Spaces:
Running
Running
File size: 4,977 Bytes
15fdcff 3aa9da6 15fdcff |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 |
import os
import gradio as gr
import pandas as pd
from dockling_parser import DocumentParser
from dockling_parser.exceptions import ParserError
import tempfile
TITLE = "📄 Smart Document Parser"
DESCRIPTION = """
A powerful document parsing application that automatically extracts structured information from various document formats.
Upload any document (PDF, DOCX, TXT, HTML, Markdown) and get structured information extracted automatically.
"""
ARTICLE = """
## 🚀 Features
- Multiple Format Support: PDF, DOCX, TXT, HTML, and Markdown
- Rich Information Extraction
- Smart Processing with Confidence Scoring
- Automatic Format Detection
Made with ❤️ using Docling and Gradio
"""
# Initialize the document parser
parser = DocumentParser()
def process_document(file):
"""Process uploaded document and return structured information"""
try:
# Create a temporary file to handle the upload
with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(file.name)[1]) as tmp_file:
tmp_file.write(file.read())
temp_path = tmp_file.name
# Parse the document
result = parser.parse(temp_path)
# Clean up temporary file
os.unlink(temp_path)
# Prepare the outputs
metadata_df = pd.DataFrame([{
"Property": k,
"Value": str(v)
} for k, v in result.metadata.dict().items()])
# Extract structured content
sections = result.structured_content.get('sections', [])
sections_text = "\n\n".join([f"Section {i+1}:\n{section}" for i, section in enumerate(sections)])
# Format entities if available
entities = result.structured_content.get('entities', {})
entities_text = "\n".join([f"{entity_type}: {', '.join(entities_list)}"
for entity_type, entities_list in entities.items()]) if entities else "No entities detected"
return (
result.content, # Main content
metadata_df, # Metadata as table
sections_text, # Structured sections
entities_text, # Named entities
f"Confidence Score: {result.confidence_score:.2f}" # Confidence score
)
except ParserError as e:
return (
f"Error parsing document: {str(e)}",
pd.DataFrame(),
"No sections available",
"No entities available",
"Confidence Score: 0.0"
)
except Exception as e:
return (
f"Unexpected error: {str(e)}",
pd.DataFrame(),
"No sections available",
"No entities available",
"Confidence Score: 0.0"
)
finally:
# Ensure temporary file is cleaned up
if 'temp_path' in locals() and os.path.exists(temp_path):
try:
os.unlink(temp_path)
except:
pass
# Create Gradio interface
with gr.Blocks(title=TITLE, theme=gr.themes.Soft()) as iface:
gr.Markdown(f"# {TITLE}")
gr.Markdown(DESCRIPTION)
with gr.Row():
with gr.Column():
file_input = gr.File(
label="Upload Document",
file_types=[".pdf", ".docx", ".txt", ".html", ".md"],
type="binary"
)
submit_btn = gr.Button("Process Document", variant="primary")
with gr.Column():
confidence = gr.Textbox(label="Processing Confidence")
with gr.Tabs():
with gr.TabItem("📝 Content"):
content_output = gr.Textbox(
label="Extracted Content",
lines=10,
max_lines=30
)
with gr.TabItem("📊 Metadata"):
metadata_output = gr.Dataframe(
label="Document Metadata",
headers=["Property", "Value"]
)
with gr.TabItem("📑 Sections"):
sections_output = gr.Textbox(
label="Document Sections",
lines=10,
max_lines=30
)
with gr.TabItem("🏷️ Entities"):
entities_output = gr.Textbox(
label="Named Entities",
lines=5,
max_lines=15
)
# Handle file submission
submit_btn.click(
fn=process_document,
inputs=[file_input],
outputs=[
content_output,
metadata_output,
sections_output,
entities_output,
confidence
]
)
gr.Markdown("""
### 📌 Supported Formats
- PDF Documents (*.pdf)
- Word Documents (*.docx)
- Text Files (*.txt)
- HTML Files (*.html)
- Markdown Files (*.md)
""")
gr.Markdown(ARTICLE)
# Launch the app
if __name__ == "__main__":
iface.launch() |