Skip to content

ReadMe.md

Latest commit

 

History

History
38 lines (23 loc) · 1.56 KB

ReadMe.md

File metadata and controls

38 lines (23 loc) · 1.56 KB

🎬 DialogGPT — Conversational Dialogue Generator AI

👉 https://codingblood.github.io/DialogGPT/

MovieGPT is an end-to-end conversational AI project that generates movie-style dialogue responses using custom-trained language models. The system integrates a backend API, a user-friendly frontend, experimentation tracking, and deployment workflows — aimed at providing a production-grade conversational experience using open datasets and modern development practices.

This repository is built as a zero-cost learning project to understand how real-world AI systems are designed, trained, deployed, and monitored from end to end.

📦 Project Summary

MovieGPT leverages the Movie Dialog Corpus dataset to train language models that can generate human-like dialogue. Initially built with simpler models (e.g., LSTM), this project is designed to evolve into a more powerful conversational model akin to GPT-style architectures.

This repo includes:

  • Backend API using FastAPI
  • Interactive chat UI built with React
  • Language model training scripts
  • Experiment tracking and version control
  • Containerization with Docker
  • CI/CD workflows
  • Deployment readiness for cloud platforms

🎯 Dataset

This project uses the MCU Dialog Corpus dataset from Kaggle:

👉 #%% md

Fetching DataSet from Kaggle

The dataset contains movie conversations and pairs of dialogue exchanges, which are preprocessed and used for training conversational models.