Smart-Home-RAG-Assistant

This project collects data on temperature, humidity, light intensity, and the number of people in an area to form a database. It leverages the Qwen2.5 large language model (LLM) to analyze this data and determine whether to turn lights and fans on or off.

Hardware Preparation

SenseCAP CO2, Temperature and Humidity Sensor	reCamera 2002 64GB	reComputer R1100
Purchase Now	Purchase Now	Purchase Now

Hardware connection

Install node-red

bash <(curl -sL https://raw.githubusercontent.com/node-red/linux-installers/master/deb/update-nodejs-and-nodered)
sudo systemctl restart nodered.service 
sudo systemctl enable nodered.service 

Install project

git clone https://github.com/Seeed-Projects/Smart-Home-RAG-Assistant.git

Prepare environment

cd Smart-Home-RAG-Assistant
python -m venv .env 
source .env/bin/activate
pip install -r requirements

Run RAG and http service

uvicorn http_service:app --host 0.0.0.0 --port 8000 --reload
python rag.py

Import the workflow into Node-RED

Note: Please refer this link to import your workflow to Node-RED

cd nodered-flow
ls

There are two Node-RED flow here, recomputer-work-flow.json is the workflow you deploy on reComputer R1100, and recamer-work-flow.json is the workflow you deploy on recamre.

Result

The dashboard of this project is show as below: