Metadata-Version: 2.5
Name: llama-index-readers-anytomarkdown
Version: 0.1.0
Summary: LlamaIndex reader for the AnyToMarkdown API: PDF, Word, Excel, PowerPoint and web pages to Markdown.
Project-URL: Homepage, https://anymarkdownapi.gtgroup.dev/
License: MIT
Keywords: llama-index,llamaindex,markdown,pdf,rag,reader
Requires-Python: <4.0,>=3.9
Requires-Dist: llama-index-core>=0.11.0
Requires-Dist: requests>=2.31
Description-Content-Type: text/markdown

# LlamaIndex Reader: AnyToMarkdown

Loads PDF, Word, Excel, PowerPoint, e-mail and web pages as Markdown documents with the [AnyToMarkdown API](https://anymarkdownapi.gtgroup.dev/api/). Tables, headings and lists are kept, and scanned pages are read with OCR.

```bash
pip install llama-index-readers-anytomarkdown
```

```python
import os
from pathlib import Path
from llama_index.readers.anytomarkdown import AnyToMarkdownReader

reader = AnyToMarkdownReader(api_key=os.environ["RAPIDAPI_KEY"])
documents = reader.load_data(file=Path("handbook.pdf"))
documents += reader.load_data(url="https://en.wikipedia.org/wiki/Markdown")
```

Get a free key on [RapidAPI](https://rapidapi.com/controller2042000/api/anytomarkdown-pdf-to-markdown-and-document-parser-api). Files are processed in memory and are not stored.
