Exploring ways to allow Optional dependencies (#1079)

* Enable optional dependencies. Starting with pptx.
* Fix CLI tests.... have them install [all]
* Added .docx to optional dependencies
* Reuse error messages for missing dependencies.
* Added xlsx and xls
* Added pdfs
* Added Ole files.
* Updated READMEs, and finished remaining feature-categories.
* Move OpenAI to hatch-test environment.

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",