tzt
c072a1a237
- 新增 router_system/llm_client.py：OpenAICompatClient 统一 experts/judge/fallback
三处复制的懒建 AsyncClient + /chat/completions + choices/usage 解析（~60 行去重）；
密钥解析统一走 config.get_api_key（激活原死代码，顺带消除 experts 默认环境名不一致）
- 语义缓存 L2：条目容器 list→OrderedDict（提升/淘汰 O(n)→O(1)），按 query 天然去重；
n-gram 向量 lru_cache 复用（同一次 miss 的 get/put 免重复分词）；
A/B：淘汰路径 0.040→0.034s，miss→put 往返 9.41→8.57s（-9%）
- RuleJudge 覆盖度：response.lower() 提出逐词循环（原 O(terms×len) 重复复制）
- extract_content_terms 纯函数 lru_cache 化（专家与 Judge 对同一查询免重复分词），返回 tuple
- RuleClassifier：_score 去掉败者领域白建的命中词 list（胜出后单独收集）；
修复 code 规则 ("api",0.7) 重复登记（原命中计 1.4 分）
- difficulty：正则模块级预编译
- tests：恢复上一轮引入的乱码中文 docstring；网关测试输入串恢复为可判 code 的中文查询
85 lines
2.8 KiB
Python
85 lines
2.8 KiB
Python
"""大模型回退层：Mock 与 OpenAI 兼容 API 两种后端。"""
|
||
from __future__ import annotations
|
||
|
||
import asyncio
|
||
from typing import Dict
|
||
|
||
from .config import get_api_key
|
||
from .llm_client import OpenAICompatClient
|
||
from .models import ExpertResponse
|
||
|
||
|
||
class FallbackProvider:
|
||
name: str = "fallback"
|
||
|
||
async def generate(self, query: str) -> ExpertResponse:
|
||
raise NotImplementedError
|
||
|
||
|
||
class MockFallback(FallbackProvider):
|
||
"""确定性 mock 大模型：标识为 fallback，便于测试升级路径。"""
|
||
|
||
def __init__(self, model: str = "mock-large"):
|
||
self.model = model
|
||
self.name = f"fallback-{model}"
|
||
|
||
async def generate(self, query: str) -> ExpertResponse:
|
||
await asyncio.sleep(0.002)
|
||
body = (
|
||
f"（大模型回退）「{query}」\n\n"
|
||
"这是一条来自大模型回退路径的完整回答。\n"
|
||
"要点：\n"
|
||
"1. 对复杂/跨域任务给出综合推理\n"
|
||
"2. 补充领域专家未覆盖的上下文\n"
|
||
"3. 给出可执行的后续建议\n"
|
||
)
|
||
return ExpertResponse(
|
||
text=body,
|
||
model_used=self.model,
|
||
latency_ms=2.0,
|
||
tokens=120,
|
||
cost_est=2.0 * 120 / 1_000_000,
|
||
)
|
||
|
||
|
||
class APIFallback(FallbackProvider):
|
||
"""OpenAI 兼容大模型 API（如 DeepSeek / OpenAI / 本地 vLLM）。"""
|
||
|
||
def __init__(self, model: str, base_url: str, api_key: str):
|
||
self.model = model
|
||
self.name = f"fallback-{model}"
|
||
self._client = OpenAICompatClient(base_url, api_key, timeout=90.0)
|
||
|
||
async def generate(self, query: str) -> ExpertResponse:
|
||
data = await self._client.chat(
|
||
self.model,
|
||
[{"role": "user", "content": query}],
|
||
temperature=0.3,
|
||
max_tokens=2048,
|
||
)
|
||
body = self._client.completion_text(data)
|
||
tokens = self._client.completion_tokens(data, body)
|
||
return ExpertResponse(
|
||
text=body,
|
||
model_used=self.model,
|
||
latency_ms=0.0,
|
||
tokens=tokens,
|
||
cost_est=2.0 * tokens / 1_000_000,
|
||
)
|
||
|
||
|
||
def build_fallback(cfg: Dict) -> FallbackProvider:
|
||
"""cfg 为 fallback 段配置。"""
|
||
ftype = cfg.get("type", "mock")
|
||
model = cfg.get("model", "deepseek-chat")
|
||
if ftype == "mock":
|
||
return MockFallback(model=model)
|
||
if ftype == "api":
|
||
api_key = cfg.get("api_key") or get_api_key(cfg)
|
||
if not api_key:
|
||
raise RuntimeError(
|
||
f"APIFallback 缺少 API Key：请设置环境变量 {cfg.get('api_key_env')} 或配置 api_key"
|
||
)
|
||
return APIFallback(model, cfg.get("base_url", "https://api.deepseek.com/v1"), api_key)
|
||
raise ValueError(f"未知 fallback 类型: {ftype}（支持 mock | api）")
|