TruEra Challenge: Build LLM Applications

Let's Kick it Off! We are starting the stream with a Hackathon opening, an introduction to lablab.ai from the NewNative co-founder, and a schedule overview.

Hackathon Kick-Off Stream

Join Anupam Datta, Co-founder, President, and Chief Scientist at TruEra, as he kicks off the Hackathon with insightful opening words, setting the tone for an engaging exploration into TruEra Challenge: Build LLM Applications with Google Vertex AI.

TruEra Opening Words

Let's dive into the platform and its features that will be useful for Hackathon participants.

Hackathon Guide and Platform Walk-through

Join the workshop with Michael Davis, Customer Engineer at Google and Anupam Datta, co-founder, President, and Chief Scientist at TruEra.

Google Cloud x TruEra Workshop: Running LLM-based Evals with PaLM 2

Join us for an insightful workshop featuring Josh Reini, DevRel Engineer at TruEra, and Yujian Tang, Developer Advocate at Zilliz.

Build and Iterate with Advanced Index Construction: Chunking, Range Search and more

General Q&A session on Discord

In this workshop on December 4, Shayak Sen, CTO of Truera, and Laurie Voss, VP of Developer Relations at LlamaIndex, will explore the building and evaluation of multimodal GenAI apps using the RAG Triad model. 

Building and Evaluating Multimodal GenAI Apps: RAG Triad is All you Need

Submissions Deadline

Extended Submission Deadline💻

TOP-5 teams will be invited to pitch their ideas for Hackathon judges - to define the Hackathon winner!

Finalists Stream

RAGnarok

Barun Saha

Building an RAG app is easy. However, optimizing its different settings, such as chunk size and context, is necessarily not. With RAG2Rich, one can identify the optimal parameters/configurations based on an answer "richness" score. Answer richness, or the "Rich" score, is a composite metric, based on the context relevance, answer relevance, and groundedness measures computed by TruLens. The average richness score is computed by transforming a relevant vector measure into a scalar using a weighted logistic function. Subsequently, the optimal parameters are chosen based on the optimal value of the average richness score. In other words, RAG2Rich offers a scientific approach to optimizing RAG-based systems.

RAG2Rich is built with several technologies, such as Vertex AI/PaLM 2, LlamaIndex, Chainlit, Milvus/Zilliz, TruLens, and Cohere. We demonstrate RAG2Rich with a use case from Substation Automation Systems.

Building an RAG app is easy. However, optimizing its different parameters is necessarily not. With RAG2Rich, identify the optimal configuration based on the average "richness" score and deploy your next RAG system with confidence.

"RAGnarok team on TruEra Challenge: Build LLM Applications Hackathon"

Team Idea

Submission