101 lines
2.7 KiB
Markdown
101 lines
2.7 KiB
Markdown
|
# 构建并行工作流
|
|||
|
|
|
|||
|
|
现在您将创建一个以最大性能并行运行您分析步骤的工作流。
|
|||
|
|
|
|||
|
|
## 创建并行工作流
|
|||
|
|
|
|||
|
|
将此工作流添加到您的文件中：
|
|||
|
|
|
|||
|
|
```typescript
|
|||
|
|
export const parallelAnalysisWorkflow = createWorkflow({
|
|||
|
|
id: "parallel-analysis-workflow",
|
|||
|
|
description: "Run multiple content analyses in parallel",
|
|||
|
|
inputSchema: z.object({
|
|||
|
|
content: z.string(),
|
|||
|
|
type: z.enum(["article", "blog", "social"]).default("article"),
|
|||
|
|
}),
|
|||
|
|
outputSchema: z.object({
|
|||
|
|
results: z.object({
|
|||
|
|
seo: z.object({
|
|||
|
|
seoScore: z.number(),
|
|||
|
|
keywords: z.array(z.string()),
|
|||
|
|
}),
|
|||
|
|
readability: z.object({
|
|||
|
|
readabilityScore: z.number(),
|
|||
|
|
gradeLevel: z.string(),
|
|||
|
|
}),
|
|||
|
|
sentiment: z.object({
|
|||
|
|
sentiment: z.enum(["positive", "neutral", "negative"]),
|
|||
|
|
confidence: z.number(),
|
|||
|
|
}),
|
|||
|
|
}),
|
|||
|
|
}),
|
|||
|
|
})
|
|||
|
|
.parallel([seoAnalysisStep, readabilityStep, sentimentStep])
|
|||
|
|
.then(
|
|||
|
|
createStep({
|
|||
|
|
id: "combine-results",
|
|||
|
|
description: "Combines parallel analysis results",
|
|||
|
|
inputSchema: z.object({
|
|||
|
|
"seo-analysis": z.object({
|
|||
|
|
seoScore: z.number(),
|
|||
|
|
keywords: z.array(z.string()),
|
|||
|
|
}),
|
|||
|
|
"readability-analysis": z.object({
|
|||
|
|
readabilityScore: z.number(),
|
|||
|
|
gradeLevel: z.string(),
|
|||
|
|
}),
|
|||
|
|
"sentiment-analysis": z.object({
|
|||
|
|
sentiment: z.enum(["positive", "neutral", "negative"]),
|
|||
|
|
confidence: z.number(),
|
|||
|
|
}),
|
|||
|
|
}),
|
|||
|
|
outputSchema: z.object({
|
|||
|
|
results: z.object({
|
|||
|
|
seo: z.object({
|
|||
|
|
seoScore: z.number(),
|
|||
|
|
keywords: z.array(z.string()),
|
|||
|
|
}),
|
|||
|
|
readability: z.object({
|
|||
|
|
readabilityScore: z.number(),
|
|||
|
|
gradeLevel: z.string(),
|
|||
|
|
}),
|
|||
|
|
sentiment: z.object({
|
|||
|
|
sentiment: z.enum(["positive", "neutral", "negative"]),
|
|||
|
|
confidence: z.number(),
|
|||
|
|
}),
|
|||
|
|
}),
|
|||
|
|
}),
|
|||
|
|
execute: async ({ inputData }) => {
|
|||
|
|
console.log("🔄 Combining parallel results...");
|
|||
|
|
|
|||
|
|
return {
|
|||
|
|
results: {
|
|||
|
|
seo: inputData["seo-analysis"],
|
|||
|
|
readability: inputData["readability-analysis"],
|
|||
|
|
sentiment: inputData["sentiment-analysis"],
|
|||
|
|
},
|
|||
|
|
};
|
|||
|
|
},
|
|||
|
|
}),
|
|||
|
|
)
|
|||
|
|
.commit();
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## 理解并行数据流
|
|||
|
|
|
|||
|
|
当步骤并行运行时：
|
|||
|
|
|
|||
|
|
1. 每个步骤接收相同的输入数据
|
|||
|
|
2. 步骤同时执行
|
|||
|
|
3. 结果被收集到以步骤ID为键的对象中
|
|||
|
|
4. 下一步接收所有并行结果
|
|||
|
|
|
|||
|
|
## 关键点
|
|||
|
|
|
|||
|
|
- **`.parallel([step1, step2, step3])`**：同时运行所有步骤
|
|||
|
|
- **结果对象键**：使用步骤ID（例如"seo-analysis"）
|
|||
|
|
- **合并步骤**：一起处理所有并行结果
|
|||
|
|
|
|||
|
|
接下来，您将测试此并行工作流并看到性能提升！
|