Doc Parser - PDF Processing & Table Querying

Smart PDF extraction tool that converts documents to structured JSON/Markdown with AI-powered table querying.

🎯 What This Project Does

• 📄 Complete PDF Extraction - Text, images, and metadata from any PDF
• 🔄 Format Conversion - Transform content to structured JSON or Markdown
• 🤖 AI-Powered Querying - Ask questions about tables using OpenAI's API
• 💾 Download Everything - Export extracted data, images, and formatted content

🌐 Live Demo

📺 Demo Video

🚀 How to Use

Using the App

1. Upload PDF - Drag and drop any PDF document
2. Choose Format - Select JSON or Markdown conversion
3. Extract Content - Get text, images, and metadata automatically
4. Query Tables - Ask AI questions about tabular data
5. Download Results - Export everything in your preferred format

Local Development

# Clone and setup
git clone https://github.com/aishwaryaj7/doc_parser.git
cd doc_parser

# Install dependencies
pip install -r requirements.txt

# Run the app
streamlit run src/app.py

🔧 Key Features

• Complete PDF Extraction: Text, images, tables, and metadata
• Multiple Output Formats: JSON and Markdown conversion
• AI-Powered Querying: OpenAI integration for table analysis
• Drag-and-Drop Interface: Intuitive file upload
• Real-time Processing: Immediate feedback and progress indicators
• Download Options: Export data in multiple formats

🛠️ Tech Stack

Processing: PyMuPDF, Python AI: OpenAI API (gpt-3.5-turbo-instruct) Frontend: Streamlit Deployment: Streamlit Cloud

🤝 Skills Demonstrated

• Document Processing & PDF Parsing
• AI Integration & Natural Language Querying
• Streamlit Development & Cloud Deployment
• Data Transformation & Format Conversion
• User Experience Design