hyungi_document_server/app/ai/client.py

"""AI 추상화 레이어 — 통합 클라이언트. 기본값은 항상 Qwen3.5."""

import json
import re
from pathlib import Path

import httpx

from core.config import settings


def strip_thinking(text: str) -> str:
    """Qwen3.5의 <think>...</think> 블록 및 Thinking Process 텍스트 제거"""
    # <think> 태그 제거
    text = re.sub(r"<think>.*?</think>", "", text, flags=re.DOTALL)
    # "Thinking Process:" 등 사고 과정 텍스트 제거 (첫 번째 { 이전의 모든 텍스트)
    json_start = text.find("{")
    if json_start > 0:
        text = text[json_start:]
    return text.strip()


def parse_json_response(raw: str) -> dict | None:
    """AI 응답에서 JSON 객체 추출 (think 태그, 코드블록 등 제거)"""
    cleaned = strip_thinking(raw)
    # 코드블록 내부 JSON 추출
    code_match = re.search(r"```(?:json)?\s*(\{.*?\})\s*```", cleaned, re.DOTALL)
    if code_match:
        cleaned = code_match.group(1)
    # 마지막 유효 JSON 객체 찾기
    matches = list(re.finditer(r"\{[^{}]*(?:\{[^{}]*\}[^{}]*)*\}", cleaned, re.DOTALL))
    for m in reversed(matches):
        try:
            return json.loads(m.group())
        except json.JSONDecodeError:
            continue
    # 최후 시도: 전체 텍스트를 JSON으로
    try:
        return json.loads(cleaned)
    except json.JSONDecodeError:
        return None

# 프롬프트 로딩
PROMPTS_DIR = Path(__file__).parent.parent / "prompts"


def _load_prompt(name: str) -> str:
    return (PROMPTS_DIR / name).read_text(encoding="utf-8")


CLASSIFY_PROMPT = _load_prompt("classify.txt") if (PROMPTS_DIR / "classify.txt").exists() else ""


class AIClient:
    """AI Gateway를 통한 통합 클라이언트. 기본값은 항상 Qwen3.5."""

    def __init__(self):
        self.ai = settings.ai
        self._http = httpx.AsyncClient(timeout=120)

    async def classify(self, text: str) -> dict:
        """문서 분류 — 항상 primary(Qwen3.5) 사용"""
        prompt = CLASSIFY_PROMPT.replace("{document_text}", text)
        response = await self._call_chat(self.ai.primary, prompt)
        return response

    async def summarize(self, text: str, force_premium: bool = False) -> str:
        """문서 요약 — 기본 primary, force_premium=True 시만 Claude"""
        if force_premium:
            return await self._call_chat(self.ai.premium, f"다음 문서를 500자 이내로 요약해주세요:\n\n{text}")
        return await self._call_chat(self.ai.primary, f"다음 문서를 500자 이내로 요약해주세요:\n\n{text}")

    async def embed(self, text: str) -> list[float]:
        """벡터 임베딩 — GPU 서버 전용"""
        response = await self._http.post(
            self.ai.embedding.endpoint,
            json={"model": self.ai.embedding.model, "prompt": text},
        )
        response.raise_for_status()
        return response.json()["embedding"]

    async def rerank(self, query: str, texts: list[str]) -> list[dict]:
        """TEI bge-reranker-v2-m3 호출 (Phase 1.3).

        TEI POST /rerank API:
            request:  {"query": str, "texts": [str, ...]}
            response: [{"index": int, "score": float}, ...] (정렬됨)

        timeout은 self.ai.rerank.timeout (config.yaml).
        호출자(rerank_service)가 asyncio.Semaphore + try/except로 감쌈.
        """
        timeout = float(self.ai.rerank.timeout) if self.ai.rerank.timeout else 5.0
        response = await self._http.post(
            self.ai.rerank.endpoint,
            json={"query": query, "texts": texts},
            timeout=timeout,
        )
        response.raise_for_status()
        return response.json()

    async def _call_chat(self, model_config, prompt: str) -> str:
        """OpenAI 호환 API 호출 + 자동 폴백"""
        try:
            return await self._request(model_config, prompt)
        except (httpx.TimeoutException, httpx.ConnectError):
            if model_config == self.ai.primary:
                return await self._request(self.ai.fallback, prompt)
            raise

    async def _request(self, model_config, prompt: str) -> str:
        """단일 모델 API 호출 (OpenAI 호환 + Anthropic Messages API)"""
        is_anthropic = "anthropic.com" in model_config.endpoint

        if is_anthropic:
            import os
            headers = {
                "x-api-key": os.getenv("CLAUDE_API_KEY", ""),
                "anthropic-version": "2023-06-01",
                "content-type": "application/json",
            }
            response = await self._http.post(
                model_config.endpoint,
                headers=headers,
                json={
                    "model": model_config.model,
                    "max_tokens": model_config.max_tokens,
                    "messages": [{"role": "user", "content": prompt}],
                },
                timeout=model_config.timeout,
            )
            response.raise_for_status()
            data = response.json()
            return data["content"][0]["text"]
        else:
            response = await self._http.post(
                model_config.endpoint,
                json={
                    "model": model_config.model,
                    "messages": [{"role": "user", "content": prompt}],
                    "max_tokens": model_config.max_tokens,
                    "chat_template_kwargs": {"enable_thinking": False},
                },
                timeout=model_config.timeout,
            )
            response.raise_for_status()
            data = response.json()
            return data["choices"][0]["message"]["content"]

    async def close(self):
        await self._http.aclose()