REMOTE INFERENCE API

诊断服务远程调用

通过 API Key 调用诊断服务批量处理时序文件；当前交付版本使用随机推理模拟器。

API KEY

获取API KEY

Key 备注

我的API KEY

暂无 Key等待生成

AUTHENTICATION

认证方式

请求时在 Header 中携带 API Key。没有密钥或密钥无效时，接口将拒绝处理文件。

Authorization: Bearer gbx_your_api_key

ENDPOINT

批量诊断接口

POST https://tinker-demo.duckdns.org/api/v1/batch-predict

文件字段: files
单次数量: 最多 10 个
支持格式: .xlsx / .csv / .tsv / .txt
输入规格: 1024 × 2，自动补齐或截断

EXAMPLE

调用示例

curl -X POST "https://tinker-demo.duckdns.org/api/v1/batch-predict" \
  -H "Authorization: Bearer gbx_your_api_key" \
  -F "files=@test0001.xlsx" \
  -F "files=@test0002.csv"

import requests

url = "https://tinker-demo.duckdns.org/api/v1/batch-predict"
headers = {"Authorization": "Bearer gbx_your_api_key"}
files = [
    ("files", open("test0001.xlsx", "rb")),
    ("files", open("test0002.csv", "rb")),
]

response = requests.post(url, headers=headers, files=files, timeout=60)
print(response.json())

const fs = require("fs");
const FormData = require("form-data");
const fetch = require("node-fetch");

const form = new FormData();
form.append("files", fs.createReadStream("test0001.xlsx"));
form.append("files", fs.createReadStream("test0002.csv"));

const response = await fetch("https://tinker-demo.duckdns.org/api/v1/batch-predict", {
  method: "POST",
  headers: {
    Authorization: "Bearer gbx_your_api_key",
    ...form.getHeaders(),
  },
  body: form,
});

console.log(await response.json());

RESPONSE

返回格式

{
  "results": [
    {
      "filename": "test0001.xlsx",
      "label": "INNER_MISSING",
      "name": "内圈缺失",
      "confidence": 0.7206
    }
  ]
}