42 lines
940 B
Python
42 lines
940 B
Python
"""
|
||
VLM Provider 抽象基类
|
||
"""
|
||
|
||
from abc import ABC, abstractmethod
|
||
from typing import List
|
||
|
||
|
||
class VLMProvider(ABC):
|
||
"""
|
||
视觉语言模型 Provider 抽象接口
|
||
所有 VLM 后端实现都应该继承此类并实现 chat_vision 方法
|
||
"""
|
||
|
||
@abstractmethod
|
||
def chat_vision(
|
||
self,
|
||
prompt: str,
|
||
image_paths: List[str],
|
||
temperature: float = 0.1,
|
||
timeout_sec: int = 120,
|
||
) -> str:
|
||
"""
|
||
调用 VLM 进行图像理解
|
||
|
||
Args:
|
||
prompt: 用户提示词
|
||
image_paths: 图片路径列表（支持单张或多张）
|
||
temperature: 采样温度（0.0-1.0）
|
||
timeout_sec: 超时时间（秒）
|
||
|
||
Returns:
|
||
模型生成的文本响应
|
||
|
||
Raises:
|
||
Exception: 调用失败时抛出异常
|
||
"""
|
||
pass
|
||
|
||
def __repr__(self):
|
||
return f"<{self.__class__.__name__}>"
|