> For the complete documentation index, see [llms.txt](https://unsloth.ai/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://unsloth.ai/docs/zh/mo-xing/decision-laya.md).
# 使用 Unsloth 在本地运行和提供决策模型：Laya + Jev API
使用 Unsloth 在本地部署并运行决策模型。
运行并提供诸如以下的决策模型： **Laya** 或 **Clef**，在本地运行开源的 Jev 替代方案， **Mac**, **Windows** 和 **Linux** 设备，使用 [Unsloth](https://github.com/unslothai/unsloth)。决策模型将文本输入转化为结构化决策，供你的应用执行——从分流支持工单、过滤邮件，到自动打标签和分类。
你可以使用 Unsloth GUI 界面，通过 TypeSafe 兼容的 Jev API 提供 Laya 和 Clef，从而让现有的 Jev 集成只需指向你的本地服务器即可工作。
所有数据都保留在你的设备上，并且 **CPU**, **统一内存**，以及 **GPU** 配置都支持。
通过 Unsloth 的决策 API 使用本地 Laya 驱动的实时打包演示：当你输入并更改旅行计划时，行李箱物品会自动更新
{% endcolumn %}
{% endcolumns %}
### 🔁 从 Jev 迁移
使用以下命令安装 SDK `pip install typesafe-sdk`，设置两个环境变量，你现有的代码就会与 Unsloth 通信：
```bash
export TYPESAFE_BASE_URL=http://localhost:8888
export TYPESAFE_API_KEY=sk-unsloth-YOUR_KEY
```
SDK 的默认模型， `jev-latest`会映射到你在设置中选择的模型。
有两点与 Jev 不同。 `置信度` 使用不同的公式，因此在 Jev 上调好的阈值无法直接迁移；应将阈值设为 `probabilities` 。另外，选择中的各个选项共享固定的 token 预算，因此当描述超过约 20 个选项后，标签会被截断。
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://unsloth.ai/docs/zh/mo-xing/decision-laya.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
