🎬 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

• https://www.kaggle.com/datasets/phiitm/marvel-cinematic-universe-dialogue-dataset/code

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

---