KimathiNewton/mental_health_assistant ? reverse-engineered prompt
Reverse engineered prompt
Build me a mental health assistant web app that feels friendly and supportive, where a user can ask questions about things like stress, grief, trauma, depression, or relationship problems and get a thoughtful answer based on a curated knowledge base instead of just a generic chatbot response.
I want it to use a retrieval and generation flow so it searches the dataset first, then writes a clear answer from that context. Please include a simple Streamlit style interface, a way to save questions, answers, and user feedback in PostgreSQL, and a basic Grafana dashboard so I can see usage and response trends.
It should run cleanly with Docker and Docker Compose, and I want the setup to be easy to start from a fresh clone. If you need to, look up current docs online for any library or model details. Also make sure the app feels safe and helpful, with a clear tone and a gentle disclaimer that it is not a replacement for professional care.
Are you gonna build this?
make sure you review the code using coderabbit