Generative AI Agents Developer Contest by NVIDIA and LangChain

The contest is now closed. Thank You for your participation.

Winners
Honorable Mentions
Winner Selection Criteria
Additional Resources
FAQs

Winners

Winners
Honorable Mentions
Winner Selection Criteria
Additional Resources
FAQs

Join the AI innovators pushing the boundaries of generative AI-powered applications using NVIDIA and LangChain technologies. Enter our contest to develop practical, efficient, and creative text and multimodal agents in an area of your choice and you could win one of several exciting prizes. To get started, check out our step-by-step developer resources and connect with NVIDIA and LangChain technical experts and the wider AI community on Discord to navigate challenges during your development journey.

The contest will run May 15–June 24 in the United States, United Kingdom, Japan, Germany, and more.

See the Contest’s Terms and Conditions

Winners

Brian Caffey

Project Name: Agents of Inference

	Demo Video

	Social

	GitHub

Panna Felsen

Project Name: AI Personal Trainer

	Demo Video

	Social

	GitHub

Malcolm White

Project Name: Mystery Manor

	Demo Video

	Social

	GitHub

Honorable Mentions

Mishran Haque

Project Name: Persona - Unreal Engine

	Demo Video

	Social

	GitHub

Miguel Zabala

Project Name: RGS Tool

	Demo Video

	Social

	GitHub

Olivier Pizzato

Project Name: L'Agent

	Demo Video

	Social

	GitHub

Gabhyun Kim

Project Name: LLM Trading Agent

	Demo Video

	Social

	GitHub

Luis Alberto Carranza CobeÃ±as

Project Name: VRM AI Facial Emotions

	Demo Video

	Social

	GitHub

Nils Durner

Project Name: Aileen 2

	Demo Video

	Social

	GitHub

Suraj Somarajan

Project Name: Test Generator App

	Demo Video

	Social

	GitHub

Aravind Shankara Narayanan

Project Name: Satyuki, the Code Mentor

	Demo Video

	Social

	GitHub

Medin Cole

Project Name: Trainer's Ally

	Demo Video

	Social

	GitHub

Jorge Pineda

Project Name: Narravive

	Demo Video

	Social

	GitHub

What to Build

Create your next GPU-accelerated generative AI agent project in one of the following categories.

Large Language Models (Over 8B Parameters)

Large language models (LLMs)—with over 8 billion parameters) are rapidly evolving, from GPT-based models to Llama, Gemma, and Mixtral. Developers can leverage these large models to build diverse agents for tasks such as question-answering, summarization, and content generation.

Small Language Models (8B Parameters or Less)

As models grow larger, a new wave is driving the development of smaller language models (SLMs)—with 8 billion parameters or less). For this option, developers are encouraged to use these smaller language models to build applications such as local copilots or on-device applications.

How to Get Started

There are several ways to build generative AI apps that are powered by LLMs and SLMs. Below are a few examples, along with resources, to guide you on your creative journey.

LLM-Powered Agents

Build powerful LLM-powered applications with LangChain, a leading framework for creating agents.

You can use popular open-source and NVIDIA foundation models either through the NVIDIA NIM APIs or by using NVIDIA AI Foundation endpoints within the LangChain framework. Once you’ve developed your app, you can add NVIDIA NeMo™ Guardrails to control the output of the LLM according to your use case.

If you’d like to develop advanced agents, you can start with LangGraph, a multi-agent framework that's built on top of LangChain.

Customizing Agents

If you’re interested in customizing an agent for a specific task, one way to do this is to fine-tune the models on your dataset. To do that, you can begin by curating the dataset using NeMo Curator and fine-tuning the model with your dataset using the NeMo framework or HuggingFace transformers.

Once you have your custom LLM, you can use the model within the LangChain framework to develop an agent.

NVIDIA ChatRTX - Your Personalized AI Chatbot

Local Copilots

For any agents that need to run locally due to privacy and security considerations, you can start developing an agent similar to LLM-powered agents.

But instead of using LLMs, you could leverage smaller language models that have 8 billion parameters or less and quantize them through NVIDIA TensorRT™-LLM to reduce the model size so it can fit on your GPU.

NVIDIA, along with the LangChain framework, lets you build agents that can run on local compute resources.

Enter the Contest

Decorative image representing get started

Step 1: Start Now

Connect with the community of LLM developers and NVIDIA and LangChain technical experts on the NVIDIA Developer Discord channel and NVIDIA Developer Forums.

Decorative image representing project building workflow

Step 2: Set up and Build Your Project

Set up your development environment and build your project. Use any one of the following NVIDIA technologies along with the LangChain/LangGraph framework to develop your agent app.

Foundation models through the NVIDIA NIM APIs or endpoints
NeMo Curator
NeMo framework
NeMo Guardrails
NVIDIA TensorRT-LLM

Decorative image representing social media feed

Step 3: Share on Social

Post a 45- to 90-second demo video of your generative AI project on X (Twitter), LinkedIn, or Instagram using the hashtags #NVIDIADevContest and #LangChain. Also, tag one of these NVIDIA social handles:

X (Twitter): @NVIDIAAIDev
LinkedIn: @NVIDIAAI
Instagram: @NVIDIAAI

Decorative image representing form submission on a mobile device

Step 4: Submit Your Entry Form

Once completed, submit all your assets, including links to the source code, demo video, social post, and any other supplementary materials. For an eligible submission, it is mandatory to fill in all the required fields on the submission form.

Submit

Prizes

Participants will have the chance to win GPUs and hundreds of dollars worth of rewards from LangChain to continue their learning journey:

Two winners will each receive an NVIDIA GeForce RTX 4090 GPU.
One special mention will receive an NVIDIA GeForce RTX 4080 SUPER.
The top 10 projects will each receive $200 in LangSmith credits and LangChain merchandise
The top 100 projects will each receive an NVIDIA Deep Learning Institute LLM course.
All valid participants will receive a digital participation certificate with NVIDIA CEO Jensen Huang’s signature.

See the contest Terms & Conditions

Winner Selection Criteria

Qualifying submissions will be judged by:

Real-world application: Evaluates the impact and novelty of the project in addressing real-world challenges and the ease of use for its target audience
Technology integration: Assesses how effectively the developer has used NVIDIA’s LLM stack and LangChain technologies in the project
Quality of submission: Reviews the comprehensiveness and clarity of the project details, instructions, and demo

Additional Resources

Explore Generative AI Examples

Explore several getting-started generative AI examples that use state-of-the-art models such as Mixtral, Llama, and Gemma, along with accelerated frameworks and libraries from NVIDIA and LangChain.

Essential NVIDIA and LangChain Resources

Get started quickly with foundation models from the NVIDIA NIM APIs, control LLM outputs with NeMo Guardrails, create high-quality datasets using NeMo Curator, and optimize inference with TensorRT-LLM

Familiarize yourself with the LangChain and LangGraph frameworks through Python and JavaScript documentation and YouTube tutorials.

Get guidance from NVIDIA & LangChain subject matter experts.

Expert Support and Community Resources

Get guidance from NVIDIA and LangChain technical experts. Join our LLM community on the NVIDIA Developer Discord channel and NVIDIA Developer Forums to ask your questions and accelerate your development process for the contest.

FAQs

Submissions will be judged based on these parameters:

Real-world application: Evaluates the impact and novelty of the project in addressing real-world challenges and the ease of use for its target audience
Technology integration: Assesses how effectively the developer has used NVIDIA’s LLM products and LangChain technologies in the project
Quality of submission: Reviews the comprehensiveness and clarity of the project’s details, instructions, and demo

Get the Latest Developer News and Contest Updates

Section

Section

First Name

Last Name

Business Email Address

Organization / University Name

NVIDIA Privacy Policy

Generative AI Agents Developer Contest by NVIDIA and LangChain

Winners

Brian Caffey

Panna Felsen

Malcolm White

Honorable Mentions

Mishran Haque

Miguel Zabala

Olivier Pizzato

Gabhyun Kim

Luis Alberto Carranza CobeÃ±as

Nils Durner

Suraj Somarajan

Aravind Shankara Narayanan

Medin Cole

Jorge Pineda

What to Build

Large Language Models (Over 8B Parameters)

Small Language Models (8B Parameters or Less)

How to Get Started

LLM-Powered Agents

Customizing Agents

Local Copilots

Enter the Contest

Step 1: Start Now

Step 2: Set up and Build Your Project

Step 3: Share on Social

Step 4: Submit Your Entry Form

Prizes

Winner Selection Criteria

Additional Resources

Explore Generative AI Examples

Essential NVIDIA and LangChain Resources

Expert Support and Community Resources

FAQs

Which countries is this contest open to?

Can I use OpenAI’s API like GPT-4 Turbo and GPT-4o ?

Can I fine-tune an LLM?

What are NVIDIA AI Foundation endpoints?

Is there any way to deploy a self-hosted NVIDIA NIM endpoint for inferencing?

Can I register with my student email address?

The ChatNVIDIA class from LangChain didn't implement bind_tools functions, and I’m getting an error message when using Chat OpenAI with the base URL NVIDIA NIM endpoint. Is there a workaround?

Is there any requirement to be a desktop app, web app, or mobile app? Or can I create whatever I want?

I don’t have the GPU cards with the specs mentioned in the contest. How do I develop my apps while taking part in the contest?

Can I use multimodal LLMs in my application?

How will my submission be judged?

Should the application be using all the tools (NVIDIA and LangChain) listed in the contest requirements?

Can participants from countries like India and China team up with other members who are participating from valid countries?

Should I submit the API keys for any model endpoints that are part of the application?

How can I use Hugging Face Inference as a Service powered by NVIDIA NIM?

What is the license of the submitted code?

Get the Latest Developer News and Contest Updates