Echo - AI-Powered Story Generation

Overview

What if we chronologically arrange textual narratives and train a model that can best predict the direction of its semantic narrative? Aka - can we make a model to predict future events?

Video & Prototype

Watch the demo video

Technical Architecture

• Backend: FastAPI, PostgreSQL, SQLAlchemy
• AI Integration: Cohere multilingual-22-12, DeepSeek R1
• Vector Database: Pinecone

Setup and Installation

Prerequisites: Python 3.10, Poetry, PostgresSQL

Environment Setup

1. Navigate to the backend directory:

cd backend

2. Create a virtual environment (optional but recommended):

python -m venv .venv
source .venv/bin/activate # On Windows use: .venv\Scripts\activate

3. Install required Python packages:

poetry install

Database set-up

1. Have postgres installed on your machine
2. Initialize database

python app/databse.py

Start the Backend Server

1. From the backend directory:

uvicorn app.main:app --reload