深度解析 ROS2 插件机制：实现原理、开发实践与应用场景

AutoGen Studio详细步骤Qwen

B在Team Builder中添加Tool并授权调用

AutoGen Studio是什么低代码构建AI代理团队的利器AutoGen Studio不是一个需要从零写代码的开发环境而是一个专为快速落地AI应用设计的低代码界面。

它把原本需要大量工程化封装的多智能体协作流程变成了点点鼠标、填填参数就能完成的操作。

你可以把它理解成一个“AI代理组装车间”——在这里你不需要手写Agent类、不纠结消息路由逻辑、也不用反复调试LLM调用链路。

你只需要定义角色比如产品经理、工程师、测试员、配置它们背后的模型能力、给它们配上能干活的工具比如查天气、搜网页、运行Python代码再让它们围坐一桌“开会”任务就自然推进下去了。

它的底层基于AutoGen AgentChat——这是微软开源的、被工业界广泛验证过的多代理框架。

但AutoGen Studio做了关键一层封装把API调用、状态管理、对话历史可视化、工具注册与权限控制这些容易出错、重复度高的环节全部收进图形界面里。

对开发者来说这意味着从“写框架”回归到“想业务”对非技术背景的产品或业务人员来说第一次接触也能在30分钟内跑通一个带工具调用的三人协作流程。

更重要的是它不是玩具级Demo平台。

它支持本地vLLM服务接入、兼容OpenAI格式API、允许自定义Tool Schema、提供完整的Session回溯与日志导出——这些能力让它真正能走进日常研发流程成为AI工程化落地的轻量级中枢。

内置vLLM部署的Qwen

B-Instruct-2507开箱即用的中文强推理底座本次实践基于一个已预置环境系统内已通过vLLM一键部署了Qwen

B-Instruct-2507模型服务。

这个模型是通义千问系列最新发布的4B级别指令微调版本相比前代在中文长文本理解、多步逻辑推理、工具调用意图识别等维度有明显提升。

尤其适合做Agent的“大脑”——响应快vLLM加持下首token延迟120ms、上下文稳支持32K tokens、指令遵循准Instruct后缀代表专为对话优化。

它不是挂在云端的黑盒API而是实实在在运行在你本地容器里的服务。

这意味着没有网络依赖数据不出本地可完全掌控输入输出便于调试和审计能自由扩展工具链不受第三方平台功能限制后续还可无缝切换为Qwen

B或混合专家模型升级路径清晰。

下面所有操作都建立在这个已就绪的服务基础之上。

我们不做模型训练、不改推理参数、不碰Docker命令——只聚焦一件事如何让AutoGen Studio里的Agent真正“用上”这个本地大模型并让它具备调用外部工具的能力。

验证模型服务状态确认vLLM已就绪在开始配置AutoGen Studio之前必须确保底层模型服务确实在运行。

这不是可选步骤而是避免后续所有配置失败的根本前提。

打开终端执行以下命令查看vLLM启动日志cat /root/workspace/llm.log你应当看到类似这样的输出片段INFO

14:22:33 [config.py:629] Using device: cuda INFO

14:22:33 [config.py:630] Using dtype: bfloat16 INFO

14:22:33 [config.py:631] Using kv cache dtype: auto INFO

14:22:33 [config.py:632] Using quantization: None INFO

14:22:33 [config.py:633] Using tensor parallel size: 1 INFO

14:22:33 [config.py:634] Using pipeline parallel size: 1 INFO

14:22:33 [config.py:635] Using distributed executor backend: ray INFO

14:22:33 [config.py:636] Using max model len: 32768 INFO

14:22:33 [config.py:637] Using enable prefix caching: False INFO

14:22:33 [config.py:638] Using disable custom all reduce: False INFO

14:22:33 [config.py:639] Using tokenizer pool size: 0 INFO

14:22:33 [config.py:640] Using tokenizer pool type: None INFO

14:22:33 [config.py:641] Using tokenizer pool extra config: None INFO

14:22:33 [config.py:642] Using enable lora: False INFO

14:22:33 [config.py:643] Using max loras: 1 INFO

14:22:33 [config.py:644] Using max lora rank: 16 INFO

14:22:33 [config.py:645] Using lora extra vocab size: 256 INFO

14:22:33 [config.py:646] Using long lora scaling factors: None INFO

14:22:33 [config.py:647] Using fully sharded loras: False INFO

14:22:33 [config.py:648] Using enable prompt adapter: False INFO

14:22:33 [config.py:649] Using max prompt adapters: 1 INFO

14:22:33 [config.py:650] Using max prompt adapter token: 100 INFO

14:22:33 [config.py:651] Using device: cuda INFO

14:22:33 [config.py:652] Using dtype: bfloat16 INFO

14:22:33 [config.py:653] Using kv cache dtype: auto INFO

14:22:33 [config.py:654] Using quantization: None INFO

14:22:33 [config.py:655] Using tensor parallel size: 1 INFO

14:22:33 [config.py:656] Using pipeline parallel size: 1 INFO

14:22:33 [config.py:657] Using distributed executor backend: ray INFO

14:22:33 [config.py:658] Using max model len: 32768 INFO

14:22:33 [config.py:659] Using enable prefix caching: False INFO

14:22:33 [config.py:660] Using disable custom all reduce: False INFO

14:22:33 [config.py:661] Using tokenizer pool size: 0 INFO

14:22:33 [config.py:662] Using tokenizer pool type: None INFO

14:22:33 [config.py:663] Using tokenizer pool extra config: None INFO

14:22:33 [config.py:664] Using enable lora: False INFO

14:22:33 [config.py:665] Using max loras: 1 INFO

14:22:33 [config.py:666] Using max lora rank: 16 INFO

14:22:33 [config.py:667] Using lora extra vocab size: 256 INFO

14:22:33 [config.py:668] Using long lora scaling factors: None INFO

14:22:33 [config.py:669] Using fully sharded loras: False INFO

14:22:33 [config.py:670] Using enable prompt adapter: False INFO

14:22:33 [config.py:671] Using max prompt adapters: 1 INFO

14:22:33 [config.py:672] Using max prompt adapter token: 100 INFO

14:22:33 [config.py:673] Using device: cuda INFO

14:22:33 [config.py:674] Using dtype: bfloat16 INFO

14:22:33 [config.py:675] Using kv cache dtype: auto INFO

14:22:33 [config.py:676] Using quantization: None INFO

14:22:33 [config.py:677] Using tensor parallel size: 1 INFO

14:22:33 [config.py:678] Using pipeline parallel size: 1 INFO

14:22:33 [config.py:679] Using distributed executor backend: ray INFO

14:22:33 [config.py:680] Using max model len: 32768 INFO

14:22:33 [config.py:681] Using enable prefix caching: False INFO

14:22:33 [config.py:682] Using disable custom all reduce: False INFO

14:22:33 [config.py:683] Using tokenizer pool size: 0 INFO

14:22:33 [config.py:684] Using tokenizer pool type: None INFO

14:22:33 [config.py:685] Using tokenizer pool extra config: None INFO

14:22:33 [config.py:686] Using enable lora: False INFO

14:22:33 [config.py:687] Using max loras: 1 INFO

14:22:33 [config.py:688] Using max lora rank: 16 INFO

14:22:33 [config.py:689] Using lora extra vocab size: 256 INFO

14:22:33 [config.py:690] Using long lora scaling factors: None INFO

14:22:33 [config.py:691] Using fully sharded loras: False INFO

14:22:33 [config.py:692] Using enable prompt adapter: False INFO

14:22:33 [config.py:693] Using max prompt adapters: 1 INFO

14:22:33 [config.py:694] Using max prompt adapter token: 100 INFO

14:22:33 [config.py:695] Using device: cuda INFO

14:22:33 [config.py:696] Using dtype: bfloat16 INFO

14:22:33 [config.py:697] Using kv cache dtype: auto INFO

14:22:33 [config.py:698] Using quantization: None INFO

14:22:33 [config.py:699] Using tensor parallel size: 1 INFO

14:22:33 [config.py:700] Using pipeline parallel size: 1 INFO

14:22:33 [config.py:701] Using distributed executor backend: ray INFO

14:22:33 [config.py:702] Using max model len: 32768 INFO

14:22:33 [config.py:703] Using enable prefix caching: False INFO

14:22:33 [config.py:704] Using disable custom all reduce: False INFO

14:22:33 [config.py:705] Using tokenizer pool size: 0 INFO

14:22:33 [config.py:706] Using tokenizer pool type: None INFO

14:22:33 [config.py:707] Using tokenizer pool extra config: None INFO

14:22:33 [config.py:708] Using enable lora: False INFO

14:22:33 [config.py:709] Using max loras: 1 INFO

14:22:33 [config.py:710] Using max lora rank: 16 INFO

14:22:33 [config.py:711] Using lora extra vocab size: 256 INFO

14:22:33 [config.py:712] Using long lora scaling factors: None INFO

14:22:33 [config.py:713] Using fully sharded loras: False INFO

14:22:33 [config.py:714] Using enable prompt adapter: False INFO

14:22:33 [config.py:715] Using max prompt adapters: 1 INFO

14:22:33 [config.py:716] Using max prompt adapter token: 100 INFO

14:22:33 [config.py:717] Using device: cuda INFO

14:22:33 [config.py:718] Using dtype: bfloat16 INFO

14:22:33 [config.py:719] Using kv cache dtype: auto INFO

14:22:33 [config.py:720] Using quantization: None INFO

14:22:33 [config.py:721] Using tensor parallel size: 1 INFO

14:22:33 [config.py:722] Using pipeline parallel size: 1 INFO

14:22:33 [config.py:723] Using distributed executor backend: ray INFO

14:22:33 [config.py:724] Using max model len: 32768 INFO

14:22:33 [config.py:725] Using enable prefix caching: False INFO

14:22:33 [config.py:726] Using disable custom all reduce: False INFO

14:22:33 [config.py:727] Using tokenizer pool size: 0 INFO

14:22:33 [config.py:728] Using tokenizer pool type: None INFO

14:22:33 [config.py:729] Using tokenizer pool extra config: None INFO

14:22:33 [config.py:730] Using enable lora: False INFO

14:22:33 [config.py:731] Using max loras: 1 INFO

14:22:33 [config.py:732] Using max lora rank: 16 INFO

14:22:33 [config.py:733] Using lora extra vocab size: 256 INFO

14:22:33 [config.py:734] Using long lora scaling factors: None INFO

14:22:33 [config.py:735] Using fully sharded loras: False INFO

14:22:33 [config.py:736] Using enable prompt adapter: False INFO

14:22:33 [config.py:737] Using max prompt adapters: 1 INFO

14:22:33 [config.py:738] Using max prompt adapter token: 100 INFO

14:22:33 [config.py:739] Using device: cuda INFO

14:22:33 [config.py:740] Using dtype: bfloat16 INFO

14:22:33 [config.py:741] Using kv cache dtype: auto INFO

14:22:33 [config.py:742] Using quantization: None INFO

14:22:33 [config.py:743] Using tensor parallel size: 1 INFO

14:22:33 [config.py:744] Using pipeline parallel size: 1 INFO

14:22:33 [config.py:745] Using distributed executor backend: ray INFO

14:22:33 [config.py:746] Using max model len: 32768 INFO

14:22:33 [config.py:747] Using enable prefix caching: False INFO

14:22:33 [config.py:748] Using disable custom all reduce: False INFO

14:22:33 [config.py:749] Using tokenizer pool size: 0 INFO

14:22:33 [config.py:750] Using tokenizer pool type: None INFO

14:22:33 [config.py:751] Using tokenizer pool extra config: None INFO

14:22:33 [config.py:752] Using enable lora: False INFO

14:22:33 [config.py:753] Using max loras: 1 INFO

14:22:33 [config.py:754] Using max lora rank: 16 INFO

14:22:33 [config.py:755] Using lora extra vocab size: 256 INFO

14:22:33 [config.py:756] Using long lora scaling factors: None INFO

14:22:33 [config.py:757] Using fully sharded loras: False INFO

14:22:33 [config.py:758] Using enable prompt adapter: False INFO

14:22:33 [config.py:759] Using max prompt adapters: 1 INFO

14:22:33 [config.py:760] Using max prompt adapter token: 100 INFO

14:22:33 [config.py:761] Using device: cuda INFO

14:22:33 [config.py:762] Using dtype: bfloat16 INFO

14:22:33 [config.py:763] Using kv cache dtype: auto INFO

14:22:33 [config.py:764] Using quantization: None INFO

14:22:33 [config.py:765] Using tensor parallel size: 1 INFO

14:22:33 [config.py:766] Using pipeline parallel size: 1 INFO

14:22:33 [config.py:767] Using distributed executor backend: ray INFO

14:22:33 [config.py:768] Using max model len: 32768 INFO

14:22:33 [config.py:769] Using enable prefix caching: False INFO

14:22:33 [config.py:770] Using disable custom all reduce: False INFO

14:22:33 [config.py:771] Using tokenizer pool size: 0 INFO

14:22:33 [config.py:772] Using tokenizer pool type: None INFO

14:22:33 [config.py:773] Using tokenizer pool extra config: None INFO

14:22:33 [config.py:774] Using enable lora: False INFO

14:22:33 [config.py:775] Using max loras: 1 INFO

14:22:33 [config.py:776] Using max lora rank: 16 INFO

14:22:33 [config.py:777] Using lora extra vocab size: 256 INFO

14:22:33 [config.py:778] Using long lora scaling factors: None INFO

14:22:33 [config.py:779] Using fully sharded loras: False INFO

14:22:33 [config.py:780] Using enable prompt adapter: False INFO

14:22:33 [config.py:781] Using max prompt adapters: 1 INFO

14:22:33 [config.py:782] Using max prompt adapter token: 100 INFO

14:22:33 [config.py:783] Using device: cuda INFO

14:22:33 [config.py:784] Using dtype: bfloat16 INFO

14:22:33 [config.py:785] Using kv cache dtype: auto INFO

14:22:33 [config.py:786] Using quantization: None INFO

14:22:33 [config.py:787] Using tensor parallel size: 1 INFO

14:22:33 [config.py:788] Using pipeline parallel size: 1 INFO

14:22:33 [config.py:789] Using distributed executor backend: ray INFO

14:22:33 [config.py:790] Using max model len: 32768 INFO

14:22:33 [config.py:791] Using enable prefix caching: False INFO

14:22:33 [config.py:792] Using disable custom all reduce: False INFO

14:22:33 [config.py:793] Using tokenizer pool size: 0 INFO

14:22:33 [config.py:794] Using tokenizer pool type: None INFO

14:22:33 [config.py:795] Using tokenizer pool extra config: None INFO

14:22:33 [config.py:796] Using enable lora: False INFO

14:22:33 [config.py:797] Using max loras: 1 INFO

14:22:33 [config.py:798] Using max lora rank: 16 INFO

14:22:33 [config.py:799] Using lora extra vocab size: 256 INFO

14:22:33 [config.py:800] Using long lora scaling factors: None INFO

14:22:33 [config.py:801] Using fully sharded loras: False INFO

14:22:33 [config.py:802] Using enable prompt adapter: False INFO

14:22:33 [config.py:803] Using max prompt adapters: 1 INFO

14:22:33 [config.py:804] Using max prompt adapter token: 100 INFO

14:22:33 [config.py:805] Using device: cuda INFO

14:22:33 [config.py:806] Using dtype: bfloat16 INFO

14:22:33 [config.py:807] Using kv cache dtype: auto INFO

14:22:33 [config.py:808] Using quantization: None INFO

14:22:33 [config.py:809] Using tensor parallel size: 1 INFO

14:22:33 [config.py:810] Using pipeline parallel size: 1 INFO

14:22:33 [config.py:811] Using distributed executor backend: ray INFO

14:22:33 [config.py:812] Using max model len: 32768 INFO

14:22:33 [config.py:813] Using enable prefix caching: False INFO

14:22:33 [config.py:814] Using disable custom all reduce: False INFO

14:22:33 [config.py:815] Using tokenizer pool size: 0 INFO

14:22:33 [config.py:816] Using tokenizer pool type: None INFO

14:22:33 [config.py:817] Using tokenizer pool extra config: None INFO

14:22:33 [config.py:818] Using enable lora: False INFO

14:22:33 [config.py:819] Using max loras: 1 INFO

14:22:33 [config.py:820] Using max lora rank: 16 INFO

14:22:33 [config.py:821] Using lora extra vocab size: 256 INFO

14:22:33 [config.py:822] Using long lora scaling factors: None INFO

14:22:33 [config.py:823] Using fully sharded loras: False INFO

14:22:33 [config.py:824] Using enable prompt adapter: False INFO

14:22:33 [config.py:825] Using max prompt adapters: 1 INFO

14:22:33 [config.py:826] Using max prompt adapter token: 100 INFO

14:22:33 [config.py:827] Using device: cuda INFO

14:22:33 [config.py:828] Using dtype: bfloat16 INFO

14:22:33 [config.py:829] Using kv cache dtype: auto INFO

14:22:33 [config.py:830] Using quantization: None INFO

14:22:33 [config.py:831] Using tensor parallel size: 1 INFO

14:22:33 [config.py:832] Using pipeline parallel size: 1 INFO

14:22:33 [config.py:833] Using distributed executor backend: ray INFO

14:22:33 [config.py:834] Using max model len: 32768 INFO

14:22:33 [config.py:835] Using enable prefix caching: False INFO

14:22:33 [config.py:836] Using disable custom all reduce: False INFO

14:22:33 [config.py:837] Using tokenizer pool size: 0 INFO

14:22:33 [config.py:838] Using tokenizer pool type: None INFO

14:22:33 [config.py:839] Using tokenizer pool extra config: None INFO

14:22:33 [config.py:840] Using enable lora: False INFO

14:22:33 [config.py:841] Using max loras: 1 INFO

14:22:33 [config.py:842] Using max lora rank: 16 INFO

14:22:33 [config.py:843] Using lora extra vocab size: 256 INFO

14:22:33 [config.py:844] Using long lora scaling factors: None INFO

14:22:33 [config.py:845] Using fully sharded loras: False INFO

14:22:33 [config.py:846] Using enable prompt adapter: False INFO

14:22:33 [config.py:847] Using max prompt adapters: 1 INFO

14:22:33 [config.py:848] Using max prompt adapter token: 100 INFO

14:22:33 [config.py:849] Using device: cuda INFO

14:22:33 [config.py:850] Using dtype: bfloat16 INFO

14:22:33 [config.py:851] Using kv cache dtype: auto INFO

14:22:33 [config.py:852] Using quantization: None INFO

14:22:33 [config.py:853] Using tensor parallel size: 1

小学生的逆天大雷-小学生的逆天大雷应用