diff --git a/.github/workflows/test_python_3_10.yml b/.github/workflows/test_python_3_10.yml
index dc1594db4..30d266379 100644
--- a/.github/workflows/test_python_3_10.yml
+++ b/.github/workflows/test_python_3_10.yml
@@ -47,7 +47,7 @@ jobs:
           installer-parallel: true
 
       - name: Install dependencies
-        run: poetry install --no-interaction
+        run: poetry install --no-interaction -E docs
 
       - name: Run unit tests
         run: poetry run pytest cognee/tests/unit/
diff --git a/.github/workflows/test_python_3_11.yml b/.github/workflows/test_python_3_11.yml
index 0ef9bf910..1bf8b50f0 100644
--- a/.github/workflows/test_python_3_11.yml
+++ b/.github/workflows/test_python_3_11.yml
@@ -47,7 +47,7 @@ jobs:
           installer-parallel: true
 
       - name: Install dependencies
-        run: poetry install --no-interaction
+        run: poetry install --no-interaction -E docs
 
       - name: Run unit tests
         run: poetry run pytest cognee/tests/unit/
diff --git a/.github/workflows/test_python_3_9.yml b/.github/workflows/test_python_3_9.yml
index adce159ad..cac4d0cd5 100644
--- a/.github/workflows/test_python_3_9.yml
+++ b/.github/workflows/test_python_3_9.yml
@@ -47,7 +47,7 @@ jobs:
           installer-parallel: true
 
       - name: Install dependencies
-        run: poetry install --no-interaction
+        run: poetry install --no-interaction -E docs
 
       - name: Run unit tests
         run: poetry run pytest cognee/tests/unit/
diff --git a/cognee/modules/data/exceptions/__init__.py b/cognee/modules/data/exceptions/__init__.py
new file mode 100644
index 000000000..fa8468c88
--- /dev/null
+++ b/cognee/modules/data/exceptions/__init__.py
@@ -0,0 +1,9 @@
+"""
+Custom exceptions for the Cognee API.
+
+This module defines a set of exceptions for handling various data errors
+"""
+
+from .exceptions import (
+    UnstructuredLibraryImportError,
+)
\ No newline at end of file
diff --git a/cognee/modules/data/exceptions/exceptions.py b/cognee/modules/data/exceptions/exceptions.py
new file mode 100644
index 000000000..3b1aac52c
--- /dev/null
+++ b/cognee/modules/data/exceptions/exceptions.py
@@ -0,0 +1,11 @@
+from cognee.exceptions import CogneeApiError
+from fastapi import status
+
+class UnstructuredLibraryImportError(CogneeApiError):
+    def __init__(
+            self,
+            message: str = "Import error. Unstructured library is not installed.",
+            name: str = "UnstructuredModuleImportError",
+            status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
+    ):
+        super().__init__(message, name, status_code)
\ No newline at end of file
diff --git a/cognee/modules/data/processing/document_types/Document.py b/cognee/modules/data/processing/document_types/Document.py
index 773fc30c8..45441dcce 100644
--- a/cognee/modules/data/processing/document_types/Document.py
+++ b/cognee/modules/data/processing/document_types/Document.py
@@ -6,6 +6,7 @@ class Document(DataPoint):
     name: str
     raw_data_location: str
     metadata_id: UUID
+    mime_type: str
 
     def read(self, chunk_size: int) -> str:
         pass
diff --git a/cognee/modules/data/processing/document_types/UnstructuredDocument.py b/cognee/modules/data/processing/document_types/UnstructuredDocument.py
new file mode 100644
index 000000000..62632cd08
--- /dev/null
+++ b/cognee/modules/data/processing/document_types/UnstructuredDocument.py
@@ -0,0 +1,32 @@
+from io import StringIO
+
+from cognee.modules.chunking.TextChunker import TextChunker
+from .Document import Document
+from cognee.modules.data.exceptions import UnstructuredLibraryImportError
+
+
+class UnstructuredDocument(Document):
+    type: str = "unstructured"
+
+    def read(self, chunk_size: int):
+        def get_text():
+            try:
+                from unstructured.partition.auto import partition
+            except ModuleNotFoundError:
+                raise UnstructuredLibraryImportError
+
+            elements = partition(self.raw_data_location, content_type=self.mime_type)
+            in_memory_file = StringIO("\n\n".join([str(el) for el in elements]))
+            in_memory_file.seek(0)
+
+            while True:
+                text = in_memory_file.read(1024)
+
+                if len(text.strip()) == 0:
+                    break
+
+                yield text
+
+        chunker = TextChunker(self, chunk_size = chunk_size, get_text = get_text)
+
+        yield from chunker.read()
diff --git a/cognee/modules/data/processing/document_types/__init__.py b/cognee/modules/data/processing/document_types/__init__.py
index 9682cc101..2e862f4ba 100644
--- a/cognee/modules/data/processing/document_types/__init__.py
+++ b/cognee/modules/data/processing/document_types/__init__.py
@@ -3,3 +3,4 @@ from .PdfDocument import PdfDocument
 from .TextDocument import TextDocument
 from .ImageDocument import ImageDocument
 from .AudioDocument import AudioDocument
+from .UnstructuredDocument import UnstructuredDocument
diff --git a/cognee/tasks/documents/classify_documents.py b/cognee/tasks/documents/classify_documents.py
index d007b6888..47beeb917 100644
--- a/cognee/tasks/documents/classify_documents.py
+++ b/cognee/tasks/documents/classify_documents.py
@@ -5,12 +5,22 @@ from cognee.modules.data.processing.document_types import (
     AudioDocument,
     ImageDocument,
     TextDocument,
+    UnstructuredDocument,
 )
 from cognee.modules.data.operations.get_metadata import get_metadata
 
 EXTENSION_TO_DOCUMENT_CLASS = {
     "pdf": PdfDocument,  # Text documents
     "txt": TextDocument,
+    "docx": UnstructuredDocument,
+    "doc": UnstructuredDocument,
+    "odt": UnstructuredDocument,
+    "xls": UnstructuredDocument,
+    "xlsx": UnstructuredDocument,
+    "ppt": UnstructuredDocument,
+    "pptx": UnstructuredDocument,
+    "odp": UnstructuredDocument,
+    "ods": UnstructuredDocument,
     "png": ImageDocument,  # Image documents
     "dwg": ImageDocument,
     "xcf": ImageDocument,
@@ -48,6 +58,7 @@ async def classify_documents(data_documents: list[Data]) -> list[Document]:
             title = f"{data_item.name}.{data_item.extension}",
             raw_data_location = data_item.raw_data_location,
             name = data_item.name,
+            mime_type = data_item.mime_type,
             metadata_id = metadata.id
         )
         documents.append(document)
diff --git a/cognee/tests/integration/documents/AudioDocument_test.py b/cognee/tests/integration/documents/AudioDocument_test.py
index a35e3892b..da8b85d0b 100644
--- a/cognee/tests/integration/documents/AudioDocument_test.py
+++ b/cognee/tests/integration/documents/AudioDocument_test.py
@@ -27,7 +27,7 @@ TEST_TEXT = """
 def test_AudioDocument():
 
     document = AudioDocument(
-        id=uuid.uuid4(), name="audio-dummy-test", raw_data_location="", metadata_id=uuid.uuid4()
+        id=uuid.uuid4(), name="audio-dummy-test", raw_data_location="", metadata_id=uuid.uuid4(), mime_type="",
     )
     with patch.object(AudioDocument, "create_transcript", return_value=TEST_TEXT):
         for ground_truth, paragraph_data in zip(
diff --git a/cognee/tests/integration/documents/ImageDocument_test.py b/cognee/tests/integration/documents/ImageDocument_test.py
index 9f5952c40..8a8ee8ef3 100644
--- a/cognee/tests/integration/documents/ImageDocument_test.py
+++ b/cognee/tests/integration/documents/ImageDocument_test.py
@@ -16,7 +16,7 @@ The commotion has attracted an audience: a murder of crows has gathered in the l
 def test_ImageDocument():
 
     document = ImageDocument(
-        id=uuid.uuid4(), name="image-dummy-test", raw_data_location="", metadata_id=uuid.uuid4()
+        id=uuid.uuid4(), name="image-dummy-test", raw_data_location="", metadata_id=uuid.uuid4(), mime_type="",
     )
     with patch.object(ImageDocument, "transcribe_image", return_value=TEST_TEXT):
 
diff --git a/cognee/tests/integration/documents/PdfDocument_test.py b/cognee/tests/integration/documents/PdfDocument_test.py
index fbfe236db..ac57eaf75 100644
--- a/cognee/tests/integration/documents/PdfDocument_test.py
+++ b/cognee/tests/integration/documents/PdfDocument_test.py
@@ -17,7 +17,8 @@ def test_PdfDocument():
         "artificial-intelligence.pdf",
     )
     document = PdfDocument(
-        id=uuid.uuid4(), name="Test document.pdf", raw_data_location=test_file_path, metadata_id=uuid.uuid4()
+        id=uuid.uuid4(), name="Test document.pdf", raw_data_location=test_file_path, metadata_id=uuid.uuid4(),
+        mime_type="",
     )
 
     for ground_truth, paragraph_data in zip(
diff --git a/cognee/tests/integration/documents/TextDocument_test.py b/cognee/tests/integration/documents/TextDocument_test.py
index 46adee094..f663418f5 100644
--- a/cognee/tests/integration/documents/TextDocument_test.py
+++ b/cognee/tests/integration/documents/TextDocument_test.py
@@ -29,7 +29,7 @@ def test_TextDocument(input_file, chunk_size):
         input_file,
     )
     document = TextDocument(
-        id=uuid.uuid4(), name=input_file, raw_data_location=test_file_path, metadata_id=uuid.uuid4()
+        id=uuid.uuid4(), name=input_file, raw_data_location=test_file_path, metadata_id=uuid.uuid4(), mime_type="",
     )
 
     for ground_truth, paragraph_data in zip(
diff --git a/cognee/tests/integration/documents/UnstructuredDocument_test.py b/cognee/tests/integration/documents/UnstructuredDocument_test.py
new file mode 100644
index 000000000..418b18810
--- /dev/null
+++ b/cognee/tests/integration/documents/UnstructuredDocument_test.py
@@ -0,0 +1,80 @@
+import os
+import uuid
+
+from cognee.modules.data.processing.document_types.UnstructuredDocument import UnstructuredDocument
+
+def test_UnstructuredDocument():
+    # Define file paths of test data
+    pptx_file_path = os.path.join(
+        os.sep,
+        *(os.path.dirname(__file__).split(os.sep)[:-2]),
+        "test_data",
+        "example.pptx",
+    )
+
+    docx_file_path = os.path.join(
+        os.sep,
+        *(os.path.dirname(__file__).split(os.sep)[:-2]),
+        "test_data",
+        "example.docx",
+    )
+
+    csv_file_path = os.path.join(
+        os.sep,
+        *(os.path.dirname(__file__).split(os.sep)[:-2]),
+        "test_data",
+        "example.csv",
+    )
+
+    xlsx_file_path = os.path.join(
+        os.sep,
+        *(os.path.dirname(__file__).split(os.sep)[:-2]),
+        "test_data",
+        "example.xlsx",
+    )
+
+    # Define test documents
+    pptx_document = UnstructuredDocument(
+        id=uuid.uuid4(), name="example.pptx", raw_data_location=pptx_file_path, metadata_id=uuid.uuid4(),
+        mime_type="application/vnd.openxmlformats-officedocument.presentationml.presentation"
+    )
+
+    docx_document = UnstructuredDocument(
+        id=uuid.uuid4(), name="example.docx", raw_data_location=docx_file_path, metadata_id=uuid.uuid4(),
+        mime_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+    )
+
+    csv_document = UnstructuredDocument(
+        id=uuid.uuid4(), name="example.csv", raw_data_location=csv_file_path, metadata_id=uuid.uuid4(),
+        mime_type="text/csv"
+    )
+
+    xlsx_document = UnstructuredDocument(
+        id=uuid.uuid4(), name="example.xlsx", raw_data_location=xlsx_file_path, metadata_id=uuid.uuid4(),
+        mime_type="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    )
+
+    # Test PPTX
+    for paragraph_data in pptx_document.read(chunk_size=1024):
+        assert 19 == paragraph_data.word_count, f' 19 != {paragraph_data.word_count = }'
+        assert 104 == len(paragraph_data.text), f' 104 != {len(paragraph_data.text) = }'
+        assert 'sentence_cut' == paragraph_data.cut_type, f' sentence_cut != {paragraph_data.cut_type = }'
+
+    # Test DOCX
+    for paragraph_data in docx_document.read(chunk_size=1024):
+        assert 16 == paragraph_data.word_count, f' 16 != {paragraph_data.word_count = }'
+        assert 145 == len(paragraph_data.text), f' 145 != {len(paragraph_data.text) = }'
+        assert 'sentence_end' == paragraph_data.cut_type, f' sentence_end != {paragraph_data.cut_type = }'
+
+    # TEST CSV
+    for paragraph_data in csv_document.read(chunk_size=1024):
+        assert 15 == paragraph_data.word_count, f' 15 != {paragraph_data.word_count = }'
+        assert 'A A A A A A A A A,A A A A A A,A A' == paragraph_data.text, \
+            f'Read text doesn\'t match expected text: {paragraph_data.text}'
+        assert 'sentence_cut' == paragraph_data.cut_type, f' sentence_cut != {paragraph_data.cut_type = }'
+
+    # Test XLSX
+    for paragraph_data in xlsx_document.read(chunk_size=1024):
+        assert 36 == paragraph_data.word_count, f' 36 != {paragraph_data.word_count = }'
+        assert 171 == len(paragraph_data.text), f' 171 != {len(paragraph_data.text) = }'
+        assert 'sentence_cut' == paragraph_data.cut_type, f' sentence_cut != {paragraph_data.cut_type = }'
diff --git a/cognee/tests/test_data/example.csv b/cognee/tests/test_data/example.csv
new file mode 100644
index 000000000..004bbf122
--- /dev/null
+++ b/cognee/tests/test_data/example.csv
@@ -0,0 +1,3 @@
+A,A,A,A,A
+A,A,A,"A,A",A
+A,A,A,"A,A",A
diff --git a/cognee/tests/test_data/example.docx b/cognee/tests/test_data/example.docx
new file mode 100644
index 000000000..81ff7f2d4
Binary files /dev/null and b/cognee/tests/test_data/example.docx differ
diff --git a/cognee/tests/test_data/example.pptx b/cognee/tests/test_data/example.pptx
new file mode 100644
index 000000000..3e49ae3df
Binary files /dev/null and b/cognee/tests/test_data/example.pptx differ
diff --git a/cognee/tests/test_data/example.xlsx b/cognee/tests/test_data/example.xlsx
new file mode 100644
index 000000000..944533d38
Binary files /dev/null and b/cognee/tests/test_data/example.xlsx differ
diff --git a/poetry.lock b/poetry.lock
index 8a0326236..dcba97b55 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -726,6 +726,17 @@ files = [
 [package.dependencies]
 pycparser = "*"
 
+[[package]]
+name = "chardet"
+version = "5.2.0"
+description = "Universal encoding detector for Python 3"
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "chardet-5.2.0-py3-none-any.whl", hash = "sha256:e1cf59446890a00105fe7b7912492ea04b6e6f06d4b742b2c788469e34c82970"},
+    {file = "chardet-5.2.0.tar.gz", hash = "sha256:1b3b6ff479a8c414bc3fa2c0852995695c4a026dcd6d0633b2dd092ca39c1cf7"},
+]
+
 [[package]]
 name = "charset-normalizer"
 version = "3.4.0"
@@ -1213,6 +1224,24 @@ files = [
     {file = "decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330"},
 ]
 
+[[package]]
+name = "deepdiff"
+version = "8.0.1"
+description = "Deep Difference and Search of any Python object/data. Recreate objects by adding adding deltas to each other."
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "deepdiff-8.0.1-py3-none-any.whl", hash = "sha256:42e99004ce603f9a53934c634a57b04ad5900e0d8ed0abb15e635767489cbc05"},
+    {file = "deepdiff-8.0.1.tar.gz", hash = "sha256:245599a4586ab59bb599ca3517a9c42f3318ff600ded5e80a3432693c8ec3c4b"},
+]
+
+[package.dependencies]
+orderly-set = "5.2.2"
+
+[package.extras]
+cli = ["click (==8.1.7)", "pyyaml (==6.0.1)"]
+optimize = ["orjson"]
+
 [[package]]
 name = "deepeval"
 version = "2.0.1"
@@ -1482,6 +1511,31 @@ files = [
 dnspython = ">=2.0.0"
 idna = ">=2.0.0"
 
+[[package]]
+name = "emoji"
+version = "2.14.0"
+description = "Emoji for Python"
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "emoji-2.14.0-py3-none-any.whl", hash = "sha256:fcc936bf374b1aec67dda5303ae99710ba88cc9cdce2d1a71c5f2204e6d78799"},
+    {file = "emoji-2.14.0.tar.gz", hash = "sha256:f68ac28915a2221667cddb3e6c589303c3c6954c6c5af6fefaec7f9bdf72fdca"},
+]
+
+[package.extras]
+dev = ["coverage", "pytest (>=7.4.4)"]
+
+[[package]]
+name = "et-xmlfile"
+version = "2.0.0"
+description = "An implementation of lxml.xmlfile for the standard library"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "et_xmlfile-2.0.0-py3-none-any.whl", hash = "sha256:7a91720bc756843502c3b7504c77b8fe44217c85c537d85037f0f536151b2caa"},
+    {file = "et_xmlfile-2.0.0.tar.gz", hash = "sha256:dab3f4764309081ce75662649be815c4c9081e88f0837825f90fd28317d4da54"},
+]
+
 [[package]]
 name = "exceptiongroup"
 version = "1.2.2"
@@ -2321,6 +2375,27 @@ files = [
     {file = "hpack-4.0.0.tar.gz", hash = "sha256:fc41de0c63e687ebffde81187a948221294896f6bdc0ae2312708df339430095"},
 ]
 
+[[package]]
+name = "html5lib"
+version = "1.1"
+description = "HTML parser based on the WHATWG HTML specification"
+optional = true
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+files = [
+    {file = "html5lib-1.1-py2.py3-none-any.whl", hash = "sha256:0d78f8fde1c230e99fe37986a60526d7049ed4bf8a9fadbad5f00e22e58e041d"},
+    {file = "html5lib-1.1.tar.gz", hash = "sha256:b2e5b40261e20f354d198eae92afc10d750afb487ed5e50f9c4eaf07c184146f"},
+]
+
+[package.dependencies]
+six = ">=1.9"
+webencodings = "*"
+
+[package.extras]
+all = ["chardet (>=2.2)", "genshi", "lxml"]
+chardet = ["chardet (>=2.2)"]
+genshi = ["genshi"]
+lxml = ["lxml"]
+
 [[package]]
 name = "htmlmin2"
 version = "0.1.13"
@@ -2823,6 +2898,17 @@ files = [
 [package.dependencies]
 ply = "*"
 
+[[package]]
+name = "jsonpath-python"
+version = "1.0.6"
+description = "A more powerful JSONPath implementation in modern python"
+optional = true
+python-versions = ">=3.6"
+files = [
+    {file = "jsonpath-python-1.0.6.tar.gz", hash = "sha256:dd5be4a72d8a2995c3f583cf82bf3cd1a9544cfdabf2d22595b67aff07349666"},
+    {file = "jsonpath_python-1.0.6-py3-none-any.whl", hash = "sha256:1e3b78df579f5efc23565293612decee04214609208a2335884b3ee3f786b575"},
+]
+
 [[package]]
 name = "jsonpointer"
 version = "3.0.0"
@@ -3464,6 +3550,160 @@ typing-extensions = ">=4.5.0"
 typing-inspect = ">=0.8.0"
 wrapt = "*"
 
+[[package]]
+name = "lxml"
+version = "5.3.0"
+description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
+optional = true
+python-versions = ">=3.6"
+files = [
+    {file = "lxml-5.3.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:dd36439be765e2dde7660212b5275641edbc813e7b24668831a5c8ac91180656"},
+    {file = "lxml-5.3.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ae5fe5c4b525aa82b8076c1a59d642c17b6e8739ecf852522c6321852178119d"},
+    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:501d0d7e26b4d261fca8132854d845e4988097611ba2531408ec91cf3fd9d20a"},
+    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb66442c2546446944437df74379e9cf9e9db353e61301d1a0e26482f43f0dd8"},
+    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9e41506fec7a7f9405b14aa2d5c8abbb4dbbd09d88f9496958b6d00cb4d45330"},
+    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f7d4a670107d75dfe5ad080bed6c341d18c4442f9378c9f58e5851e86eb79965"},
+    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:41ce1f1e2c7755abfc7e759dc34d7d05fd221723ff822947132dc934d122fe22"},
+    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:44264ecae91b30e5633013fb66f6ddd05c006d3e0e884f75ce0b4755b3e3847b"},
+    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_ppc64le.whl", hash = "sha256:3c174dc350d3ec52deb77f2faf05c439331d6ed5e702fc247ccb4e6b62d884b7"},
+    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_s390x.whl", hash = "sha256:2dfab5fa6a28a0b60a20638dc48e6343c02ea9933e3279ccb132f555a62323d8"},
+    {file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:b1c8c20847b9f34e98080da785bb2336ea982e7f913eed5809e5a3c872900f32"},
+    {file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:2c86bf781b12ba417f64f3422cfc302523ac9cd1d8ae8c0f92a1c66e56ef2e86"},
+    {file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:c162b216070f280fa7da844531169be0baf9ccb17263cf5a8bf876fcd3117fa5"},
+    {file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:36aef61a1678cb778097b4a6eeae96a69875d51d1e8f4d4b491ab3cfb54b5a03"},
+    {file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:f65e5120863c2b266dbcc927b306c5b78e502c71edf3295dfcb9501ec96e5fc7"},
+    {file = "lxml-5.3.0-cp310-cp310-win32.whl", hash = "sha256:ef0c1fe22171dd7c7c27147f2e9c3e86f8bdf473fed75f16b0c2e84a5030ce80"},
+    {file = "lxml-5.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:052d99051e77a4f3e8482c65014cf6372e61b0a6f4fe9edb98503bb5364cfee3"},
+    {file = "lxml-5.3.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:74bcb423462233bc5d6066e4e98b0264e7c1bed7541fff2f4e34fe6b21563c8b"},
+    {file = "lxml-5.3.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a3d819eb6f9b8677f57f9664265d0a10dd6551d227afb4af2b9cd7bdc2ccbf18"},
+    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5b8f5db71b28b8c404956ddf79575ea77aa8b1538e8b2ef9ec877945b3f46442"},
+    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2c3406b63232fc7e9b8783ab0b765d7c59e7c59ff96759d8ef9632fca27c7ee4"},
+    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2ecdd78ab768f844c7a1d4a03595038c166b609f6395e25af9b0f3f26ae1230f"},
+    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:168f2dfcfdedf611eb285efac1516c8454c8c99caf271dccda8943576b67552e"},
+    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa617107a410245b8660028a7483b68e7914304a6d4882b5ff3d2d3eb5948d8c"},
+    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:69959bd3167b993e6e710b99051265654133a98f20cec1d9b493b931942e9c16"},
+    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_ppc64le.whl", hash = "sha256:bd96517ef76c8654446fc3db9242d019a1bb5fe8b751ba414765d59f99210b79"},
+    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_s390x.whl", hash = "sha256:ab6dd83b970dc97c2d10bc71aa925b84788c7c05de30241b9e96f9b6d9ea3080"},
+    {file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:eec1bb8cdbba2925bedc887bc0609a80e599c75b12d87ae42ac23fd199445654"},
+    {file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:6a7095eeec6f89111d03dabfe5883a1fd54da319c94e0fb104ee8f23616b572d"},
+    {file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:6f651ebd0b21ec65dfca93aa629610a0dbc13dbc13554f19b0113da2e61a4763"},
+    {file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:f422a209d2455c56849442ae42f25dbaaba1c6c3f501d58761c619c7836642ec"},
+    {file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:62f7fdb0d1ed2065451f086519865b4c90aa19aed51081979ecd05a21eb4d1be"},
+    {file = "lxml-5.3.0-cp311-cp311-win32.whl", hash = "sha256:c6379f35350b655fd817cd0d6cbeef7f265f3ae5fedb1caae2eb442bbeae9ab9"},
+    {file = "lxml-5.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:9c52100e2c2dbb0649b90467935c4b0de5528833c76a35ea1a2691ec9f1ee7a1"},
+    {file = "lxml-5.3.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:e99f5507401436fdcc85036a2e7dc2e28d962550afe1cbfc07c40e454256a859"},
+    {file = "lxml-5.3.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:384aacddf2e5813a36495233b64cb96b1949da72bef933918ba5c84e06af8f0e"},
+    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:874a216bf6afaf97c263b56371434e47e2c652d215788396f60477540298218f"},
+    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:65ab5685d56914b9a2a34d67dd5488b83213d680b0c5d10b47f81da5a16b0b0e"},
+    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aac0bbd3e8dd2d9c45ceb82249e8bdd3ac99131a32b4d35c8af3cc9db1657179"},
+    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b369d3db3c22ed14c75ccd5af429086f166a19627e84a8fdade3f8f31426e52a"},
+    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c24037349665434f375645fa9d1f5304800cec574d0310f618490c871fd902b3"},
+    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:62d172f358f33a26d6b41b28c170c63886742f5b6772a42b59b4f0fa10526cb1"},
+    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_ppc64le.whl", hash = "sha256:c1f794c02903c2824fccce5b20c339a1a14b114e83b306ff11b597c5f71a1c8d"},
+    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_s390x.whl", hash = "sha256:5d6a6972b93c426ace71e0be9a6f4b2cfae9b1baed2eed2006076a746692288c"},
+    {file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:3879cc6ce938ff4eb4900d901ed63555c778731a96365e53fadb36437a131a99"},
+    {file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:74068c601baff6ff021c70f0935b0c7bc528baa8ea210c202e03757c68c5a4ff"},
+    {file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:ecd4ad8453ac17bc7ba3868371bffb46f628161ad0eefbd0a855d2c8c32dd81a"},
+    {file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:7e2f58095acc211eb9d8b5771bf04df9ff37d6b87618d1cbf85f92399c98dae8"},
+    {file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e63601ad5cd8f860aa99d109889b5ac34de571c7ee902d6812d5d9ddcc77fa7d"},
+    {file = "lxml-5.3.0-cp312-cp312-win32.whl", hash = "sha256:17e8d968d04a37c50ad9c456a286b525d78c4a1c15dd53aa46c1d8e06bf6fa30"},
+    {file = "lxml-5.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:c1a69e58a6bb2de65902051d57fde951febad631a20a64572677a1052690482f"},
+    {file = "lxml-5.3.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:8c72e9563347c7395910de6a3100a4840a75a6f60e05af5e58566868d5eb2d6a"},
+    {file = "lxml-5.3.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:e92ce66cd919d18d14b3856906a61d3f6b6a8500e0794142338da644260595cd"},
+    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1d04f064bebdfef9240478f7a779e8c5dc32b8b7b0b2fc6a62e39b928d428e51"},
+    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c2fb570d7823c2bbaf8b419ba6e5662137f8166e364a8b2b91051a1fb40ab8b"},
+    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0c120f43553ec759f8de1fee2f4794452b0946773299d44c36bfe18e83caf002"},
+    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:562e7494778a69086f0312ec9689f6b6ac1c6b65670ed7d0267e49f57ffa08c4"},
+    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:423b121f7e6fa514ba0c7918e56955a1d4470ed35faa03e3d9f0e3baa4c7e492"},
+    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:c00f323cc00576df6165cc9d21a4c21285fa6b9989c5c39830c3903dc4303ef3"},
+    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_ppc64le.whl", hash = "sha256:1fdc9fae8dd4c763e8a31e7630afef517eab9f5d5d31a278df087f307bf601f4"},
+    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_s390x.whl", hash = "sha256:658f2aa69d31e09699705949b5fc4719cbecbd4a97f9656a232e7d6c7be1a367"},
+    {file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:1473427aff3d66a3fa2199004c3e601e6c4500ab86696edffdbc84954c72d832"},
+    {file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a87de7dd873bf9a792bf1e58b1c3887b9264036629a5bf2d2e6579fe8e73edff"},
+    {file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:0d7b36afa46c97875303a94e8f3ad932bf78bace9e18e603f2085b652422edcd"},
+    {file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:cf120cce539453ae086eacc0130a324e7026113510efa83ab42ef3fcfccac7fb"},
+    {file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:df5c7333167b9674aa8ae1d4008fa4bc17a313cc490b2cca27838bbdcc6bb15b"},
+    {file = "lxml-5.3.0-cp313-cp313-win32.whl", hash = "sha256:c802e1c2ed9f0c06a65bc4ed0189d000ada8049312cfeab6ca635e39c9608957"},
+    {file = "lxml-5.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:406246b96d552e0503e17a1006fd27edac678b3fcc9f1be71a2f94b4ff61528d"},
+    {file = "lxml-5.3.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:8f0de2d390af441fe8b2c12626d103540b5d850d585b18fcada58d972b74a74e"},
+    {file = "lxml-5.3.0-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1afe0a8c353746e610bd9031a630a95bcfb1a720684c3f2b36c4710a0a96528f"},
+    {file = "lxml-5.3.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:56b9861a71575f5795bde89256e7467ece3d339c9b43141dbdd54544566b3b94"},
+    {file = "lxml-5.3.0-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:9fb81d2824dff4f2e297a276297e9031f46d2682cafc484f49de182aa5e5df99"},
+    {file = "lxml-5.3.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:2c226a06ecb8cdef28845ae976da407917542c5e6e75dcac7cc33eb04aaeb237"},
+    {file = "lxml-5.3.0-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:7d3d1ca42870cdb6d0d29939630dbe48fa511c203724820fc0fd507b2fb46577"},
+    {file = "lxml-5.3.0-cp36-cp36m-win32.whl", hash = "sha256:094cb601ba9f55296774c2d57ad68730daa0b13dc260e1f941b4d13678239e70"},
+    {file = "lxml-5.3.0-cp36-cp36m-win_amd64.whl", hash = "sha256:eafa2c8658f4e560b098fe9fc54539f86528651f61849b22111a9b107d18910c"},
+    {file = "lxml-5.3.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:cb83f8a875b3d9b458cada4f880fa498646874ba4011dc974e071a0a84a1b033"},
+    {file = "lxml-5.3.0-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:25f1b69d41656b05885aa185f5fdf822cb01a586d1b32739633679699f220391"},
+    {file = "lxml-5.3.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23e0553b8055600b3bf4a00b255ec5c92e1e4aebf8c2c09334f8368e8bd174d6"},
+    {file = "lxml-5.3.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ada35dd21dc6c039259596b358caab6b13f4db4d4a7f8665764d616daf9cc1d"},
+    {file = "lxml-5.3.0-cp37-cp37m-manylinux_2_28_aarch64.whl", hash = "sha256:81b4e48da4c69313192d8c8d4311e5d818b8be1afe68ee20f6385d0e96fc9512"},
+    {file = "lxml-5.3.0-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:2bc9fd5ca4729af796f9f59cd8ff160fe06a474da40aca03fcc79655ddee1a8b"},
+    {file = "lxml-5.3.0-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:07da23d7ee08577760f0a71d67a861019103e4812c87e2fab26b039054594cc5"},
+    {file = "lxml-5.3.0-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:ea2e2f6f801696ad7de8aec061044d6c8c0dd4037608c7cab38a9a4d316bfb11"},
+    {file = "lxml-5.3.0-cp37-cp37m-win32.whl", hash = "sha256:5c54afdcbb0182d06836cc3d1be921e540be3ebdf8b8a51ee3ef987537455f84"},
+    {file = "lxml-5.3.0-cp37-cp37m-win_amd64.whl", hash = "sha256:f2901429da1e645ce548bf9171784c0f74f0718c3f6150ce166be39e4dd66c3e"},
+    {file = "lxml-5.3.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c56a1d43b2f9ee4786e4658c7903f05da35b923fb53c11025712562d5cc02753"},
+    {file = "lxml-5.3.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ee8c39582d2652dcd516d1b879451500f8db3fe3607ce45d7c5957ab2596040"},
+    {file = "lxml-5.3.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0fdf3a3059611f7585a78ee10399a15566356116a4288380921a4b598d807a22"},
+    {file = "lxml-5.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:146173654d79eb1fc97498b4280c1d3e1e5d58c398fa530905c9ea50ea849b22"},
+    {file = "lxml-5.3.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:0a7056921edbdd7560746f4221dca89bb7a3fe457d3d74267995253f46343f15"},
+    {file = "lxml-5.3.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:9e4b47ac0f5e749cfc618efdf4726269441014ae1d5583e047b452a32e221920"},
+    {file = "lxml-5.3.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:f914c03e6a31deb632e2daa881fe198461f4d06e57ac3d0e05bbcab8eae01945"},
+    {file = "lxml-5.3.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:213261f168c5e1d9b7535a67e68b1f59f92398dd17a56d934550837143f79c42"},
+    {file = "lxml-5.3.0-cp38-cp38-win32.whl", hash = "sha256:218c1b2e17a710e363855594230f44060e2025b05c80d1f0661258142b2add2e"},
+    {file = "lxml-5.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:315f9542011b2c4e1d280e4a20ddcca1761993dda3afc7a73b01235f8641e903"},
+    {file = "lxml-5.3.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:1ffc23010330c2ab67fac02781df60998ca8fe759e8efde6f8b756a20599c5de"},
+    {file = "lxml-5.3.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2b3778cb38212f52fac9fe913017deea2fdf4eb1a4f8e4cfc6b009a13a6d3fcc"},
+    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4b0c7a688944891086ba192e21c5229dea54382f4836a209ff8d0a660fac06be"},
+    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:747a3d3e98e24597981ca0be0fd922aebd471fa99d0043a3842d00cdcad7ad6a"},
+    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:86a6b24b19eaebc448dc56b87c4865527855145d851f9fc3891673ff97950540"},
+    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b11a5d918a6216e521c715b02749240fb07ae5a1fefd4b7bf12f833bc8b4fe70"},
+    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:68b87753c784d6acb8a25b05cb526c3406913c9d988d51f80adecc2b0775d6aa"},
+    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:109fa6fede314cc50eed29e6e56c540075e63d922455346f11e4d7a036d2b8cf"},
+    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_ppc64le.whl", hash = "sha256:02ced472497b8362c8e902ade23e3300479f4f43e45f4105c85ef43b8db85229"},
+    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_s390x.whl", hash = "sha256:6b038cc86b285e4f9fea2ba5ee76e89f21ed1ea898e287dc277a25884f3a7dfe"},
+    {file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:7437237c6a66b7ca341e868cda48be24b8701862757426852c9b3186de1da8a2"},
+    {file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:7f41026c1d64043a36fda21d64c5026762d53a77043e73e94b71f0521939cc71"},
+    {file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:482c2f67761868f0108b1743098640fbb2a28a8e15bf3f47ada9fa59d9fe08c3"},
+    {file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:1483fd3358963cc5c1c9b122c80606a3a79ee0875bcac0204149fa09d6ff2727"},
+    {file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:2dec2d1130a9cda5b904696cec33b2cfb451304ba9081eeda7f90f724097300a"},
+    {file = "lxml-5.3.0-cp39-cp39-win32.whl", hash = "sha256:a0eabd0a81625049c5df745209dc7fcef6e2aea7793e5f003ba363610aa0a3ff"},
+    {file = "lxml-5.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:89e043f1d9d341c52bf2af6d02e6adde62e0a46e6755d5eb60dc6e4f0b8aeca2"},
+    {file = "lxml-5.3.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:7b1cd427cb0d5f7393c31b7496419da594fe600e6fdc4b105a54f82405e6626c"},
+    {file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:51806cfe0279e06ed8500ce19479d757db42a30fd509940b1701be9c86a5ff9a"},
+    {file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ee70d08fd60c9565ba8190f41a46a54096afa0eeb8f76bd66f2c25d3b1b83005"},
+    {file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:8dc2c0395bea8254d8daebc76dcf8eb3a95ec2a46fa6fae5eaccee366bfe02ce"},
+    {file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:6ba0d3dcac281aad8a0e5b14c7ed6f9fa89c8612b47939fc94f80b16e2e9bc83"},
+    {file = "lxml-5.3.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:6e91cf736959057f7aac7adfc83481e03615a8e8dd5758aa1d95ea69e8931dba"},
+    {file = "lxml-5.3.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:94d6c3782907b5e40e21cadf94b13b0842ac421192f26b84c45f13f3c9d5dc27"},
+    {file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c300306673aa0f3ed5ed9372b21867690a17dba38c68c44b287437c362ce486b"},
+    {file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78d9b952e07aed35fe2e1a7ad26e929595412db48535921c5013edc8aa4a35ce"},
+    {file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:01220dca0d066d1349bd6a1726856a78f7929f3878f7e2ee83c296c69495309e"},
+    {file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:2d9b8d9177afaef80c53c0a9e30fa252ff3036fb1c6494d427c066a4ce6a282f"},
+    {file = "lxml-5.3.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:20094fc3f21ea0a8669dc4c61ed7fa8263bd37d97d93b90f28fc613371e7a875"},
+    {file = "lxml-5.3.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ace2c2326a319a0bb8a8b0e5b570c764962e95818de9f259ce814ee666603f19"},
+    {file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:92e67a0be1639c251d21e35fe74df6bcc40cba445c2cda7c4a967656733249e2"},
+    {file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd5350b55f9fecddc51385463a4f67a5da829bc741e38cf689f38ec9023f54ab"},
+    {file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:4c1fefd7e3d00921c44dc9ca80a775af49698bbfd92ea84498e56acffd4c5469"},
+    {file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:71a8dd38fbd2f2319136d4ae855a7078c69c9a38ae06e0c17c73fd70fc6caad8"},
+    {file = "lxml-5.3.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:97acf1e1fd66ab53dacd2c35b319d7e548380c2e9e8c54525c6e76d21b1ae3b1"},
+    {file = "lxml-5.3.0-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:68934b242c51eb02907c5b81d138cb977b2129a0a75a8f8b60b01cb8586c7b21"},
+    {file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b710bc2b8292966b23a6a0121f7a6c51d45d2347edcc75f016ac123b8054d3f2"},
+    {file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18feb4b93302091b1541221196a2155aa296c363fd233814fa11e181adebc52f"},
+    {file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:3eb44520c4724c2e1a57c0af33a379eee41792595023f367ba3952a2d96c2aab"},
+    {file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:609251a0ca4770e5a8768ff902aa02bf636339c5a93f9349b48eb1f606f7f3e9"},
+    {file = "lxml-5.3.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:516f491c834eb320d6c843156440fe7fc0d50b33e44387fcec5b02f0bc118a4c"},
+    {file = "lxml-5.3.0.tar.gz", hash = "sha256:4e109ca30d1edec1ac60cdbe341905dc3b8f55b16855e03a54aaf59e51ec8c6f"},
+]
+
+[package.extras]
+cssselect = ["cssselect (>=0.7)"]
+html-clean = ["lxml-html-clean"]
+html5 = ["html5lib"]
+htmlsoup = ["BeautifulSoup4"]
+source = ["Cython (>=3.0.11)"]
+
 [[package]]
 name = "makefun"
 version = "1.15.6"
@@ -4388,6 +4628,20 @@ rsa = ["cryptography (>=3.0.0)"]
 signals = ["blinker (>=1.4.0)"]
 signedtoken = ["cryptography (>=3.0.0)", "pyjwt (>=2.0.0,<3)"]
 
+[[package]]
+name = "olefile"
+version = "0.47"
+description = "Python package to parse, read and write Microsoft OLE2 files (Structured Storage or Compound Document, Microsoft Office)"
+optional = true
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+files = [
+    {file = "olefile-0.47-py2.py3-none-any.whl", hash = "sha256:543c7da2a7adadf21214938bb79c83ea12b473a4b6ee4ad4bf854e7715e13d1f"},
+    {file = "olefile-0.47.zip", hash = "sha256:599383381a0bf3dfbd932ca0ca6515acd174ed48870cbf7fee123d698c192c1c"},
+]
+
+[package.extras]
+tests = ["pytest", "pytest-cov"]
+
 [[package]]
 name = "openai"
 version = "1.52.0"
@@ -4412,6 +4666,20 @@ typing-extensions = ">=4.11,<5"
 [package.extras]
 datalib = ["numpy (>=1)", "pandas (>=1.2.3)", "pandas-stubs (>=1.1.0.11)"]
 
+[[package]]
+name = "openpyxl"
+version = "3.1.5"
+description = "A Python library to read/write Excel 2010 xlsx/xlsm files"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "openpyxl-3.1.5-py2.py3-none-any.whl", hash = "sha256:5282c12b107bffeef825f4617dc029afaf41d0ea60823bbb665ef3079dc79de2"},
+    {file = "openpyxl-3.1.5.tar.gz", hash = "sha256:cf0e3cf56142039133628b5acffe8ef0c12bc902d2aadd3e0fe5878dc08d1050"},
+]
+
+[package.dependencies]
+et-xmlfile = "*"
+
 [[package]]
 name = "opentelemetry-api"
 version = "1.27.0"
@@ -4506,6 +4774,17 @@ files = [
 deprecated = ">=1.2.6"
 opentelemetry-api = "1.27.0"
 
+[[package]]
+name = "orderly-set"
+version = "5.2.2"
+description = "Orderly set"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "orderly_set-5.2.2-py3-none-any.whl", hash = "sha256:f7a37c95a38c01cdfe41c3ffb62925a318a2286ea0a41790c057fc802aec54da"},
+    {file = "orderly_set-5.2.2.tar.gz", hash = "sha256:52a18b86aaf3f5d5a498bbdb27bf3253a4e5c57ab38e5b7a56fa00115cd28448"},
+]
+
 [[package]]
 name = "orjson"
 version = "3.10.12"
@@ -5631,6 +5910,17 @@ bulk-writer = ["azure-storage-blob", "minio (>=7.0.0)", "pyarrow (>=12.0.0)", "r
 dev = ["black", "grpcio (==1.62.2)", "grpcio-testing (==1.62.2)", "grpcio-tools (==1.62.2)", "pytest (>=5.3.4)", "pytest-cov (>=2.8.1)", "pytest-timeout (>=1.3.4)", "ruff (>0.4.0)"]
 model = ["milvus-model (>=0.1.0)"]
 
+[[package]]
+name = "pypandoc"
+version = "1.14"
+description = "Thin wrapper for pandoc."
+optional = true
+python-versions = ">=3.6"
+files = [
+    {file = "pypandoc-1.14-py3-none-any.whl", hash = "sha256:1315c7ad7fac7236dacf69a05b521ed2c3f1d0177f70e9b92bfffce6c023df22"},
+    {file = "pypandoc-1.14.tar.gz", hash = "sha256:6b4c45f5f1b9fb5bb562079164806bdbbc3e837b5402bcf3f1139edc5730a197"},
+]
+
 [[package]]
 name = "pyparsing"
 version = "3.2.0"
@@ -5754,6 +6044,21 @@ files = [
 [package.dependencies]
 six = ">=1.5"
 
+[[package]]
+name = "python-docx"
+version = "1.1.2"
+description = "Create, read, and update Microsoft Word .docx files."
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "python_docx-1.1.2-py3-none-any.whl", hash = "sha256:08c20d6058916fb19853fcf080f7f42b6270d89eac9fa5f8c15f691c0017fabe"},
+    {file = "python_docx-1.1.2.tar.gz", hash = "sha256:0cf1f22e95b9002addca7948e16f2cd7acdfd498047f1941ca5d293db7762efd"},
+]
+
+[package.dependencies]
+lxml = ">=3.1.0"
+typing-extensions = ">=4.9.0"
+
 [[package]]
 name = "python-dotenv"
 version = "1.0.1"
@@ -5768,6 +6073,20 @@ files = [
 [package.extras]
 cli = ["click (>=5.0)"]
 
+[[package]]
+name = "python-iso639"
+version = "2024.10.22"
+description = "ISO 639 language codes, names, and other associated information"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "python_iso639-2024.10.22-py3-none-any.whl", hash = "sha256:02d3ce2e01c6896b30b9cbbd3e1c8ee0d7221250b5d63ea9803e0d2a81fd1047"},
+    {file = "python_iso639-2024.10.22.tar.gz", hash = "sha256:750f21b6a0bc6baa24253a3d8aae92b582bf93aa40988361cd96852c2c6d9a52"},
+]
+
+[package.extras]
+dev = ["black (==24.10.0)", "build (==1.2.1)", "flake8 (==7.1.1)", "pytest (==8.3.3)", "requests (==2.32.3)", "twine (==5.1.1)"]
+
 [[package]]
 name = "python-json-logger"
 version = "2.0.7"
@@ -5779,6 +6098,17 @@ files = [
     {file = "python_json_logger-2.0.7-py3-none-any.whl", hash = "sha256:f380b826a991ebbe3de4d897aeec42760035ac760345e57b812938dc8b35e2bd"},
 ]
 
+[[package]]
+name = "python-magic"
+version = "0.4.27"
+description = "File type identification using libmagic"
+optional = true
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+files = [
+    {file = "python-magic-0.4.27.tar.gz", hash = "sha256:c1ba14b08e4a5f5c31a302b7721239695b2f0f058d125bd5ce1ee36b9d9d3c3b"},
+    {file = "python_magic-0.4.27-py2.py3-none-any.whl", hash = "sha256:c212960ad306f700aa0d01e5d7a325d20548ff97eb9920dcd29513174f0294d3"},
+]
+
 [[package]]
 name = "python-multipart"
 version = "0.0.17"
@@ -5790,6 +6120,39 @@ files = [
     {file = "python_multipart-0.0.17.tar.gz", hash = "sha256:41330d831cae6e2f22902704ead2826ea038d0419530eadff3ea80175aec5538"},
 ]
 
+[[package]]
+name = "python-oxmsg"
+version = "0.0.1"
+description = "Extract attachments from Outlook .msg files."
+optional = true
+python-versions = ">=3.9"
+files = [
+    {file = "python_oxmsg-0.0.1-py3-none-any.whl", hash = "sha256:8ea7d5dda1bc161a413213da9e18ed152927c1fda2feaf5d1f02192d8ad45eea"},
+    {file = "python_oxmsg-0.0.1.tar.gz", hash = "sha256:b65c1f93d688b85a9410afa824192a1ddc39da359b04a0bd2cbd3874e84d4994"},
+]
+
+[package.dependencies]
+click = "*"
+olefile = "*"
+typing-extensions = ">=4.9.0"
+
+[[package]]
+name = "python-pptx"
+version = "1.0.2"
+description = "Create, read, and update PowerPoint 2007+ (.pptx) files."
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "python_pptx-1.0.2-py3-none-any.whl", hash = "sha256:160838e0b8565a8b1f67947675886e9fea18aa5e795db7ae531606d68e785cba"},
+    {file = "python_pptx-1.0.2.tar.gz", hash = "sha256:479a8af0eaf0f0d76b6f00b0887732874ad2e3188230315290cd1f9dd9cc7095"},
+]
+
+[package.dependencies]
+lxml = ">=3.1.0"
+Pillow = ">=3.3.2"
+typing-extensions = ">=4.9.0"
+XlsxWriter = ">=0.5.7"
+
 [[package]]
 name = "pytz"
 version = "2024.2"
@@ -6064,6 +6427,106 @@ urllib3 = ">=1.26.14,<3"
 fastembed = ["fastembed (==0.3.6)"]
 fastembed-gpu = ["fastembed-gpu (==0.3.6)"]
 
+[[package]]
+name = "rapidfuzz"
+version = "3.10.1"
+description = "rapid fuzzy string matching"
+optional = true
+python-versions = ">=3.9"
+files = [
+    {file = "rapidfuzz-3.10.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f17d9f21bf2f2f785d74f7b0d407805468b4c173fa3e52c86ec94436b338e74a"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b31f358a70efc143909fb3d75ac6cd3c139cd41339aa8f2a3a0ead8315731f2b"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f4f43f2204b56a61448ec2dd061e26fd344c404da99fb19f3458200c5874ba2"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9d81bf186a453a2757472133b24915768abc7c3964194406ed93e170e16c21cb"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3611c8f45379a12063d70075c75134f2a8bd2e4e9b8a7995112ddae95ca1c982"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3c3b537b97ac30da4b73930fa8a4fe2f79c6d1c10ad535c5c09726612cd6bed9"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:231ef1ec9cf7b59809ce3301006500b9d564ddb324635f4ea8f16b3e2a1780da"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:ed4f3adc1294834955b7e74edd3c6bd1aad5831c007f2d91ea839e76461a5879"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:7b6015da2e707bf632a71772a2dbf0703cff6525732c005ad24987fe86e8ec32"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:1b35a118d61d6f008e8e3fb3a77674d10806a8972c7b8be433d6598df4d60b01"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:bc308d79a7e877226f36bdf4e149e3ed398d8277c140be5c1fd892ec41739e6d"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:f017dbfecc172e2d0c37cf9e3d519179d71a7f16094b57430dffc496a098aa17"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-win32.whl", hash = "sha256:36c0e1483e21f918d0f2f26799fe5ac91c7b0c34220b73007301c4f831a9c4c7"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-win_amd64.whl", hash = "sha256:10746c1d4c8cd8881c28a87fd7ba0c9c102346dfe7ff1b0d021cdf093e9adbff"},
+    {file = "rapidfuzz-3.10.1-cp310-cp310-win_arm64.whl", hash = "sha256:dfa64b89dcb906835e275187569e51aa9d546a444489e97aaf2cc84011565fbe"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:92958ae075c87fef393f835ed02d4fe8d5ee2059a0934c6c447ea3417dfbf0e8"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ba7521e072c53e33c384e78615d0718e645cab3c366ecd3cc8cb732befd94967"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:00d02cbd75d283c287471b5b3738b3e05c9096150f93f2d2dfa10b3d700f2db9"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:efa1582a397da038e2f2576c9cd49b842f56fde37d84a6b0200ffebc08d82350"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f12912acee1f506f974f58de9fdc2e62eea5667377a7e9156de53241c05fdba8"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:666d5d8b17becc3f53447bcb2b6b33ce6c2df78792495d1fa82b2924cd48701a"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:26f71582c0d62445067ee338ddad99b655a8f4e4ed517a90dcbfbb7d19310474"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8a2ef08b27167bcff230ffbfeedd4c4fa6353563d6aaa015d725dd3632fc3de7"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:365e4fc1a2b95082c890f5e98489b894e6bf8c338c6ac89bb6523c2ca6e9f086"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:1996feb7a61609fa842e6b5e0c549983222ffdedaf29644cc67e479902846dfe"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:cf654702f144beaa093103841a2ea6910d617d0bb3fccb1d1fd63c54dde2cd49"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:ec108bf25de674781d0a9a935030ba090c78d49def3d60f8724f3fc1e8e75024"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-win32.whl", hash = "sha256:031f8b367e5d92f7a1e27f7322012f3c321c3110137b43cc3bf678505583ef48"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-win_amd64.whl", hash = "sha256:f98f36c6a1bb9a6c8bbec99ad87c8c0e364f34761739b5ea9adf7b48129ae8cf"},
+    {file = "rapidfuzz-3.10.1-cp311-cp311-win_arm64.whl", hash = "sha256:f1da2028cb4e41be55ee797a82d6c1cf589442504244249dfeb32efc608edee7"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:1340b56340896bede246f612b6ecf685f661a56aabef3d2512481bfe23ac5835"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:2316515169b7b5a453f0ce3adbc46c42aa332cae9f2edb668e24d1fc92b2f2bb"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8e06fe6a12241ec1b72c0566c6b28cda714d61965d86569595ad24793d1ab259"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d99c1cd9443b19164ec185a7d752f4b4db19c066c136f028991a480720472e23"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a1d9aa156ed52d3446388ba4c2f335e312191d1ca9d1f5762ee983cf23e4ecf6"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:54bcf4efaaee8e015822be0c2c28214815f4f6b4f70d8362cfecbd58a71188ac"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c0c955e32afdbfdf6e9ee663d24afb25210152d98c26d22d399712d29a9b976b"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:191633722203f5b7717efcb73a14f76f3b124877d0608c070b827c5226d0b972"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:195baad28057ec9609e40385991004e470af9ef87401e24ebe72c064431524ab"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:0fff4a6b87c07366662b62ae994ffbeadc472e72f725923f94b72a3db49f4671"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:4ffed25f9fdc0b287f30a98467493d1e1ce5b583f6317f70ec0263b3c97dbba6"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:d02cf8e5af89a9ac8f53c438ddff6d773f62c25c6619b29db96f4aae248177c0"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-win32.whl", hash = "sha256:f3bb81d4fe6a5d20650f8c0afcc8f6e1941f6fecdb434f11b874c42467baded0"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-win_amd64.whl", hash = "sha256:aaf83e9170cb1338922ae42d320699dccbbdca8ffed07faeb0b9257822c26e24"},
+    {file = "rapidfuzz-3.10.1-cp312-cp312-win_arm64.whl", hash = "sha256:c5da802a0d085ad81b0f62828fb55557996c497b2d0b551bbdfeafd6d447892f"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:fc22d69a1c9cccd560a5c434c0371b2df0f47c309c635a01a913e03bbf183710"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:38b0dac2c8e057562b8f0d8ae5b663d2d6a28c5ab624de5b73cef9abb6129a24"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6fde3bbb14e92ce8fcb5c2edfff72e474d0080cadda1c97785bf4822f037a309"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9141fb0592e55f98fe9ac0f3ce883199b9c13e262e0bf40c5b18cdf926109d16"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:237bec5dd1bfc9b40bbd786cd27949ef0c0eb5fab5eb491904c6b5df59d39d3c"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:18123168cba156ab5794ea6de66db50f21bb3c66ae748d03316e71b27d907b95"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b75fe506c8e02769cc47f5ab21ce3e09b6211d3edaa8f8f27331cb6988779be"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:9da82aa4b46973aaf9e03bb4c3d6977004648c8638febfc0f9d237e865761270"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:c34c022d5ad564f1a5a57a4a89793bd70d7bad428150fb8ff2760b223407cdcf"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:1e96c84d6c2a0ca94e15acb5399118fff669f4306beb98a6d8ec6f5dccab4412"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:e8e154b84a311263e1aca86818c962e1fa9eefdd643d1d5d197fcd2738f88cb9"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:335fee93188f8cd585552bb8057228ce0111bd227fa81bfd40b7df6b75def8ab"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-win32.whl", hash = "sha256:6729b856166a9e95c278410f73683957ea6100c8a9d0a8dbe434c49663689255"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-win_amd64.whl", hash = "sha256:0e06d99ad1ad97cb2ef7f51ec6b1fedd74a3a700e4949353871cf331d07b382a"},
+    {file = "rapidfuzz-3.10.1-cp313-cp313-win_arm64.whl", hash = "sha256:8d1b7082104d596a3eb012e0549b2634ed15015b569f48879701e9d8db959dbb"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:779027d3307e1a2b1dc0c03c34df87a470a368a1a0840a9d2908baf2d4067956"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:440b5608ab12650d0390128d6858bc839ae77ffe5edf0b33a1551f2fa9860651"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:82cac41a411e07a6f3dc80dfbd33f6be70ea0abd72e99c59310819d09f07d945"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:958473c9f0bca250590200fd520b75be0dbdbc4a7327dc87a55b6d7dc8d68552"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9ef60dfa73749ef91cb6073be1a3e135f4846ec809cc115f3cbfc6fe283a5584"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a7fbac18f2c19fc983838a60611e67e3262e36859994c26f2ee85bb268de2355"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9a0d519ff39db887cd73f4e297922786d548f5c05d6b51f4e6754f452a7f4296"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:bebb7bc6aeb91cc57e4881b222484c26759ca865794187217c9dcea6c33adae6"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:fe07f8b9c3bb5c5ad1d2c66884253e03800f4189a60eb6acd6119ebaf3eb9894"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:bfa48a4a2d45a41457f0840c48e579db157a927f4e97acf6e20df8fc521c79de"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:2cf44d01bfe8ee605b7eaeecbc2b9ca64fc55765f17b304b40ed8995f69d7716"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:1e6bbca9246d9eedaa1c84e04a7f555493ba324d52ae4d9f3d9ddd1b740dcd87"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-win32.whl", hash = "sha256:567f88180f2c1423b4fe3f3ad6e6310fc97b85bdba574801548597287fc07028"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-win_amd64.whl", hash = "sha256:6b2cd7c29d6ecdf0b780deb587198f13213ac01c430ada6913452fd0c40190fc"},
+    {file = "rapidfuzz-3.10.1-cp39-cp39-win_arm64.whl", hash = "sha256:9f912d459e46607ce276128f52bea21ebc3e9a5ccf4cccfef30dd5bddcf47be8"},
+    {file = "rapidfuzz-3.10.1-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:ac4452f182243cfab30ba4668ef2de101effaedc30f9faabb06a095a8c90fd16"},
+    {file = "rapidfuzz-3.10.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:565c2bd4f7d23c32834652b27b51dd711814ab614b4e12add8476be4e20d1cf5"},
+    {file = "rapidfuzz-3.10.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:187d9747149321607be4ccd6f9f366730078bed806178ec3eeb31d05545e9e8f"},
+    {file = "rapidfuzz-3.10.1-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:616290fb9a8fa87e48cb0326d26f98d4e29f17c3b762c2d586f2b35c1fd2034b"},
+    {file = "rapidfuzz-3.10.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:073a5b107e17ebd264198b78614c0206fa438cce749692af5bc5f8f484883f50"},
+    {file = "rapidfuzz-3.10.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:39c4983e2e2ccb9732f3ac7d81617088822f4a12291d416b09b8a1eadebb3e29"},
+    {file = "rapidfuzz-3.10.1-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:ac7adee6bcf0c6fee495d877edad1540a7e0f5fc208da03ccb64734b43522d7a"},
+    {file = "rapidfuzz-3.10.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:425f4ac80b22153d391ee3f94bc854668a0c6c129f05cf2eaf5ee74474ddb69e"},
+    {file = "rapidfuzz-3.10.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:65a2fa13e8a219f9b5dcb9e74abe3ced5838a7327e629f426d333dfc8c5a6e66"},
+    {file = "rapidfuzz-3.10.1-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:75561f3df9a906aaa23787e9992b228b1ab69007932dc42070f747103e177ba8"},
+    {file = "rapidfuzz-3.10.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:edd062490537e97ca125bc6c7f2b7331c2b73d21dc304615afe61ad1691e15d5"},
+    {file = "rapidfuzz-3.10.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:cfcc8feccf63245a22dfdd16e222f1a39771a44b870beb748117a0e09cbb4a62"},
+    {file = "rapidfuzz-3.10.1.tar.gz", hash = "sha256:5a15546d847a915b3f42dc79ef9b0c78b998b4e2c53b252e7166284066585979"},
+]
+
+[package.extras]
+all = ["numpy"]
+
 [[package]]
 name = "redis"
 version = "5.2.0"
@@ -7725,6 +8188,105 @@ files = [
     {file = "ujson-5.10.0.tar.gz", hash = "sha256:b3cd8f3c5d8c7738257f1018880444f7b7d9b66232c64649f562d7ba86ad4bc1"},
 ]
 
+[[package]]
+name = "unstructured"
+version = "0.16.10"
+description = "A library that prepares raw documents for downstream ML tasks."
+optional = true
+python-versions = "<3.13,>=3.9.0"
+files = [
+    {file = "unstructured-0.16.10-py3-none-any.whl", hash = "sha256:738fc020fb4d9dfd1a3e54fee255221f7f916afafa16ff4e1a7a14495ba5b5ce"},
+    {file = "unstructured-0.16.10.tar.gz", hash = "sha256:61c4a447514ab5d6f8629fde2da03833cf29e0bee26a1d3b901ac57d3b5d523a"},
+]
+
+[package.dependencies]
+backoff = "*"
+beautifulsoup4 = "*"
+chardet = "*"
+dataclasses-json = "*"
+emoji = "*"
+filetype = "*"
+html5lib = "*"
+langdetect = "*"
+lxml = "*"
+markdown = {version = "*", optional = true, markers = "extra == \"md\""}
+networkx = {version = "*", optional = true, markers = "extra == \"xlsx\""}
+nltk = "*"
+numpy = "<2"
+openpyxl = {version = "*", optional = true, markers = "extra == \"xlsx\""}
+pandas = {version = "*", optional = true, markers = "extra == \"csv\" or extra == \"tsv\" or extra == \"xlsx\""}
+psutil = "*"
+pypandoc = {version = "*", optional = true, markers = "extra == \"epub\" or extra == \"odt\" or extra == \"org\" or extra == \"rst\" or extra == \"rtf\""}
+python-docx = {version = ">=1.1.2", optional = true, markers = "extra == \"doc\" or extra == \"docx\" or extra == \"odt\""}
+python-iso639 = "*"
+python-magic = "*"
+python-oxmsg = "*"
+python-pptx = {version = ">=1.0.1", optional = true, markers = "extra == \"ppt\" or extra == \"pptx\""}
+rapidfuzz = "*"
+requests = "*"
+tqdm = "*"
+typing-extensions = "*"
+unstructured-client = "*"
+wrapt = "*"
+xlrd = {version = "*", optional = true, markers = "extra == \"xlsx\""}
+
+[package.extras]
+all-docs = ["effdet", "google-cloud-vision", "markdown", "networkx", "onnx", "openpyxl", "pandas", "pdf2image", "pdfminer.six", "pi-heif", "pikepdf", "pypandoc", "pypdf", "python-docx (>=1.1.2)", "python-pptx (>=1.0.1)", "unstructured-inference (==0.8.1)", "unstructured.pytesseract (>=0.3.12)", "xlrd"]
+csv = ["pandas"]
+doc = ["python-docx (>=1.1.2)"]
+docx = ["python-docx (>=1.1.2)"]
+epub = ["pypandoc"]
+huggingface = ["langdetect", "sacremoses", "sentencepiece", "torch", "transformers"]
+image = ["effdet", "google-cloud-vision", "onnx", "pdf2image", "pdfminer.six", "pi-heif", "pikepdf", "pypdf", "unstructured-inference (==0.8.1)", "unstructured.pytesseract (>=0.3.12)"]
+local-inference = ["effdet", "google-cloud-vision", "markdown", "networkx", "onnx", "openpyxl", "pandas", "pdf2image", "pdfminer.six", "pi-heif", "pikepdf", "pypandoc", "pypdf", "python-docx (>=1.1.2)", "python-pptx (>=1.0.1)", "unstructured-inference (==0.8.1)", "unstructured.pytesseract (>=0.3.12)", "xlrd"]
+md = ["markdown"]
+odt = ["pypandoc", "python-docx (>=1.1.2)"]
+org = ["pypandoc"]
+paddleocr = ["paddlepaddle (==3.0.0b1)", "unstructured.paddleocr (==2.8.1.0)"]
+pdf = ["effdet", "google-cloud-vision", "onnx", "pdf2image", "pdfminer.six", "pi-heif", "pikepdf", "pypdf", "unstructured-inference (==0.8.1)", "unstructured.pytesseract (>=0.3.12)"]
+ppt = ["python-pptx (>=1.0.1)"]
+pptx = ["python-pptx (>=1.0.1)"]
+rst = ["pypandoc"]
+rtf = ["pypandoc"]
+tsv = ["pandas"]
+xlsx = ["networkx", "openpyxl", "pandas", "xlrd"]
+
+[[package]]
+name = "unstructured-client"
+version = "0.25.9"
+description = "Python Client SDK for Unstructured API"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "unstructured-client-0.25.9.tar.gz", hash = "sha256:fcc461623f58fefb0e22508e28bf653a8f6934b9779cb4a90dd68d77a39fb5b2"},
+    {file = "unstructured_client-0.25.9-py3-none-any.whl", hash = "sha256:c984c01878c8fc243be7c842467d1113a194d885ab6396ae74258ee42717c5b5"},
+]
+
+[package.dependencies]
+certifi = ">=2023.7.22"
+charset-normalizer = ">=3.2.0"
+cryptography = ">=3.1"
+dataclasses-json = ">=0.6.4"
+deepdiff = ">=6.0"
+httpx = ">=0.27.0"
+idna = ">=3.4"
+jsonpath-python = ">=1.0.6"
+marshmallow = ">=3.19.0"
+mypy-extensions = ">=1.0.0"
+nest-asyncio = ">=1.6.0"
+packaging = ">=23.1"
+pypdf = ">=4.0"
+python-dateutil = ">=2.8.2"
+requests = ">=2.31.0"
+requests-toolbelt = ">=1.0.0"
+six = ">=1.16.0"
+typing-extensions = ">=4.7.1"
+typing-inspect = ">=0.9.0"
+urllib3 = ">=1.26.18"
+
+[package.extras]
+dev = ["pylint (==3.1.0)"]
+
 [[package]]
 name = "uri-template"
 version = "1.3.0"
@@ -8012,6 +8574,33 @@ files = [
     {file = "wrapt-1.17.0.tar.gz", hash = "sha256:16187aa2317c731170a88ef35e8937ae0f533c402872c1ee5e6d079fcf320801"},
 ]
 
+[[package]]
+name = "xlrd"
+version = "2.0.1"
+description = "Library for developers to extract data from Microsoft Excel (tm) .xls spreadsheet files"
+optional = true
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
+files = [
+    {file = "xlrd-2.0.1-py2.py3-none-any.whl", hash = "sha256:6a33ee89877bd9abc1158129f6e94be74e2679636b8a205b43b85206c3f0bbdd"},
+    {file = "xlrd-2.0.1.tar.gz", hash = "sha256:f72f148f54442c6b056bf931dbc34f986fd0c3b0b6b5a58d013c9aef274d0c88"},
+]
+
+[package.extras]
+build = ["twine", "wheel"]
+docs = ["sphinx"]
+test = ["pytest", "pytest-cov"]
+
+[[package]]
+name = "xlsxwriter"
+version = "3.2.0"
+description = "A Python module for creating Excel XLSX files."
+optional = true
+python-versions = ">=3.6"
+files = [
+    {file = "XlsxWriter-3.2.0-py3-none-any.whl", hash = "sha256:ecfd5405b3e0e228219bcaf24c2ca0915e012ca9464a14048021d21a995d490e"},
+    {file = "XlsxWriter-3.2.0.tar.gz", hash = "sha256:9977d0c661a72866a61f9f7a809e25ebbb0fb7036baa3b9fe74afcfca6b3cb8c"},
+]
+
 [[package]]
 name = "xxhash"
 version = "3.5.0"
@@ -8261,6 +8850,7 @@ type = ["pytest-mypy"]
 
 [extras]
 deepeval = ["deepeval"]
+docs = ["unstructured"]
 falkordb = ["falkordb"]
 filesystem = ["botocore"]
 groq = ["groq"]
@@ -8278,4 +8868,4 @@ weaviate = ["weaviate-client"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9.0,<3.12"
-content-hash = "9aea4fbf426c44acda7af97be059598057eef35f51e32ce60a771ac9ab2f57af"
+content-hash = "c1f30981f79db94213a89aec3207f0b4775944968e97dda8aa49c3aa143ce7b5"
diff --git a/pyproject.toml b/pyproject.toml
index dc99ed65c..0bbf545c2 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -73,6 +73,9 @@ llama-index-core = {version = "^0.11.22", optional = true}
 deepeval = {version = "^2.0.1", optional = true}
 transformers = "^4.46.3"
 pymilvus = {version = "^2.5.0", optional = true}
+unstructured = { extras = ["csv", "doc", "docx", "epub", "md", "odt", "org", "ppt", "pptx", "rst", "rtf", "tsv", "xlsx"], version = "^0.16.10", optional = true }
+
+
 
 [tool.poetry.extras]
 filesystem = ["s3fs", "botocore"]
@@ -89,6 +92,7 @@ falkordb = ["falkordb"]
 groq = ["groq"]
 langfuse = ["langfuse"]
 milvus = ["pymilvus"]
+docs = ["unstructured"]
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^7.4.0"