📰 Autonomous News Aggregation, Summarization, and Publishing Agent

🚀 Overview

This project is an AI-powered autonomous news agent that automatically fetches, summarizes, and publishes news articles on various topics. It ensures relevance and reliability by fetching multiple sources, verifying content, and generating fact-checked summaries.

Core Features

✅ Fetches news from multiple sources based on a location & topic.
✅ Filters duplicates & redundant articles.
✅ Summarizes news using NLP models.
✅ Classifies articles into relevant categories.
✅ Optimizes content for SEO.
✅ Publishes news automatically on a web app.
✅ Generates AI-powered images to enhance news content.

---

🏗 Tech Stack

• Frontend: React.js
• Backend: Flask (Python)
• AI Models: Gemini Flash 1.5
• Web Scraping: SerpAPI, BeautifulSoup
• LLM Summarization & Merging: Gemini API
• Similarity Search & Classification: BERT embeddings

---

🛠 Installation and Setup

1️⃣ Clone the Repository

git clone https://github.com/divyansh44/flipr25_Indigo.git

---

🖥 Backend Setup (Flask API)

2️⃣ Creating a Virtual Environment

Using Conda :

conda create --name news_env python=3.8 -y
conda activate news_env

Using venv(Recommended):

python -m venv news_env
source news_env/bin/activate  # macOS/Linux
news_env\Scripts\activate     # Windows

3️⃣ Installing Dependencies

cd backend
pip install -r requirements.txt

4️⃣ Configuring API Keys

Update the configs.yaml file with:

location: "Delhi"
topic: "Technology News"

Set up API keys inside config.py:

gemini_api_key = "your-gemini-api-key"
serp_api_key = "your-serp-api-key"
imgBB_api_key = "your-imgBB-api-key"

5️⃣ Running the Flask Backend

cd backend
python3 server.py

The backend will start at http://127.0.0.1:5000/.

---

🌐 Frontend Setup (React)

6️⃣ Installing Dependencies

cd frontend
npm install

7️⃣ Running the React Frontend

npm run dev

The frontend will be available at http://localhost:5173/.

---

---

🎯 Future Improvements

✅ Advanced NLP: Improve summarization with better LLMs
✅ User Metrics: Track views, shares, and engagement
✅ Multilingual Support: Translate news into multiple languages

📜 License

This project is open-source and available under the MIT License.