Build Your Own CLI Chatbot with RAG Support! An All-Code, No-Slides Session
Details
Please register via the official page to get your ticket : https://luma.com/r804wslo
Join us for an all-code no-slides session, where we demystify AI by showing just how approachable it can be. You will build your own CLI chatbot with support for Retrieval-Augmented Generation (RAG) - combining the reasoning of Large Language Models (LLMs) with the accuracy of your own data.
We will start by introducing the essentials: how LLMs, embeddings and vector databases work together to enable semantic search. We'll then see how Couchbase Shell, a Nushell-based CLI, can be used to build a chatbot, and connect to Couchbase to implement RAG.
All you need to follow along is an OpenAI API key as well as basic programming and command-line experience. You will be given access to Couchbase Shell and a Capella Free Tier account.
After the session you will have the opportunity to relax over drinks and snacks while connecting with fellow developers, architects, IT leaders, Couchbase users, and AI enthusiasts.
What You Will Learn
- How LLMs are used for Chatbots
- What is Retrieval Augmented Generation (RAG)
- Couchbase's Semantic Search and AI capabilities
- Discover Couchbase Shell, based on Nushell, a next generation shell to build awesome CLIs
What You Need to Get Started:
A laptop, basic knowledge of databases, curiosity to learn new stuff, an OpenAI API key as well as basic programming and command-line experience.
Free-Tier Access:
During the workshop, you will receive free-tier access to Couchbase Capella™ to experiment with data, queries, vector search and indexes-completely free of charge.
Workshop Schedule:
18:00 - 18:30 Welcome & Networking
18:30 - 19:00 Couchbase: Initial Setup
19:00 - 19:15 Break
19:15 - 20:30 Hands-on Workshop
20:30 - 22:00 Join us for drinks, finger food and great conversations