RAG and Elasticsearch: Bringing Context to Search

Описание: Learn about Retrieval Augmented Generation (RAG) and how it can help improve the quality of an LLM's generated responses by providing relevant source knowledge as context.

Speaker: Nastia Havriushenko, MLE II, Elastic

This is a recording from an Elastic meetup. Make sure to join your local Elastic User Group to stay up-to-date on upcoming events: https://community.elastic.co/

Timestamps:
0:00 Introduction
1:02 Generative AI app challenges
5:20 Retrieval Augmented Generation (RAG)
7:26 Playground chatbot demo
12:28 Retrieval: dense and sparse vectors
35:53 ELSER & Elastic demo

Questions? Check out https://discuss.elastic.co/
Connect with the Elastic community through Slack: https://ela.st/slack

#RAG #Elasticsearch #LLMs #ElasticPlayground #ELSER #Elastic