https://github.com/tushcmd/ai-customer-support
An AI-powered customer support chatbot using Next.js and the OpenAI API.
https://github.com/tushcmd/ai-customer-support
Last synced: 2 months ago
JSON representation
An AI-powered customer support chatbot using Next.js and the OpenAI API.
- Host: GitHub
- URL: https://github.com/tushcmd/ai-customer-support
- Owner: tushcmd
- Created: 2024-08-05T11:04:54.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2024-08-12T10:06:09.000Z (10 months ago)
- Last Synced: 2025-01-31T19:14:04.095Z (4 months ago)
- Language: TypeScript
- Homepage: https://ai-customer-support-rho.vercel.app
- Size: 416 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# AI Customer Chat Bot
## Project Overview
This is an AI-powered customer support chatbot using Next.js and the OpenAI API.
## Technologies
- Next.js - React Framework
- Shadcn UI - Components
- Next-auth - Authentication
- Prisma - ORM
- PostgreSQL - Database
- Neon - Database Hosting
- OpenAI - LLM(genAI)
- TailwindCSS - Styling
## Features
- Chatbot interface
- Respond to the user intelligently using any Gen-AI model
- Authentication for personalised chat experience
- Feedback implementation to rate chatbot's responses
## Features to Add
- AWS Bedrock responses
- Multi-language support for a diverse culture base
- Implement RAG so the chatbot responds based on a given knowledge base
- Create an LLM orchestration pattern with a router and task specific models
## Getting Started
1.Clone the repository:
```bash
git clone https://github.com/tushcmd/ai-customer-support.git
```
2.Install dependencies:
```bash
cd ai-customer-support
npm install
```
3.Set up environment variables:
```bash
cp .env.example .env
```
Edit the `.env` file with all the necessary environment variables.
4.Run prisma commands to setup
```bash
npx prisma generate
# then
npx prisma migrate dev
# then
npx db push
```
5.Run the development server:
```bash
npm run dev
```
Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
## Contributing
Contributions are welcome! Please feel free to open issues or submit pull requests.
## License
MIT License