BEGIN:VCALENDAR VERSION:2.0 PRODID:-//PYVOBJECT//NONSGML Version 1//EN BEGIN:VTIMEZONE TZID:Europe/Brussels BEGIN:STANDARD DTSTART:20001029T030000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET TZOFFSETFROM:+0200 TZOFFSETTO:+0100 END:STANDARD BEGIN:DAYLIGHT DTSTART:20000326T020000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST TZOFFSETFROM:+0100 TZOFFSETTO:+0200 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:20260610T061126Z - 40688@eu441a.odoo.com DTSTART;TZID=Europe/Brussels:20260420T090000 DTEND;TZID=Europe/Brussels:20260422T130000 CREATED:20260610T061126Z DESCRIPTION:Building Advanced AI Workflows with LL Ms\nCourse Description As organisations move beyond experimentation wi th AI\, the ability to build custom workflows and integrate large language models into existing systems becomes a critical technical capability. Thi s course offers an in-depth\, hands-on exploration of modern language mode ls and provides participants with the skills required to design\, implemen t\, and deploy AI-powered applications. The module begins with a technical deep dive into the internal architecture of large language models\, inclu ding transformers\, tokenisation\, and embeddings. Participants will gain a clear understanding of how proprietary and open-source models differ\, a nd how these differences affect performance\, cost\, and deployment choice s. Building on this foundation\, the course focuses on practical integrati on\, showing how to call models through APIs such as those provided by Ope nAI\, Anthropic\, and open-source alternatives. Participants will learn ho w to construct robust data-processing pipelines for real-world inputs\, in cluding emails\, documents\, and OCR-based content. The course also introd uces semantic clustering using embeddings\, enabling more advanced analysi s and organisation of unstructured data. To complete the end-to-end workfl ow\, participants will design a simple yet functional web interface using Gradio\, allowing users to interact with AI-generated insights. Throughout the course\, emphasis is placed on reusable code\, best practices\, and p ractical deployment considerations. By the end of the module\, participant s will have built a complete AI-driven application\, developed a reusable Python codebase\, and acquired the technical confidence needed to integrat e language models into production-ready workflows. Course Content Day Cont ent 1 Deep architecture overview of LLMs: Transformers\, tokenisation\, em beddings. Proprietary vs. open-source models 2 Calling LLMs through APIs [ ...] DTSTAMP:20260610T061126Z LOCATION:BeCentral\, Cantersteen 12\, 1000 Bruxelles\, Belgium SUMMARY:Building Advanced AI Workflows with LLMs X-ALT-DESC;FMTTYPE=text/html:Building Advanced AI Workflows with LLMs\nCourse Description As organisations move beyond e xperimentation with AI\, the ability to build custom workflows and integra te large language models into existing systems becomes a critical technica l capability. This course offers an in-depth\, hands-on exploration of mod ern language models and provides participants with the skills required to design\, implement\, and deploy AI-powered applications. The module begins with a technical deep dive into the internal architecture of large langua ge models\, including transformers\, tokenisation\, and embeddings. Partic ipants will gain a clear understanding of how proprietary and open-source models differ\, and how these differences affect performance\, cost\, and deployment choices. Building on this foundation\, the course focuses on pr actical integration\, showing how to call models through APIs such as thos e provided by OpenAI\, Anthropic\, and open-source alternatives. Participa nts will learn how to construct robust data-processing pipelines for real- world inputs\, including emails\, documents\, and OCR-based content. The c ourse also introduces semantic clustering using embeddings\, enabling more advanced analysis and organisation of unstructured data. To complete the end-to-end workflow\, participants will design a simple yet functional web interface using Gradio\, allowing users to interact with AI-generated ins ights. Throughout the course\, emphasis is placed on reusable code\, best practices\, and practical deployment considerations. By the end of the mod ule\, participants will have built a complete AI-driven application\, deve loped a reusable Python codebase\, and acquired the technical confidence n eeded to integrate language models into production-ready workflows. Course Content Day Content 1 Deep architecture overview of LLMs: Transformers\, tokenisation\, embeddings. Proprietary vs. open-source models 2 Calling LL Ms through APIs [...] END:VEVENT END:VCALENDAR