What is Zenify

Zenify is an AI-powered mental health chatbot that utilizes Retrieval Augmented Generation (RAG) and Machine Classification Pipeline (MCP) to provide personalized support through journaling, mood tracking, and crisis alerts. It operates locally with a calming, animated user interface.

Use cases

Use cases for Zenify include providing immediate support for individuals in crisis, helping users track and reflect on their emotional well-being, offering resources and guidance for mental health challenges, and serving as a tool for mental health professionals to monitor client progress.

How to use

Users can interact with Zenify by engaging in conversations through the chatbot interface, utilizing journaling features to record thoughts, and tracking their mood over time. The system also alerts users to potential crises based on their inputs.

Key features

Key features of Zenify include automatic suicide risk detection using machine learning, real-time keyword screening for harmful content, integration of curated resources via RAG, generative AI support for empathetic conversations, and an admin dashboard for message review and escalation.

Where to use

Zenify can be utilized in various fields including mental health support services, educational institutions, corporate wellness programs, and community health initiatives, where there is a need for mental health monitoring and support.

🧠 AI-Powered Mental Health Support System

A comprehensive, safety-first, and scalable platform leveraging machine learning and generative AI to detect, respond to, and manage mental health risks—while also providing journaling and mood-tracking capabilities.

Table of Contents

1. Overview
2. Features
3. System Architecture
4. Tech Stack
5. Key Modules
6. Installation
7. Usage
8. Data Privacy & Compliance
9. Contributing / Journal
10. License
11. Disclaimer
12. Acknowledgments
13. Contact

Overview

This system is designed to identify and respond to potential suicide risks in real-time using advanced machine learning classification (TF-IDF and Logistic Regression) and Retrieval Augmented Generation (RAG), integrated with generative models (e.g., OpenAI GPT, Gemini) to provide empathetic, context-aware responses. In addition to AI-based direct support, it offers a journal and mood tracking feature set for users to record personal reflections and monitor their emotional well-being over time.

Features

• Automatic Suicide Risk Detection
  Uses a Machine Learning Classification Pipeline (MCP) with TF-IDF and logistic regression to flag concerning user-generated text.

• Keyword Screening
  Real-time filter for suicide/self-harm keywords to initially flag content for review.

• RAG (Retrieval Augmented Generation)
  Integration of curated resources and knowledge bases to enhance AI responses with relevant context.

• Generative AI Support
  Empathetic and context-rich conversations powered by OpenAI GPT and Gemini APIs.

• Admin Dashboard
  A React-based interface for administrators to:

  • Review flagged messages
  • Escalate urgent cases
  • Annotate conversation histories
  • View mood/journal summaries (according to user consent)

• Mood & Journal Tracking
  Enables users to log daily/weekly moods and maintain private journals with optional sentiment analysis and personal progress charts.

• Compliance & Audit Logging
  Facilitates compliance with data privacy regulations (GDPR, HIPAA-like requirements for health data).

System Architecture

1. FastAPI Backend
   • Hosts the classification model, manages user data, handles API routes.
2. Gemini / OpenAI Integration
   • Powers generative responses using relevant context.
3. React Admin Dashboard
   • Allows moderators or mental health professionals to review and manage flagged content.

Tech Stack

• Backend: Python, FastAPI, Scikit-learn, SQLite/PostgreSQL
• Frontend: React, Material-UI
• AI APIs: Gemini, OpenAI GPT
• Others: Docker (optional), JWT-based Auth, RESTful Services

Key Modules

1. MCP Model

   • Preprocessing: Text cleaning & tokenization
   • Feature Extraction: TF-IDF
   • Classifier: Logistic Regression
   • Keyword Matching for initial detection

2. Mood & Journal Tracking

   • Users can log their mood on a daily/weekly schedule (numeric scale, emoji-based, etc.).
   • A journal for personal reflections—can optionally run sentiment analysis.
   • Trend charts to visualize emotional patterns.

3. RAG Pipeline

   • Combines AI knowledge retrieval with generative models for context-aware responses.
   • Ideal for referencing relevant mental health resources/articles.

4. Generative Response Integration

   • Uses OpenAI GPT or Gemini to generate empathetic, context-tuned messages.
   • Automatic escalation triggers for high-risk user statements.

5. Admin Dashboard

   • Secure login for mental health professionals or moderators.
   • Flagged messages review, risk assessment, and escalation.
   • Oversees mood/journal entries (with the user’s permission).
   • Maintains audit logs for compliance.

Installation

1. Clone the Repository

   git clone https://github.com/your-org/ai-mental-health-support.git
   cd ai-mental-health-support
   
   

Screenshots