Videoverständnis

const response = await fetch("https://aihubmix.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIHUBMIX_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen3.7-plus",
    enable_thinking: false,
    max_tokens: 800,
    response_format: { type: "json_object" },
    messages: [{
      role: "user",
      content: [
        {
          type: "video_url",
          video_url: {
            url: "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241115/cqqkru/1.mp4",
          },
        },
        {
          type: "text",
          text: 'Analyze the attached video. Return a JSON object with a scenes array. Each scene must contain start_seconds, end_seconds and description. If no video is available, return {"error":"no_video"}.',
        },
      ],
    }],
  }),
  signal: AbortSignal.timeout(120000),
});
const result = await response.json();
if (!response.ok) throw new Error(JSON.stringify(result));
const scenes = JSON.parse(result.choices[0].message.content);
console.log(JSON.stringify({
  request_id: response.headers.get("x-aihubmix-request-id"),
  result: scenes,
  usage: result.usage,
}, null, 2));

import { readFileSync } from "node:fs";

const video = readFileSync(process.argv[2] ?? "video.mp4").toString("base64");
const response = await fetch("https://aihubmix.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIHUBMIX_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen3.7-plus",
    enable_thinking: false,
    max_tokens: 800,
    response_format: { type: "json_object" },
    messages: [{
      role: "user",
      content: [
        {
          type: "video_url",
          video_url: { url: `data:video/mp4;base64,${video}` },
        },
        {
          type: "text",
          text: 'Analyze the attached video. Return a JSON object with a scenes array. Each scene must contain start_seconds, end_seconds and description. If no video is available, return {"error":"no_video"}.',
        },
      ],
    }],
  }),
  signal: AbortSignal.timeout(120000),
});
const result = await response.json();
if (!response.ok) throw new Error(JSON.stringify(result));
const scenes = JSON.parse(result.choices[0].message.content);
console.log(JSON.stringify({
  request_id: response.headers.get("x-aihubmix-request-id"),
  result: scenes,
  usage: result.usage,
}, null, 2));

import { readFileSync } from "node:fs";

const video = readFileSync(process.argv[2] ?? "video.mp4").toString("base64");
const response = await fetch("https://aihubmix.com/v1/responses", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIHUBMIX_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen3.7-plus",
    max_output_tokens: 800,
    text: { format: { type: "json_object" } },
    input: [{
      role: "user",
      content: [
        {
          type: "video_url",
          video_url: { url: `data:video/mp4;base64,${video}` },
        },
        {
          type: "input_text",
          text: 'Analyze the attached video. Return a JSON object with a scenes array. Each scene must contain start_seconds, end_seconds and description. If no video is available, return {"error":"no_video"}.',
        },
      ],
    }],
  }),
  signal: AbortSignal.timeout(120000),
});
const result = await response.json();
if (!response.ok || result.status !== "completed") {
  throw new Error(JSON.stringify(result));
}
const text = result.output
  .filter((item) => item.type === "message")
  .flatMap((item) => item.content)
  .filter((part) => part.type === "output_text")
  .map((part) => part.text)
  .join("");
console.log(JSON.stringify({
  request_id: response.headers.get("x-aihubmix-request-id"),
  result: JSON.parse(text),
  usage: result.usage,
}, null, 2));