100 lines
3.4 KiB
Python
100 lines
3.4 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, Optional
|
||
|
||
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.base_url = base_url.rstrip("/")
|
||
self.api_key = api_key
|
||
self.name = f"fallback-{model}"
|
||
self._client = None
|
||
|
||
def _get_client(self):
|
||
if self._client is None:
|
||
import httpx
|
||
self._client = httpx.AsyncClient(timeout=90.0)
|
||
return self._client
|
||
|
||
async def generate(self, query: str) -> ExpertResponse:
|
||
client = self._get_client()
|
||
resp = await client.post(
|
||
f"{self.base_url}/chat/completions",
|
||
headers={"Authorization": f"Bearer {self.api_key}"},
|
||
json={
|
||
"model": self.model,
|
||
"messages": [{"role": "user", "content": query}],
|
||
"temperature": 0.3,
|
||
"max_tokens": 2048,
|
||
},
|
||
)
|
||
resp.raise_for_status()
|
||
data = resp.json()
|
||
body = data["choices"][0]["message"]["content"]
|
||
usage = data.get("usage", {})
|
||
tokens = usage.get("completion_tokens", int(len(body) / 2.2))
|
||
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":
|
||
import os
|
||
api_key = cfg.get("api_key") or os.environ.get(cfg.get("api_key_env", "API_KEY"))
|
||
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）")
|
||
|