/Conversation-AI-System-using-LLMs-on-E-commerce-Data

Explore the Conversation AI System using LLMs on E-commerce Data repository! This GitHub project showcases a solution for building a Conversational AI system tailored for E-commerce. Dive into the code, discover innovative approaches, and enhance your understanding of creating effective AI-driven conversations in the E-commerce domain.

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

Recommender-System-and-ConvAI-using-LLMs-on-e-commerce-Data

Project Summary:

We'll use amazon's data for our project. You can either download data directly from Kaggle, or you can donwload using Kaggle's API.

ConvAI using LLMs

The idea of the project is to implement a Conversation AI for different tasks ( explained below).

Conversational AI using LLMs:

  • Sentiment Analysis: We'll do sentiment analysis using BERT Model.
  • Generate Questions: We'll generate 4 questions per record that users could potentially ask to Virtual Assistant.
  • Answers users' questions: We'll use OpenAI's davinci engine to answer each question that users could potentially ask.
  • Summarize Product Description: We'll use t5-small model from Google to summarize product using product description to users.

Instructions for Installation

Dependencies: You'll need to install below dependencies to run this project.

  • numpy: 1.18.1
  • pandas: 1.0.1
  • matplotlib: 3.5.3
  • seaborn: 0.10.0
  • re: 2.2.1
  • sklearn: 0.22.1
  • xlsxwriter: 1.2.7
  • scipy: 1.4.1
  • transformers: 4.30.2
  • openai: 0.28.1
  • torch: 1.13.1+cpu

License

This repository and its contents are open-sourced under the MIT License. Feel free to use, modify, and distribute these projects in accordance with the terms specified in the license.

Issues:

If you encounter any issues or have suggestions for improvement, please open an issue in the Issues section of this repository.

Contributing

If you have a Data Science mini-project that you'd like to share, please follow the guidelines in CONTRIBUTING.md.

Code of Conduct

Please adhere to our Code of Conduct in all your interactions with the project.

Contact:

The code has been tested on Windows system. It should work well on other distributions but has not yet been tested. In case of any issue with installation or otherwise, please contact me on Linkedin

Happy coding!!

About Me:

I’m a seasoned Data Scientist and founder of TowardsMachineLearning.Org. I've worked on various Machine Learning, NLP, and cutting-edge deep learning frameworks to solve numerous business problems.