Preparing and Using Data for AI with LangChain and OpenSearch^®

What's in the Workshop Recipe?

We’ll work together to generate embeddings for podcast transcriptions and load that data into OpenSearch. Then we’ll search the documents using similarity search and use those results to improve our responses from an LLM (Large Language Model). Along the way we’ll explain the Retrieval Augmented Generation (RAG) pattern and show how it’s possible to try different LLMs without having to completely rewrite your code.

This workshop is particularly useful for determining what would be required to make your data usable with the RAG pattern.

Prepare for a Brain Upgrade

You will learn how to:

• Find and generate embeddings for existing content
• Ingest that content and its embeddings into OpenSearch
• Use OpenSearch and LangChain to implement the RAG (Retrieval Augmented Generation) pattern with an LLM (Large Language Model)

Prerequisities

• A web browser.
• An Aiven account, using our free trial. We will lead you through setting that up in the workshop, if you don’t already have one.
• A GitHub account. Here’s the GitHub repository we’ll be using.