Search & LLM: Building a GenZ Search Application for 12 million students

Gregor Weber and Alexandra Klochko • Location: TUECHTIG • Back to Haystack EU 2024

In today’s rapidly evolving digital landscape, where information overload is the norm, creating a search experience that resonates with Gen Z demands more than just relevance—it requires, personalization and adaptability. At Knowunity, an Ed-Tech startup with over 12 million students, we’ve are leveraging Large Language Models to further develop our search. Our search team consist of 1 PM and 1.5 Engineers.

This talk will dive into the role of LLMs in building a Gen Z-focused search application, exploring the challenges, triumphs, and lessons learned along the way. We’ll showcase our real-world implementations, including: – “Did You Mean?” with LLM – Follow-up Question Generation using GPT – Building a knowledge graph with AI – Results page with AI summarised answer based on retrieved content – Using GPT Vision to extract images from PDF content – using LLMs to extract Keywords from UGC, and improving transcript quality of UGC – show AI tools based on user use case

Download the Slides Watch the Video

Gregor Weber

Knowunity

Alexandra Klochko

Knowunity