新闻
New in LangSmith: Engine v2, Managed Deep Agents, Fine-Tuning, and more
LangChain · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- LangSmith released Engine v2 with red teaming and automated fix validation, Managed Deep Agents with user-scoped memory and web search, Trajectories for readable session views, Fine-Tuning for open models, and Custom Apps for building interfaces.
- 为何重要
- Engineers building production agents need these tools to detect issues proactively, manage authentication and memory, debug long sessions, optimize model costs, and customize workflows.
- 注意
- Self-hosted LangSmith BYOK support for Engine comes in a future release. Fine-tuning quality depends on trajectory data quality. Custom Apps require building against LangSmith APIs.
- agent
- fine-tun
- red team
还有谁报道了
- Introducing LangSmith Fine-TuningLangChain
- New in LangSmith Engine: red teaming and automated testingLangChain
- Fine-tune on your LangSmith traces with Baseten LoopsBaseten
同一件事，来自我们关注的其他媒体。
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。