Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/vinayakvthayil/health_chatbot
An AI-powered healthcare support system utilizing a three-model architecture for accurate, safe, and research-backed health assistance.
https://github.com/vinayakvthayil/health_chatbot
ai final-year-project healthcare phase-1 python rag streamlit twilio
Last synced: 14 days ago
JSON representation
An AI-powered healthcare support system utilizing a three-model architecture for accurate, safe, and research-backed health assistance.
- Host: GitHub
- URL: https://github.com/vinayakvthayil/health_chatbot
- Owner: vinayakvthayil
- Created: 2025-01-01T18:10:20.000Z (about 1 month ago)
- Default Branch: main
- Last Pushed: 2025-01-30T07:13:36.000Z (15 days ago)
- Last Synced: 2025-01-30T08:20:50.633Z (15 days ago)
- Topics: ai, final-year-project, healthcare, phase-1, python, rag, streamlit, twilio
- Language: Python
- Homepage:
- Size: 47.9 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Health Chatbot: AI-Powered Personalized Health Assistant
### Final Year Project Phase - 1
An AI-powered healthcare support system utilizing a three-model architecture for accurate, safe, and research-backed health assistance.## Features
- Intelligent health assistance with research-backed responses
- Multi-platform support (Web & WhatsApp)
- Real-time health tips and recommendations
- Secure human handoff capabilities
- Vector database for efficient knowledge management## Technical Architecture
**AI Models**
- Gemini Flash (Query Analysis)
- Temperature: 0.3
- Response time: 1-2s
- Fast query decomposition
- Perplexity Sonar (Research)
- Context window: 128k tokens
- Real-time data retrieval
- Gemini Pro (Response)
- Temperature: 0.7
- Enhanced prompting## Tech Stack
- Frontend: Streamlit
- Backend: Flask with RESTful API
- Database: ChromaDB
- Integration: Twilio for WhatsApp
- AI: Google Gemini and Perplexity Sonar## System Components
**Frontend Features**
- Interactive chat interface
- Health tips display
- Assessment interface
- Feedback system**Backend Features**
- Vector database integration
- Knowledge base management
- Chat history tracking
- Multi-layer safety system## Safety Features
- Content filtering
- Intent detection
- Source credibility checks
- Medical disclaimer injection
- Warning generation