Slide 1

Slide 1 text

Image Β© NASA Goddard Space Flight Center https://flic.kr/p/YdWQqe (CC BY 2.0) Gunnar Morling Hans-Peter Grahsl @gunnarmorling @hpgrahsl Putting AI Into Real-time ETL with Apache Flink, Debezium, and LangChain4j

Slide 2

Slide 2 text

Real-Time ETL with Apache Flink and Debezium | @hpgrahsl @gunnarmorling ● Software engineer at Decodable ● Former project lead of Debezium ● kcctl 🧸, JfrUnit, ModiTect, MapStruct ● Java Champion ● 1⃣ 🐝 🏎 Gunnar Morling

Slide 3

Slide 3 text

Real-Time ETL with Apache Flink and Debezium | @hpgrahsl @gunnarmorling ● Developer Advocate at Decodable ● Open-source community enthusiast ● Stream processing addict ● Regular conference speaker Hans-Peter Grahsl

Slide 4

Slide 4 text

Real-Time ETL with Apache Flink and Debezium | @hpgrahsl @gunnarmorling Apache Flink Stateful Computations over Data Streams https://flink.apache.org/

Slide 5

Slide 5 text

Real-Time ETL with Apache Flink and Debezium | @hpgrahsl @gunnarmorling Apache Flink APIs for Application Development Image source: β€œChange Data Capture with Flink SQL and Debezium” by Marta Paes at DataEngBytes (https://noti.st/morsapaes/liQzgs/change-data-capture-with-flink-sql-and-debezium)

Slide 6

Slide 6 text

The observer pattern for your database

Slide 7

Slide 7 text

Real-Time ETL with Apache Flink and Debezium | @hpgrahsl @gunnarmorling Debezium Log-Based Change Data Capture

Slide 8

Slide 8 text

Real-Time ETL with Apache Flink and Debezium | @hpgrahsl @gunnarmorling Change Data Capture Liberation for Your Data https://www.decodable.co/blog/seven-ways-to-put-cdc-to-work

Slide 9

Slide 9 text

Real-Time ETL with Apache Flink and Debezium | @hpgrahsl @gunnarmorling langchain4j Simplify integrating LLMs into Java Apps Integration with Unified APIs ● 15 LLM Providers ● 15 Embedding Models ● 20 Vector Stores Comprehensive AI Toolbox ● Prompt Templating ● Chat Memory ● Function Calling

Slide 10

Slide 10 text

Real-Time ETL with Apache Flink and Debezium | @hpgrahsl @gunnarmorling langchain4j Two Abstraction Levels

Slide 11

Slide 11 text

Real-Time ETL with Apache Flink and Debezium | @hpgrahsl @gunnarmorling langchain4j Nicely Bridges to ONNX ONNX runtime + format ● Use customized models in ONNX format ● Supports many existing HuggingFace models & tokenizers ● In-process model inference β†’ nicely fits stream processing

Slide 12

Slide 12 text

Colin Howley https://flic.kr/p/698F5j (CC BY-ND 2.0) Hands-On Time! https://dcbl.link/devoxx24lab0

Slide 13

Slide 13 text

Real-Time ETL with Apache Flink and Debezium | @hpgrahsl @gunnarmorling Thank You! Q & A [email protected] @gunnarmorling morling.dev πŸ“§ [email protected] @hpgrahsl

Slide 14

Slide 14 text

No content