DocuMate AI (documate)

A smart PDF processing tool designed to extract text, generate intelligent summaries using a local AI model (Ollama), and deliver them instantly via WhatsApp and a formatted Word document.

🚀 Features

• PDF Text Extraction: Uses pdfplumber to extract content page-by-page.
• Local AI Processing: Integrates with Ollama (llama3.2 by default) for high-quality, privacy-focused summaries.
• Docx Export: Automatically formats the AI-generated summaries into a clean Word document.
• WhatsApp Alerts: Sends live page-by-page summaries to your WhatsApp number using pywhatkit.
• Customizable: Control the model, prompt, and layout settings with a few tweaks in main.py.

🛠 Prerequisites

1. Python 3.8+
2. Ollama: Install and run Ollama locally from ollama.com.
   • Pull the model: ollama pull llama3.2
3. WhatsApp Web: Ensure your default browser is logged into WhatsApp Web for the automated messaging feature.

📦 Installation

1. Create and Activate a Virtual Environment:

   python -m venv .venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate

2. Install Core Dependencies:

   pip install pdfplumber python-docx requests ollama pywhatkit

3. Install Google API Client (Optional): If you plan to sync with Google Docs:

   pip install google-api-python-client google-auth-httplib2 google-auth-oauthlib

🖥 Usage

1. Prepare your PDF: Place your document in the project root and name it input.pdf (or update PDF_PATH in main.py).
2. Set WhatsApp Number: Update WHATSAPP_NUMBER and SEND_TO_WHATSAPP in main.py.
3. Run the Script:

   python main.py

The script will process each page, send a message to WhatsApp (if enabled), and save the final compilation to output.docx.

⚙️ Configuration

• MODEL_NAME: Change the LLM (default llama3.2).
• PROMPT: Define what information you want extracted (Summary, Key Points, etc.).
• DOC_TITLE: Change the title of the generated Word document.
• FONT_NAME / FONT_SIZE: Change docx formatting.