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

A reimagined US Immigration personal assistant.

AskPriya

Bassim

Fadil Eledath

Phuc Nguyen

Ask Priya" is a pioneering AI chatbot designed to streamline the process of acquiring US immigration information. Leveraging data from the USCIS website, this bot addresses queries relating to American immigration with enhanced precision. Its backbone consists of the llama-index and Google Vertex AI, which significantly mitigate common issues associated with conventional large language models (LLMs) like ChatGPT. When prompted with a question, "Ask Priya" sifts through its USCIS-indexed data, selecting relevant documents to guide the LLM's response, thereby reducing 'hallucinations' – instances where models inaccurately fabricate plausible-sounding information.

In light of the substantial international arrivals to the United States, which totaled 22.1 million in 2021, and the presence of over 1.08 million international students with active study visas as of January 2023, the demand for tailored immigration services is immense. Additionally, with 483,927 registrations for H1B visas in 2023 and only 127,600 selected to apply, the complexity and breadth of US immigration, encompassing 35 nonimmigrant and 13 immigrant visa categories, becomes evident.

"Ask Priya," in its beta phase, is gearing up for an imminent rollout. The immediate agenda includes multilingual query handling for Trulens evaluations, integrating these evaluations with GitHub actions, transitioning from Streamlit Community Cloud to Google Cloud, and storing chat logs on Google Cloud Storage.

Looking towards the future, the development team aims to refine retrieval methods for better context relevance scoring. Plans include enhancing Trulens evaluations through finetuning, in addition to the current use of Retrieval-Augmented Generation (RAG). Moreover, the team is focused on creating a persistent chat memory, enabling users to access their chat history, thereby offering a more seamless and personalized experience.

Ask Priya is a reimagined US Immigration personal assistant. 
It outperforms Ask Emma (current chatbot solution on USCIS website) on all evaluation metrics by an order of magnitude.


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

Team Idea

Submission