Question

我愿以某种结构化的数据格式,例如,将用户申请转化为机票。 JSON。例如:

User: I want to order two chairs and a desk with three drawers on the left side.
Output:

{
    "type": "furniture",
    "items": [
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 3, "position": "left" }] },
        { "type": "chair", "qty": 2 }
    ]
}

它认为GPT-3本身并不适合这项任务,因为产出不是以自然语言的形式,但法典可能不是这样? 但是,在开放审计协会的“APIC”文件中,我可以找到我如何(如果它完全有可能)为开放审计协会的《规则》模式建立一个习惯/经过微调的模式?

Answer 1

@xara 法典不支持调整模式。

你可以做的是迅速工程。

提供一些示范,并尝试《刑法》是否能够使你获得预期产出。

Answer 2

如果你没有参与,你可能根本需要创造性的迅速工程。例如,我首先向查谟和克什米尔爱国者运动表示,你会迅速展示标准投入和反应,然后把它确定为一项完成的任务。这是我所用的准确的迅速结果:

Please complete the following:
User: I want to order two chairs and a desk with three drawers on the left side.
Output:
```json
{
    "type": "furniture",
    "items": [
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 3, "position": "left" }] },
        { "type": "chair", "qty": 2 }
    ]
}
```
User: I want three chairs and a desk with 2 drawers on the left and a desk with 3 drawers on the right.
Output:
```

请注意,我最后用三个标准表示,它应立即从守则开始。

ChatGPT 退回如下:

{
    "type": "furniture",
    "items": [
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 2, "position": "left" }] },
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 3, "position": "right" }] },
        { "type": "chair", "qty": 3 }
    ]
}

友情链接