Ticket Contents

Description

The idea is to enhance Music Blocks with an AI-powered debugger.
This feature aims to bridge the gap between users'
creative ideas and their ability to troubleshoot or fully utilize the
platform's features. This AI-powered debugger will provide real-time assistance by answering questions, explaining features, and offering creative suggestions. It will help users quickly identify and resolve issues in their projects or block connections
This enhancement would make the platform more accessible
for beginners while streamlining the debugging and experimentation
process for advanced users.

Goals & Mid-Point Milestone

Goals

• Train an open-source LLM to understand Music Blocks projects and develop the ability to debug them effectively.
• Implement robust Retrieval-Augmented Generation (RAG) for the LLM model to enhance contextual understanding.
• Integrate the AI chatbot and debugger into the Music Blocks platform.
• Develop FastAPI endpoints to deploy the model efficiently.
• Work on techniques to minimize hallucinations and improve accuracy.
• Document progress, outcomes, and technical guides for future contributors

Setup/Installation

No response

Expected Outcome

Upon successful completion, students should be able to interact with a server-side chatbot from within Music Blocks to help them problem solve and troubleshoot when building their projects.

Acceptance Criteria

No response

Implementation Details

• An open-source LLM
• Javascript

Mockups/Wireframes

No response

Product Name

Music Blocks

Organisation Name

Sugar Labs

Domain

⁠Education

Tech Skills Needed

Artificial Intelligence

Mentor(s)

Coding Mentors

Walter Bender Sumit Srivastava

Assisting Mentors

Devin Ulibarri

Category

Machine Learning