Skip to content

Echo-Lian/CareSoul

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CareSoul

This application demonstrates a production-grade mental health AI application.

Structure

project-root/
├── data/               # Raw PDFs/TXTs clinical guides
├── src/
│   ├── processor.py    # Logic for chunking and metadata
│   ├── database.py     # Supabase/pgvector connection
│   └── main.py         # The entry script to run the pipeline
├── .env                # API Keys
└── requirements.txt    # Python dependencies

Features

Clinical Grounding

The application avoids scraping blog posts, instead, it uses structured, evidence-based frameworks to demonstrate an understanding of the industry's high standards for accuracy, such as:

  • CBT Manuals
  • WHO Guidelines
  • Crisis Protocols

Chunking

Split documents into manageable chunks with metadata.

About

An AI-powered wellbeing assistant focused on natural dialogue which implements an agentic RAG workflow to retrieve clinically-grounded relationship tips while utilizing a 'Safety-First' pre-processing layer to intercept high-risk queries, ensuring all interactions remain within health-tech compliance boundaries.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages