https://github.com/cllspy/sumora

Sumora — An AI-powered blog summarization system.
https://github.com/cllspy/sumora

beautifulsoup4 c4model llmops python3 streamlit-webapp

Last synced: 7 months ago
JSON representation

Sumora — An AI-powered blog summarization system.

• Host: GitHub
• URL: https://github.com/cllspy/sumora
• Owner: CllsPy
• License: mit
• Created: 2025-10-18T22:22:13.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-10-24T09:05:03.000Z (7 months ago)
• Last Synced: 2025-10-24T11:12:17.628Z (7 months ago)
• Topics: beautifulsoup4, c4model, llmops, python3, streamlit-webapp
• Language: Python
• Homepage:
• Size: 32.2 KB
• Stars: 1
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Blog Summary System



## Tech Stack

![Python](https://img.shields.io/badge/Python-3776AB?logo=python&logoColor=white)

![Streamlit](https://img.shields.io/badge/Streamlit-FF4B4B?logo=streamlit&logoColor=white)

![BeautifulSoup](https://img.shields.io/badge/BeautifulSoup-4B8BBE?logo=python&logoColor=white)

![C4 Model](https://img.shields.io/badge/C4%20Model-232F3E?logo=diagram&logoColor=white)

## Overview

This project demonstrates how to enhance a personal blog through automated content summarization. It uses a Large Language Model (LLM) to generate concise and engaging summaries of blog articles. The system retrieves a blog URL, extracts text content, and produces a short, humorous summary that helps users quickly understand the main ideas.

## About This Project

### C4 Model

![c4lvl2](https://github.com/user-attachments/assets/11669801-7bd6-49b8-81ea-fe0f0e23cee7)

This system uses the GPT-5-Nano model via the [OpenAI API](https://openai.com/fr-FR/index/openai-api/). The workflow receives a blog URL from the user, extracts content with [BeautifulSoup4](https://www.crummy.com/software/BeautifulSoup/bs4/doc.ptbr/), and generates a lighthearted summary. Finally, the application is deployed using [Streamlit Community Cloud](https://streamlit.io/cloud).

## Development Roadmap

1. **Environment Setup** – Initialize the project structure.  

2. **Data Collection** – Fetch blog content using the provided URL.  

3. **Data Preprocessing** – Clean and prepare the extracted text.  

4. **Summarization Pipeline** –  

   - Extract data  

   - Process text  

   - Generate summary  

5. **Cloud Deployment** – Publish the app on Streamlit Community Cloud.

## Prerequisites

- Python 3.11.9  

- Streamlit Cloud Community account (Free Tier)  

- OpenAI API key (Paid)

## Required Packages

Install the dependencies before running the project:

```bash

pip install -e .