Information Retrieval System

This repository implements an Information Retrieval System based on the Vector Information Retrieval Model. It includes a visual interface powered by Streamlit and provides evaluation using various objective metrics across different test collections.

Features

• Implements Vector Information Retrieval Model
• Visual interface using Streamlit
• Evaluation with different test collections and objective metrics
• Clustering techniques to group documents
• Implementation of a crawler to gain information.
• NLP techniques and different metrics in different collections are applied to check the functionality of the system.

Installation

1. Clone the repository and install dependencies:
2. Install dependencies

git clone https://github.com/lorainemg/information-retrieval-system.git
cd information-retrieval-system
pip install -r requirements.txt

3. Run the main program:

python main.py

Documentation

For more information see https://github.com/lorainemg/information-retrieval-system/blob/main/doc/C511%20Loraine%20Monteagudo%2C%20Tony%20Raul%20Blanco.pdf