Temperature scales token probabilities during generation. Lower values make responses more deterministic; higher values make token probabilities more even and responses more random. section 3.4.1
Configuring temperature
Set temperature globally with spring.ai.openai.chat.options.temperature=0.7, or configure ChatOptions programmatically with .temperature(0.7). section 3.4.1
ChatOptions chatOptions = ChatOptions.builder()
.temperature(0.7)
.build();
Use the ChatOptions listing to apply temperature when constructing generation options. section 3.4.1
