/undoc

Frontend implementation of the Undoc medical consultation chatbot, built with Next.js.

Primary LanguageTypeScript

Undoc: Health Care Chatbot

banner

webpage implementation of AI Undoc Chatbot.

For more details on RAG and RAFT methods, please visit main repo: health-care-advisor.

DEMO PAGE

demo

How To Start

Create Env file

cp .env.local.example .env.local

Copy the example file and update it according to your environment.

Run Server

To start the development server, run:

npm install

# and

npm run dev
# or
yarn dev
# or
pnpm dev

Once the server is running, open http://localhost:3000 in your browser to view the application.

This project is built using Next.js and was bootstrapped with create-next-app.

System Structure

structure

Citation

  • 초거대 AI 헬스케어 질의응답 데이터: AI 허브, 초거대 AI 헬스케어 질의응답 데이터
  • Gemma 2 Model: "Gemma 2: Improving Open Language Models at a Practical Size", 2023.
  • RAFT Methodology: "Adapting Language Model to Domain Specific RAG", arXiv preprint arXiv:2403.10131, 2023.
  • RAGAS Evaluation: "RAGAS: Automated Evaluation of Retrieval Augmented Generation", 2023.