.0,<5",
     "jsonschema>=4.25.1",
     "python-calamine>=0.6.1",
+    "python-docx>=1.1.0",
     "urllib3>=2.6.0",
     "zstandard>=0.25.0",
     "sse-starlette>=3.0.3,<4",

skyvern/forge/sdk/workflow/models/block.py

@@ -20,6 +20,7 @@ from urllib.parse import quote, urlparse
 
 import aiofiles
 import aiohttp
+import docx
 import filetype
 import pandas as pd
 import pyotp
@@ -35,6 +36,7 @@ from skyvern.config import settings
 from skyvern.constants import (
     AZURE_BLOB_STORAGE_MAX_UPLOAD_FILE_COUNT,
     GET_DOWNLOADED_FILES_TIMEOUT,
+    MAX_FILE_PARSE_INPUT_TOKENS,
     MAX_UPLOAD_FILE_COUNT,
 )
 from skyvern.exceptions import (
@@ -76,6 +78,7 @@ from skyvern.forge.sdk.services.bitwarden import BitwardenConstants
 from skyvern.forge.sdk.services.credentials import AzureVaultConstants, OnePasswordConstants
 from skyvern.forge.sdk.trace import traced
 from skyvern.forge.sdk.utils.pdf_parser import extract_pdf_file, validate_pdf_file
+from skyvern.forge.sdk.utils.sanitization import sanitize_postgres_text
 from skyvern.forge.sdk.workflow.context_manager import BlockMetadata, WorkflowRunContext
 from skyvern.forge.sdk.workflow.exceptions import (
     CustomizedCodeException,
@@ -100,6 +103,7 @@ from skyvern.schemas.runs import RunEngine
 from skyvern.schemas.workflows import BlockResult, BlockStatus, BlockType, FileStorageType, FileType
 from skyvern.utils.strings import generate_random_string
 from skyvern.utils.templating import get_missing_variables
+from skyvern.utils.token_counter import count_tokens
 from skyvern.utils.url_validators import prepend_scheme_and_validate_url
 from skyvern.webeye.browser_state import BrowserState
 from skyvern.webeye.utils.page import SkyvernFrame
@@ -3065,6 +3069,14 @@ class FileParserBlock(Block):
             return FileType.CSV  # TSV files are handled by the CSV parser
         elif suffix in (".png", ".jpg", ".jpeg", ".gif", ".bmp", ".webp", ".tiff", ".tif"):
             return FileType.IMAGE
+        elif suffix == ".docx":
+            return FileType.DOCX
+        elif suffix == ".doc":
+            raise InvalidFileType(
+                file_url=file_url,
+                file_type=FileType.DOCX,
+                error="Legacy .doc format (Word 97-2003) is not supported. Please convert the file to .docx format.",
+            )
         else:
             return FileType.CSV  # Default to CSV for .csv and any other extensions
 
@@ -3120,6 +3132,14 @@ class FileParserBlock(Block):
                 raise InvalidFileType(
                     file_url=file_url_used, file_type=self.file_type, error="File is not a valid image"
                 )
+        elif self.file_type == FileType.DOCX:
+            try:
+                # Try to open the file with python-docx to validate it's a valid DOCX file
+                docx.Document(file_path)
+            except Exception as e:
+                raise InvalidFileType(
+                    file_url=file_url_used, file_type=self.file_type, error=f"Invalid DOCX file format: {str(e)}"
+                )
 
     async def _parse_csv_file(self, file_path: str) -> list[dict[str, Any]]:
         """Parse CSV/TSV file and return list of dictionaries."""
@@ -3213,6 +3233,76 @@ class FileParserBlock(Block):
             LOG.exception("Failed to extract text from image via OCR", file_url=self.file_url)
             raise
 
+    async def _parse_docx_file(self, file_path: str, max_tokens: int = MAX_FILE_PARSE_INPUT_TOKENS) -> str:
+        """Parse DOCX file and return extracted text.
+
+        Extracts text from all paragraphs and tables in the document,
+        respecting the token limit.
+        """
+        try:
+            document = docx.Document(file_path)
+            text_parts = []
+            current_tokens = 0
+            truncated = False
+
+            # Extract text from paragraphs
+            for paragraph in document.paragraphs:
+                if paragraph.text.strip():
+                    para_tokens = count_tokens(paragraph.text)
+                    if max_tokens and current_tokens + para_tokens > max_tokens:
+                        LOG.warning(
+                            "DOCX text exceeds token limit, truncating",
+                            file_url=self.file_url,
+                            current_tokens=current_tokens,
+                            max_tokens=max_tokens,
+                        )
+                        truncated = True
+                        break
+                    text_parts.append(paragraph.text)
+                    current_tokens += para_tokens
+
+            # Extract text from tables (only if not already truncated)
+            if not truncated:
+                for table in document.tables:
+                    if truncated:
+                        break
+                    for row in table.rows:
+                        row_text = []
+                        for cell in row.cells:
+                            cell_text = cell.text.strip()
+                            if cell_text:
+                                row_text.append(cell_text)
+                        if row_text:
+                            row_str = " | ".join(row_text)
+                            row_tokens = count_tokens(row_str)
+                            if max_tokens and current_tokens + row_tokens > max_tokens:
+                                LOG.warning(
+                                    "DOCX text exceeds token limit, truncating at table",
+                                    file_url=self.file_url,
+                                    current_tokens=current_tokens,
+                                    max_tokens=max_tokens,
+                                )
+                                truncated = True
+                                break
+                            text_parts.append(row_str)
+                            current_tokens += row_tokens
+
+            extracted_text = "\n".join(text_parts)
+            extracted_text = sanitize_postgres_text(extracted_text)
+            LOG.info(
+                "Successfully parsed DOCX file",
+                file_url=self.file_url,
+                paragraph_count=len(document.paragraphs),
+                table_count=len(document.tables),
+                text_length=len(extracted_text),
+                truncated=truncated,
+            )
+            return extracted_text
+        except Exception as e:
+            raise InvalidFileType(
+                file_url=self.file_url, file_type=self.file_type, error=f"Failed to parse DOCX file: {str(e)}"
+            )
+
     async def _extract_with_ai(
         self, content: str | list[dict[str, Any]], workflow_run_context: WorkflowRunContext
     ) -> dict[str, Any]:
@@ -3289,8 +3379,8 @@ class FileParserBlock(Block):
         else:
             file_path = await download_file(self.file_url)
 
-        # Auto-detect file type if not explicitly set (IMAGE/EXCEL/PDF are explicit choices)
+        # Auto-detect file type if not explicitly set (IMAGE/EXCEL/PDF/DOCX are explicit choices)
-        if self.file_type not in (FileType.IMAGE, FileType.EXCEL, FileType.PDF):
+        if self.file_type not in (FileType.IMAGE, FileType.EXCEL, FileType.PDF, FileType.DOCX):
             self.file_type = self._detect_file_type_from_url(self.file_url)
 
         # Validate the file type
@@ -3313,6 +3403,8 @@ class FileParserBlock(Block):
             parsed_data = await self._parse_pdf_file(file_path)
         elif self.file_type == FileType.IMAGE:
             parsed_data = await self._parse_image_file(file_path)
+        elif self.file_type == FileType.DOCX:
+            parsed_data = await self._parse_docx_file(file_path)
         else:
             return await self.build_block_result(
                 success=False,

skyvern/schemas/workflows.py

@@ -382,6 +382,7 @@ class FileType(StrEnum):
     EXCEL = "excel"
     PDF = "pdf"
     IMAGE = "image"
+    DOCX = "docx"
 
 
 class PDFFormat(StrEnum):

uv.lock

@@ -2730,6 +2730,72 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f9/b4/55e885834c847ea610e111d87b9ed4768f0afdaeebc00cd46810f25029f6/lupa-2.6-cp313-cp313-win_amd64.whl", hash = "sha256:b1335a5835b0a25ebdbc75cf0bda195e54d133e4d994877ef025e218c2e59db9", size = 1683424, upload-time = "2025-10-24T07:18:50.976Z" },
 ]
 
+[[package]]
+name = "lxml"
+version = "6.0.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/aa/88/262177de60548e5a2bfc46ad28232c9e9cbde697bd94132aeb80364675cb/lxml-6.0.2.tar.gz", hash = "sha256:cd79f3367bd74b317dda655dc8fcfa304d9eb6e4fb06b7168c5cf27f96e0cd62", size = 4073426, upload-time = "2025-09-22T04:04:59.287Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/77/d5/becbe1e2569b474a23f0c672ead8a29ac50b2dc1d5b9de184831bda8d14c/lxml-6.0.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:13e35cbc684aadf05d8711a5d1b5857c92e5e580efa9a0d2be197199c8def607", size = 8634365, upload-time = "2025-09-22T04:00:45.672Z" },
+    { url = "https://files.pythonhosted.org/packages/28/66/1ced58f12e804644426b85d0bb8a4478ca77bc1761455da310505f1a3526/lxml-6.0.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3b1675e096e17c6fe9c0e8c81434f5736c0739ff9ac6123c87c2d452f48fc938", size = 4650793, upload-time = "2025-09-22T04:00:47.783Z" },
+    { url = "https://files.pythonhosted.org/packages/11/84/549098ffea39dfd167e3f174b4ce983d0eed61f9d8d25b7bf2a57c3247fc/lxml-6.0.2-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8ac6e5811ae2870953390452e3476694196f98d447573234592d30488147404d", size = 4944362, upload-time = "2025-09-22T04:00:49.845Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/bd/f207f16abf9749d2037453d56b643a7471d8fde855a231a12d1e095c4f01/lxml-6.0.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:5aa0fc67ae19d7a64c3fe725dc9a1bb11f80e01f78289d05c6f62545affec438", size = 5083152, upload-time = "2025-09-22T04:00:51.709Z" },
+    { url = "https://files.pythonhosted.org/packages/15/ae/bd813e87d8941d52ad5b65071b1affb48da01c4ed3c9c99e40abb266fbff/lxml-6.0.2-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:de496365750cc472b4e7902a485d3f152ecf57bd3ba03ddd5578ed8ceb4c5964", size = 5023539, upload-time = "2025-09-22T04:00:53.593Z" },
+    { url = "https://files.pythonhosted.org/packages/02/cd/9bfef16bd1d874fbe0cb51afb00329540f30a3283beb9f0780adbb7eec03/lxml-6.0.2-cp311-cp311-manylinux_2_26_i686.manylinux_2_28_i686.whl", hash = "sha256:200069a593c5e40b8f6fc0d84d86d970ba43138c3e68619ffa234bc9bb806a4d", size = 5344853, upload-time = "2025-09-22T04:00:55.524Z" },
+    { url = "https://files.pythonhosted.org/packages/b8/89/ea8f91594bc5dbb879734d35a6f2b0ad50605d7fb419de2b63d4211765cc/lxml-6.0.2-cp311-cp311-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7d2de809c2ee3b888b59f995625385f74629707c9355e0ff856445cdcae682b7", size = 5225133, upload-time = "2025-09-22T04:00:57.269Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/37/9c735274f5dbec726b2db99b98a43950395ba3d4a1043083dba2ad814170/lxml-6.0.2-cp311-cp311-manylinux_2_31_armv7l.whl", hash = "sha256:b2c3da8d93cf5db60e8858c17684c47d01fee6405e554fb55018dd85fc23b178", size = 4677944, upload-time = "2025-09-22T04:00:59.052Z" },
+    { url = "https://files.pythonhosted.org/packages/20/28/7dfe1ba3475d8bfca3878365075abe002e05d40dfaaeb7ec01b4c587d533/lxml-6.0.2-cp311-cp311-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:442de7530296ef5e188373a1ea5789a46ce90c4847e597856570439621d9c553", size = 5284535, upload-time = "2025-09-22T04:01:01.335Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/cf/5f14bc0de763498fc29510e3532bf2b4b3a1c1d5d0dff2e900c16ba021ef/lxml-6.0.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:2593c77efde7bfea7f6389f1ab249b15ed4aa5bc5cb5131faa3b843c429fbedb", size = 5067343, upload-time = "2025-09-22T04:01:03.13Z" },
+    { url = "https://files.pythonhosted.org/packages/1c/b0/bb8275ab5472f32b28cfbbcc6db7c9d092482d3439ca279d8d6fa02f7025/lxml-6.0.2-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:3e3cb08855967a20f553ff32d147e14329b3ae70ced6edc2f282b94afbc74b2a", size = 4725419, upload-time = "2025-09-22T04:01:05.013Z" },
+    { url = "https://files.pythonhosted.org/packages/25/4c/7c222753bc72edca3b99dbadba1b064209bc8ed4ad448af990e60dcce462/lxml-6.0.2-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:2ed6c667fcbb8c19c6791bbf40b7268ef8ddf5a96940ba9404b9f9a304832f6c", size = 5275008, upload-time = "2025-09-22T04:01:07.327Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/8c/478a0dc6b6ed661451379447cdbec77c05741a75736d97e5b2b729687828/lxml-6.0.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b8f18914faec94132e5b91e69d76a5c1d7b0c73e2489ea8929c4aaa10b76bbf7", size = 5248906, upload-time = "2025-09-22T04:01:09.452Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/d9/5be3a6ab2784cdf9accb0703b65e1b64fcdd9311c9f007630c7db0cfcce1/lxml-6.0.2-cp311-cp311-win32.whl", hash = "sha256:6605c604e6daa9e0d7f0a2137bdc47a2e93b59c60a65466353e37f8272f47c46", size = 3610357, upload-time = "2025-09-22T04:01:11.102Z" },
+    { url = "https://files.pythonhosted.org/packages/e2/7d/ca6fb13349b473d5732fb0ee3eec8f6c80fc0688e76b7d79c1008481bf1f/lxml-6.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:e5867f2651016a3afd8dd2c8238baa66f1e2802f44bc17e236f547ace6647078", size = 4036583, upload-time = "2025-09-22T04:01:12.766Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/a2/51363b5ecd3eab46563645f3a2c3836a2fc67d01a1b87c5017040f39f567/lxml-6.0.2-cp311-cp311-win_arm64.whl", hash = "sha256:4197fb2534ee05fd3e7afaab5d8bfd6c2e186f65ea7f9cd6a82809c887bd1285", size = 3680591, upload-time = "2025-09-22T04:01:14.874Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/c8/8ff2bc6b920c84355146cd1ab7d181bc543b89241cfb1ebee824a7c81457/lxml-6.0.2-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:a59f5448ba2ceccd06995c95ea59a7674a10de0810f2ce90c9006f3cbc044456", size = 8661887, upload-time = "2025-09-22T04:01:17.265Z" },
+    { url = "https://files.pythonhosted.org/packages/37/6f/9aae1008083bb501ef63284220ce81638332f9ccbfa53765b2b7502203cf/lxml-6.0.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:e8113639f3296706fbac34a30813929e29247718e88173ad849f57ca59754924", size = 4667818, upload-time = "2025-09-22T04:01:19.688Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/ca/31fb37f99f37f1536c133476674c10b577e409c0a624384147653e38baf2/lxml-6.0.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:a8bef9b9825fa8bc816a6e641bb67219489229ebc648be422af695f6e7a4fa7f", size = 4950807, upload-time = "2025-09-22T04:01:21.487Z" },
+    { url = "https://files.pythonhosted.org/packages/da/87/f6cb9442e4bada8aab5ae7e1046264f62fdbeaa6e3f6211b93f4c0dd97f1/lxml-6.0.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:65ea18d710fd14e0186c2f973dc60bb52039a275f82d3c44a0e42b43440ea534", size = 5109179, upload-time = "2025-09-22T04:01:23.32Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/20/a7760713e65888db79bbae4f6146a6ae5c04e4a204a3c48896c408cd6ed2/lxml-6.0.2-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c371aa98126a0d4c739ca93ceffa0fd7a5d732e3ac66a46e74339acd4d334564", size = 5023044, upload-time = "2025-09-22T04:01:25.118Z" },
+    { url = "https://files.pythonhosted.org/packages/a2/b0/7e64e0460fcb36471899f75831509098f3fd7cd02a3833ac517433cb4f8f/lxml-6.0.2-cp312-cp312-manylinux_2_26_i686.manylinux_2_28_i686.whl", hash = "sha256:700efd30c0fa1a3581d80a748157397559396090a51d306ea59a70020223d16f", size = 5359685, upload-time = "2025-09-22T04:01:27.398Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/e1/e5df362e9ca4e2f48ed6411bd4b3a0ae737cc842e96877f5bf9428055ab4/lxml-6.0.2-cp312-cp312-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c33e66d44fe60e72397b487ee92e01da0d09ba2d66df8eae42d77b6d06e5eba0", size = 5654127, upload-time = "2025-09-22T04:01:29.629Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/d1/232b3309a02d60f11e71857778bfcd4acbdb86c07db8260caf7d008b08f8/lxml-6.0.2-cp312-cp312-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:90a345bbeaf9d0587a3aaffb7006aa39ccb6ff0e96a57286c0cb2fd1520ea192", size = 5253958, upload-time = "2025-09-22T04:01:31.535Z" },
+    { url = "https://files.pythonhosted.org/packages/35/35/d955a070994725c4f7d80583a96cab9c107c57a125b20bb5f708fe941011/lxml-6.0.2-cp312-cp312-manylinux_2_31_armv7l.whl", hash = "sha256:064fdadaf7a21af3ed1dcaa106b854077fbeada827c18f72aec9346847cd65d0", size = 4711541, upload-time = "2025-09-22T04:01:33.801Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/be/667d17363b38a78c4bd63cfd4b4632029fd68d2c2dc81f25ce9eb5224dd5/lxml-6.0.2-cp312-cp312-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:fbc74f42c3525ac4ffa4b89cbdd00057b6196bcefe8bce794abd42d33a018092", size = 5267426, upload-time = "2025-09-22T04:01:35.639Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/47/62c70aa4a1c26569bc958c9ca86af2bb4e1f614e8c04fb2989833874f7ae/lxml-6.0.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6ddff43f702905a4e32bc24f3f2e2edfe0f8fde3277d481bffb709a4cced7a1f", size = 5064917, upload-time = "2025-09-22T04:01:37.448Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/55/6ceddaca353ebd0f1908ef712c597f8570cc9c58130dbb89903198e441fd/lxml-6.0.2-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:6da5185951d72e6f5352166e3da7b0dc27aa70bd1090b0eb3f7f7212b53f1bb8", size = 4788795, upload-time = "2025-09-22T04:01:39.165Z" },
+    { url = "https://files.pythonhosted.org/packages/cf/e8/fd63e15da5e3fd4c2146f8bbb3c14e94ab850589beab88e547b2dbce22e1/lxml-6.0.2-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:57a86e1ebb4020a38d295c04fc79603c7899e0df71588043eb218722dabc087f", size = 5676759, upload-time = "2025-09-22T04:01:41.506Z" },
+    { url = "https://files.pythonhosted.org/packages/76/47/b3ec58dc5c374697f5ba37412cd2728f427d056315d124dd4b61da381877/lxml-6.0.2-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:2047d8234fe735ab77802ce5f2297e410ff40f5238aec569ad7c8e163d7b19a6", size = 5255666, upload-time = "2025-09-22T04:01:43.363Z" },
+    { url = "https://files.pythonhosted.org/packages/19/93/03ba725df4c3d72afd9596eef4a37a837ce8e4806010569bedfcd2cb68fd/lxml-6.0.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:6f91fd2b2ea15a6800c8e24418c0775a1694eefc011392da73bc6cef2623b322", size = 5277989, upload-time = "2025-09-22T04:01:45.215Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/80/c06de80bfce881d0ad738576f243911fccf992687ae09fd80b734712b39c/lxml-6.0.2-cp312-cp312-win32.whl", hash = "sha256:3ae2ce7d6fedfb3414a2b6c5e20b249c4c607f72cb8d2bb7cc9c6ec7c6f4e849", size = 3611456, upload-time = "2025-09-22T04:01:48.243Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/d7/0cdfb6c3e30893463fb3d1e52bc5f5f99684a03c29a0b6b605cfae879cd5/lxml-6.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:72c87e5ee4e58a8354fb9c7c84cbf95a1c8236c127a5d1b7683f04bed8361e1f", size = 4011793, upload-time = "2025-09-22T04:01:50.042Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/7b/93c73c67db235931527301ed3785f849c78991e2e34f3fd9a6663ffda4c5/lxml-6.0.2-cp312-cp312-win_arm64.whl", hash = "sha256:61cb10eeb95570153e0c0e554f58df92ecf5109f75eacad4a95baa709e26c3d6", size = 3672836, upload-time = "2025-09-22T04:01:52.145Z" },
+    { url = "https://files.pythonhosted.org/packages/53/fd/4e8f0540608977aea078bf6d79f128e0e2c2bba8af1acf775c30baa70460/lxml-6.0.2-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:9b33d21594afab46f37ae58dfadd06636f154923c4e8a4d754b0127554eb2e77", size = 8648494, upload-time = "2025-09-22T04:01:54.242Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/f4/2a94a3d3dfd6c6b433501b8d470a1960a20ecce93245cf2db1706adf6c19/lxml-6.0.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:6c8963287d7a4c5c9a432ff487c52e9c5618667179c18a204bdedb27310f022f", size = 4661146, upload-time = "2025-09-22T04:01:56.282Z" },
+    { url = "https://files.pythonhosted.org/packages/25/2e/4efa677fa6b322013035d38016f6ae859d06cac67437ca7dc708a6af7028/lxml-6.0.2-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:1941354d92699fb5ffe6ed7b32f9649e43c2feb4b97205f75866f7d21aa91452", size = 4946932, upload-time = "2025-09-22T04:01:58.989Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/0f/526e78a6d38d109fdbaa5049c62e1d32fdd70c75fb61c4eadf3045d3d124/lxml-6.0.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:bb2f6ca0ae2d983ded09357b84af659c954722bbf04dea98030064996d156048", size = 5100060, upload-time = "2025-09-22T04:02:00.812Z" },
+    { url = "https://files.pythonhosted.org/packages/81/76/99de58d81fa702cc0ea7edae4f4640416c2062813a00ff24bd70ac1d9c9b/lxml-6.0.2-cp313-cp313-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:eb2a12d704f180a902d7fa778c6d71f36ceb7b0d317f34cdc76a5d05aa1dd1df", size = 5019000, upload-time = "2025-09-22T04:02:02.671Z" },
+    { url = "https://files.pythonhosted.org/packages/b5/35/9e57d25482bc9a9882cb0037fdb9cc18f4b79d85df94fa9d2a89562f1d25/lxml-6.0.2-cp313-cp313-manylinux_2_26_i686.manylinux_2_28_i686.whl", hash = "sha256:6ec0e3f745021bfed19c456647f0298d60a24c9ff86d9d051f52b509663feeb1", size = 5348496, upload-time = "2025-09-22T04:02:04.904Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/8e/cb99bd0b83ccc3e8f0f528e9aa1f7a9965dfec08c617070c5db8d63a87ce/lxml-6.0.2-cp313-cp313-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:846ae9a12d54e368933b9759052d6206a9e8b250291109c48e350c1f1f49d916", size = 5643779, upload-time = "2025-09-22T04:02:06.689Z" },
+    { url = "https://files.pythonhosted.org/packages/d0/34/9e591954939276bb679b73773836c6684c22e56d05980e31d52a9a8deb18/lxml-6.0.2-cp313-cp313-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ef9266d2aa545d7374938fb5c484531ef5a2ec7f2d573e62f8ce722c735685fd", size = 5244072, upload-time = "2025-09-22T04:02:08.587Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/27/b29ff065f9aaca443ee377aff699714fcbffb371b4fce5ac4ca759e436d5/lxml-6.0.2-cp313-cp313-manylinux_2_31_armv7l.whl", hash = "sha256:4077b7c79f31755df33b795dc12119cb557a0106bfdab0d2c2d97bd3cf3dffa6", size = 4718675, upload-time = "2025-09-22T04:02:10.783Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/9f/f756f9c2cd27caa1a6ef8c32ae47aadea697f5c2c6d07b0dae133c244fbe/lxml-6.0.2-cp313-cp313-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:a7c5d5e5f1081955358533be077166ee97ed2571d6a66bdba6ec2f609a715d1a", size = 5255171, upload-time = "2025-09-22T04:02:12.631Z" },
+    { url = "https://files.pythonhosted.org/packages/61/46/bb85ea42d2cb1bd8395484fd72f38e3389611aa496ac7772da9205bbda0e/lxml-6.0.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:8f8d0cbd0674ee89863a523e6994ac25fd5be9c8486acfc3e5ccea679bad2679", size = 5057175, upload-time = "2025-09-22T04:02:14.718Z" },
+    { url = "https://files.pythonhosted.org/packages/95/0c/443fc476dcc8e41577f0af70458c50fe299a97bb6b7505bb1ae09aa7f9ac/lxml-6.0.2-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:2cbcbf6d6e924c28f04a43f3b6f6e272312a090f269eff68a2982e13e5d57659", size = 4785688, upload-time = "2025-09-22T04:02:16.957Z" },
+    { url = "https://files.pythonhosted.org/packages/48/78/6ef0b359d45bb9697bc5a626e1992fa5d27aa3f8004b137b2314793b50a0/lxml-6.0.2-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:dfb874cfa53340009af6bdd7e54ebc0d21012a60a4e65d927c2e477112e63484", size = 5660655, upload-time = "2025-09-22T04:02:18.815Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/ea/e1d33808f386bc1339d08c0dcada6e4712d4ed8e93fcad5f057070b7988a/lxml-6.0.2-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:fb8dae0b6b8b7f9e96c26fdd8121522ce5de9bb5538010870bd538683d30e9a2", size = 5247695, upload-time = "2025-09-22T04:02:20.593Z" },
+    { url = "https://files.pythonhosted.org/packages/4f/47/eba75dfd8183673725255247a603b4ad606f4ae657b60c6c145b381697da/lxml-6.0.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:358d9adae670b63e95bc59747c72f4dc97c9ec58881d4627fe0120da0f90d314", size = 5269841, upload-time = "2025-09-22T04:02:22.489Z" },
+    { url = "https://files.pythonhosted.org/packages/76/04/5c5e2b8577bc936e219becb2e98cdb1aca14a4921a12995b9d0c523502ae/lxml-6.0.2-cp313-cp313-win32.whl", hash = "sha256:e8cd2415f372e7e5a789d743d133ae474290a90b9023197fd78f32e2dc6873e2", size = 3610700, upload-time = "2025-09-22T04:02:24.465Z" },
+    { url = "https://files.pythonhosted.org/packages/fe/0a/4643ccc6bb8b143e9f9640aa54e38255f9d3b45feb2cbe7ae2ca47e8782e/lxml-6.0.2-cp313-cp313-win_amd64.whl", hash = "sha256:b30d46379644fbfc3ab81f8f82ae4de55179414651f110a1514f0b1f8f6cb2d7", size = 4010347, upload-time = "2025-09-22T04:02:26.286Z" },
+    { url = "https://files.pythonhosted.org/packages/31/ef/dcf1d29c3f530577f61e5fe2f1bd72929acf779953668a8a47a479ae6f26/lxml-6.0.2-cp313-cp313-win_arm64.whl", hash = "sha256:13dcecc9946dca97b11b7c40d29fba63b55ab4170d3c0cf8c0c164343b9bfdcf", size = 3671248, upload-time = "2025-09-22T04:02:27.918Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/11/29d08bc103a62c0eba8016e7ed5aeebbf1e4312e83b0b1648dd203b0e87d/lxml-6.0.2-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:1c06035eafa8404b5cf475bb37a9f6088b0aca288d4ccc9d69389750d5543700", size = 3949829, upload-time = "2025-09-22T04:04:45.608Z" },
+    { url = "https://files.pythonhosted.org/packages/12/b3/52ab9a3b31e5ab8238da241baa19eec44d2ab426532441ee607165aebb52/lxml-6.0.2-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:c7d13103045de1bdd6fe5d61802565f1a3537d70cd3abf596aa0af62761921ee", size = 4226277, upload-time = "2025-09-22T04:04:47.754Z" },
+    { url = "https://files.pythonhosted.org/packages/a0/33/1eaf780c1baad88224611df13b1c2a9dfa460b526cacfe769103ff50d845/lxml-6.0.2-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:0a3c150a95fbe5ac91de323aa756219ef9cf7fde5a3f00e2281e30f33fa5fa4f", size = 4330433, upload-time = "2025-09-22T04:04:49.907Z" },
+    { url = "https://files.pythonhosted.org/packages/7a/c1/27428a2ff348e994ab4f8777d3a0ad510b6b92d37718e5887d2da99952a2/lxml-6.0.2-pp311-pypy311_pp73-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:60fa43be34f78bebb27812ed90f1925ec99560b0fa1decdb7d12b84d857d31e9", size = 4272119, upload-time = "2025-09-22T04:04:51.801Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/d0/3020fa12bcec4ab62f97aab026d57c2f0cfd480a558758d9ca233bb6a79d/lxml-6.0.2-pp311-pypy311_pp73-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:21c73b476d3cfe836be731225ec3421fa2f048d84f6df6a8e70433dff1376d5a", size = 4417314, upload-time = "2025-09-22T04:04:55.024Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/77/d7f491cbc05303ac6801651aabeb262d43f319288c1ea96c66b1d2692ff3/lxml-6.0.2-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:27220da5be049e936c3aca06f174e8827ca6445a4353a1995584311487fc4e3e", size = 3518768, upload-time = "2025-09-22T04:04:57.097Z" },
+]
+
 [[package]]
 name = "mako"
 version = "1.3.10"
@@ -4842,6 +4908,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/ec/57/56b9bcc3c9c6a792fcbaf139543cee77261f3651ca9da0c93f5c1221264b/python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427", size = 229892, upload-time = "2024-03-01T18:36:18.57Z" },
 ]
 
+[[package]]
+name = "python-docx"
+version = "1.2.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "lxml" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a9/f7/eddfe33871520adab45aaa1a71f0402a2252050c14c7e3009446c8f4701c/python_docx-1.2.0.tar.gz", hash = "sha256:7bc9d7b7d8a69c9c02ca09216118c86552704edc23bac179283f2e38f86220ce", size = 5723256, upload-time = "2025-06-16T20:46:27.921Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d0/00/1e03a4989fa5795da308cd774f05b704ace555a70f9bf9d3be057b680bcf/python_docx-1.2.0-py3-none-any.whl", hash = "sha256:3fd478f3250fbbbfd3b94fe1e985955737c145627498896a8a6bf81f4baf66c7", size = 252987, upload-time = "2025-06-16T20:46:22.506Z" },
+]
+
 [[package]]
 name = "python-dotenv"
 version = "1.2.1"
@@ -5535,6 +5614,7 @@ dependencies = [
     { name = "pyotp" },
     { name = "pypdf" },
     { name = "python-calamine" },
+    { name = "python-docx" },
     { name = "python-dotenv" },
     { name = "python-jose", extra = ["cryptography"] },
     { name = "python-multipart" },
@@ -5649,6 +5729,7 @@ requires-dist = [
     { name = "pyotp", specifier = ">=2.9.0,<3" },
     { name = "pypdf", specifier = ">=5.1.0,<7" },
     { name = "python-calamine", specifier = ">=0.6.1" },
+    { name = "python-docx", specifier = ">=1.1.0" },
     { name = "python-dotenv", specifier = ">=1.0.0,<2" },
     { name = "python-jose", extras = ["cryptography"], specifier = ">=3.4.0,<4" },
     { name = "python-multipart", specifier = ">=0.0.22,<1" },