Local File Summarizer with Ollama

A simple Python-based AI file summarizer that reads different file types and generates concise summaries using locally running LLMs through Ollama.

This project works completely offline after setup and supports multiple AI models such as Llama 3.2, Gemma, and TinyLlama.

Features

• Read and summarize multiple file types
• Uses local AI models with Ollama
• Offline & privacy-friendly
• Fast summarization
• Option to save summaries
• Supports multiple models:
• llama3.2
• gemma3
• tinyllama

⚙️ Installation

1️⃣ Clone the Repository

git clone https://github.com/IndiraV5/Summar.io

cd local-file-summarizer

2️⃣ Create Virtual Environment (Recommended)

Windows

python -m venv venv

venv\Scripts\activate

Linux / Mac

python3 -m venv venv

source venv/bin/activate

3️⃣ Install Dependencies

pip install requests PyPDF2 python-docx

Or create a requirements.txt:

requests
PyPDF2
python-docx

Then run:

pip install -r requirements.txt

Install Ollama

Download and install Ollama from:

https://ollama.com/download

Pull AI Models

Run these commands:

ollama pull llama3.2

ollama pull gemma3

ollama pull tinyllama

▶️ Run Ollama

Start the Ollama server:

ollama serve

▶️ Run the Project

python summarizer.py

Example Usage

============================================================
LOCAL FILE SUMMARIZER WITH OLLAMA
============================================================

📁 Enter file path:
sample.pdf

Available models:
1. llama3.2
2. gemma3
3. tinyllama

Choose model:
1

How It Works

1. User selects a file
2. Python reads the file content
3. Content is sent to Ollama API
4. Local LLM generates summary
5. Summary is displayed and optionally saved

---

Technologies Used

• Python
• Ollama
• Llama 3.2 / Gemma / TinyLlama
• PyPDF2
• python-docx
• Requests

---

Author

Developed by Indira Verma