WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
WeAreDevelopers LIVE • Jan 19, 2024

Enter the Brave New World of GenAI with Vector Search

Mary Grygleski

Why do traditional databases fail modern context-aware AI? Discover how Java developers can leverage vector search and the RAG pattern to eliminate GenAI hallucinations.

Pause
Mute Enter Fullscreen
#1 about 3 min

Introduction to generative AI and vector search

A brief overview guiding developers into the foundational concepts of generative AI.

#2 about 4 min

Historical timeline of artificial intelligence development

A walk through computing history from the earliest mechanical automata to modern chess-playing machines.

#3 about 3 min

Distinguishing between AI, machine learning, and deep learning

How the overlapping layers of artificial intelligence build upon neural networks and automated pattern recognition.

#4 about 5 min

How generative models disrupt traditional machine interaction

The shift from structured command-line inputs to natural language prompts in creative AI applications.

#5 about 3 min

Historical breakthroughs in natural language processing models

The progression from early feedforward networks to Word2Vec and the foundational Transformer architecture.

#6 about 6 min

Exploring popular generative AI models and applications

An overview of text, image, code, and audio models like GPT-4, Stable Diffusion, and GitHub Copilot.

#7 about 3 min

Essential engineering roles in the generative AI space

How software developers, data scientists, and MLOps engineers collaborate to build AI solutions.

#8 about 6 min

Defining GPT architectures and natural language processing tasks

How pre-trained transformers and linguistic subfields enable machines to understand contextual language nuances.

#9 about 3 min

Resource demands and foundational tasks of large language models

The compute requirements for training LLMs and their role in generating and classifying complex text blocks.

#10 about 3 min

Utilizing Java frameworks to interface with AI models

An introduction to Java-based tools like LangChain4j, Jlama, and JVector for building AI applications.

#11 about 4 min

Storing machine learning data with specialized vector databases

Why complex AI data needs purpose-built databases for feature engineering rather than standard scalar storage.

#12 about 4 min

Understanding numerical representations of vector embeddings

How textual data is converted into floating-point coordinates across high-dimensional spaces to represent semantic proximity.

#13 about 3 min

Accelerating similarity searches with specialized retrieval algorithms

A look into how hierarchical algorithms like HNSW and DiskANN rapidly navigate vector databases.

#14 about 3 min

Common application scenarios leveraging vector similarity matching

Practical ways to utilize vector embeddings for clustering, anomaly detection, recommendations, and text classification.

#15 about 3 min

Enhancing language models with retrieval-augmented generation

Overcoming the knowledge cutoffs of LLMs by injecting real-time stateful data during context retrieval.

#16 about 9 min

Setting up a managed vector database with Astra DB

A walkthrough demonstrating how to create, configure, and query a free serverless vector database environment.

#17 about 2 min

Mitigating the inherent challenges of generative AI tools

A review of AI risks like hallucinations, ethical data usage constraints, and temporal knowledge limits.

#18 about 4 min

Providing Q&A insights on model-specific vector embeddings

Wrapping up the session with educational resources and answering a specific question about model-specific embeddings.

Matching moments

1:24 min

Expanding AI capabilities using retrieval-augmented generation

Cedric Clyburn Cedric Clyburn · WWC 2024

2:08 min

Navigating the components of the modern generative AI stack

Julián Duque Julián Duque · WWC 2025

3:46 min

Substituting traditional classification models with search-based AI architecture

Erik Bamberg · LIVE

1:36 min

Understanding vector databases and retrieval-augmented generation pipelines

Sandra Ahlgrimm Sandra Ahlgrimm +1 · WWC 2024

3:36 min

Overview of generative AI and the presentation agenda

juarezjunior juarezjunior · WWC 2024

2:04 min

Exploring breakthroughs in large generalist machine learning models

Toju Duke · WWC 2022

More from WeAreDevelopers LIVE

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz thumbnail
5:43
5 days ago

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz

Chris Heilmann, Daniel Cranney

WeAreDevelopers LIVE - Node and Package Security thumbnail
1:08:30
5 days ago

WeAreDevelopers LIVE - Node and Package Security

Chris Heilmann, Daniel Cranney, Zbyszek Tenerowicz

WeAreDevelopers LIVE - Streaming HTML thumbnail
1:10:26
12 days ago

WeAreDevelopers LIVE - Streaming HTML

Chris Heilmann, Daniel Cranney, Jad Joubran

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe thumbnail
1:02:34
19 days ago

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe

Chris Heilmann, Daniel Cranney, Justin Halsall, Werner Jeschko, Nicole Jeschko, Mirco Tomić

WeAreDevelopers LIVE - Web Performance in an AI World thumbnail
1:07:59
26 days ago

WeAreDevelopers LIVE - Web Performance in an AI World

Chris Heilmann, Daniel Cranney

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko thumbnail
5:55
about 2 months ago

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko

Chris Heilmann, Daniel Cranney

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

Who Tests the AI? Building Trustworthy AI Systems at Enterprise Scale

Him Raj Singh

PayPal, Manager, Software Engineer

Him Raj Singh
Open session

World Congress 2026 North America

The Broken Rung: How AI is Rebuilding Software Development from the Ground Up

Tomislav Tipurić

Chief Technology Officer, Nephos

Tomislav Tipurić
Open session

World Congress 2026 North America

Making Science Larger, not just Faster

Yuval Dvir

Commercial Executive, SandboxAQ

Yuval Dvir
Open session

World Congress 2026 North America

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine at Intuit

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

Look What Java Can Do Now: Live-Coding a GenAI MCP Server with the JAQ Stack

Suren Konathala

Senior Engineering Leader, Marketing & AdTech, AI GTM & Digital Experience Platforms, Java x AI

Suren Konathala

Related videos

Accelerating GenAI Development: Harnessing Astra DB Vector Store and Langflow for LLM-Powered Apps thumbnail
28:57
WWC 2024 • almost 2 years ago

Accelerating GenAI Development: Harnessing Astra DB Vector Store and Langflow for LLM-Powered Apps

David Leconte, Michel de Ru

How to Decipher User Uncertainty with GenAI and Vector Search thumbnail
24:47
WWC 2025 • 12 months ago

How to Decipher User Uncertainty with GenAI and Vector Search

Ben Greenberg

What comes after ChatGPT? Vector Databases - the Simple and powerful future of ML? thumbnail
59:38
LIVE • over 2 years ago

What comes after ChatGPT? Vector Databases - the Simple and powerful future of ML?

Erik Bamberg

Building Real-Time AI/ML Agents with Distributed Data using Apache Cassandra and Astra DB thumbnail
28:20
WWC 2023 • almost 3 years ago

Building Real-Time AI/ML Agents with Distributed Data using Apache Cassandra and Astra DB

Dieter Flick

Harry Potter and the Elastic Semantic Search thumbnail
57:52
LIVE • over 2 years ago

Harry Potter and the Elastic Semantic Search

Iulia Feroli

Build RAG from Scratch thumbnail
28:04
WWC 2024 • almost 2 years ago

Build RAG from Scratch

philnash

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.