Cloud Lunch and Learn -Microsoft Semantic Kernel for Java
0 likes47 views
Cloud Lunch and Learn -Microsoft Semantic Kernel for Java
More Related Content
More from Juarez Junior (20)
Recently uploaded (20)
![Windows 8.1 Pro Activator Crack Version [April-2025]](https://cdn.slidesharecdn.com/ss_thumbnails/lecture9-250228130043-bd676d0e-250401141425-60508047-250401150607-9cd2b2bd-thumbnail.jpg?width=560&fit=bounds)
Cloud Lunch and Learn -Microsoft Semantic Kernel for Java
- 1. An Introduction to Semantic Kernel for Java CLOUD LUNCH AND LEARN 2024 Juarez Barbosa Junior @juarezjunior Senior Principal Java Developer Evangelist ORACLE Copyright 息 2024, Oracle and/or its affiliates
- 2. Juarez Barbosa Junior Senior Principal Java Developer Evangelist @ Oracle Coming from Dublin, Ireland 29 years of experience in SW Engineering & DevRel Oracle, Microsoft, IBM, Nokia, Unisys, Accenture, startups Microsoft Azure Developer Relations Lead IBM Watson Tech Evangelist & Cloud Rockstar IBM Mobile Tech Evangelist & Global Thought Leader Nokia Developers Global Champion Java, Python, Cloud, DevOps, SRE, Cloud-native, IoT, AI, Blockchain, Rust Speaker at conferences Oracle CloudWorld, Oracle Code, Microsoft Ignite & TechX, jPrime, JCON, DevConf.cz, GeeCon, DevOpsDays, DeveloperWeek, DevOps Institute, CloudLand, DWX, The Developers Conference (TDC), Sec4Dev, JSNation, NodeConf, Conf42, Shift Conf, Global Azure, Open-Source Lisbon, CodeFrenzy, M棚l辿e Num辿rique, React Summit, Test.js Summit, Porto TechHub Conf, Pyjamas, MiTechCon, Data Science Summit, OpenSourceNorth, WeAreDevelopers, Global Software Architecture Summit, JavaCro, Compass AI Session, I Love Tech, DeVTalks, BuildStuff, JUGs, OUGs, GDGs, meetups, hackathons, and customer engagements. @juarezjunior @juarezjunior
- 3. Agenda AI and GenAI Synthetic Content Artificial Intelligence and GenAI OpenAI AI - Microsoft Semantic Kernel Demo Semantic Kernel for Java Oracle for Java / Database Developers Technical References Audience: Its an intro for business / technical audiences - not necessarily ML / DL Engineers Copyright 息 2024, Oracle and/or its affiliates
- 4. AI and GenAI Synthetic Content Dublin in Ireland pictured in a futuristic cityscape Copyright 息 2024, Oracle and/or its affiliates
- 5. Artificial Intelligence and GenAI Core concepts in a nutshell GenAI - Artificial intelligence algorithms and transformer models with the capability of generating content. Content - Text, images, videos, code, and others. Generation a result of an input prompt (prompt engineering). Ethical issues misuse, deep fakes, bias and discrimination, automation and job replacements, cybersecurity and cybercriminals. Copyright 息 2024, Oracle and/or its affiliates
- 6. Artificial Intelligence and GenAI Core concepts in a nutshell Apps Applied currently in the fields of content development, entertainment, drug discovery, software development, healthcare, material generation sciences, and others. AI is now a commodity! Artificial General Intelligence (AGI) Research ultimate goal Copyright 息 2024, Oracle and/or its affiliates
- 7. OpenAI Generative AI with OpenAI Natural Language Processing (NLP) Powerful, pre-trained and customizable Machine Learning Models OpenAI API (REST interface) Scalable infrastructure (GPUs) https://openai.com/sora Copyright 息 2024, Oracle and/or its affiliates
- 8. Lets talk about AI aka.ms/semantic-kernel 8 Check out the resources here to learn about the latest on AI at Microsoft. You dream it. AI helps build it. Microsoft is empowering the world to achieve more with AI and its copilot ecosystem.
- 9. Modernized & augmented flagship products with copilot aka.ms/semantic-kernel 9 AI-based search with Microsoft Copilot Biometric identity verification Personalized recommendations Copilot for Work across Office 365 Copilot assisted coding
- 10. S E M A N T I C K E R N E L / Microsoft confidential At the center of it all is Semantic Kernel AI orchestration Copilots Plugin extensibility Apps AI infrastructure Foundation models 10
- 11. What is Semantic Kernel? aka.ms/semantic-kernel 11 An open-source SDK that lets you easily build agents that call your existing code. As a highly extensible framework, it can be used with models from OpenAI, Azure OpenAI, Hugging Face, and more! By combining your existing C#, Python, and Java code with these models, you can build agents that answer questions and automate processes. .Net Java Python
- 12. A bridge between LLMs and your code ML RESEARCHER APP DEVELOPER keepingupwith advances cutting edge models e x p e r i m e n t a t i o n stable and performant efficient to deliver e a s i l y s c a l a b l e m a i n t a i n a b l e algorithm analysis Your models Your code Your memories Your prompts
- 13. Plugins & aka.ms/semantic-kernel 13 Planners & Personas These are the core building blocks of Semantic Kernel. By customizing these key components, you can create solutions to suite exactly your needs.
- 14. Plugins aka.ms/semantic-kernel 14 Plugins encapsulate capabilities into a single unit of functionality. When you build a plugin for Semantic Kernel, you can leverage it on other services, like ChatGTP, Bing, and Microsoft 365. Likewise, any plugin built for those services can seamlessly import to Semantic Kernel. Semantic Kernel Your app Plugins Other AI apps
- 15. Semantic or native? aka.ms/semantic-kernel 15 To make a plugin, you'll need to create some functions. These are either semantic or native you decide. Endpoint Semantic Kernel Semantic functions Semantic functions Time plugin
- 16. Planners aka.ms/semantic-kernel 16 A Planner is a function that takes the initial request and returns a list of steps needed to fulfill the request. AI is used to mix-and- match plugins registered in the kernel so it can recombine them into a series of steps. Semantic Kernel Person has a request Plugins Plan
- 17. Handlebars or stepwise? aka.ms/semantic-kernel 17 To make plans, you'll need to define which planner to use. Choose between handlebars or stepwise planner. Handlebars Stepwise Planner
- 18. Personas aka.ms/semantic-kernel 18 Personas are what defines an agent's role, like a set of instructions. They hold their own memories which provide broader context to the requests made. This is what empowers multi-agent systems where specialists are defined to execute requests they were designed to fulfil. Project manager agent Researcher agent Copywriter agent Designer agent
- 19. Managing personas aka.ms/semantic-kernel 19 Through plugins, planners orchestrate agents. Choosing the best agent for the request. Researcher agent Copywriter agent Designer agent Agent orchestrator plugin Project manager agent
- 20. Memories aka.ms/semantic-kernel 20 This is what provides context to the initial request. Memories are fed into Semantic Kernel in a few different ways. Conventional key-value pairs: Just like you would set an environment variable in your shell, the same can be done when using Semantic Kernel. The lookup is "conventional" because it's a one-to-one match between a key and your query. Conventional local-storage: When you save information to a file, it can be retrieved with its filename. When you have a lot of information to store in a key-value pair, you're best off keeping it on disk. Semantic memory search: You can also represent text information as a long vector of numbers, known as "embeddings." This lets you execute a "semantic" search that compares meaning-to-meaning with your query.
- 21. Prompts aka.ms/semantic-kernel 21 This is how you communicate with model. It serves as the input which elicits a response from the model. Selecting the right words, phrases, symbols, and formats that guide the model in generating high- quality and relevant results.
- 22. Demo 22 Oracle DatabaseWorld @ CloudWorld Copyright 息 2023, Oracle and/or its affiliates Semantic Kernel for Java
- 23. oracle.com/developer oracle.com/jdbc 23 Oracle DatabaseWorld @ CloudWorld Copyright 息 2023, Oracle and/or its affiliates Oracle for Java / Database Developers
- 24. New | Oracle Database 23ai Next-Generation Converged Database Services Over 300 major new features plus thousands of enhancements Available on OCI and Azure Major focus on AI for Data features Developer/Analyst features Mission-Critical features Addresses data management pain points that have frustrated customers forever Copyright 息 2024, Oracle and/or its affiliates
- 25. Oracle Database 23ai - AI for Data Algorithmic AI AI Vector Search Augmented Generative AI (LLMs) Distributed AI AI Storage AI Developer Tools Copyright 息 2024, Oracle and/or its affiliates
- 26. Oracle Database 23ai - Dev for Data JSON Relational Duality Views Property Graph Views JavaScript Stored Procedures Data Intent Language Lock-free Consistent Updates, Long-running Transactions True Cache Copyright 息 2024, Oracle and/or its affiliates
- 27. Oracle Database 23ai - Mission-Critical Data RAFT Replication for Globally Distributed Database In-Database Firewall Real-Time SQL Plan Management RAC, Exadata, Data Guard Simplicity and Scalability Analytic SQL Simplicity and Scalability Priority Transactions Copyright 息 2024, Oracle and/or its affiliates
- 28. Free | Oracle Database 23ai For Developers Oracle Always Free ADB Available on OCI ADB Free Container Image Available for download Oracle Database Free Available as RPM, Docker Image, VBox VM Copyright 息 2024, Oracle and/or its affiliates | Confidential - Internal Very Low Cost Supported Developer Edition of ADB, BaseDB, ExaDB-D, and ExaDB-C@C
- 29. Java App Dev with Oracle Database Copyright 息 2024, Oracle and/or its affiliates
- 30. Overview of Oracle DB Access with Java Copyright 息 2024, Oracle and/or its affiliates
- 31. Oracle JDBC - Support for the Latest Java Versions Support to the latest Java versions (11, 17, 21) and GraalVM Project Loom - Virtual Threads support Java Virtual Threads and Pipelined Database Operations JDBC Standards - 4.2 and 4.3 Reactive Streams - Java Flow API support R2DBC, Reactive Streams Ingestion (RSI) Pipelined Database Operations Data access is critical in mission-critical applications! Copyright 息 2024, Oracle and/or its affiliates
- 32. Oracle LiveLabs Showcasing how Oracles solutions can solve your business problems 500+ free workshops, available or in development 3.5 million people have already visited LiveLabs developer.oracle.com/livelabs learn something new at your pace! 600+ events run using LiveLabs workshops
- 33. 3 membership tiers Connect: @oracleace facebook.com/OracleACEs aceprogram_ww@oracle.com 500+ technical experts & community leaders helping peers globally The Oracle ACE Program recognizes & rewards individuals for their technical & community contributions to the Oracle community Nominate yourself or a candidate: ace.oracle.com/nominate Learn more - ace.oracle.com blogs.oracle.com/ace
- 34. Create your FREE Cloud Account Go to https://signup.cloud.oracle.com/ Copyright 息 2024, Oracle and/or its affiliates
- 35. Copyright 息 2024, Oracle and/or its affiliates Technical References Semantic Kernel - https://learn.microsoft.com/en-us/semantic-kernel/overview/ Semantic Kernel for Java 1.4.0 - https://devblogs.microsoft.com/semantic- kernel/announcing-semantic-kernel-for-java-1-4-0/ Java Intelligent Application Templates - https://devblogs.microsoft.com/java/java- intelligent-application-templates-in-the-azure-ai-gallery/ OpenAI - https://openai.com/ Oracle Database 23ai Free - https://www.oracle.com/uk/database/free/get-started/ Retrieval-Augmented Generation (RAG) with Spring AI, Oracle Database 23ai, and OpenAI - https://rb.gy/e1mwt4 LangChain4J - Retrieval-Augmented Generation (RAG) with LangChain4j and the Oracle Database 23ai https://rb.gy/pdmwmz A GenAI Solution with Virtual Threads, JDBC Reactive Extensions, and Pipelined Database Operations - https://rb.gy/jcxvph Java / JDBC https://www.oracle.com/jdbc