routers/text_router.py

from fastapi import APIRouter, HTTPException
from fastapi.responses import StreamingResponse, JSONResponse
import logging

from models.schemas import ChatRequest, ErrorResponse
from services.text_service import text_service

logger = logging.getLogger("text-router")

router = APIRouter(prefix="/v1/text", tags=["Text Generation"])

@router.post("/chat/completions")
async def create_chat_completion(request: ChatRequest):
    """
    Create a chat completion using the text model
    
    Supports:
    - Standard completions
    - Streaming responses
    - JSON extraction mode
    """
    if not text_service.is_ready():
        raise HTTPException(status_code=503, detail="Text model not ready")
    
    try:
        messages = [msg.model_dump() for msg in request.messages]
        
        result = await text_service.generate_completion(
            messages=messages,
            temperature=request.temperature,
            max_tokens=request.max_tokens,
            stream=request.stream,
            return_json=request.returnJson
        )
        
        if request.stream:
            return StreamingResponse(result, media_type="text/event-stream")
        
        return JSONResponse(content=result)
        
    except ValueError as e:
        raise HTTPException(status_code=400, detail=str(e))
    except Exception as e:
        logger.error(f"Chat completion error: {e}")
        raise HTTPException(status_code=500, detail=str(e))

@router.get("/health")
async def text_health():
    """Check text model health status"""
    return {
        "status": "healthy" if text_service.is_ready() else "initializing",
        "model_ready": text_service.is_ready()
    }