Ollama本地运行命令ollama run qwen3:4bpom 依赖dependencygroupIdorg.springframework.ai/groupIdartifactIdspring-ai-bom/artifactIdversion${spring-ai.version}/versiontypepom/typescopeimport/scope/dependencydependencygroupIdorg.springframework.ai/groupIdartifactIdspring-ai-starter-model-ollama/artifactId/dependencyyml配置#Ollama配置 spring.ai.ollama.base-urlhttp://localhost:11434spring.ai.ollama.chat.options.modelqwen3:4b # 应用启动时不自动拉取模型如需自动拉取可改为 when_missing spring.ai.ollama.init.pull-model-strategynever测试代码TestpublicvoidtestOllama(AutowiredOllamaChatModelollamaChatModel){PromptpromptnewPrompt(你是谁);ChatResponsecallollamaChatModel.call(prompt);Stringtextcall.getResult().getOutput().getText();System.out.println(-------------- Ollama --------------);System.out.println(text);}TestpublicvoidtestOllamaStream(AutowiredOllamaChatModelollamaChatModel){FluxStringstreamollamaChatModel.stream(你是谁);stream.toStream().forEach(System.out::println);System.out.println(-------------- Ollama --------------);}多层级记忆短期记忆中期记忆长期记忆skill平台https://skillsmp.com/大模型渐进式加载
