LangChain 发布 LangSmith Fine-Tuning，基于 Baseten Loops 微调智能体 traces
Fine-tune on your LangSmith traces with Baseten Loops
LangChain 在纽约 Interrupt 26 大会上发布 LangSmith Fine-Tuning，可把 LangSmith 中的 traces 转成监督微调数据集并在 Baseten Loops 上训练。该功能由开源 CLI smithtune 驱动，它读取 traces、筛选成功运行、训练后经 LangSmith 评估，再由 smithtune deploy 部署到 Baseten Dedicated Inference。训练使用用户自己的 Baseten API key 并在其工作区专用 GPU 上计费，代码位于 github.com/langchain-ai/smithtune，Loops 处于早期访问阶段可能需要先申请开通。
推荐理由
AI 评分 63
原文给出了从 LangSmith traces 到微调数据集再到 Baseten 部署的完整链路，可据此判断自有数据训练智能体的落地路径。
主题
正文
当前显示原文，中文全文译文尚未就绪。
LangChain's applied research team trains the models behind LangSmith Engine on Baseten Loops . They fine-tune an open model on agent traces from LangSmith, and we wrote about that work earlier this month.
That workflow is now open to anyone building on LangSmith. LangChain announced LangSmith Fine-Tuning today at their Interrupt 26 Conference in New York. It runs on smithtune, an open-source CLI you can use yourself or hand to a coding agent.
The CLI reads your LangSmith traces and turns the successful runs into a supervised fine-tuning dataset. Training then runs on Baseten Loops. Once LangSmith has evaluated the new checkpoint, smithtune deploy puts it on a Baseten Dedicated Inference deployment.
With Baseten as the training provider, smithtune trains through the Loops Python SDK on dedicated GPUs in your own Baseten workspace. Checkpoints are saved on Baseten during the run, so deploying one never means downloading weights and uploading them somewhere else.
Before scheduling a run, the CLI checks which models your workspace is enabled to train. This mostly helps when a coding agent is typing the commands. It can see what's available and won't queue a job that can't start.
You use your own Baseten API key, and training and inference bill to your Baseten account.
"LangSmith users have been asking for a way to turn their production traces into models built for their own agents. We gave our agent the smithtune README and the agent skill and let it go. It took us all the way to a model deployed on Baseten, and it was pretty hands off!
Most LangSmith users are already sitting on thousands of traces from their agents, and we wanted training on them to feel about that easy. The Baseten team has worked closely with ours through this launch, and we're excited to give LangSmith users a direct path from their traces to a model running on Baseten." –Vivek Trivedy, Applied Research, LangChain Labs
The code is at github.com/langchain-ai/smithtune . Training on Baseten needs an account with Loops enabled, and because Loops is in early access, you may need to request it for your workspace first.
If a coding agent will be running smithtune, the agent skill in the repo points to docs.baseten.co/agent-setup . That page sets your agent up with our agent skills and the Baseten docs MCP server.
Talk to us
Connect with our product experts to see how we can help.