Hello, I’m working on a Java Spring Boot based generative AI application. The LLM we’re using is served through our own API, and I’d like to log the spans into Arize Phoenix. Is there any documentation or examples on how to set this up for Java? Any pointers would be super helpful. Thanks!
Yes, you can instrument your Java Spring Boot app to send traces to Arize Phoenix using OpenTelemetry and OpenInference. There are example projects and documentation showing how to configure the OpenTelemetry SDK, set up exporters, and send traces to Phoenix. See the Spring AI Java example and the OpenInference Java SDK guide for step-by-step setup.You’ll need to configure an OTLP exporter in your Java app to point to your Phoenix instance, and instrument your code to create spans for LLM calls. Would you like more detail or a code snippet for this setup?Sources: - Spring AI Java example - OpenInference Java SDK guide
💡 Hint: Mention RunLLM in the thread for followups.
Hey Helee P., we may be missing documentation, but we do have a Java libraries here https://central.sonatype.com/artifact/com.arize/openinference-instrumentation-springAI https://central.sonatype.com/artifact/com.arize/openinference-semantic-conventions
