# Parser Service

Extracts text from 7 file formats.

## Supported Formats

| Format | Library |
|---|---|
| PDF | PyMuPDF (fitz) |
| Word (.docx) | python-docx |
| PowerPoint (.pptx) | python-pptx |
| Excel (.xlsx) | openpyxl |
| Images (.png/.jpg) | Tesseract OCR |
| Markdown (.md) | Raw text |
| Text (.txt) | Python built-in |

## Source Code
```{eval-rst}
.. automodule:: backend.services.parser_service
   :members:
```