Skip to content

The orchestrator repository for the Helm project, an AI-based research assistant for innovation managers and academics

License

Notifications You must be signed in to change notification settings

AlbertoMarinelli/Helm-AI-SA22

 
 

Repository files navigation

Helm AI

Project for the Smart Applications course @ University of Pisa

Unipi logo

Authors: Alberto Marinelli, Luca Moroni, Davide Amadei, Diego Arcelli, Pietro Francaviglia, Giacomo Cignoni, Gabriele Marino, Irene Pisani, Alessandro Capurso, Roberto Esposito, Sergio Latrofa, Veronica Pistolesi

💡 Goal

Helm is a customizable AI-based research assistant, for innovation managers and academics who need to retrieve and analyze the most significant sources for any research field.

Helm will propose to users the best documents and insights according to their queries through a simple interactive dashboard.

Unlike traditional academic search engines, Helm intuitively provides topic-centered visualizations, filters and rankings.

🔧 Running the Project

Clone the entire orchestrator repository with the command

git clone --recurse-submodules https://github.com/Helm-AI-SA22/orchestrator

move to the orchestrator folder

cd orchestrator

check that you are on the master branch and have pulled the last commits

git checkout master

git pull

Update the three sub repos with the instruction:

git submodule update --recursive --remote

Containers of the three sub-modules can be executed by launching them from the orchestrator folder (execution will take several minutes):

make build

To test the correct functioning of the containers, query the following addresses:

localhost:5000 localhost:5001 localhost:3000

Command 'make' not found

If you do not have the make command (i.e. you are on a Windows environment) install make via chocolately, opening the terminal with administrator permissions:

choco install make

If you do not have chocolately, install from https://docs.chocolatey.org/en-us/choco/setup

Frontend in windows environment

Running the frontend from the Docker container can take several minutes in a Windows environment, slowing down the development process too much. If you wish to develop on FE via a Windows environment, it is recommended to stop the frontend container (i.e. via Docker Desktop) and run the module locally:

cd frontend

npm install

npm start

To activate the BE and AI modules, use the instruction directly from the orchestrator:

make build-dev

👨‍💻 System Architecture

System Architecture

🖥️ GUI

GUI Helm AI

About

The orchestrator repository for the Helm project, an AI-based research assistant for innovation managers and academics

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Makefile 100.0%