"""Qwen Provider (兼容 OpenAI SDK)"""
from openai import AsyncOpenAI

from app.providers.base import BaseLLMProvider, LLMMessage, LLMResponse


class QwenProvider(BaseLLMProvider):
    """通义千问 Provider，使用 OpenAI SDK 兼容模式"""

    def __init__(
        self,
        api_key: str,
        model: str = "qwen-turbo",
        base_url: str = "https://dashscope.aliyuncs.com/compatible-mode/v1",
    ):
        self.api_key = api_key
        self.model = model
        self.client = AsyncOpenAI(api_key=api_key, base_url=base_url)

    async def chat(self, messages: list[LLMMessage]) -> LLMResponse:
        response = await self.client.chat.completions.create(
            model=self.model,
            messages=[{"role": m.role, "content": m.content} for m in messages],
        )
        return LLMResponse(
            content=response.choices[0].message.content or "",
            model=response.model,
            usage={
                "total_tokens": response.usage.total_tokens,
                "prompt_tokens": response.usage.prompt_tokens,
                "completion_tokens": response.usage.completion_tokens,
            },
        )

    async def chat_stream(self, messages: list[LLMMessage]) -> str:
        stream = await self.client.chat.completions.create(
            model=self.model,
            messages=[{"role": m.role, "content": m.content} for m in messages],
            stream=True,
        )
        async for chunk in stream:
            if chunk.choices[0].delta.content:
                yield chunk.choices[0].delta.content

    async def embed(self, texts: list[str]) -> list[list[float]]:
        # Qwen embedding 使用不同接口
        response = await self.client.embeddings.create(
            model="text-embedding-v3",
            input=texts,
        )
        return [item.embedding for item in response.data]