Gemini AI Hackathon

Hackathon Kick-Off 

We'll onboard you in the Gemini AI technology, newly released by Deep Mind, with Fabian Stehle, Data Scientist at New Native.

Introduction to Gemini AI

Join for the tech session with Shayak Sen, CTO of TruEra. We'll dive deeper in integration of TruLense into Gemini AI-based application.  

Tech Workshop with TruEra

Join experts Shayak from TruEra and Jerry Liu from LlamaIndex as they delve into the world of multimodal AI applications.

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

Q&A Session with lablab.ai mentors on Discord

Submissions Deadline

Gemini is not working for non english prompts. We make it work for non english prompts

PolyGlot Gemini

Raghavan

Problem Statement:
1) Over 70% of PDFs contain critical data in images like charts and tables, especially research articles
2) Gemini is released for English only today. 
Can we build a solution for 
1) Answering natural language questions based on images in PDFs ?
2) Making Gemini accessible for non english speakers?  

By leveraging Spire, Open AI GPT 3.5, Gemini Pro Vision and Trulens, I have built an application that solves both problems

- Spire for Image Extraction
- Open AI for Translation to English (optional)
- Gemini-Pro-Vision for the answer
- TruLens for Monitoring 



















Gemini talks to images in research articles answering natural language questions that are in English and Non English
Tacking 2 problems of extending Gemini's reach to non english and helping researchers talk to images in PDFs.

"PolyGlot Gemini team on Gemini AI Hackathon Hackathon"

Team Idea

Submission