调用 AI — Downcity City SDK Docs

SDK 通路

import { City } from "@downcity/city";

const client = new City({
  role: "user",
  city_url,
  town_id,
  user_token,
});

// 获取模型目录
const catalog = await client.ai.listModels();
const model = catalog.get("deepseek-v4-flash");

// 文本生成
const msg = await client.ai.text({ prompt: "hello", model });
console.log(msg.parts[0].text);

// 流式生成
const stream = await client.ai.stream({ prompt: "hello", model });
const reader = stream.getReader();
while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  if (value.type === "text-delta") process.stdout.write(value.textDelta);
}

client.ai.listModels() 在 user_token 身份下只返回当前已经满足运行时 env 的模型；同一条路由在 admin_secret_key 身份下会返回全部代码注册模型和它们的 env_requirements。

OpenAI 兼容通路

curl

curl http://127.0.0.1:43127/v1/ai/chat/completions \
  -H "Authorization: Bearer <user_token>" \
  -d '{"model":"deepseek-v4-flash","messages":[{"role":"user","content":"hello"}],"stream":true}'

OpenAI SDK

import OpenAI from "openai";

const handle = client.ai.model(catalog.get("deepseek-v4-flash"));
const openai = new OpenAI({ baseURL: handle.url(), apiKey: handle.token });

const stream = await openai.chat.completions.create({
  model: handle.modelName(),
  messages: [{ role: "user", content: "你好" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}