pierreguillou commited on
Commit
448f55b
·
verified ·
1 Parent(s): b740887

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +2 -1
app.py CHANGED
@@ -285,9 +285,10 @@ def reset_form():
285
 
286
  # Gradio Interface
287
  with gr.Blocks(title="LLM-Ready Document Converter") as app:
 
288
  gr.Markdown("# 📄 LLM-Ready Document Converter")
289
  gr.Markdown("**HOWTO** : Upload a document or image and get 4 output files: Docling JSON, TXT, Markdown, and HTML")
290
- gr.Markdown("**EXPLANATION** : This app transforms various document formats (like TXT, standard and scanned PDFs, DOCX, PPT, CSV, XLS, XLSX) and **images (PNG, JPG, JPEG, BMP, TIFF)** into structured, machine-readable outputs optimized for Large Language Models (LLMs). For images, it uses OCR (Optical Character Recognition) to extract text. For all input documents, it extracts and converts content into clean formats such as DocLing JSON (for document structure), plain text, Markdown, and HTML making it easier for AI models to process, analyze, or generate responses from complex documents without losing key details like layout or formatting. Essentially, it's a bridge between raw files and AI-ready data.")
291
 
292
  with gr.Row():
293
  with gr.Column():
 
285
 
286
  # Gradio Interface
287
  with gr.Blocks(title="LLM-Ready Document Converter") as app:
288
+
289
  gr.Markdown("# 📄 LLM-Ready Document Converter")
290
  gr.Markdown("**HOWTO** : Upload a document or image and get 4 output files: Docling JSON, TXT, Markdown, and HTML")
291
+ gr.Markdown("**EXPLANATION** : This app transforms various document formats (like TXT, standard and scanned PDFs, DOCX, PPT, CSV, XLS, XLSX) and **images (PNG, JPG, JPEG, BMP, TIFF)** into structured, machine-readable outputs optimized for Large Language Models (LLMs). For images, it uses OCR (Optical Character Recognition) to extract text. For all input documents, it extracts and converts content into clean formats such as DocLing JSON (for document structure), plain text, Markdown, and HTML making it easier for AI models to process, analyze, or generate responses from complex documents without losing key details like layout or formatting. Essentially, it's a bridge between raw files and AI-ready data.")
292
 
293
  with gr.Row():
294
  with gr.Column():