Skip to content

ashishyadav18/Perspective-AI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Perspective AI

Perspective AI is a conversational AI assistant designed to encourage critical thinking, perspective analysis, and balanced discussion.

The project combines a React frontend with a Flask backend and uses a locally hosted Ollama model for AI responses.

Version React Flask Ollama


Live Demo

🌐 https://perspective-ai-lac.vercel.app

Highlights

  • 🤖 AI-powered assistant
  • 🧠 Perspective analysis
  • ⚖️ Bias awareness
  • 🔒 Privacy-friendly local AI
  • ⚡ React + Flask architecture
  • 🦙 Powered by Ollama & Llama 3

Features

  • AI-powered conversation
  • Perspective-focused responses
  • Simple bias detection tool
  • Basic misinformation keyword alerts
  • Modern React user interface
  • Local AI processing through Ollama
  • Privacy-friendly architecture

Tech Stack

Frontend

  • React
  • JavaScript
  • CSS

Backend

  • Flask
  • Flask-CORS
  • Python

AI Model

  • Ollama
  • Llama 3

Architecture

User ↓ React Frontend ↓ Flask API ↓ Ollama ↓ Llama 3

Project Structure

perspective-ai/
│
├── backend/
│   ├── app.py
│   ├── requirements.txt
│   └── .env
│
├── frontend/
│   ├── public/
│   ├── src/
│   ├── package.json
│   └── package-lock.json
│
└── README.md

Screenshots

Home Screen

Home Screen

Home Screen

AI Conversation

Perspective Analysis

Installation

Clone Repository

git clone https://github.com/ashishyadav18/Perspective-AI.git
cd perspective-ai

Backend Setup

cd backend

pip install -r requirements.txt

python app.py

Backend runs at:

http://localhost:5000

Frontend Setup

cd frontend

npm install

npm start

Frontend runs at:

http://localhost:3000

Ollama Setup

Install Ollama:

https://ollama.com

Pull the model:

ollama pull llama3

Verify:

ollama list

Current Limitations

  • Bias analysis uses a simple keyword-based approach.
  • Misinformation detection is basic and rule-based.
  • AI responses require Ollama running locally.
  • Backend is not deployed publicly.

Future Improvements

  • Advanced bias detection
  • Source credibility analysis
  • Public cloud deployment
  • Better fact-checking system
  • Multi-model AI support
  • Conversation history
  • Export chat sessions

Author

Ashish Yadav

Computer Science Student

Built as a learning project exploring AI applications, critical thinking tools, and full-stack development.

About

AI-powered conversation, perspective analysis, and critical thinking assistant built with React, Flask, and Ollama.

Topics

Resources

Stars

Watchers

Forks

Contributors