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

  • πŸ‘©β€πŸ’» 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!
  • πŸ’Έ $10,000 USD cash prize pool, with special prizes for the best use of Tool Sets!
  • πŸš€ 7 days of online development with workshop sessions from experts in LLM!
  • 🀝 Connect with developers and startup enthusiasts for future opportunities.
  • πŸ’‘ Develop impactful apps for meaningful and positive change in the world with strategic approach!
Tool Face-Off: OpenAI Assistants API VS Llama-Index/MongoDB. An Eval-Driven Battle. event thumbnail

What is exciting about TruLens?

  • 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:

Get started with TruLens today and unlock the potential of your LLM-based applications.

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.

Create with Assistants API

Assistants API empowers developers to integrate intelligent virtual assistants into apps!

πŸ’» Assistants API

The Assistants API enables the creation of AI assistants in your applications, responding to user queries with models and tools. Currently supporting Code Interpreter, Retrieval, and Function calling, it offers a preview of upcoming OpenAI-built tools. Explore using the πŸ‘‰ Assistants playground or integrate following our guide.

πŸ€“ Useful links

Check out OpenAI models!

Check out the models available for you over the Hackathon to get started!

πŸ’» GPT-4 (Vision)

GPT-4 with Vision, or GPT-4V, seamlessly integrates image understanding into language models. Answer questions about images and unlock new possibilities. πŸ‘‰ GPT-4 Turbo and GPT-4V on Clarifai for Hackathon participants

πŸ’» Text-to-Speech

The Text-to-Speech API transforms written text into lifelike spoken audio. With six built-in voices, it's ideal for various applications, including narrating blog posts and real-time streaming output. πŸ‘‰ Text-to-Speech model.

πŸ’» Custom GPTs

Create tailored versions of ChatGPT without coding. Custom GPTs cater to specific tasks, making AI more helpful in various scenarios. Craft your custom GPT effortlessly with the πŸ‘‰ quick onboarding guide.

πŸ’» GPT-4 Turbo

With an updated knowledge cutoff of April 2023, a 128k context window, and unmatched cost efficiency (3X for input tokens, 2X for output tokens), it's the go-to choice for enhanced performance. Accessible with an OpenAI API account and existing GPT-4 access, simply use "gpt-4-1106-preview" as the model name.

Hackathon Challange

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 app.

Prizes

Main track

  • First place: $1750 cash
  • Second place: $1250 cash
  • Third place: $1000 cash

Special Prizes

  • Special prize for "best use of Tool Set 1 (Assistants API)": $3000 cash”
  • Special prize for "Best use of tool set 2 (Llama-Index, MongoDB, GPT-4)": $3000 cash”

You are eligible to win both an overall prize and a top tool set prize!

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.

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!

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.

πŸ—“οΈ 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.

πŸ¦ΈπŸΌβ€β™‚οΈ 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.

πŸ˜… 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

πŸ› οΈ 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
Approved

0