DeepSeek 接入多模态识图配置教程

图片 → vision.js 转 base64 → 视觉模型 API → 返回文字描述 → 主模型

#!/usr/bin/env node
const fs = require("fs");
const path = require("path");
const https = require("https");

// ==== 需要修改的三个配置 ====
const BASE_URL = process.env.DASHSCOPE_BASE_URL || "https://dashscope.aliyuncs.com/compatible-mode/v1";
const API_KEY  = process.env.DASHSCOPE_API_KEY  || "sk-你的Key";        // ← API Key
const MODEL    = process.env.VISION_MODEL       || "qwen3.5-omni-plus"; // ← 模型名
// ============================

function resolveImageUrl(source) {
  const resolved = path.resolve(source);
  if (!fs.existsSync(resolved)) throw new Error(`文件不存在: ${resolved}`);
  const ext = path.extname(resolved).toLowerCase().replace(".", "");
  const mimeMap = { jpg: "jpeg", jpeg: "jpeg", png: "png", gif: "gif", webp: "webp", bmp: "bmp" };
  const data = fs.readFileSync(resolved);
  return `data:image/${mimeMap[ext] || "jpeg"};base64,${data.toString("base64")}`;
}

function request(payload) {
  const url = new URL(BASE_URL.replace(/\/?$/, "/") + "chat/completions");
  const body = JSON.stringify(payload);
  return new Promise((resolve, reject) => {
    const req = https.request(url, {
      method: "POST",
      headers: {
        Authorization: `Bearer ${API_KEY}`,
        "Content-Type": "application/json",
        "Content-Length": Buffer.byteLength(body),
      },
    }, (res) => {
      let data = "";
      res.on("data", (c) => data += c);
      res.on("end", () => {
        if (res.statusCode >= 400) return reject(new Error(`API ${res.statusCode}: ${data.slice(0, 300)}`));
        try { resolve(JSON.parse(data)?.choices?.[0]?.message?.content || data); }
        catch { resolve(data); }
      });
    });
    req.on("error", reject);
    req.write(body);
    req.end();
  });
}

async function main() {
  const args = process.argv.slice(2);
  const imagePath = args[0];
  const prompt = args[1] || "请详细描述这张图片的内容。";
  if (!imagePath) {
    console.error("用法: node vision.js <图片路径> [问题]");
    process.exit(1);
  }
  const imageUrl = resolveImageUrl(imagePath);
  const result = await request({
    model: MODEL,
    messages: [{ role: "user", content: [
      { type: "image_url", image_url: { url: imageUrl } },
      { type: "text", text: prompt },
    ]}],
    stream: false,
    max_tokens: 1024,
  });
  console.log(result);
}

main().catch(e => { console.error("识图失败:", e.message); process.exit(1); });

# 识图能力

你的底层模型不具备原生识图能力。遇到图片时,不要用 Read 工具,改用 vision.js:

    node vision.js "<图片路径>" "用中文描述这张图片"

## 触发场景

- 用户分享图片路径(本地或网络 URL)
- 消息中出现 "Saved attachments:" 并列出图片
- 用户要求分析、描述、识别图片内容

node vision.js "/path/to/image.png" "请用中文描述这张图片的内容"