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

Junior AI Engineer looking to improve elderly accessibility to worldwide news

Louis Jefferson Zhang

Senior-Digest is an innovative web application designed to simplify news consumption, making it more accessible and personalized. Imagine a dashboard where, in one tab labeled "Summary," the app neatly displays top 10 news headlines with generated summaries. Users can then switch to the "Query" tab to ask questions that dive into particular topics, either by typing or speaking. Here, the app processes the queries using smart language models and quickly fetches relevant answers from its database. Before showing these answers to the user, it checks them for accuracy and relevance. 

Senior-Digest uses several key technologies to work smoothly and efficiently. Streamlit makes the app's interface easy to use and interactive. Google Cloud offers VertexAI models needed by the application, like LLM, embeddings, speech-to-text and text-to-speech APIs. gspread connects the app to Google Sheets for retrieval of daily news summary. Pinecone is used for storing news embeddings over a period of time. Langchain helps to integrate summarization and RAG components. Finally, Trulens evaluates the query and responses for relevance and groundedness.

Senior-Digest's features are especially beneficial for the elderly. Its simple access to the top 10 daily news stories and AI-generated summaries reduces the need for lengthy reading, ideal for those who might struggle with small text. Additionally, its voice-based query system and audio outputs make news consumption easier and more accessible for elderly users, accommodating potential visual challenges.

News Made Easy: Keeping Seniors Connected and Informed

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

Team Idea

Submission