Getting things done with Open AI functions, chains, and agents

When ChatGPT became available, we all witnessed the democratization of AI. Suddenly everybody is talking about AI. A talk show from Eva Jinek was all about AI. My newspaper regularly posts articles about AI. Not somewhere hidden but in plain sight.

Talking to a chatbot powered by a Large Language Model was fun. However, soon the limitations arose. After a while, everybody spoke about Hallucinations and having no access to recent or dynamic content. Using OpenAI Functions, chains, and agents systems called Retrieval Augmented Generation are created.

This talk gives you an overview of the power of OpenAI Functions. How can you combine prompts with functions? How can you compare functions to chains and agents? You learn to combine these tools to create interactive digital assistants using the OpenAI chatbot.

The Art of Questions: Creating a Semantic Search-Based Question-Answering System with LLMs

Ever thought about building your very own question-answering system? Like the one that powers Siri, Alexa, or Google Assistant? Well, we've got something awesome lined up for you!

In our hands-on workshop, we'll guide you through the ins and outs of creating a question-answering system. We prefer using Python for the workshop. We have prepared a GUI that works with python. If you prefer another language, you can still do the workshop, but you will miss the GUI to test your application. You'll get your hands dirty with vector stores and Large Language Models, we help you combine these two in a way you've never done before.

You've probably used search engines for keyword-based searches, right? Well, prepare to have your mind blown. We'll dive into something called semantic search, which is the next big thing after traditional searches. It’s like moving from asking Google to search "best pizza places" to "Where can I find a pizza place that my gluten-intolerant, vegan friend would love?" – you get the idea, right?

We’ll be teaching you how to build an entire pipeline, starting from collecting data from various sources, converting that into vectors (yeah, it’s more math, but it’s cool, we promise), and storing it so you can use it to answer all sorts of queries. It's like building your own mini Google!

We've got a repository ready to help you set up everything you need on your laptop. By the end of our workshop, you'll have your question-answering system ready and running.

So, why wait? Grab your laptop, bring your coding hat, and let's start building something fantastic together. Trust us, it’s going to be a blast!

Some of the highlights of the workshop:

Use a vector store (OpenSearch, Elasticsearch, Weaviate)
Use a Large Language Model (OpenAI, HuggingFace, Cohere, PaLM, Bedrock)
Use a tool for content extraction (Unstructured, Llama)
Create your pipeline (Langchain, Custom)

This is a workshop

EventStorming, from Knowledge to Working Domain Model

Two brains, one domain, one laptop, and a guarantee for a day of fun and learning. You’ll go back to basics. Talking about the domain, exploring it using EventStorming with a small group and then pair up to design and code the model.

## Agenda:
The day starts with an EventStorming session to explore an interesting domain. You will work in small groups, making sure everyone in the group guards a portion of the EventStorming session by taking on specific roles. But we won't stop after we've explored the domain.
During the second part of the day you will work in pairs, together with other participants. You will use the output of the EventStorming session and all the knowledge that you've gathered about the domain. Together, you'll play around, modeling parts of the domain in code, using tests to guide your design. You can choose from several starter templates, to help you code the domain using different approaches. From a typical object oriented domain model to an event sourced domain model. Throughout the workshop, pairs will share their approach so we can all learn from each other.

All you have to bring is a laptop with a recent version of IntelliJ installed (only one laptop per pair is needed). Java or Kotlin templates will be provided, or you can choose to use your own preferred stack.

## What you will learn:
- Why you need to start by understanding the problem and exploring a domain before you start coding.
- How to 'sketch' in code and tease out a model bit by bit.
- Not to be afraid to throw away the model and sketch again.
- That there are many ways to implement a model and that there are tradeoffs to make when choosing an approach.

Especially the part where pairs share and explain their approach is really insightful and helps to realize that there are many (good) solutions to a problem. It also creates a lot of interaction between participants which always makes for many views being shared and for lively discussions.

Playing with domain models in code

(This is a hands-on lab with limited capacity)

Two brains, one domain, one laptop, and a guarantee for 2 hours of fun and learning. You’ll go back to basics. Talking about the domain, designing the model and explore coding the model in Java or Kotlin with close to no libraries.

This is a hands-on coding workshop where you will work in pairs together with other participants. Your base will be the output of an EventStorming session and some context about the domain that you'll be modeling. Together, you'll play around, modeling parts of the domain in code, using tests to guide your design.

A starter project will be provided to get you up and running quickly, you can choose between Java or Kotlin. All you have to bring is a laptop with a recent version of IntelliJ installed (only one laptop per pair is needed). Throughout the workshop, pairs will share their approach so we can all learn from each other.

What you will learn:

- Why you need to start by understanding the problem before you start coding.
- How to 'sketch' in code and tease out a model bit by bit.
- Not to be afraid to throw away the model and sketch again.

Revolutionizing Customer Experience: Enhancing Information Access with Question-Answering Systems

Are you tired of customers struggling to find the answers they need on your website? Say goodbye to frustrating searches and embrace a new era of effortless information access. Join us for an exciting talk on revolutionizing customer experience through question-answering systems.

In this presentation, we invite you to explore the potential of the newest language libraries and tools. Discover how they can transform users’ interactions with your online platform.

We'll start by demystifying the core concepts behind question-answering systems, breaking down their purpose and functionality. Dive into the world of index-based search, vector-based search, and Large Language Models (LLMs), the essential building blocks powering this technological leap forward.

But we won't stop at theory alone. We give you a demonstration where you'll see these systems in action. Follow along as we walk you through a content pipeline that extracts content from different sources and indexes the content into vector databases—followed by different patterns to retrieve information from the vector databases and generate answers with multiple LLMs, enabling the dynamic generation of accurate and personalized answers in real-time.

By the end of our presentation, you'll understand the underlying structure of a question-answering system, empowering you to enhance information access on your website or within your application. Join us on this exciting journey and unlock the true potential of question-answering systems!

Deep dive into a Retrieval Augmented Generation system using Amazon OpenSearch Service, Langchain, a

This talk aims to show you a working sample of a Retrieval Augmented Generation (RAG) system running on AWS using components like Langchain, Amazon OpenSearch Service, and OpenAI. Let me explain to you why you need such a system.

Visitors to your website are looking for something. Maybe they are looking for something to buy. They can also seek information about delivery terms, opening hours, or advice about a product. Google and other websites see an increasing trend in users that use sentences instead of keywords. Wouldn’t it be great if you could answer the questions instead of pointing them to a page where they need to find the answer themselves?

You get an introduction to question-answering systems, what they do, and how it works. We briefly introduce the components we need: index-based search, vector-based search, LLMs, and Retrieval Augmented generation (RAG).

Next is an extensive demo, plus an explanation of the code. You will see a content pipeline to index content. Then you will see how to utilize different search engines in combination with a Large Language Model to generate answers on the fly. The demo shows you different mechanisms like content extraction and content generation for creating the answer. The results utilizing the different components are compared.

After the presentation, you have a fair understanding of the generic structure of a Retrieval Augmented Generation system to support question-answering on your website or within your application.

Adjustments to run on other platform, use other vector store are possible.

The Good, the Bad and the Ugly data

In the cinematic masterpiece "The Good, the Bad, and the Ugly," characters mirror the nuances of data in analysis. "The Good" stands for high-quality, reliable data with a clear lineage; "The Bad" signifies anomalies in need of valorization efforts; and "The Ugly" represents unstructured data with hidden potential.

This presentation explores strategies for identifying and extracting the gold nuggets of insight from the "Ugly" data while mitigating the influence of the "Bad" data. We show data cleaning, validation, transformation, and presentation techniques to turn ugly data into good data, remove bad data and extract value from the good data.