SlideShare a Scribd company logo
Emily Jiang, Java Champion, FBCS
IBM, STSM, Cloud Native Architect and Advocate
16th May 2024
AI-Powered Java
Developers
2
Java Developers
– You Build It, You Run It
– Dev and Ops together
– IDE
– Build (Jenkins, Containers)
– Deploy (CI/CD)
– Maintain (SBOM, Vulnerabilities)
3
What can Improve Developer
Experience?
4
Remove the tedious tasks!
5
Java Developers need to be AI-
Powered!!!
AI-Powered Java Developer Checklist
1. What is AI, LLM?
2. What is RAG?
3. What code assistant tools available?
4. What can help with building AI-Infused apps?
AI
Artificial intelligence (AI) is the simulation of human intelligence in
machines that are programmed to think and act like humans.
Learning, reasoning, problem-solving, perception, and
language comprehension are all examples of cognitive abilities.
AI History 1956 John McCarthy held a
workshop at Dartmouth on
“artificial intelligence”
1957-1974 AI flourished
2011 IBM Watson won the
game Jeopardy!
Apple released Siri, the first
popular virtual assistant.
2015 OpenAI founded
2020, OpenAI announced
GPT-3
2021, OpenAI introduced
DALL-E
1950 Alan Turing “Computing
Machinery and Intelligence”
1997 IBM Deep Blue beat the
world chess champion, Gary
Kasparov.
8
– https://www.youtube.com/watch?v=056v4OxKwlI
GenAI
Generative AI (GenAI) refers to deep-learning models that can
generate high-quality text, images, and other content based on
the data they were trained on.
– https://research.ibm.com/blog/what-is-generative-AI
Generative AI
Anything
that creates
new content
Large language model
Great
at text
Foundation
model
Unlabeled
data
Transformer
ChatGPT
inspired interest…
But there is a
bigger concept,
e.g. GPT
Which will
change business
Building blocks of generative AI – Foundation Models
– BERT
– GPT
– Claude
– Cohere
– Stable Diffusion
11
What is LLM?
12
What is LLM?
LLM =Data + Architecture + Training
specialized in Texts
Foundation Models
Foundation Model AI system Applications
LaMDA (Google) Bard (Google) AI chat
GPT-4 (OpenAI) ChatGPT (OpenAI) AI Chat
Codex (OpenAI) GitHub copilot (Microsoft) Code generation
AudioLM (Google) MusicLM (Google) Create Music
BLOOM (Hugging Face) Use directly Mutiple NLP tasks. Trained in 46
languages and 13 programming
languages.
LLaMA (Meta) Use directly AI research
DALL-E 2 (OpenAI) Use directly Image creation
– https://www.datacamp.com/blog/what-are-foundation-models
– https://github.com/ibm-granite/granite-code-models
Comparison of LLMs
– https://research.ibm.com/blog/granite-code-models-open-source
Chat
Q&A
Summarization
Summarize info – meeting
minutes, etc
Content Generation
Create email, marketing
materials, etc.
Named Entity
Recognition
Produce audit data
Insight Extraction
Medical diagnose, etc.
Classification
Sort customer complainants,
security vulnerability
classification, etc.
The most common
generative AI tasks
implemented today
Issues related to AI
• License
• Audit
• Hallucinations
• Potentially generate bad code
• Security risk
• Lack of innovation
17
How to reduce LLM Hallucination
• Domain knowledge gaps
• Data out of date
Introducing…
RAG
Retrieval Augmented
generation (RAG)
An AI framework for improving the quality
of LLM-generated responses
Grounds a model on additional sources of
knowledge to supplement its internal
representation of information
33
RAG involves three basic steps:
Search for relevant content in your knowledge base
Pull the most relevant content into your model
prompt as context
Send the combined prompt text to the model to
generate output
1
2
3
Significantly elevates level of trust:
• Ensures that the model has access to the
most current and reliable facts
• System becomes "business-aware"
• Sources are known, ensuring output can be
checked for accuracy
• Less likely to make-up a factually inaccurate
responses, with ability to say, "I don't know."
RAG
components
Knowledge
Base
Can be any collection of information containing
artifacts such as:
• Internal procedural wiki pages
• Files in GitHub (various formats)
• Messages in a collaboration tool
• Topics in product documentation
• PDF files
• Customer support tickets
• more
Can be any combination of search and content
tools that reliably return relevant content from
a knowledge base (or bases):
• Search and content APIs like GitHub APIs
• Vector databases like Milvus
A generative LLM that suits your use case, prompt
format, and content being pulled in for context
Retriever
Generator
Typical RAG process
User Question
Search &
Retrieval
Prompt =
Instructions +
Search
Results +
Question
LLM
Generated
output with
sources
Top search
results
Data storage – using embedding and a vector database
Passages
of text
“Embeddings”
New step
Data storage process
(a) Original files to documents
(b) Documents to chunks
(c) Chunks to embeddings
(d) Embeddings to vector store
Vector
database
Semantic vs.
Syntactic match
Tasks AI will do for us
• Generate code snippet
• Create tests
• Debugging
• Code review
• Code summarization
• Refactoring
24
Some GenAI tools
Chatbot
– Anthropic’s Claude 2
– Google’s Bard
– Meta AI’s Hugging Face Llama 2 Chat
– Microsoft’s Bing Chat
– OpenAI’s ChatGPT
AI code assistant
Github Copilot
Amazon CodeWisperer
Divi AI
Tabnine
Replit
Sourcegraphy Cody
25
– https://www.elegantthemes.com/blog/wordpress/best-ai-coding-assistant#4-tabnine
– https://www.youtube.com/watch?v=TXtnFw9eDmM
Introducing…
AI-infused apps
– An app using LLMs
27
Using LangChain4J to simplify
integrating with AI/LLM
capabilities into Java
applications
LangChain4J
28
– https://docs.langchain4j.dev/intro
LangChain4J example
29
– https://github.com/langchain4j/langchain4j-examples/tree/main/jakartaee-microprofile-example
– https://openliberty.io/blog/2024/04/01/open-liberty-with-langchain4j-example.html
AI-Powered Java Developer Checklist
1. What is AI, LLM? √
2. What is RAG? √
3. What code assistant tools available? √
4. What can help with building AI-Infused apps? √
31
Join MicroProfile AI group to create a MicroProfile AI Spec
Monday weekly meeting
5pm CEST
Zoom: https://eclipse.zoom.us/j/83815795087
Crucial skills for Java
Developers
• Focus on the architecture
• Innovation
• Serviceability
• AI-infused apps
32
33
AI-Powered Java Developers
won’t be replaced by AI!!!
34
Thank You
Emily Jiang
IBM, Cloud Native Architect and Advocate
emijiang@uk.ibm.com
X/LinkedIn: @emilyfhjiang
What need to be mastered as AI-Powered Java Developers

More Related Content

Similar to What need to be mastered as AI-Powered Java Developers

Open techai 20180429 v1
Open techai 20180429 v1Open techai 20180429 v1
Open techai 20180429 v1
ISSIP
 
Introducción al Machine Learning Automático
Introducción al Machine Learning AutomáticoIntroducción al Machine Learning Automático
Introducción al Machine Learning Automático
Sri Ambati
 
Intel 20180608 v2
Intel 20180608 v2Intel 20180608 v2
Intel 20180608 v2
ISSIP
 
antrikshindutrialmachinelearningPPT.pptx
antrikshindutrialmachinelearningPPT.pptxantrikshindutrialmachinelearningPPT.pptx
antrikshindutrialmachinelearningPPT.pptx
AnkitMishra616883
 
AI Playing Go and Driving Cars, What’s Next?
AI Playing Go and Driving Cars, What’s Next?AI Playing Go and Driving Cars, What’s Next?
AI Playing Go and Driving Cars, What’s Next?
Rakuten Group, Inc.
 
Lfai governance board 20191031 v3
Lfai governance board 20191031 v3Lfai governance board 20191031 v3
Lfai governance board 20191031 v3
ISSIP
 
Artificially Intelligent chatbot Implementation
Artificially Intelligent chatbot ImplementationArtificially Intelligent chatbot Implementation
Artificially Intelligent chatbot Implementation
Rakesh Chintha
 
2024 Build Generative AI for Non-Profits
2024 Build Generative AI for Non-Profits2024 Build Generative AI for Non-Profits
2024 Build Generative AI for Non-Profits
Timothy Spann
 
Software Analytics: Towards Software Mining that Matters (2014)
Software Analytics:Towards Software Mining that Matters (2014)Software Analytics:Towards Software Mining that Matters (2014)
Software Analytics: Towards Software Mining that Matters (2014)
Tao Xie
 
Analytical Superpower June 2023.pdf
Analytical Superpower June 2023.pdfAnalytical Superpower June 2023.pdf
Analytical Superpower June 2023.pdf
Hari Kumar
 
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Naoki (Neo) SATO
 
Major Project Presentation (7th Sem) - Code Detection.pptx
Major Project Presentation (7th Sem) - Code Detection.pptxMajor Project Presentation (7th Sem) - Code Detection.pptx
Major Project Presentation (7th Sem) - Code Detection.pptx
sohanmahanta1
 
AI Security : Machine Learning, Deep Learning and Computer Vision Security
AI Security : Machine Learning, Deep Learning and Computer Vision SecurityAI Security : Machine Learning, Deep Learning and Computer Vision Security
AI Security : Machine Learning, Deep Learning and Computer Vision Security
Cihan Özhan
 
20240411 QFM009 Machine Intelligence Reading List March 2024
20240411 QFM009 Machine Intelligence Reading List March 202420240411 QFM009 Machine Intelligence Reading List March 2024
20240411 QFM009 Machine Intelligence Reading List March 2024
Matthew Sinclair
 
AI and Python: Developing a Conversational Interface using Python
AI and Python: Developing a Conversational Interface using PythonAI and Python: Developing a Conversational Interface using Python
AI and Python: Developing a Conversational Interface using Python
amyiris
 
TechEvent 2019: Artificial Intelligence in Dev & Ops; Martin Luckow - Trivadis
TechEvent 2019: Artificial Intelligence in Dev & Ops; Martin Luckow - TrivadisTechEvent 2019: Artificial Intelligence in Dev & Ops; Martin Luckow - Trivadis
TechEvent 2019: Artificial Intelligence in Dev & Ops; Martin Luckow - Trivadis
Trivadis
 
Machine Learning - Know Enough To Be Dangerous #SearchLove
Machine Learning - Know Enough To Be Dangerous #SearchLoveMachine Learning - Know Enough To Be Dangerous #SearchLove
Machine Learning - Know Enough To Be Dangerous #SearchLove
Britney Muller
 
SearchLove San Diego 2019 - Britney Muller - Machine Learning: Know Enough To...
SearchLove San Diego 2019 - Britney Muller - Machine Learning: Know Enough To...SearchLove San Diego 2019 - Britney Muller - Machine Learning: Know Enough To...
SearchLove San Diego 2019 - Britney Muller - Machine Learning: Know Enough To...
Distilled
 
Ai progress = leaderboards compute data algorithms 20180817 v3
Ai progress = leaderboards compute data algorithms 20180817 v3Ai progress = leaderboards compute data algorithms 20180817 v3
Ai progress = leaderboards compute data algorithms 20180817 v3
ISSIP
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AI
abhishek36461
 

Similar to What need to be mastered as AI-Powered Java Developers (20)

Open techai 20180429 v1
Open techai 20180429 v1Open techai 20180429 v1
Open techai 20180429 v1
 
Introducción al Machine Learning Automático
Introducción al Machine Learning AutomáticoIntroducción al Machine Learning Automático
Introducción al Machine Learning Automático
 
Intel 20180608 v2
Intel 20180608 v2Intel 20180608 v2
Intel 20180608 v2
 
antrikshindutrialmachinelearningPPT.pptx
antrikshindutrialmachinelearningPPT.pptxantrikshindutrialmachinelearningPPT.pptx
antrikshindutrialmachinelearningPPT.pptx
 
AI Playing Go and Driving Cars, What’s Next?
AI Playing Go and Driving Cars, What’s Next?AI Playing Go and Driving Cars, What’s Next?
AI Playing Go and Driving Cars, What’s Next?
 
Lfai governance board 20191031 v3
Lfai governance board 20191031 v3Lfai governance board 20191031 v3
Lfai governance board 20191031 v3
 
Artificially Intelligent chatbot Implementation
Artificially Intelligent chatbot ImplementationArtificially Intelligent chatbot Implementation
Artificially Intelligent chatbot Implementation
 
2024 Build Generative AI for Non-Profits
2024 Build Generative AI for Non-Profits2024 Build Generative AI for Non-Profits
2024 Build Generative AI for Non-Profits
 
Software Analytics: Towards Software Mining that Matters (2014)
Software Analytics:Towards Software Mining that Matters (2014)Software Analytics:Towards Software Mining that Matters (2014)
Software Analytics: Towards Software Mining that Matters (2014)
 
Analytical Superpower June 2023.pdf
Analytical Superpower June 2023.pdfAnalytical Superpower June 2023.pdf
Analytical Superpower June 2023.pdf
 
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
 
Major Project Presentation (7th Sem) - Code Detection.pptx
Major Project Presentation (7th Sem) - Code Detection.pptxMajor Project Presentation (7th Sem) - Code Detection.pptx
Major Project Presentation (7th Sem) - Code Detection.pptx
 
AI Security : Machine Learning, Deep Learning and Computer Vision Security
AI Security : Machine Learning, Deep Learning and Computer Vision SecurityAI Security : Machine Learning, Deep Learning and Computer Vision Security
AI Security : Machine Learning, Deep Learning and Computer Vision Security
 
20240411 QFM009 Machine Intelligence Reading List March 2024
20240411 QFM009 Machine Intelligence Reading List March 202420240411 QFM009 Machine Intelligence Reading List March 2024
20240411 QFM009 Machine Intelligence Reading List March 2024
 
AI and Python: Developing a Conversational Interface using Python
AI and Python: Developing a Conversational Interface using PythonAI and Python: Developing a Conversational Interface using Python
AI and Python: Developing a Conversational Interface using Python
 
TechEvent 2019: Artificial Intelligence in Dev & Ops; Martin Luckow - Trivadis
TechEvent 2019: Artificial Intelligence in Dev & Ops; Martin Luckow - TrivadisTechEvent 2019: Artificial Intelligence in Dev & Ops; Martin Luckow - Trivadis
TechEvent 2019: Artificial Intelligence in Dev & Ops; Martin Luckow - Trivadis
 
Machine Learning - Know Enough To Be Dangerous #SearchLove
Machine Learning - Know Enough To Be Dangerous #SearchLoveMachine Learning - Know Enough To Be Dangerous #SearchLove
Machine Learning - Know Enough To Be Dangerous #SearchLove
 
SearchLove San Diego 2019 - Britney Muller - Machine Learning: Know Enough To...
SearchLove San Diego 2019 - Britney Muller - Machine Learning: Know Enough To...SearchLove San Diego 2019 - Britney Muller - Machine Learning: Know Enough To...
SearchLove San Diego 2019 - Britney Muller - Machine Learning: Know Enough To...
 
Ai progress = leaderboards compute data algorithms 20180817 v3
Ai progress = leaderboards compute data algorithms 20180817 v3Ai progress = leaderboards compute data algorithms 20180817 v3
Ai progress = leaderboards compute data algorithms 20180817 v3
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AI
 

More from EmilyJiang23

Master a Cloud Native Standard - MicroProfile.pdf
Master a Cloud Native Standard - MicroProfile.pdfMaster a Cloud Native Standard - MicroProfile.pdf
Master a Cloud Native Standard - MicroProfile.pdf
EmilyJiang23
 
Hybrid Cloud Application Development without vendor lockin
Hybrid Cloud Application Development without vendor lockinHybrid Cloud Application Development without vendor lockin
Hybrid Cloud Application Development without vendor lockin
EmilyJiang23
 
Master a Cloud Native Standard - MicroProfile.pptx
Master a Cloud Native Standard - MicroProfile.pptxMaster a Cloud Native Standard - MicroProfile.pptx
Master a Cloud Native Standard - MicroProfile.pptx
EmilyJiang23
 
OpenCloudNative-BeJUG.pptx
OpenCloudNative-BeJUG.pptxOpenCloudNative-BeJUG.pptx
OpenCloudNative-BeJUG.pptx
EmilyJiang23
 
JakartaData-JCon.pptx
JakartaData-JCon.pptxJakartaData-JCon.pptx
JakartaData-JCon.pptx
EmilyJiang23
 
WillMicroserviceDie.pdf
WillMicroserviceDie.pdfWillMicroserviceDie.pdf
WillMicroserviceDie.pdf
EmilyJiang23
 

More from EmilyJiang23 (6)

Master a Cloud Native Standard - MicroProfile.pdf
Master a Cloud Native Standard - MicroProfile.pdfMaster a Cloud Native Standard - MicroProfile.pdf
Master a Cloud Native Standard - MicroProfile.pdf
 
Hybrid Cloud Application Development without vendor lockin
Hybrid Cloud Application Development without vendor lockinHybrid Cloud Application Development without vendor lockin
Hybrid Cloud Application Development without vendor lockin
 
Master a Cloud Native Standard - MicroProfile.pptx
Master a Cloud Native Standard - MicroProfile.pptxMaster a Cloud Native Standard - MicroProfile.pptx
Master a Cloud Native Standard - MicroProfile.pptx
 
OpenCloudNative-BeJUG.pptx
OpenCloudNative-BeJUG.pptxOpenCloudNative-BeJUG.pptx
OpenCloudNative-BeJUG.pptx
 
JakartaData-JCon.pptx
JakartaData-JCon.pptxJakartaData-JCon.pptx
JakartaData-JCon.pptx
 
WillMicroserviceDie.pdf
WillMicroserviceDie.pdfWillMicroserviceDie.pdf
WillMicroserviceDie.pdf
 

Recently uploaded

WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
Luigi Fugaro
 
Going AOT: Everything you need to know about GraalVM for Java applications
Going AOT: Everything you need to know about GraalVM for Java applicationsGoing AOT: Everything you need to know about GraalVM for Java applications
Going AOT: Everything you need to know about GraalVM for Java applications
Alina Yurenko
 
🏎️Tech Transformation: DevOps Insights from the Experts 👩‍💻
🏎️Tech Transformation: DevOps Insights from the Experts 👩‍💻🏎️Tech Transformation: DevOps Insights from the Experts 👩‍💻
🏎️Tech Transformation: DevOps Insights from the Experts 👩‍💻
campbellclarkson
 
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
kgyxske
 
Microsoft-Power-Platform-Adoption-Planning.pptx
Microsoft-Power-Platform-Adoption-Planning.pptxMicrosoft-Power-Platform-Adoption-Planning.pptx
Microsoft-Power-Platform-Adoption-Planning.pptx
jrodriguezq3110
 
Superpower Your Apache Kafka Applications Development with Complementary Open...
Superpower Your Apache Kafka Applications Development with Complementary Open...Superpower Your Apache Kafka Applications Development with Complementary Open...
Superpower Your Apache Kafka Applications Development with Complementary Open...
Paul Brebner
 
Building API data products on top of your real-time data infrastructure
Building API data products on top of your real-time data infrastructureBuilding API data products on top of your real-time data infrastructure
Building API data products on top of your real-time data infrastructure
confluent
 
一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理
dakas1
 
ppt on the brain chip neuralink.pptx
ppt  on   the brain  chip neuralink.pptxppt  on   the brain  chip neuralink.pptx
ppt on the brain chip neuralink.pptx
Reetu63
 
The Power of Visual Regression Testing_ Why It Is Critical for Enterprise App...
The Power of Visual Regression Testing_ Why It Is Critical for Enterprise App...The Power of Visual Regression Testing_ Why It Is Critical for Enterprise App...
The Power of Visual Regression Testing_ Why It Is Critical for Enterprise App...
kalichargn70th171
 
Ensuring Efficiency and Speed with Practical Solutions for Clinical Operations
Ensuring Efficiency and Speed with Practical Solutions for Clinical OperationsEnsuring Efficiency and Speed with Practical Solutions for Clinical Operations
Ensuring Efficiency and Speed with Practical Solutions for Clinical Operations
OnePlan Solutions
 
14 th Edition of International conference on computer vision
14 th Edition of International conference on computer vision14 th Edition of International conference on computer vision
14 th Edition of International conference on computer vision
ShulagnaSarkar2
 
Cost-Effective Strategies For iOS App Development
Cost-Effective Strategies For iOS App DevelopmentCost-Effective Strategies For iOS App Development
Cost-Effective Strategies For iOS App Development
Softradix Technologies
 
Flutter vs. React Native: A Detailed Comparison for App Development in 2024
Flutter vs. React Native: A Detailed Comparison for App Development in 2024Flutter vs. React Native: A Detailed Comparison for App Development in 2024
Flutter vs. React Native: A Detailed Comparison for App Development in 2024
dhavalvaghelanectarb
 
Modelling Up - DDDEurope 2024 - Amsterdam
Modelling Up - DDDEurope 2024 - AmsterdamModelling Up - DDDEurope 2024 - Amsterdam
Modelling Up - DDDEurope 2024 - Amsterdam
Alberto Brandolini
 
一比一原版(UMN毕业证)明尼苏达大学毕业证如何办理
一比一原版(UMN毕业证)明尼苏达大学毕业证如何办理一比一原版(UMN毕业证)明尼苏达大学毕业证如何办理
一比一原版(UMN毕业证)明尼苏达大学毕业证如何办理
dakas1
 
42 Ways to Generate Real Estate Leads - Sellxpert
42 Ways to Generate Real Estate Leads - Sellxpert42 Ways to Generate Real Estate Leads - Sellxpert
42 Ways to Generate Real Estate Leads - Sellxpert
vaishalijagtap12
 
Beginner's Guide to Observability@Devoxx PL 2024
Beginner's  Guide to Observability@Devoxx PL 2024Beginner's  Guide to Observability@Devoxx PL 2024
Beginner's Guide to Observability@Devoxx PL 2024
michniczscribd
 
All you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVMAll you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVM
Alina Yurenko
 
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSISDECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
Tier1 app
 

Recently uploaded (20)

WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
 
Going AOT: Everything you need to know about GraalVM for Java applications
Going AOT: Everything you need to know about GraalVM for Java applicationsGoing AOT: Everything you need to know about GraalVM for Java applications
Going AOT: Everything you need to know about GraalVM for Java applications
 
🏎️Tech Transformation: DevOps Insights from the Experts 👩‍💻
🏎️Tech Transformation: DevOps Insights from the Experts 👩‍💻🏎️Tech Transformation: DevOps Insights from the Experts 👩‍💻
🏎️Tech Transformation: DevOps Insights from the Experts 👩‍💻
 
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
 
Microsoft-Power-Platform-Adoption-Planning.pptx
Microsoft-Power-Platform-Adoption-Planning.pptxMicrosoft-Power-Platform-Adoption-Planning.pptx
Microsoft-Power-Platform-Adoption-Planning.pptx
 
Superpower Your Apache Kafka Applications Development with Complementary Open...
Superpower Your Apache Kafka Applications Development with Complementary Open...Superpower Your Apache Kafka Applications Development with Complementary Open...
Superpower Your Apache Kafka Applications Development with Complementary Open...
 
Building API data products on top of your real-time data infrastructure
Building API data products on top of your real-time data infrastructureBuilding API data products on top of your real-time data infrastructure
Building API data products on top of your real-time data infrastructure
 
一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理
 
ppt on the brain chip neuralink.pptx
ppt  on   the brain  chip neuralink.pptxppt  on   the brain  chip neuralink.pptx
ppt on the brain chip neuralink.pptx
 
The Power of Visual Regression Testing_ Why It Is Critical for Enterprise App...
The Power of Visual Regression Testing_ Why It Is Critical for Enterprise App...The Power of Visual Regression Testing_ Why It Is Critical for Enterprise App...
The Power of Visual Regression Testing_ Why It Is Critical for Enterprise App...
 
Ensuring Efficiency and Speed with Practical Solutions for Clinical Operations
Ensuring Efficiency and Speed with Practical Solutions for Clinical OperationsEnsuring Efficiency and Speed with Practical Solutions for Clinical Operations
Ensuring Efficiency and Speed with Practical Solutions for Clinical Operations
 
14 th Edition of International conference on computer vision
14 th Edition of International conference on computer vision14 th Edition of International conference on computer vision
14 th Edition of International conference on computer vision
 
Cost-Effective Strategies For iOS App Development
Cost-Effective Strategies For iOS App DevelopmentCost-Effective Strategies For iOS App Development
Cost-Effective Strategies For iOS App Development
 
Flutter vs. React Native: A Detailed Comparison for App Development in 2024
Flutter vs. React Native: A Detailed Comparison for App Development in 2024Flutter vs. React Native: A Detailed Comparison for App Development in 2024
Flutter vs. React Native: A Detailed Comparison for App Development in 2024
 
Modelling Up - DDDEurope 2024 - Amsterdam
Modelling Up - DDDEurope 2024 - AmsterdamModelling Up - DDDEurope 2024 - Amsterdam
Modelling Up - DDDEurope 2024 - Amsterdam
 
一比一原版(UMN毕业证)明尼苏达大学毕业证如何办理
一比一原版(UMN毕业证)明尼苏达大学毕业证如何办理一比一原版(UMN毕业证)明尼苏达大学毕业证如何办理
一比一原版(UMN毕业证)明尼苏达大学毕业证如何办理
 
42 Ways to Generate Real Estate Leads - Sellxpert
42 Ways to Generate Real Estate Leads - Sellxpert42 Ways to Generate Real Estate Leads - Sellxpert
42 Ways to Generate Real Estate Leads - Sellxpert
 
Beginner's Guide to Observability@Devoxx PL 2024
Beginner's  Guide to Observability@Devoxx PL 2024Beginner's  Guide to Observability@Devoxx PL 2024
Beginner's Guide to Observability@Devoxx PL 2024
 
All you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVMAll you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVM
 
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSISDECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
 

What need to be mastered as AI-Powered Java Developers

  • 1. Emily Jiang, Java Champion, FBCS IBM, STSM, Cloud Native Architect and Advocate 16th May 2024 AI-Powered Java Developers
  • 2. 2 Java Developers – You Build It, You Run It – Dev and Ops together – IDE – Build (Jenkins, Containers) – Deploy (CI/CD) – Maintain (SBOM, Vulnerabilities)
  • 3. 3 What can Improve Developer Experience?
  • 5. 5 Java Developers need to be AI- Powered!!!
  • 6. AI-Powered Java Developer Checklist 1. What is AI, LLM? 2. What is RAG? 3. What code assistant tools available? 4. What can help with building AI-Infused apps?
  • 7. AI Artificial intelligence (AI) is the simulation of human intelligence in machines that are programmed to think and act like humans. Learning, reasoning, problem-solving, perception, and language comprehension are all examples of cognitive abilities.
  • 8. AI History 1956 John McCarthy held a workshop at Dartmouth on “artificial intelligence” 1957-1974 AI flourished 2011 IBM Watson won the game Jeopardy! Apple released Siri, the first popular virtual assistant. 2015 OpenAI founded 2020, OpenAI announced GPT-3 2021, OpenAI introduced DALL-E 1950 Alan Turing “Computing Machinery and Intelligence” 1997 IBM Deep Blue beat the world chess champion, Gary Kasparov. 8 – https://www.youtube.com/watch?v=056v4OxKwlI
  • 9. GenAI Generative AI (GenAI) refers to deep-learning models that can generate high-quality text, images, and other content based on the data they were trained on. – https://research.ibm.com/blog/what-is-generative-AI
  • 10. Generative AI Anything that creates new content Large language model Great at text Foundation model Unlabeled data Transformer ChatGPT inspired interest… But there is a bigger concept, e.g. GPT Which will change business Building blocks of generative AI – Foundation Models – BERT – GPT – Claude – Cohere – Stable Diffusion
  • 12. 12 What is LLM? LLM =Data + Architecture + Training specialized in Texts
  • 13. Foundation Models Foundation Model AI system Applications LaMDA (Google) Bard (Google) AI chat GPT-4 (OpenAI) ChatGPT (OpenAI) AI Chat Codex (OpenAI) GitHub copilot (Microsoft) Code generation AudioLM (Google) MusicLM (Google) Create Music BLOOM (Hugging Face) Use directly Mutiple NLP tasks. Trained in 46 languages and 13 programming languages. LLaMA (Meta) Use directly AI research DALL-E 2 (OpenAI) Use directly Image creation – https://www.datacamp.com/blog/what-are-foundation-models
  • 15. Comparison of LLMs – https://research.ibm.com/blog/granite-code-models-open-source
  • 16. Chat Q&A Summarization Summarize info – meeting minutes, etc Content Generation Create email, marketing materials, etc. Named Entity Recognition Produce audit data Insight Extraction Medical diagnose, etc. Classification Sort customer complainants, security vulnerability classification, etc. The most common generative AI tasks implemented today
  • 17. Issues related to AI • License • Audit • Hallucinations • Potentially generate bad code • Security risk • Lack of innovation 17
  • 18. How to reduce LLM Hallucination • Domain knowledge gaps • Data out of date
  • 20. Retrieval Augmented generation (RAG) An AI framework for improving the quality of LLM-generated responses Grounds a model on additional sources of knowledge to supplement its internal representation of information 33 RAG involves three basic steps: Search for relevant content in your knowledge base Pull the most relevant content into your model prompt as context Send the combined prompt text to the model to generate output 1 2 3 Significantly elevates level of trust: • Ensures that the model has access to the most current and reliable facts • System becomes "business-aware" • Sources are known, ensuring output can be checked for accuracy • Less likely to make-up a factually inaccurate responses, with ability to say, "I don't know."
  • 21. RAG components Knowledge Base Can be any collection of information containing artifacts such as: • Internal procedural wiki pages • Files in GitHub (various formats) • Messages in a collaboration tool • Topics in product documentation • PDF files • Customer support tickets • more Can be any combination of search and content tools that reliably return relevant content from a knowledge base (or bases): • Search and content APIs like GitHub APIs • Vector databases like Milvus A generative LLM that suits your use case, prompt format, and content being pulled in for context Retriever Generator
  • 22. Typical RAG process User Question Search & Retrieval Prompt = Instructions + Search Results + Question LLM Generated output with sources Top search results
  • 23. Data storage – using embedding and a vector database Passages of text “Embeddings” New step Data storage process (a) Original files to documents (b) Documents to chunks (c) Chunks to embeddings (d) Embeddings to vector store Vector database Semantic vs. Syntactic match
  • 24. Tasks AI will do for us • Generate code snippet • Create tests • Debugging • Code review • Code summarization • Refactoring 24
  • 25. Some GenAI tools Chatbot – Anthropic’s Claude 2 – Google’s Bard – Meta AI’s Hugging Face Llama 2 Chat – Microsoft’s Bing Chat – OpenAI’s ChatGPT AI code assistant Github Copilot Amazon CodeWisperer Divi AI Tabnine Replit Sourcegraphy Cody 25 – https://www.elegantthemes.com/blog/wordpress/best-ai-coding-assistant#4-tabnine – https://www.youtube.com/watch?v=TXtnFw9eDmM
  • 27. 27 Using LangChain4J to simplify integrating with AI/LLM capabilities into Java applications
  • 29. LangChain4J example 29 – https://github.com/langchain4j/langchain4j-examples/tree/main/jakartaee-microprofile-example – https://openliberty.io/blog/2024/04/01/open-liberty-with-langchain4j-example.html
  • 30. AI-Powered Java Developer Checklist 1. What is AI, LLM? √ 2. What is RAG? √ 3. What code assistant tools available? √ 4. What can help with building AI-Infused apps? √
  • 31. 31 Join MicroProfile AI group to create a MicroProfile AI Spec Monday weekly meeting 5pm CEST Zoom: https://eclipse.zoom.us/j/83815795087
  • 32. Crucial skills for Java Developers • Focus on the architecture • Innovation • Serviceability • AI-infused apps 32
  • 34. 34 Thank You Emily Jiang IBM, Cloud Native Architect and Advocate emijiang@uk.ibm.com X/LinkedIn: @emilyfhjiang