[Draft] Exploring ways to allow Optional dependencies

README.md

@@ -5,7 +5,8 @@
 [![Built by AutoGen Team](https://img.shields.io/badge/Built%20by-AutoGen%20Team-blue)](https://github.com/microsoft/autogen)
 
 > [!IMPORTANT]
-> MarkItDown 0.0.2 alpha 1 (0.0.2a1) introduces a plugin-based architecture. As much as was possible, command-line and Python interfaces have remained the same as 0.0.1a3 to support backward compatibility. Please report any issues you encounter. Some interface changes may yet occur as we continue to refine MarkItDown to a first non-alpha release.
+> Breaking changes between 0.0.1 to 0.0.2:
+> * Dependencies are now organized into optional feature-groups (further details below). Use `pip install markitdown[all]` to have backward-compatible behavior. 
 
 MarkItDown is a utility for converting various files to Markdown (e.g., for indexing, text analysis, etc).
 It supports:
@@ -22,12 +23,12 @@ It supports:
 - Youtube URLs
 - ... and more!
 
-To install MarkItDown, use pip: `pip install markitdown`. Alternatively, you can install it from the source:
+To install MarkItDown, use pip: `pip install markitdown[all]`. Alternatively, you can install it from the source:
 
 ```bash
 git clone git@github.com:microsoft/markitdown.git
 cd markitdown
-pip install -e packages/markitdown
+pip install -e packages/markitdown[all]
 ```
 
 ## Usage
@@ -50,6 +51,28 @@ You can also pipe content:
 cat path-to-file.pdf | markitdown
 ```
 
+### Optional Dependencies
+MarkItDown has optional dependencies for activating various file formats. Earlier in this document, we installed all optional dependencies with the `[all]` option. However, you can also install them individually for more control. For example:
+
+```bash
+pip install markitdown[pdf, docx, pptx]
+```
+
+will install only the dependencies for PDF, DOCX, and PPTX files.
+
+At the moment, the following optional dependencies are available:
+
+* `[all]` Installs all optional dependencies
+* `[pptx]` Installs dependencies for PowerPoint files
+* `[docx]` Installs dependencies for Word files
+* `[xlsx]` Installs dependencies for Excel files
+* `[xls]` Installs dependencies for older Excel files
+* `[pdf]` Installs dependencies for PDF files
+* `[outlook]` Installs dependencies for Outlook messages
+* `[az-doc-intel]` Installs dependencies for Azure Document Intelligence
+* `[audio-transcription]` Installs dependencies for audio transcription of wav and mp3 files
+* `[youtube-transcription]` Installs dependencies for fetching YouTube video transcription
+
 ### Plugins
 
 MarkItDown also supports 3rd-party plugins. Plugins are disabled by default. To list installed plugins:

packages/markitdown/README.md

@@ -10,15 +10,15 @@
 From PyPI:
 
 ```bash
-pip install markitdown
+pip install markitdown[all]
 ```
 
 From source:
 
 ```bash
 git clone git@github.com:microsoft/markitdown.git
 cd markitdown
-pip install -e packages/markitdown
+pip install -e packages/markitdown[all]
 ```
 
 ## Usage

packages/markitdown/pyproject.toml

@@ -26,25 +26,36 @@ classifiers = [
 dependencies = [
   "beautifulsoup4",
   "requests",
-  "mammoth",
   "markdownify~=0.14.1",
-  "numpy",
+  "puremagic",
+  "pathvalidate",
+  "charset-normalizer",
+]
+
+[project.optional-dependencies]
+all = [
   "python-pptx",
+  "mammoth",
   "pandas",
   "openpyxl",
   "xlrd",
   "pdfminer.six",
-  "puremagic",
-  "pydub",
   "olefile",
-  "youtube-transcript-api",
+  "pydub",
   "SpeechRecognition",
-  "pathvalidate",
-  "charset-normalizer",
-  "openai",
+  "youtube-transcript-api",
   "azure-ai-documentintelligence",
   "azure-identity"
 ]
+pptx = ["python-pptx"]
+docx = ["mammoth"]
+xlsx = ["pandas", "openpyxl"]
+xls = ["pandas", "xlrd"]
+pdf = ["pdfminer.six"]
+outlook = ["olefile"]
+audio-transcription = ["pydub", "SpeechRecognition"]
+youtube-transcription = ["youtube-transcript-api"]
+az-doc-intel = ["azure-ai-documentintelligence", "azure-identity"]
 
 [project.urls]
 Documentation = "https://github.com/microsoft/markitdown#readme"
@@ -57,6 +68,15 @@ path = "src/markitdown/__about__.py"
 [project.scripts]
 markitdown = "markitdown.__main__:main"
 
+[tool.hatch.envs.default]
+features = ["all"]
+
+[tool.hatch.envs.hatch-test]
+features = ["all"]
+extra-dependencies = [
+  "openai",
+]
+
 [tool.hatch.envs.types]
 extra-dependencies = [
   "mypy>=1.0.0",

packages/markitdown/src/markitdown/__init__.py

@@ -6,7 +6,7 @@
 from ._markitdown import MarkItDown
 from ._exceptions import (
     MarkItDownException,
-    ConverterPrerequisiteException,
+    MissingDependencyException,
     FailedConversionAttempt,
     FileConversionException,
     UnsupportedFormatException,
@@ -19,7 +19,7 @@
     "DocumentConverter",
     "DocumentConverterResult",
     "MarkItDownException",
-    "ConverterPrerequisiteException",
+    "MissingDependencyException",
     "FailedConversionAttempt",
     "FileConversionException",
     "UnsupportedFormatException",

packages/markitdown/src/markitdown/_exceptions.py

@@ -1,5 +1,12 @@
 from typing import Optional, List, Any
 
+MISSING_DEPENDENCY_MESSAGE = """{converter} recognized the input as a potential {extension} file, but the dependencies needed to read {extension} files have not been installed. To resolve this error, include the optional dependency [{feature}] or [all] when installing MarkItDown. For example:
+
+* pip install markitdown[{feature}]
+* pip install markitdown[all]
+* pip install markitdown[{feature}, ...]
+* etc."""
+
 
 class MarkItDownException(Exception):
     """
@@ -9,15 +16,16 @@ class MarkItDownException(Exception):
     pass
 
 
-class ConverterPrerequisiteException(MarkItDownException):
+class MissingDependencyException(MarkItDownException):
     """
-    Thrown when instantiating a DocumentConverter in cases where
-    a required library or dependency is not installed, an API key
-    is not set, or some other prerequisite is not met.
-
-    This is not necessarily a fatal error. If thrown during
-    MarkItDown's plugin loading phase, the converter will simply be
-    skipped, and a warning will be issued.
+    Converters shipped with MarkItDown may depend on optional
+    dependencies. This exception is thrown when a converter's
+    convert() method is called, but the required dependency is not
+    installed. This is not necessarily a fatal error, as the converter
+    will simply be skipped (an error will bubble up only if no other
+    suitable converter is found).
+
+    Error messages should clearly indicate which dependency is missing.
     """
 
     pass

packages/markitdown/src/markitdown/_markitdown.py

@@ -42,7 +42,6 @@
 from ._exceptions import (
     FileConversionException,
     UnsupportedFormatException,
-    ConverterPrerequisiteException,
     FailedConversionAttempt,
 )
 

packages/markitdown/src/markitdown/converters/_doc_intel_converter.py

@@ -1,16 +1,24 @@
 from typing import Any, Union
 import re
-
-# Azure imports
-from azure.ai.documentintelligence import DocumentIntelligenceClient
-from azure.ai.documentintelligence.models import (
-    AnalyzeDocumentRequest,
-    AnalyzeResult,
-    DocumentAnalysisFeature,
-)
-from azure.identity import DefaultAzureCredential
+import sys
 
 from ._base import DocumentConverter, DocumentConverterResult
+from .._exceptions import MissingDependencyException
+
+# Try loading optional (but in this case, required) dependencies
+# Save reporting of any exceptions for later
+_dependency_exc_info = None
+try:
+    from azure.ai.documentintelligence import DocumentIntelligenceClient
+    from azure.ai.documentintelligence.models import (
+        AnalyzeDocumentRequest,
+        AnalyzeResult,
+        DocumentAnalysisFeature,
+    )
+    from azure.identity import DefaultAzureCredential
+except ImportError:
+    # Preserve the error and stack trace for later
+    _dependency_exc_info = sys.exc_info()
 
 
 # TODO: currently, there is a bug in the document intelligence SDK with importing the "ContentFormat" enum.
@@ -30,6 +38,16 @@ def __init__(
     ):
         super().__init__(priority=priority)
 
+        # Raise an error if the dependencies are not available.
+        # This is different than other converters since this one isn't even instantiated
+        # unless explicitly requested.
+        if _dependency_exc_info is not None:
+            raise MissingDependencyException(
+                "DocumentIntelligenceConverter requires the optional dependency [az-doc-intel] (or [all]) to be installed. E.g., `pip install markitdown[az-doc-intel]`"
+            ) from _dependency_exc_info[1].with_traceback(
+                _dependency_exc_info[2]
+            )  # Restore the original traceback
+
         self.endpoint = endpoint
         self.api_version = api_version
         self.doc_intel_client = DocumentIntelligenceClient(

packages/markitdown/src/markitdown/converters/_docx_converter.py

@@ -1,13 +1,23 @@
-from typing import Union
+import sys
 
-import mammoth
+from typing import Union
 
 from ._base import (
     DocumentConverterResult,
 )
 
 from ._base import DocumentConverter
 from ._html_converter import HtmlConverter
+from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
+
+# Try loading optional (but in this case, required) dependencies
+# Save reporting of any exceptions for later
+_dependency_exc_info = None
+try:
+    import mammoth
+except ImportError:
+    # Preserve the error and stack trace for later
+    _dependency_exc_info = sys.exc_info()
 
 
 class DocxConverter(HtmlConverter):
@@ -26,6 +36,18 @@ def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
         if extension.lower() != ".docx":
             return None
 
+        # Check: the dependencies
+        if _dependency_exc_info is not None:
+            raise MissingDependencyException(
+                MISSING_DEPENDENCY_MESSAGE.format(
+                    converter=type(self).__name__,
+                    extension=".docx",
+                    feature="docx",
+                )
+            ) from _dependency_exc_info[1].with_traceback(
+                _dependency_exc_info[2]
+            )  # Restore the original traceback
+
         result = None
         with open(local_path, "rb") as docx_file:
             style_map = kwargs.get("style_map", None)

packages/markitdown/src/markitdown/converters/_image_converter.py

@@ -7,7 +7,7 @@
 
 class ImageConverter(MediaConverter):
     """
-    Converts images to markdown via extraction of metadata (if `exiftool` is installed), OCR (if `easyocr` is installed), and description via a multimodal LLM (if an llm_client is configured).
+    Converts images to markdown via extraction of metadata (if `exiftool` is installed), and description via a multimodal LLM (if an llm_client is configured).
     """
 
     def __init__(

packages/markitdown/src/markitdown/converters/_outlook_msg_converter.py

@@ -1,6 +1,16 @@
-import olefile
+import sys
 from typing import Any, Union
 from ._base import DocumentConverter, DocumentConverterResult
+from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
+
+# Try loading optional (but in this case, required) dependencies
+# Save reporting of any exceptions for later
+_dependency_exc_info = None
+try:
+    import olefile
+except ImportError:
+    # Preserve the error and stack trace for later
+    _dependency_exc_info = sys.exc_info()
 
 
 class OutlookMsgConverter(DocumentConverter):
@@ -24,6 +34,18 @@ def convert(
         if extension.lower() != ".msg":
             return None
 
+        # Check: the dependencies
+        if _dependency_exc_info is not None:
+            raise MissingDependencyException(
+                MISSING_DEPENDENCY_MESSAGE.format(
+                    converter=type(self).__name__,
+                    extension=".msg",
+                    feature="outlook",
+                )
+            ) from _dependency_exc_info[1].with_traceback(
+                _dependency_exc_info[2]
+            )  # Restore the original traceback
+
         try:
             msg = olefile.OleFileIO(local_path)
             # Extract email metadata
@@ -59,10 +81,12 @@ def convert(
                 f"Could not convert MSG file '{local_path}': {str(e)}"
             )
 
-    def _get_stream_data(
-        self, msg: olefile.OleFileIO, stream_path: str
-    ) -> Union[str, None]:
+    def _get_stream_data(self, msg: Any, stream_path: str) -> Union[str, None]:
         """Helper to safely extract and decode stream data from the MSG file."""
+        assert isinstance(
+            msg, olefile.OleFileIO
+        )  # Ensure msg is of the correct type (type hinting is not possible with the optional olefile package)
+
         try:
             if msg.exists(stream_path):
                 data = msg.openstream(stream_path).read()

packages/markitdown/src/markitdown/converters/_pdf_converter.py

@@ -1,7 +1,17 @@
-import pdfminer
-import pdfminer.high_level
+import sys
 from typing import Union
 from ._base import DocumentConverter, DocumentConverterResult
+from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
+
+# Try loading optional (but in this case, required) dependencies
+# Save reporting of any exceptions for later
+_dependency_exc_info = None
+try:
+    import pdfminer
+    import pdfminer.high_level
+except ImportError:
+    # Preserve the error and stack trace for later
+    _dependency_exc_info = sys.exc_info()
 
 
 class PdfConverter(DocumentConverter):
@@ -20,6 +30,18 @@ def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
         if extension.lower() != ".pdf":
             return None
 
+        # Check the dependencies
+        if _dependency_exc_info is not None:
+            raise MissingDependencyException(
+                MISSING_DEPENDENCY_MESSAGE.format(
+                    converter=type(self).__name__,
+                    extension=".pdf",
+                    feature="pdf",
+                )
+            ) from _dependency_exc_info[1].with_traceback(
+                _dependency_exc_info[2]
+            )  # Restore the original traceback
+
         return DocumentConverterResult(
             title=None,
             text_content=pdfminer.high_level.extract_text(local_path),