数据模式

可以强制让LLM生成符合特定模式的数据。这种技术效果相当不错，GenAIScript还提供了自动验证功能"以防万一"。

您会注意到GenAIScript支持的架构比完整的JSON架构规范要简单得多。我们建议使用简单的架构以避免混淆大语言模型；之后再将它们移植到您的应用程序特定的数据格式中。

`defSchema`

使用defSchema为提示输出定义JSON/YAML模式。

const schema = defSchema("CITY_SCHEMA", {
    type: "array",
    description: "A list of cities with population and elevation information.",
    items: {
        type: "object",
        description: "A city with population and elevation information.",
        properties: {
            name: { type: "string", description: "The name of the city." },
            population: {
                type: "number",
                description: "The population of the city.",
            },
            url: {
                type: "string",
                description: "The URL of the city's Wikipedia page.",
            },
        },
        required: ["name", "population", "url"],
    },
})

$`Generate data using JSON compliant with ${schema}.`

👤 user

CITY_SCHEMA:

```typescript-schema
// A list of cities with population and elevation information.
type CITY_SCHEMA = Array<{
    // The name of the city.
    name: string,
    // The population of the city.
    population: number,
    // The URL of the city's Wikipedia page.
    url: string,
  }>
```

Generate data using JSON compliant with CITY_SCHEMA.

🤖 assistant

File ./data.json:

```json schema=CITY_SCHEMA
[
    {
        "name": "New York",
        "population": 8398748,
        "url": "https://en.wikipedia.org/wiki/New_York_City"
    },
    {
        "name": "Los Angeles",
        "population": 3990456,
        "url": "https://en.wikipedia.org/wiki/Los_Angeles"
    },
    {
        "name": "Chicago",
        "population": 2705994,
        "url": "https://en.wikipedia.org/wiki/Chicago"
    }
]
```

原生zod支持

GenAIScript runtime 提供了 z 模块。

可以将Zod类型传入defSchema，它会自动转换为JSON模式。为了方便起见，GenAIScript还从Zod导出了z对象。

// import from genaiscript
import { z } from "genaiscript/runtime"
// or directly from zod
// import { z } from "zod"
// create schema using zod
const CitySchema = z.array(
    z.object({
        name: z.string(),
        population: z.number(),
        url: z.string(),
    })
)
// JSON schema to constrain the output of the tool.
const schema = defSchema("CITY_SCHEMA", CitySchema)

提示编码

遵循TypeChat提出的“All You Need Is Types”方法，在将模式注入LLM提示之前，会先将其转换为TypeScript类型。

// A list of cities with population and elevation information.
type CITY_SCHEMA = Array<{
    // The name of the city.
    name: string
    // The population of the city.
    population: number
    // The URL of the city's Wikipedia page.
    url: string
}>

您可以通过使用{ format: "json" }选项来更改此行为。

const schema = defSchema("CITY_SCHEMA", {...}, { format: "json" })

跟踪功能允许您查看模式源和渲染后的提示，同时cli也会将生成的TypeScript文件写入输出文件夹。

schema CITY_SCHEMA

来源：

{
    "type": "array",
    "description": "A list of cities with population and elevation information.",
    "items": {
        "type": "object",
        "description": "A city with population and elevation information.",
        "properties": {
            "name": {
                "type": "string",
                "description": "The name of the city."
            },
            "population": {
                "type": "number",
                "description": "The population of the city."
            },
            "url": {
                "type": "string",
                "description": "The URL of the city's Wikipedia page."
            }
        },
        "required": ["name", "population", "url"]
    }
}

提示（以TypeScript格式呈现）：

// A list of cities with population and elevation information.
type CITY_SCHEMA = Array<{
    // The name of the city.
    name: string
    // The population of the city.
    population: number
    // The URL of the city's Wikipedia page.
    url: string
}>

使用该模式

然后告诉LLM使用这个模式来生成数据。

const schema = defSchema(...)
$`Use ${schema} for the JSON schema.`

验证

当使用模式标识符生成JSON/YAML有效负载时，GenAIScript会自动根据模式验证该有效负载。

修复

GenAIScript会自动尝试通过向LLM发送带有解析输出的附加消息来修复数据问题。

运行时验证

在运行脚本时使用parsers.validateJSON来验证JSON。

const validation = parsers.validateJSON(schema, json)