Bump version.

README.md

@@ -87,6 +87,42 @@ print(result.text_content)
 docker build -t markitdown:latest .
 docker run --rm -i markitdown:latest < ~/your-file.pdf > output.md
 ```
+<details>
+    
+<summary>Batch Processing Multiple Files</summary>
+
+This example shows how to convert multiple files to markdown format in a single run. The script processes all supported files in a directory and creates corresponding markdown files.
+
+
+```python convert.py
+from markitdown import MarkItDown
+from openai import OpenAI
+import os
+client = OpenAI(api_key="your-api-key-here")
+md = MarkItDown(llm_client=client, llm_model="gpt-4o-2024-11-20")
+supported_extensions = ('.pptx', '.docx', '.pdf', '.jpg', '.jpeg', '.png')
+files_to_convert = [f for f in os.listdir('.') if f.lower().endswith(supported_extensions)]
+for file in files_to_convert:
+    print(f"\nConverting {file}...")
+    try:
+        md_file = os.path.splitext(file)[0] + '.md'
+        result = md.convert(file)
+        with open(md_file, 'w') as f:
+            f.write(result.text_content)
+        
+        print(f"Successfully converted {file} to {md_file}")
+    except Exception as e:
+        print(f"Error converting {file}: {str(e)}")
+
+print("\nAll conversions completed!")
+```
+2. Place the script in the same directory as your files
+3. Install required packages: like openai
+4. Run script ```bash python convert.py ```
+
+Note that original files will remain unchanged and new markdown files are created with the same base name.
+
+</details>
    
 ## Contributing
 

src/markitdown/__about__.py

@@ -1,4 +1,4 @@
 # SPDX-FileCopyrightText: 2024-present Adam Fourney <adamfo@microsoft.com>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.2"
+__version__ = "0.0.1a5"

src/markitdown/__main__.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: MIT
 import argparse
 import sys
+import shutil
 from textwrap import dedent
 from .__about__ import __version__
 from ._markitdown import MarkItDown, DocumentConverterResult
@@ -74,6 +75,8 @@ def main():
     parser.add_argument("filename", nargs="?")
     args = parser.parse_args()
 
+    which_exiftool = shutil.which("exiftool")
+
     if args.use_docintel:
         if args.endpoint is None:
             raise ValueError(
@@ -81,9 +84,11 @@ def main():
             )
         elif args.filename is None:
             raise ValueError("Filename is required when using Document Intelligence.")
-        markitdown = MarkItDown(docintel_endpoint=args.endpoint)
+        markitdown = MarkItDown(
+            exiftool_path=which_exiftool, docintel_endpoint=args.endpoint
+        )
     else:
-        markitdown = MarkItDown()
+        markitdown = MarkItDown(exiftool_path=which_exiftool)
 
     if args.filename is None:
         result = markitdown.convert_stream(sys.stdin.buffer)

src/markitdown/_markitdown.py

@@ -17,7 +17,7 @@ from xml.dom import minidom
 from typing import Any, Dict, List, Optional, Union
 from pathlib import Path
 from urllib.parse import parse_qs, quote, unquote, urlparse, urlunparse
-from warnings import warn, filterwarnings
+from warnings import warn, resetwarnings, catch_warnings
 
 import mammoth
 import markdownify
@@ -51,14 +51,21 @@ mimetypes.add_type("text/csv", ".csv")
 
 # Optional Transcription support
 IS_AUDIO_TRANSCRIPTION_CAPABLE = False
-filterwarnings("ignore", message=r".*Couldn\'t find ffmpeg or avconv.*", module="pydub")
 try:
-    import pydub
+    # Using warnings' catch_warnings to catch
+    # pydub's warning of ffmpeg or avconv missing
+    with catch_warnings(record=True) as w:
+        import pydub
+
+        if w:
+            raise ModuleNotFoundError
     import speech_recognition as sr
 
     IS_AUDIO_TRANSCRIPTION_CAPABLE = True
 except ModuleNotFoundError:
     pass
+finally:
+    resetwarnings()
 
 # Optional YouTube transcription support
 try:
@@ -967,6 +974,18 @@ class MediaConverter(DocumentConverter):
 
     def _get_metadata(self, local_path, exiftool_path=None):
         if not exiftool_path:
+            which_exiftool = shutil.which("exiftool")
+            if which_exiftool:
+                warn(
+                    f"""Implicit discovery of 'exiftool' is disabled. If you would like to continue to use exiftool in MarkItDown, please set the exiftool_path parameter in the MarkItDown consructor. E.g., 
+
+    md = MarkItDown(exiftool_path="{which_exiftool}")
+
+This warning will be removed in future releases.
+""",
+                    DeprecationWarning,
+                )
+
             return None
         else:
             try:
@@ -1069,14 +1088,6 @@ class Mp3Converter(WavConverter):
             handle, temp_path = tempfile.mkstemp(suffix=".wav")
             os.close(handle)
             try:
-                # Check if pydub defaulted to ffmpeg
-                if pydub.AudioSegment.converter == "ffmpeg" and not shutil.which(
-                    "ffmpeg"
-                ):
-                    warn(
-                        "pydub: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work",
-                        RuntimeWarning,
-                    )
                 sound = pydub.AudioSegment.from_mp3(local_path)
                 sound.export(temp_path, format="wav")
 
@@ -1487,26 +1498,34 @@ class MarkItDown:
         if exiftool_path is None:
             exiftool_path = os.environ.get("EXIFTOOL_PATH")
 
-        # Still none? Check well-known paths
+        # Handle deprecation notices
-        if exiftool_path is None:
+        #############################
-            candidate = shutil.which("exiftool")
+        if mlm_client is not None:
-            if candidate:
+            if llm_client is None:
-                candidate = os.path.abspath(candidate)
+                warn(
-                if any(
+                    "'mlm_client' is deprecated, and was renamed 'llm_client'.",
-                    d == os.path.dirname(candidate)
+                    DeprecationWarning,
-                    for d in [
+                )
-                        "/usr/bin",
+                llm_client = mlm_client
-                        "/usr/local/bin",
+                mlm_client = None
-                        "/opt",
+            else:
-                        "/opt/bin",
+                raise ValueError(
-                        "/opt/local/bin",
+                    "'mlm_client' is deprecated, and was renamed 'llm_client'. Do not use both at the same time. Just use 'llm_client' instead."
-                        "/opt/homebrew/bin",
+                )
-                        "C:\\Windows\\System32",
+
-                        "C:\\Program Files",
+        if mlm_model is not None:
-                        "C:\\Program Files (x86)",
+            if llm_model is None:
-                    ]
+                warn(
-                ):
+                    "'mlm_model' is deprecated, and was renamed 'llm_model'.",
-                    exiftool_path = candidate
+                    DeprecationWarning,
+                )
+                llm_model = mlm_model
+                mlm_model = None
+            else:
+                raise ValueError(
+                    "'mlm_model' is deprecated, and was renamed 'llm_model'. Do not use both at the same time. Just use 'llm_model' instead."
+                )
+        #############################
 
         self._llm_client = llm_client
         self._llm_model = llm_model

tests/test_markitdown.py

@@ -6,6 +6,8 @@ import shutil
 import pytest
 import requests
 
+from warnings import catch_warnings, resetwarnings
+
 from markitdown import MarkItDown
 
 skip_remote = (
@@ -275,6 +277,18 @@ def test_markitdown_local() -> None:
     reason="do not run if exiftool is not installed",
 )
 def test_markitdown_exiftool() -> None:
+    # Test the automatic discovery of exiftool throws a warning
+    # and is disabled
+    try:
+        with catch_warnings(record=True) as w:
+            markitdown = MarkItDown()
+            result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.jpg"))
+            assert len(w) == 1
+            assert w[0].category is DeprecationWarning
+            assert result.text_content.strip() == ""
+    finally:
+        resetwarnings()
+
     # Test explicitly setting the location of exiftool
     which_exiftool = shutil.which("exiftool")
     markitdown = MarkItDown(exiftool_path=which_exiftool)
@@ -292,6 +306,40 @@ def test_markitdown_exiftool() -> None:
         assert target in result.text_content
 
 
+def test_markitdown_deprecation() -> None:
+    try:
+        with catch_warnings(record=True) as w:
+            test_client = object()
+            markitdown = MarkItDown(mlm_client=test_client)
+            assert len(w) == 1
+            assert w[0].category is DeprecationWarning
+            assert markitdown._llm_client == test_client
+    finally:
+        resetwarnings()
+
+    try:
+        with catch_warnings(record=True) as w:
+            markitdown = MarkItDown(mlm_model="gpt-4o")
+            assert len(w) == 1
+            assert w[0].category is DeprecationWarning
+            assert markitdown._llm_model == "gpt-4o"
+    finally:
+        resetwarnings()
+
+    try:
+        test_client = object()
+        markitdown = MarkItDown(mlm_client=test_client, llm_client=test_client)
+        assert False
+    except ValueError:
+        pass
+
+    try:
+        markitdown = MarkItDown(mlm_model="gpt-4o", llm_model="gpt-4o")
+        assert False
+    except ValueError:
+        pass
+
+
 @pytest.mark.skipif(
     skip_llm,
     reason="do not run llm tests without a key",
@@ -316,4 +364,5 @@ if __name__ == "__main__":
     # test_markitdown_remote()
     # test_markitdown_local()
     test_markitdown_exiftool()
+    # test_markitdown_deprecation()
     # test_markitdown_llm()