Tool Face-Off: OpenAI Assistants API VS Llama-Index/MongoDB. An Eval-Driven Battle

Unveil the ultimate AI Tool in the clash of titans, and win main & special prize for Tool Set usage

👩‍💻 Unleash your creativity in the preferred tool set from Assistants API or Llama-Index/MongoDB for building your app!
🤝 Work in teams of 1 to 6 members, fostering community connections!
💸 $10,000 USD cash prize pool, with special prizes for the best use of Tool Sets!
🚀 7 days of online development with workshop sessions from experts in LLM!
🤝 Connect with developers and startup enthusiasts for future opportunities.
💡 Develop impactful apps for meaningful and positive change in the world with strategic approach!

Get Started With TruLens!

To dive deeper with the Hackathon technology, check out guides on the evaluation and tracking of LLM experiments with TruLens.

Build better AI with TruLens - an open source platform for testing and analyzing large language models. This video guide provides an overview of key TruLens features like comprehensive testing, explainability analysis, and robust metrics. See how TruLens helps minimize risks and ensures greater accuracy in your LLM experiments.

Get Started With TruLens!

Twelve Labs is excited to host a virtual hackathon to explore innovative applications of video AI in sports. Unleash your creativity and technical skills to build cutting-edge solutions that enhance the world of sports using Twelve Labs' powerful video understanding capabilities.

Twelve Labs is leading the charge in the evolution of AI, focusing on crafting technologies that mirror the complexity of human perception. With an understanding that video content closely aligns with human sensory experiences, the company is committed to redefining the landscape of video comprehension through the development of innovative multimodal models.

Build an application that leverages Twelve Labs' video AI to provide novel insights and experiences in sports. Potential areas to explore include: performance Assessment, sports match analysis, sport events, fitness and athletics. The key is to utilize Twelve Labs' video search, classification, and text generation capabilities in an innovative way to enhance some aspect of sports - whether it's for athletes, coaches, broadcasters, or fans.

What is exciting about TruLens?

RAG (retrieval augmented generation) is an AI methodology that enables large language models (LLMs) to utilize up-to-date, reliable information from external sources, avoiding hallucinations. It enhances LLMs' responses, ensuring accuracy, transparency, and trust. With RAG, developers can create smarter, more reliable GenAI applications in various fields, while reducing the risk of errors and data leaks.

Evaluation: TruLens empowers you to assess the quality of your LLM-based applications by evaluating inputs, outputs, and internal workings. It offers built-in feedback mechanisms, including groundedness, relevance, and toxicity, while being adaptable to custom evaluation needs.

Tracking: TruLens provides essential instrumentation for a range of LLM applications, from question answering to retrieval-augmented generation and agent-based solutions. This instrumentation allows you to monitor diverse usage metrics and metadata, providing valuable insights into your model's performance.

TruLens Resources

To kickstart your journey with TruLens, explore the following resources:

Quick Start Guide - A step-by-step guide to quickly set up and start using TruLens-Eval.
TruLens Docs - Visit the docs for comprehensive information on using TruLens
GitHub Repository - Access the TruLens codebase and contribute to its development.

Core Concepts

Learn about the core concepts behind TruLens:

What is Rag?

Hackathon Challenge

In this hackathon, you will build and iterate on an LLM-based application using AI observability to validate the performance of your app.

You can choose between two sets of tools for building your app:

• Tool set 1: The OpenAI Assistants API

• Tool set 2: Llama-Index, MongoDB and GPT-4.

With either choice, you will use TruLens to validate and improve the performance of your application. By bringing together TruEra, OpenAI, Llama-Index, and MongoDB you have the bleeding edge tools at your disposal for building AI applications.

Your challenge is to build a high performing application leveraging either set of tools and validate its performance on key tasks using TruLens. This requires creating a TruLens evaluation suite on the key axis of your app’s performance. If the evaluation identifies failure modes on the app’s critical path, use TruLens to debug and improve the

In this hackathon, you will build and iterate on an LLM-based application using AI observability to validate the performance of your app.

Prizes

Special prizes from Twelve Labs

🥇 1st Place: 💰: 50 hours of Twelve Labs video credits
🥈 2nd Place: 💰: 40 hours Twelve Labs video credits
🥉 3rd Place: 💰: 30 hours Twelve Labs video credits

From lablab.ai Hackathons to Your Startup

For lablab.ai Community members excelling in our Hackathons, this is your gateway to building the foundations of your very own startup. Top performers may seize the opportunity to join prestigious startup accelerator programs like GAIA and Slingshot.

Slingshot refines startup concepts and MVPs. GAIA is an intensive 10-week accelerator, located in Saudi Arabia.

Remember, admission to these programs depends on availability and specific criteria. Don't miss your chance to bring your innovative project to life!

Judging Criteria

Application of Technology

How effectively the chosen model(s) are integrated into the solution.

Presentation

The clarity and effectiveness of the project presentation.

Business Value

The potential impact and practical value of the solution.

Originality

Uniqueness and creativity in addressing the challenge.

The community can judge!

The community judge will review hackathon projects and vote for the best use case, carefully following the rules. For the micro hackathons, the community feedback decides the winner! 🏆

Apply for community judge

Hackathon Details

Join lablab.ai for a 7 days hackathon and innovate using the latest models in the market. Discover all the relevant details below.

🗓️ Where and when

The start date of the hackathon is mentioned according to the date specified on the hackathon page, cover and schedule. The hackathon will take place on the lablab.ai platform and lablab.ai Discord server.

🦸🏼‍♂️ Who can join?

Everyone is welcome to participate, regardless of previous AI or coding experience! We encourage anyone with a passion for AI or an interest in exploring how it can be used in their field to join.

😅 What about teams?

If you don't have a team, don't worry! You can connect with other participants from all over the world on our dashboard or Discord server. We also recommend checking out our Discord server to find teammates and bounce around ideas. You can join the server here

🛠️ How to participate

The hackathon will take place online on lablab.ai platform and lablab.ai Discord Server. Please register for both in order to participate. To participate click the "Enroll" button at the bottom of the page and read our Hackathon Guidelines and Getting Started Guide.

🧠 Get prepared / Use Lablab.ai to Learn About AI

To get ready for the hackathon, visit our AI Tech pages and read up on all the available technologies. You can also check out our tutorials page for more information on how to use them. Get a head start on your project by using the resources on lablab.ai!

Event Schedule

To be announced

Enrolled