BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Sabre//Sabre VObject 4.5.8//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Zurich X-LIC-LOCATION:Europe/Zurich TZURL:http://tzurl.org/zoneinfo/Europe/Zurich BEGIN:DAYLIGHT TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST DTSTART:19810329T020000 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET DTSTART:19961027T030000 RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT UID:news129@rds.unibas.ch DTSTAMP;TZID=Europe/Zurich:20240611T113104 DTSTART;TZID=Europe/Zurich:20240627T161500 SUMMARY:Insights from One Year of Customer Implementations of RAG-based Cha tbot Systems Using MongoDB Vector Search DESCRIPTION:Speaker:\\r\\nPhilip Eschenbacher\, MongoDB\\r\\nAbstract:\\r\\ nIn this talk we will explore the journey of building chatbots using Retri eval-Augmented Generation (RAG) systems with MongoDB Atlas\, focusing on v aluable insights and lessons learned over the past year. As RAG systems be come increasingly vital for enhancing information retrieval and generation and to tailor chatbots to corporate documents\, our experiences and custo mer implementations provide a rich source of knowledge. We will delve into the technical aspects and best practices on MongoDB Vector Search and how to make customer data accessible for language models. Through real-world examples\, we will highlight the challenges faced and solutions devised by our customers in building such chatbots\, showcasing the practical applic ations and benefits.\\r\\nCurriculum Vitae:\\r\\nPhilip's tech journey beg an as a developer\, with a keen interest sparked by programming on a Commo dore 64 at age 10. By 1998\, he emerged as a product manager for a pioneer ing Swiss Internet banking solution. His career path included significant detours into operations\, notably in the large-scale migration from Tru64 to Linux\, and a thrilling stint at a startup refining his web development skills. Most recently\, before joining MongoDB\, Philip spearheaded the d evelopment of an innovative web-based workplace solution for a large Swiss bank\, transitioning it from MySQL to MongoDB. In this role\, he demonstr ated his versatility\, wearing multiple hats from developer to solutions a rchitect and team leader\, before taking on his current position as an Adv isory Solutions Architect at 🍃MongoDB. X-ALT-DESC:

Speaker:

\n

Philip Eschenbacher\, MongoDB

\n

Abstract:

\n

In this talk we will explore the journey of buil ding chatbots using Retrieval-Augmented Generation (RAG) systems with Mong oDB Atlas\, focusing on valuable insights and lessons learned over the pas t year. As RAG systems become increasingly vital for enhancing information retrieval and generation and to tailor chatbots to corporate documents\, our experiences and customer implementations provide a rich source of know ledge.
We will delve into the technical aspects and best practices o n MongoDB Vector Search and how to make customer data accessible for langu age models. Through real-world examples\, we will highlight the challenges faced and solutions devised by our customers in building such chatbots\, showcasing the practical applications and benefits.

\n

Curriculum Vitae:

\n

Philip's tech journey began as a developer\, with a kee n interest sparked by programming on a Commodore 64 at age 10. By 1998\, h e emerged as a product manager for a pioneering Swiss Internet banking sol ution. His career path included significant detours into operations\, nota bly in the large-scale migration from Tru64 to Linux\, and a thrilling sti nt at a startup refining his web development skills. Most recently\, befor e joining MongoDB\, Philip spearheaded the development of an innovative we b-based workplace solution for a large Swiss bank\, transitioning it from MySQL to MongoDB. In this role\, he demonstrated his versatility\, wearing multiple hats from developer to solutions architect and team leader\, bef ore taking on his current position as an Advisory Solutions Architect at 🍃MongoDB.

END:VEVENT END:VCALENDAR