import { InferenceClient } from "@huggingface/inference";

let out = "";

const stream = client.chatCompletionStream({
    provider: "hf-inference",
    model: "Qwen/Qwen3-235B-A22B",
    messages: [
        {
            role: "user",
            content: "你是谁？",
        },
        {
            role: "assistant",
            content: "",
        },
    ],
    temperature: 1.2,
    max_tokens: 50000,
    top_p: 0.6,
    response_format: undefined
});

for await (const chunk of stream) {
	if (chunk.choices && chunk.choices.length > 0) {
		const newContent = chunk.choices[0].delta.content;
		out += newContent;
		console.log(newContent);
	}
}