Project - Hotline Service Tool
rekindle is an online mental health hotline service accessible to both users and hotline responders. users are encouraged to talk to trained personnel, first describing their situation to an input system; instantaneously; OpenAI natural language processing models (initially co:here) extract needed information from the user circumstance and provides a summary and a list of potential solutions. The summary of the alleged case and list of solutions are delivered to an open hotline worker/volunteer, who is informed with crucial facts and resources such as emergency phone numbers or counselling options for the user.
Try it out: https://rekindle.vercel.app/
React | ChakraUI | Next.js | Cohere | Firebase | OpenAI
- ✅Create form for caller input
- ✅Display calls for admin view
- ✅Integrate Cohere AI text summarization API
- ❌Dark mode
- ❌Speech-to-text
- ❌Twilio Notifications
- ❌Responsive
- Used Figma to prototype the UI/UX
- Prototype Link
- Used Chakra-UI as a frontend React component Library
- Additionally customized styling using inline CSS
- React web framework that fast-tracks the creation of web apps
- Fed example training data to demonstrate task to model
- Set up collections of documents on Cloud Firestore via Firebase JavaScript SDK
- Deployed frontend on Vercel
- Better performance and faster compared to Heroku
- No need to awaken Dyno (from Heroku) resulting in crashed applications, slower bootup, and slower user experience.
- Integrate speech-to-text capabilities for callers
- Develop a notification system that will email/SMS users about their queue position update
- Security features
- Protected/Authenticated Endpoints
- Encryption of Environmental Variables
- Customer support section in the form of a chat bot for immediate interaction
- Initiated presets in co:here with user text summarization and artificial intelligence implementation for responses
- Contributed to UI/UX development with React and Figma
- Took leadership with UI/UX development and wireframing
- Developed HTML / CSS React elements
- Led the development of the caller queue system with React and Next.js
- Setup/developed backend routes for handling logic for caller and operator views
- Implemented database to store user summaries and solutions using Firebase Cloud Firestore
- Helped set up Firebase Cloud Firestore
- Transferred the frontend repository to utilize Next.js