Java, LLMs, and Seamless AI Integration with langchain4j, Quarkus and MicroProfile

An airhacks.fm conversation with Ladislav Thon (@ladicek) about: Didaktik Gama to Red Hat, early programming experiences with Basic and Karel, learning Pascal and C in school, working with Java in university and early career, joining Red Hat as a quality engineer for JBoss Enterprise Application Platform, testing clustering and load balancing with SmartFrog, transitioning to WildFly Swarm / Thorntail development, becoming Thorntail project lead, moving to quarkus development, involvement in CDI specification improvements, discussion about portable extensions in CDI, interest in science fiction literature, mention of favorite authors and books including Neal Stephenson's Anathem and The Expanse series Ladislav Thon on github: @ladicek

An airhacks.fm conversation with Alfonso Peterssen (@TheMukel) about: updates on Lama 3 Java project and performance improvements, GraalVM Vector API support and performance enhancements, Espresso's ability to run Java code within GraalVM, implementation of Continuations and serializable continuations in Espresso, development of a debugger for native image using Espresso, potential for adding dynamism to native image, Espresso's use in sandboxing and isolating Java code execution, potential applications in cloud environments and serverless computing, possibility of using Espresso for LLM-generated code execution, potential for Espresso as a replacement for the deprecated SecurityManager, discussion of Espresso's performance compared to full virtualization stacks, class reloading capabilities in Espresso, invitation for future discussions on debugging and Espresso deep dive Alfonso Peterssen on twitter: @TheMukel

An airhacks.fm conversation with Mario Fusco (@mariofusco) about: early programming on ZX Spectrum and Commodore 64, father's computer shop in South Italy, work experiences with Olivetti and IBM, the Olivetti M10 laptop, introduction to Java and aspect-oriented programming, project on advertisement optimization for Berlusconi's company, experience with Scala and presenting at Scala Days, joining Red Hat to work on Drools rule engine, current work on quarkus and langchain4j integration, importance of open source contribution and conference participation for career growth, evolution of programming languages and technologies, thoughts on AI and rule engines, social aspects of software development, importance of community involvement in tech industry Mario Fusco on twitter: @mariofusco

An airhacks.fm conversation with Phillip Krueger (@phillipkruger) about: early programming experiences with Visual Basic and Java, transition from actuarial science to computer science, first job at a bank working with Java Swing and RMI over CORBA, experience with J2EE and XML technologies, working with XML and XSLT, development of open-source Swing components, work on dotMobi sites for mobile phones in Africa, creation of API extensions for Java EE and MicroProfile, involvement in the MicroProfile GraphQL specification, joining Red Hat and working on quarkus, development of SmallRye GraphQL, improvements to OpenAPI support in Quarkus, work on Quarkus Dev UI, discussion about the evolution of Java application servers and frameworks, comparison of REST and GraphQL, thoughts on Java development culture in South Africa Phillip Krueger on twitter: @phillipkruger

An airhacks.fm conversation with Bruce Hopkins about: discussion on using ChatGPT for Java development, challenges and benefits of AI-assisted coding, importance of understanding and reviewing AI-generated code, bootstrapping approach in Bruce's book, using ChatGPT as a pair programmer, limitations of AI in making architectural decisions, potential pitfalls of relying too heavily on AI-generated code, multi-modal capabilities of AI models, creating a podcast visualizer project, integrating with Slack and Discord APIs, hallucination issues in AI responses, importance of prompt engineering, potential for Java in AI and LLM integration, advantages of Java in enterprise environments, energy efficiency and performance of Java compared to other languages, upcoming trends in Java development including project valhalla and Vector API, potential for a follow-up book on quarkus and langchain4j, modern Java syntax and features making it competitive with other languages, challenges of translating technical books to other languages, the ChatGPT for Java book

An airhacks.fm conversation with Christos Kotselidis (@CKotselidis) about: early experiences with computers and programming, transition to studying Java and virtual machines at university, work on Jikes compiler and distributed software transactional memory for PhD, current roles as professor at University of Manchester and working on motorcycle electronics at KTM, overview of tornadovm project for accelerating Java on GPUs and other hardware, discussion of recent Java implementations of LLMs like jlama and llama3 java, potential for TornadoVM to accelerate model inference, challenges around quantized types for large models, integration with Project Panama for improved native interop, importance of performance and energy efficiency for enterprise Java applications, potential for Java Flight Recorder to provide power consumption metrics, need for standardized quantized types in Java, opportunities for Java in AI/ML workloads, invitation for companies to reach out about using Tornado VM for their use cases Christos Kotselidis on twitter: @CKotselidis

An airhacks.fm conversation with Vadym Kazulkin (@VKazulkin) about: journey as a Java developer from the late 1990s to present, early experiences with Java and J2EE development, transition to cloud and serverless technologies, particularly AWS Lambda, discussion of Java performance on lambda compared to node.js, detailed explanation of AWS SnapStart technology for improving Java cold starts, pros and cons of "fat" Lambda functions versus microservices, challenges of using GraalVM with Lambda, importance of optimizing Lambda package size and dependencies, comparison of quarkus and Spring Boot on Lambda, benefits of serverless architecture for business logic focus, involvement with Java User Group Bonn and AWS Community Builder program, brief mention of asynchronous patterns in serverless architectures, importance of staying technically hands-on as a manager in the rapidly evolving cloud world Vadym Kazulkin on twitter: @VKazulkin

An airhacks.fm conversation with Gerald Venzl (@geraldvenzl) about: discussion about the evolution of Oracle's annual conference from OpenWorld to CloudWorld, the JavaOne conference, explanation of JDBC driver types and their evolution, Oracle's thin JDBC driver becoming the preferred option, availability of Oracle JDBC drivers on Maven Central, proprietary features of Oracle's JDBC driver including Continuous Query Notification (CQN) and Application Continuity, comparison of CQN to Change Data Capture (CDC) and CQRS patterns, Oracle's Flashback Data Archive for auditing and time travel capabilities, Oracle's Advanced Queuing and Transactional Event Queues, ORDS REST APIs, Oracle product page, Oracle JDBC client libraries, the plug-in mechanism implemented in early Java versions for JDBC drivers using Class.forName and static initializers, Gerald Venzl's online presence and recent blog post about running Oracle database on Raspberry Pi Gerald Venzl on twitter: @geraldvenzl

An airhacks.fm conversation with Dmytro Liubarsky (@langchain4j) about: discussion on recent developments in Java and LLM integration, new features in langchain4j including Easy RAG for simplified setup, SQL database retrieval with LLM-generated queries, integration with graph databases like Neo4j, Neo4j and graphrag, metadata filtering for improved search capabilities, observability improvements with listeners and potential integration with opentelemetry, increased configurability for AI services enabling state machine-like behavior, the trend towards CPU inference and smaller, more focused models, langchain4j integration with quarkus and MicroProfile, parallels between AI integration and microservices architecture, the importance of decomposing complex AI tasks into smaller, more manageable pieces, potential cost optimization strategies for AI applications, the excitement around creating smooth APIs that integrate well with the Java ecosystem, the potential future of CPU inference and its parallels with the evolution of server infrastructure, the upcoming Devoxx conference, Dmytro Liubarsky on twitter: @langchain4j

An airhacks.fm conversation with Georgios Andrianakis (@geoand86) about: discussion on integrating langchain4j with quarkus for enterprise AI applications, similarities between LLM integration and microservice architecture, benefits of using Java and MicroProfile for AI development, explanation of AI services, chat memory, and tools in LangChain4J, importance of session management and fault tolerance in LLM applications, vector databases and embeddings for efficient information retrieval, RAG (Retrieve Augmented Generation) implementation in enterprise settings, Quarkus dev mode features for LLM experimentation, native image support with GraalVM, local inference possibilities with Java 21's Vector API and quantized models, challenges in prompt engineering and model selection, upcoming features in LangChain4J including Ollama tool support and improved result streaming, future developments in Java for AI and GPU support with Project Babylon, importance of enterprise-grade features like CI/CD, testing, and cloud deployment for LLM applications Georgios Andrianakis on twitter: @geoand86