Apache Kafkaยฎ๏ธ ๋น„์šฉ ์ ˆ๊ฐ ๋ฐฉ๋ฒ• ๋ฐ ์ตœ์ ์˜ ๋น„์šฉ ์„ค๊ณ„ ์•ˆ๋‚ด ์›จ๋น„๋‚˜ | ์ž์„ธํžˆ ์•Œ์•„๋ณด๋ ค๋ฉด ์ง€๊ธˆ ๋“ฑ๋กํ•˜์„ธ์š”

Online Talk

Data Streaming and Retrieval-Augmented Generation (RAG) for Generative AI

์ง€๊ธˆ ์‹œ์ฒญํ•˜๊ธฐ

Available On-demand

Is your AI chatbot hallucinating? LLMs are a great foundational tool that has made AI accessible for everyone, but they lack real-time domain-specific data. Building cutting-edge GenAI applications requires an understanding of context around a query and generating relevant, accurate results.

This is where RAG comes in. RAG is a pattern that pairs prompts with real-time external data to improve LLM responses.

Join Confluent experts Andrew Sellers, Head of Technology Strategy, and Kai Waehner, Global Field CTO, as they deep dive into RAG and the 4 Steps for Building Event-Driven GenAI Applications. Register now to learn:

  • How to build a real-time, contextualized, and trustworthy knowledge base
  • Where a data streaming platform and Apache Flinkยฎ stream processing (with AI model inference) fit in the RAG architecture
  • Key steps of data augmentation, inference, workflows, and post-processing
  • How a RAG demo works, featuring an AI chatbot that provides personalized product recommendationsโ€”built using Confluent, OpenAI, ChatGPT-4, Flink, MongoDB, and D-ID

์•ค๋“œ๋ฅ˜ ์…€๋Ÿฌ์Šค(Andrew Sellers)๋Š” ์ „๋žต ๊ฐœ๋ฐœ, ๊ฒฝ์Ÿ ๋ถ„์„ ๋ฐ ์‚ฌ๊ณ  ๋ฆฌ๋”์‹ญ์„ ์ง€์›ํ•˜๋Š” ํŒ€์ธ Confluent์˜ ๊ธฐ์ˆ  ์ „๋žต ๊ทธ๋ฃน์„ ์ด๋Œ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.

Kai๋Š” Confluent์˜ ๊ธ€๋กœ๋ฒŒ ํ•„๋“œ CTO๋กœ์„œ ๋น…๋ฐ์ดํ„ฐ ๋ถ„์„, ๋จธ์‹  ๋Ÿฌ๋‹, ๋ฉ”์‹œ์ง•, ํ†ตํ•ฉ, ๋งˆ์ดํฌ๋กœ์„œ๋น„์Šค, ์‚ฌ๋ฌผ ์ธํ„ฐ๋„ท, ์ŠคํŠธ๋ฆผ ์ฒ˜๋ฆฌ, ๋ธ”๋ก์ฒด์ธ ๋“ฑ์„ ์ „๋ฌธ์œผ๋กœ ํ•ฉ๋‹ˆ๋‹ค. ๋˜ํ•œ ๊ธฐ์ˆ  ๊ด€๋ จ ๊ธฐ์‚ฌ๋ฅผ ์ž‘์„ฑํ•˜๊ณ  ๊ตญ์ œ ์ปจํผ๋Ÿฐ์Šค์—์„œ ๊ฐ•์—ฐ์„ ํ•˜๋ฉฐ ๋ธ”๋กœ๊ทธ(www.kai-waehner.de/blog)๋ฅผ ํ†ตํ•ด ์‹ ๊ธฐ์ˆ ์— ๋Œ€ํ•œ ๊ฒฝํ—˜์„ ๊ณต์œ ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.