llama-scan 0.1.3

A tool for converting PDFs to text files using Ollama.

llama-scan

A tool for converting PDFs to text files using Ollama.

Features

• Convert PDFs to text files locally, no token costs.
• Use the latest multimodal models supported by Ollama.
• Turn images and diagrams into detailed text descriptions.

Requirements

• Python 3.10+
• Ollama installed and running locally

Installing Ollama and the Default Model

1. Install Ollama
2. Pull the default model:

ollama run qwen2.5vl:latest

Installation

Install using pip:

pip install "git+ssh://[e-mail]/ngafar/llama-scan.git"

or uv:

uv tool install https://github.com/ngafar/llama-scan.git

Usage

Basic usage:

llama-scan path/to/your/file.pdf

Options

• --output, -o: Output directory (default: "output")
• --model, -m: Ollama model to use (default: "qwen2.5vl:latest")
• --keep-images, -k: Keep the intermediate image files (default: False)
• --width, -w: Width of the resized images (0 to skip resizing; default: 0)
• --start, -s: Start page number (default: 0)
• --end, -e: End page number (default: 0)

Examples

Process specific pages with custom width:

llama-scan document.pdf --start 1 --end 5 --width 1000

Use a different Ollama model:

llama-scan document.pdf --model qwen2.5vl:3b