Plug and Play: Construct a G-Help Plug-In Right this moment

Plug and Play: Construct a G-Help Plug-In Right this moment

Undertaking G-Help — accessible by means of the NVIDIA App — is an experimental AI assistant that helps tune, management and optimize NVIDIA GeForce RTX programs.

NVIDIA’s Plug and Play: Undertaking G-Help Plug-In Hackathon — operating just about by means of Wednesday, July 16 — invitations the neighborhood to discover AI and construct customized G-Help plug-ins for an opportunity to win prizes and be featured on NVIDIA social media channels.

G-Help permits customers to regulate their RTX GPU and different system settings utilizing pure language, because of a small language mannequin that runs on gadget. It may be used from the NVIDIA Overlay within the NVIDIA App without having to tab out or swap applications. Customers can broaden its capabilities through plug-ins and even join it to agentic frameworks comparable to Langflow.

Under, discover fashionable G-Help plug-ins, hackathon particulars and tricks to get began.

Plug-In and Win

Be a part of the hackathon by registering and testing the curated technical assets.

G-Help plug-ins could be in-built a number of methods, together with with Python for speedy growth, with C++ for performance-critical apps and with customized system interactions for {hardware} and working system automation.

For those who favor vibe coding, the G-Help Plug-In Builder — a ChatGPT-based app that enables no-code or low-code growth with pure language instructions — makes it straightforward for fans to start out creating plug-ins.

To submit an entry, contributors should present a GitHub repository, together with supply code file (plugin.py), necessities.txt, manifest.json, config.json (if relevant), a plug-in executable file and READme code.

Then, submit a video — between 30 seconds and two minutes — showcasing the plug-in in motion.

Lastly, hackathoners should promote their plug-in utilizing #AIonRTXHackathon on a social media channel: Instagram, TikTok or X. Submit tasks through this kind by Wednesday, July 16.

Judges will assess plug-ins based mostly on three predominant standards: 1) innovation and creativity, 2) technical execution and integration, reviewing technical depth, G-Help integration and scalability, and three) usability and neighborhood impression, aka how straightforward it’s to make use of the plug-in.

Winners shall be chosen on Wednesday, Aug. 20. First place will obtain a GeForce RTX 5090 laptop computer, second place a GeForce RTX 5080 GPU and third a GeForce RTX 5070 GPU. These prime three may also be featured on NVIDIA’s social media channels, get the chance to satisfy the NVIDIA G-Help staff and earn an NVIDIA Deep Studying Institute self-paced course credit score.

Undertaking G-Help requires a GeForce RTX 50, 40 or 30 Sequence Desktop GPU with at the least 12GB of VRAM, Home windows 11 or 10 working system, a suitable CPU (Intel Pentium G Sequence, Core i3, i5, i7 or greater; AMD FX, Ryzen 3, 5, 7, 9, Threadripper or greater), particular disk house necessities and a current GeForce Sport Prepared Driver or NVIDIA Studio Driver.

Plug-In(spiration)

Discover open-source plug-in samples accessible on GitHub, which showcase the various methods on-device AI can improve PC and gaming workflows.

Widespread plug-ins embrace:

  • Google Gemini: Permits search-based queries utilizing Google Search integration and massive language mannequin-based queries utilizing Gemini capabilities in actual time without having to modify applications from the comfort of the NVIDIA App Overlay.
  • Discord: Permits customers to simply share sport highlights or messages on to Discord servers with out disrupting gameplay.
  • IFTTT: Lets customers create automations throughout a whole bunch of suitable endpoints to set off IoT routines — comparable to adjusting room lights and sensible shades, or pushing the newest gaming information to a cellular gadget.
  • Spotify: Lets customers management Spotify utilizing easy voice instructions or the G-Help interface to play favourite tracks and handle playlists.
  • Twitch: Checks if any Twitch streamer is at the moment dwell and might entry detailed stream data comparable to titles, video games, view counts and extra.

Get G-Help(ance) 

Be a part of the NVIDIA Developer Discord channel to collaborate, share creations and achieve assist from fellow AI fans and NVIDIA employees.

Save the date for NVIDIA’s The way to Construct a G-Help Plug-In webinar on Wednesday, July 9, from 10-11 a.m. PT, to study extra about Undertaking G-Help capabilities, uncover the basics of constructing, testing and deploying Undertaking G-Help plug-ins, and take part in a dwell Q&A session.

Discover NVIDIA’s GitHub repository, which offers every thing wanted to get began creating with G-Help, together with pattern plug-ins, step-by-step directions and documentation for constructing customized functionalities.

Be taught extra concerning the ChatGPT Plug-In Builder to rework concepts into practical G-Help plug-ins with minimal coding. The device makes use of OpenAI’s customized GPT builder to generate plug-in code and streamline the event course of.

NVIDIA’s technical weblog walks by means of the structure of a G-Help plug-in, utilizing a Twitch integration for instance. Uncover how plug-ins work, how they convey with G-Help and find out how to construct them from scratch.

Every week, the RTX AI Storage weblog collection options community-driven AI improvements and content material for these trying to study extra about NVIDIA NIM microservices and AI Blueprints, in addition to constructing AI brokers, inventive workflows, digital people, productiveness apps and extra on AI PCs and workstations. 

Plug in to NVIDIA AI PC on Fb, Instagram, TikTok and X — and keep knowledgeable by subscribing to the RTX AI PC e-newsletter.

Comply with NVIDIA Workstation on LinkedIn and X

See discover relating to software program product data.