图像搜索

图像搜索 API

从你自己的代码调用此流水线。一次请求即可发起运行；模型是一个输入字段，而不是独立的接口。

import { createClient } from "@pipe2-ai/sdk";

const client = createClient(process.env.PIPE2_TOKEN!);

const { run_pipeline } = await client.RunPipeline({
  pipeline_slug: "image-search",
  input: {
    topic: "minimalist workspace with warm morning light",
  },
});

import asyncio
import os

from pipe2 import Pipe2Client

client = Pipe2Client(token=os.environ["PIPE2_TOKEN"])

run = asyncio.run(client.run_pipeline(
    pipeline_slug="image-search",
    input={
        "topic": "minimalist workspace with warm morning light",
    },
))

client := pipe2.NewClient(os.Getenv("PIPE2_TOKEN"))

input := json.RawMessage(`{
  "topic": "minimalist workspace with warm morning light"
}`)

run, err := pipe2.RunPipeline(context.Background(), client, "image-search", input)
if err != nil {
    log.Fatal(err)
}

pipe2 pipelines run \
  --pipeline image-search \
  --input-json '{"topic": "minimalist workspace with warm morning light"}' \
  --wait

获取 API 令牌 →

参数

topic 必填

描述你需要哪些图像

string

image_count

How many images to return.

10203050 默认 20

在 AI 智能体中使用

将任意 MCP 客户端指向 pipe2，你的智能体就能获得这些工具。它会找到这条流水线，读取上方相同的 schema，然后运行它。

• list_pipelines
• get_pipeline_schema
• run_pipeline
• get_pipeline_run_status
• request_upload

{
  "mcpServers": {
    "pipe2ai": {
      "url": "https://mcp.pipe2.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_TOKEN" }
    }
  }
}

完整 API 参考→ MCP 设置→ CLI 参考→

常见问题