55 lines
1.5 KiB
Python
55 lines
1.5 KiB
Python
|
"""Local LLM endpoints for bundled Qwen3 inference."""
|
||
|
|
|
||
|
|
import logging
|
||
|
|
from typing import Optional
|
||
|
|
|
||
|
|
from fastapi import APIRouter, HTTPException
|
||
|
|
from pydantic import BaseModel
|
||
|
|
|
||
|
|
from services.local_llm import get_status, download_model, complete
|
||
|
|
|
||
|
|
logger = logging.getLogger(__name__)
|
||
|
|
router = APIRouter()
|
||
|
|
|
||
|
|
|
||
|
|
class CompleteRequest(BaseModel):
|
||
|
|
prompt: str
|
||
|
|
model_id: str = "qwen3-1.7b"
|
||
|
|
system_prompt: Optional[str] = None
|
||
|
|
temperature: float = 0.3
|
||
|
|
max_tokens: int = 2048
|
||
|
|
|
||
|
|
|
||
|
|
@router.get("/local-llm/status")
|
||
|
|
async def llm_status():
|
||
|
|
try:
|
||
|
|
return get_status()
|
||
|
|
except Exception as e:
|
||
|
|
logger.error(f"Local LLM status failed: {e}", exc_info=True)
|
||
|
|
raise HTTPException(status_code=500, detail=str(e))
|
||
|
|
|
||
|
|
|
||
|
|
@router.post("/local-llm/download")
|
||
|
|
async def llm_download(model_id: str = "qwen3-1.7b"):
|
||
|
|
try:
|
||
|
|
return download_model(model_id)
|
||
|
|
except Exception as e:
|
||
|
|
logger.error(f"Local LLM download failed: {e}", exc_info=True)
|
||
|
|
raise HTTPException(status_code=500, detail=str(e))
|
||
|
|
|
||
|
|
|
||
|
|
@router.post("/local-llm/complete")
|
||
|
|
async def llm_complete(req: CompleteRequest):
|
||
|
|
try:
|
||
|
|
result = complete(
|
||
|
|
prompt=req.prompt,
|
||
|
|
model_id=req.model_id,
|
||
|
|
system_prompt=req.system_prompt,
|
||
|
|
temperature=req.temperature,
|
||
|
|
max_tokens=req.max_tokens,
|
||
|
|
)
|
||
|
|
return {"response": result}
|
||
|
|
except Exception as e:
|
||
|
|
logger.error(f"Local LLM completion failed: {e}", exc_info=True)
|
||
|
|
raise HTTPException(status_code=500, detail=str(e))
|