Urgent.News

What's breaking now, across thousands of outlets.

AI

SANKALP: I Built an AI That Turns School Concepts into Interactive 3D Experiences

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built I built SANKALP for my younger brother, who is currently around Class 6 . While helping him study, I noticed that he could read a chapter, look at a textbook diagram, and still struggle to understand the actual concept. Take something as simple as a mitochondrion . A textbook gives you a 2D diagram with…

I built an AI-powered 3D visualization system called SANKALP for my younger brother, who is in Class 6. Helping him study, I realized that students could read textbook diagrams but struggled to understand the actual 3D concept. For example, a textbook shows a 2D diagram of a mitochondrion with labels like outer membrane, inner membrane, cristae, and matrix, but visualizing how these structures are arranged in three dimensions is much harder.

The same issue occurs with other complex concepts like the human heart, engines, and more. To address this, I created SANKALP, an AI-powered system that turns school concepts into interactive 3D experiences for students from Class 1 to Class 12. The goal is to provide a better understanding by letting students see, rotate, and explore the 3D models.

The system uses a hybrid retrieval and generation architecture, first trying to retrieve relevant resources and existing 3D assets before generating a new model if needed. It processes natural-language queries to identify main entities, category information, and descriptive visual properties. SANKALP searches across multiple sources, including local cached assets, curated model sources, Sketchfab, public CDNs, and Three.js public repositories.

Semantic validation compares candidate metadata with the original query, calculating a normalized confidence score to ensure relevance. If a suitable asset isn't found, SANKALP falls back to Hugging Face Shap-E for 3D generation. Once an appropriate asset is selected or generated, it is rendered through an interactive browser-based 3D viewer built with Three.js, React Three Fiber, and Drei.

Students can rotate, inspect, and explore the model instead of relying on a static textbook image. Open innovation played a significant role in building SANKALP, combining AI, information retrieval, and 3D graphics rendering into a reliable pipeline. Using open technologies allowed for experimentation and improvement without being tied to a single proprietary platform.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Running LLMs locally on Linux: what actually works on a Raspberry Pi

Running LLMs locally on Linux: what actually works on a Raspberry Pi A 5B-parameter model can run on a Raspberry Pi 5 every day. It is not fast.

  • Raspberry Pi 5 has 8GB RAM shared with system
  • 4-bit quantized 5B model uses 3.5-4GB RAM, limiting context to 2-3k tokens
  • Ollama and Llama.cpp effective tools for Raspberry Pi LLM inference

Buddy: A Private AI Companion Built for a Friend with Local Gemma

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend. What I Built Meet Buddy — a personal AI companion I built for a friend who wanted a more natural and private way to…

  • Buddy is an AI companion for private, natural interactions
  • Uses local Gemma model via Ollama, no cloud data transmission
  • Features voice interaction with ElevenLabs for natural responses

I Built an Offline AI Interview Coach for My Friend's Job Hunt

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend I Built an Offline AI Interview Coach for My Friend's Job Hunt Job interviews are stressful enough without having to…

  • Created offline AI interview coach for friend's job hunt
  • Uses open-weight Gemma model for local AI processing
  • Focuses on facilitating practice, not providing answers

AI: A Godsend for those with dyslexia in education and careers

By Murray Hunter ACCORDING to the Ministry of Education’s Special Education database, around 314,000 primary school students—or 17 per cent—show some form of dyslexia. Many more go undiagnosed.

  • Dyslexia affects 17% of Malaysian primary school students, with many undetected cases.
  • AI offers compensatory tools like text-to-speech and speech-to-text for dyslexic learners.

More from Sunday 4 October →