2f7e083db0
- MLX(맥미니 27B) 우선 → Ollama(조립컴 9B) fallback 구조 - pydantic-settings 기반 config 전환 - health check에 MLX 상태 추가 - 텍스트 모델 qwen3:8b → qwen3.5:9b-q8_0 변경 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
58 lines
1.6 KiB
Python
58 lines
1.6 KiB
Python
from fastapi import APIRouter, HTTPException
|
|
from pydantic import BaseModel
|
|
from services.rag_service import (
|
|
rag_suggest_solution,
|
|
rag_ask,
|
|
rag_analyze_pattern,
|
|
rag_classify_with_context,
|
|
)
|
|
|
|
router = APIRouter(tags=["rag"])
|
|
|
|
|
|
class AskRequest(BaseModel):
|
|
question: str
|
|
project_id: int | None = None
|
|
|
|
|
|
class PatternRequest(BaseModel):
|
|
description: str
|
|
n_results: int = 10
|
|
|
|
|
|
class ClassifyRequest(BaseModel):
|
|
description: str
|
|
detail_notes: str = ""
|
|
|
|
|
|
@router.post("/rag/suggest-solution/{issue_id}")
|
|
async def suggest_solution(issue_id: int):
|
|
try:
|
|
return await rag_suggest_solution(issue_id)
|
|
except Exception as e:
|
|
raise HTTPException(status_code=500, detail="AI 서비스 처리 중 오류가 발생했습니다")
|
|
|
|
|
|
@router.post("/rag/ask")
|
|
async def ask_question(req: AskRequest):
|
|
try:
|
|
return await rag_ask(req.question, req.project_id)
|
|
except Exception as e:
|
|
raise HTTPException(status_code=500, detail="AI 서비스 처리 중 오류가 발생했습니다")
|
|
|
|
|
|
@router.post("/rag/pattern")
|
|
async def analyze_pattern(req: PatternRequest):
|
|
try:
|
|
return await rag_analyze_pattern(req.description, req.n_results)
|
|
except Exception as e:
|
|
raise HTTPException(status_code=500, detail="AI 서비스 처리 중 오류가 발생했습니다")
|
|
|
|
|
|
@router.post("/rag/classify")
|
|
async def classify_with_rag(req: ClassifyRequest):
|
|
try:
|
|
return await rag_classify_with_context(req.description, req.detail_notes)
|
|
except Exception as e:
|
|
raise HTTPException(status_code=500, detail="AI 서비스 처리 중 오류가 발생했습니다")
|