CAIML #35
Meetup Cologne
The 35th community meetup of Cologne AI ML (CAIML) took place on March 18th at Publicis Sapient in downtown Cologne. We were pleased to welcome about 50 AI ML enthusiasts at the second CAIML meetup this year and to spend an evening full of interesting talks and inspiring discussions with them.
Venue
The CAIML #35 meetup took place at Publicis Sapient GmbH in Cologne.
Great #CAIML meetup at #PublicisSapient #Köln#CAIML #Cologne #Ai #ML #Ki #GenAI #LLM #STEM #physics #chemistry #science #DeepLearning #machinelearning #chem @BASF @PublicisSapient #engineering #datascience #dataanalytics #datascientist #datavisualization #dataanalysis
Thanx… pic.twitter.com/a203me3zxQ
— Thomas Fabula (@TFConsult) March 19, 2025
Agenda
Welcome CAIML community
Intro Publicis Sapient
Talk 1
Sinem Unal, Ph.D.: Senior Associate, Data Science at Publicis Sapient
Keeping RAG in Check: Optimizing Retrieval-Augmented Generation for Enterprise Applications
“RAG architecture has proven its effectiveness in various GenAI applications. While setting up a generic one is relatively straightforward with current tools and technologies, optimizing it for specific business needs is a different challenge. In this talk, we will explore some design considerations to have a performant RAG in production, including evaluation, quality and latency trade-offs, and scalability. We will also address critical aspects such as ongoing maintenance, security / privacy. Join us as we dive into the full lifecycle of a RAG system and share insights on how to successfully sustain it in enterprise settings.”
Talk 2
Dr. Hergen Schultze: Head of Data Analytics at BASF
Mathematical optimization and open source software development to create autonomous research machines
“Optimization of reaction conditions has a long history in chemical industry. While progress was originally based on random discoveries and the intuition of chemists, in the last century we developed techniques and statistical methods for process optimization. Now, we are taking the next step, using artificial intelligence to automate and accelerate reaction optimization, not least to better address the major chemical industry challenges such as CO2 management and the transformation of energy and raw materials. We believe that all significant decisions in R&D should be driven by evidence, that means by well designed, executed, and analyzed experiments. To accelerate this process we create machines, that “close the loop” for autonomous research and development. Such a machine is basically a fully automized lab setup. It is controlled by a lab management and execution software, which is orchestrated by a higher-level (Bayesian) optimization algorithm. The context and goals are set by the scientist, but the augmentation by generative large language models is perceivable and currently under development. Whereas academic groups focus on proving the principle for new technologies and applications, we in industry focus on establishing the technologies in a reliable way. For the digital level of the autonomous research machine, we collaborate with external partners on open-source algorithm development [1]. We provide the capabilities internally as digital products, that means the optimization functionality is readily available and maintained long-term by an internal team [2]. For a certain application, these capabilities are coupled with a professional lab execution system. If time permits, we can discuss the experimental lab set-up as well.”
Impressions
Dr. Fabian Hadiji launching the CAIML meetup at the Publicis Sapient location.
Fabian Hadiji
Sinem Unal
Hergen Schultze
Conclusion
Sinem gave us deep insights into RAG development, from the concept phase to the most robustly implemented architectures. She did not miss the opportunity to point out the importance and significance of careful data preprocessing. Furthermore, she also pointed out the use of LLM for the evaluations and emphasized the aspects of system security.
Hergen showed us, among other things, with the help of open source software (BoFire), what the future of chemical research in experiment design will look like in the near future: mathematical optimization with the help of automated AI. Impressive examples also using LLM, how AI-automated mathematical optimization will change chemical research and development in the future.
Further information
CAIML aims to bring together people interested in AI and ML (machine learning). For more information visit & join us:
Please follow our CAIML community also on Linkedin:
Slides
Sinem and Hergen were so open and kind as to provide us with their respective presentations:
Sinem
Keeping RAG in Check: Optimizing Retrieval-Augmented Generation for Enterprise Applications
Hergen
Mathematical optimization and open source software development to create autonomous research machines
Networking
As usual, the two talks and discussions were followed by a personal networking round with food and drinks, sponsored by Publicis Sapient. Many thanks also to Aaqib, Fabian and Marc for once again organizing an excellent event with well-chosen topics and outstanding speakers.
GitHub repository
BoFire is an open-source Bayesian Optimization Framework Intended for Real Experiments.
Retrospective
Don’t miss the previous meetups of the CAIML community in Cologne:
Next meetup
Join us on may 20th: www.meetup.com/CAIML/36/