Pdf & images lab

A project to explore libraries to extract text from pdfs such as:

• pdfminer
• pyMuPDF
• pyPDF2
• ptpdfium2

Besides, I explore others to extract text from images such as

• pytesseract
• easyocr
• transformers models from huggingface

Additionally, how to extract text from pdfs using LLMs is also explored

• Gemini

Setup

Step 1. Navigate to the root directory of the repository and create a new conda environment for development:

uv venv .venv

Step 2. Activate the environment:

source .venv/Scripts/activate

Step 3. Install the dependencies:

uv pip install -e .

Usage

Go to the notebook and select your environment to run the cells.