36 lines
1.3 KiB
Python
36 lines
1.3 KiB
Python
"""
|
|
QA - 智能问答编排
|
|
|
|
run_qa(prompt): 按 models 顺序尝试 chat()，首个成功返回 (answer, provider)。
|
|
顺序 = vision 模型(Gemini -> NVIDIA) + text 模型(Ollama 兜底)。
|
|
即 Gemini -> NVIDIA -> Ollama 三级降级。
|
|
"""
|
|
from typing import Optional, Tuple
|
|
|
|
from .logger import setup_logger
|
|
from .config_loader import load_config
|
|
from .model_adapters.adapter_factory import build_adapters
|
|
|
|
logger = setup_logger('fam-edge.qa')
|
|
|
|
|
|
class QAOrchestrator:
|
|
def __init__(self):
|
|
self.config = load_config()
|
|
self.adapters = build_adapters(self.config.get('models', []))
|
|
|
|
def run_qa(self, prompt: str,
|
|
max_tokens: int = 1024) -> Tuple[Optional[str], Optional[str]]:
|
|
"""依次尝试各适配器的 chat()，返回 (answer, provider)。"""
|
|
for adapter in self.adapters:
|
|
try:
|
|
answer = adapter.chat(prompt, max_tokens=max_tokens)
|
|
except Exception as e:
|
|
logger.warning(f"QA {adapter.provider_name} 异常: {e}")
|
|
continue
|
|
if answer:
|
|
logger.info(f"QA 命中 provider={adapter.provider_name}")
|
|
return answer, adapter.provider_name
|
|
logger.info(f"QA {adapter.provider_name} 无返回，降级下一模型")
|
|
return None, None
|