"""OpenAI-compatible providers (one implementation, many vendors).

OpenAI, xAI (api.x.ai/v1), Ollama (…:11434/v1), OpenRouter, Together, vLLM, etc.
all speak the OpenAI Chat Completions / Embeddings API — they differ only by
base URL, key, and model name. So a single class, parameterized by those, plugs
in every one of them via the official `openai` SDK.
"""

from openai import AsyncOpenAI

from app.integrations.models.base import EmbeddingProvider, LLMProvider


class OpenAICompatibleLLMProvider(LLMProvider):
    def __init__(self, *, api_key: str | None, base_url: str, model: str, max_tokens: int = 4096) -> None:
        # Local backends (Ollama) ignore the key but the SDK requires a non-empty one.
        self._client = AsyncOpenAI(api_key=api_key or "not-needed", base_url=base_url)
        self._model = model
        self._max_tokens = max_tokens

    async def complete(self, *, prompt: str, system: str | None = None) -> str:
        messages: list[dict] = []
        if system:
            messages.append({"role": "system", "content": system})
        messages.append({"role": "user", "content": prompt})
        resp = await self._client.chat.completions.create(
            model=self._model, max_tokens=self._max_tokens, messages=messages
        )
        return resp.choices[0].message.content or ""


class OpenAICompatibleEmbeddingProvider(EmbeddingProvider):
    def __init__(self, *, api_key: str | None, base_url: str, model: str, dimensions: int) -> None:
        self._client = AsyncOpenAI(api_key=api_key or "not-needed", base_url=base_url)
        self._model = model
        self.dimensions = dimensions

    async def embed(self, texts: list[str]) -> list[list[float]]:
        resp = await self._client.embeddings.create(model=self._model, input=texts)
        return [d.embedding for d in resp.data]