An <a href="https://airhacks.fm">airhacks.fm</a> conversation with Dimitris Andreadis (<a href="https://twitter.com/dandreadis">@dandreadis</a>) about:
<blockquote>Dimitris appeared previously on <a href="https://airhacks.fm/#episode_64">"#64 Quarkus 1.0 and SpringBoot"</a>,
discussion about integrating AI language models (LLMs) with <a href="https://www.java.com/en/">Java</a> applications using <a href="https://quarkus.io">quarkus</a> and <a href="https://github.com/langchain4j/langchain4j">langchain4j</a>,
<a href="https://www.redhat.com/en/technologies/cloud-computing/openshift/openshift-ai">OpenShift AI</a>,
the benefits of using Quarkus for AI integration,
<a href="https://www.drools.org">Drools</a> and ML,
the potential of using AI for rule engines and decision making,
the challenges of handling state and context with LLMs,
<a href="https://infinispan.org/">InfiniSpan</a> and vector databases,
the role of vector stores and embeddings for semantic search,
the advantages of Java for enterprise applications and maintenance,
the potential of using AI models natively with <a href="https://www.graalvm.org">GraalVM</a>,
the importance of tools functionality for LLMs to call Java methods,
the excitement around AI in the Java community,
the future trajectory of tighter integration between Java and AI models,
the potential of using AI for code generation and intelligent developer tooling</blockquote>
<p> Dimitris Andreadis on twitter: <a href="https://twitter.com/dandreadis">@dandreadis</a></p>
