GenAI Bootcamp: Master AI with Apache Kafka® and Apache Flink®

Please join us for a special IN-PERSON meetup hosted by Clari, where you will learn the fundamentals of Apache Kafka® and Apache Flink® along with building real-time Retrieval Augmented Generation (RAG) pipelines!

Event Details:

🗓Date: 18 March 2025 (Tuesday)

🗓Time: 5:30 PM - 8:00 PM

📍Location:
ClayWorks 371
3rd Block, 371, 1st Cross Road, Santhosapuram, Koramangala 3 Block, Koramangala, Bengaluru, Karnataka 560034

Price: Free
*Please note: space is limited. Please RSVP to confirm your presence and fill out the form here for security purposes to enter the venue*

🗓 Agenda:

• 5:30PM - 5:45PM: Welcome & Icebreaker
• 5:45PM - 6:45PM: GenAI Hands on Workshop by Viktor Gamov
• 6:45PM - 8:00PM: Q&A/Food, Drinks & Additional networking

Workshop Abstract:
* Bring your laptop device for the hands-on session.
This hands-on workshop dives deep into building a real-time sentiment analysis pipeline leveraging the power of FlinkSQL, vector databases, and Large Language Models (LLMs). We'll explore how to:

• Harness FlinkSQL for data enrichment: Aggregate real-time financial data and market news analysis, enriching prompts with context retrieved from a vector database using FlinkSQL's powerful JOIN capabilities.
• Connect to the AI ecosystem: Seamlessly integrate embedding models, LLMs, and external APIs through Kafka Connectors, simplifying communication and data flow.
• Build scalable pipelines with Confluent Cloud: Leverage the robustness of Confluent Cloud Kafka clusters and Flink compute pools for real-time processing and analysis.

Real-World Application: We'll apply these techniques to build a sentiment analysis pipeline, demonstrating how to extract insights from financial data and market news in real-time.

Key Takeaways: Participants will gain practical experience with Confluent's "Connect, Process, Stream" paradigm, enabling them to build and deploy their real-time RAG pipelines using any context search vector database and LLM HTTP endpoint.
This workshop provides a stepping stone toward Confluent certification and unlocks new possibilities for real-time data analysis and decision-making.

About the speaker:
Viktor Gamov is a Principal Developer Advocate at Confluent, founded by the original creators of Apache Kafka®. With a rich background in implementing and advocating for distributed systems and cloud-native architectures, Viktor excels in open-source technologies. He is passionate about assisting architects, developers, and operators in crafting systems that are not only low in latency and scalable but also highly available.
As a Java Champion and an esteemed speaker, Viktor is known for his insightful presentations at top industry events like JavaOne, Devoxx, Kafka Summit, and QCon. His expertise spans distributed systems, real-time data streaming, JVM, and DevOps.

Viktor has co-authored "Enterprise Web Development" from O'Reilly and "Apache Kafka® in Action" from Manning.

Follow Viktor on X - @gamussa to stay updated with Viktor's latest thoughts on technology, his gym and food adventures, and insights into open-source and developer advocacy.