my_voice_assistant_v3/app/providers/llm/base.py

import json
from abc import ABC, abstractmethod
from collections.abc import AsyncIterator


def sse_delta(line: str) -> str | None:
    """Extrahiert das Token-Delta aus einer OpenAI-kompatiblen SSE-Zeile (oder None)."""
    if not line.startswith("data:"):
        return None
    data = line[len("data:"):].strip()
    if not data or data == "[DONE]":
        return None
    try:
        obj = json.loads(data)
        return obj["choices"][0]["delta"].get("content")
    except (ValueError, KeyError, IndexError, TypeError):
        return None


class LLMProvider(ABC):
    @abstractmethod
    async def complete(
        self,
        text: str,
        history: list[dict] | None = None,
        session_id: str | None = None,
    ) -> str: ...

    async def stream(
        self,
        text: str,
        history: list[dict] | None = None,
        session_id: str | None = None,
    ) -> AsyncIterator[str]:
        """Token-Stream. Default: kein echtes Streaming -> komplette Antwort als ein Chunk.

        Provider mit SSE-Unterstuetzung ueberschreiben diese Methode.
        """
        yield await self.complete(text, history=history, session_id=session_id)