markitdown
markitdown copied to clipboard
microsoft
Python tool for converting files and office documents to Markdown.
this user https://github.com/rayan3030 is opening issue full of spam in arabic like the following https://github.com/microsoft/markitdown/issues/851
The text written in Japanese on the image is translated into English and output. ``` from markitdown import MarkItDown from openai import OpenAI client = OpenAI() md = MarkItDown(llm_client=client, llm_model="gpt-4o")...
When run the code in the sample to convert an image to Markdown, an error occurs. ``` from markitdown import MarkItDown from openai import OpenAI client = OpenAI() md =...
in _get_llm_description function, base64 and mimetypes used, but not imported. ``` client = OpenAI() md = MarkItDown(llm_client=client, llm_model="gpt-4o") result = md.convert("example.jpg") >>> NameError: name 'mimetypes' is not defined ``` in...
Traceback (most recent call last): File "", line 198, in _run_module_as_main File "", line 88, in _run_code File "D:\install\python\Scripts\markitdown.exe\__main__.py", line 7, in File "D:\install\python\Lib\site-packages\markitdown\__main__.py", line 43, in main print(result.text_content) UnicodeEncodeError:...
When I use this: ``` from markitdown import MarkItDown md = MarkItDown(docintel_endpoint="") result = md.convert("test.pdf") print(result.text_content) ``` I get an error saying: No parameter named "docintel_endpoint" I have version: markitdown==0.0.1a3
Hi guys, Love the work. In our current approach we convert documents to a list of markdown, where each element consists of the markdown for that specific page. This is...
Code: ``` try: result = md.convert(str(pdf_file)) except Exception as e: log.error(f"MarkItDown conversion failed for {pdf_file.name}: {e}") print(f"DEBUG: Exception caught in conversion - {e}") ``` Error: ``` Traceback (most recent call...
## Changes - Added OpenAI Whisper support for audio transcription in `WavConverter` and `Mp3Converter` - Implemented automatic fallback to speech_recognition if Whisper fails or non-OpenAI client passed in. - Added...
