Zero to RAG in 60s with Elastic

Using several new capabilities in Elastic, quickly prototyping RAG (combining a large language model and semantic search) is easier than ever.
In this demo we use:
PDF File upload (available in serverless today, coming soon to other deployments as of Oct 2024)
The semantic_text mapping which automates chunking and vectorisation
Playground which lets you prototype a RAG architecture with the LLM of your choice.