文字卡片

• Nano Banana 2

文字卡片 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: "text-card",
  input: {
    text: "The best time to plant a tree was 20 years ago.",
  },
});

import asyncio
import os

from pipe2 import Pipe2Client

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

run = asyncio.run(client.run_pipeline(
    pipeline_slug="text-card",
    input={
        "text": "The best time to plant a tree was 20 years ago.",
    },
))

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

input := json.RawMessage(`{
  "text": "The best time to plant a tree was 20 years ago."
}`)

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

pipe2 pipelines run \
  --pipeline text-card \
  --input-json '{"text": "The best time to plant a tree was 20 years ago."}' \
  --wait

获取 API 令牌 →

参数

text 必填

Text to typeset on the card. Short lines read best.

string

background_url

Public URL of a background image. Leave unset for a generated background.

string

instructions

AI 的可选样式提示

string

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