🕵️‍♀️ Truth Seeker: Fake News Detector

Truth Seeker is a full-stack Fake News Detection application that utilizes Machine Learning and Retrieval-Augmented Generation (RAG) to evaluate the authenticity of news articles.

🚀 Key Features

• Machine Learning Predictor: Evaluates textual patterns to classify news credibility.
• RAG Architecture (ChromaDB): Retrieves factual context from a vector database to cross-reference and verify news queries.
• Modern User Interface: A responsive React frontend for users to input news text and receive an instant analysis.
• Robust Python API: A scalable backend handling text vectorization, RAG queries, and ML classification.

🛠️ Technology Stack

• Frontend: React, JavaScript, CSS
• Backend: Python, API Architecture handling RAG and Predictions
• Vector Database: ChromaDB
• Machine Learning: Jupyter Notebooks (training_model.ipynb), predictive models

📂 Project Structure

├── backend/             # Python API backend (Routes, RAG Service, Predictor logic)
├── frontend/            # React frontend user interface 
├── models/              # Exported ML model weights (Not checked into source control)
├── notebooks/           # Jupyter notebooks for model training and experiments
├── chroma_db/           # Chroma Vector Storage for RAG (Not checked into source control)
├── data/                # Raw and processed datasets
└── requirements.txt     # Python dependencies

⚙️ How to Run Locally

1. Backend Setup

1. Navigate to the backend directory:

   cd backend

2. Create and activate a Python virtual environment:

   python -m venv venv
   # On Windows use:
   venv\Scripts\activate

3. Install dependencies (located in the root folder):

   pip install -r ../requirements.txt

4. Run the API Server:

   python main.py

2. Frontend Setup

1. Navigate to the frontend directory:

   cd frontend

2. Install dependencies:

   npm install

3. Start the React development server:

   npm start

---

(Note: Several directories including datasets, ML model checkpoints, and database stores are intentionally excluded from GitHub via .gitignore.)