增加Kimi多模态Api,这样可以灵活选择！

2025-11-10 11:41:23 +08:00
parent 34135bbb75
commit f204799b3e
9 changed files with 11720 additions and 20 deletions
@@ -0,0 +1,10 @@
+"""
+VLM Provider 抽象层
+支持多种视觉语言模型后端：Ollama、Kimi、OpenAI GPT-4V 等
+"""
+
+from .base import VLMProvider
+from .ollama_provider import OllamaProvider
+from .kimi_provider import KimiProvider
+
+__all__ = ["VLMProvider", "OllamaProvider", "KimiProvider"]
@@ -0,0 +1,41 @@
+"""
+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__}>"
@@ -0,0 +1,123 @@
+"""
+Kimi VLM Provider
+使用 Moonshot AI 的 Kimi 1.5 视觉模型
+"""
+
+import base64
+import time
+from typing import List
+
+from .base import VLMProvider
+
+
+class KimiProvider(VLMProvider):
+    """
+    Kimi (Moonshot AI) 视觉模型提供商
+    使用 OpenAI SDK 兼容接口
+    """
+
+    def __init__(
+        self,
+        api_key: str,
+        base_url: str = "https://api.moonshot.cn/v1",
+        model: str = "moonshot-v1-32k-vision-preview",
+    ):
+        """
+        Args:
+            api_key: Moonshot AI API Key
+            base_url: API 端点地址
+            model: 模型名称
+        """
+        if not api_key:
+            raise ValueError("Kimi API Key 不能为空")
+
+        self.api_key = api_key
+        self.base_url = base_url
+        self.model = model
+
+    def chat_vision(
+        self,
+        prompt: str,
+        image_paths: List[str],
+        temperature: float = 0.1,
+        timeout_sec: int = 120,
+    ) -> str:
+        """调用 Kimi API 进行视觉推理"""
+        try:
+            from openai import OpenAI
+        except ImportError:
+            raise ImportError(
+                "Kimi Provider 需要 openai 库，请安装: pip install openai"
+            )
+
+        print(
+            f"[Kimi] Prepare chat model={self.model} temp={temperature} "
+            f"images={len(image_paths)} timeout={timeout_sec}s"
+        )
+
+        # 初始化 OpenAI 客户端
+        client = OpenAI(
+            api_key=self.api_key,
+            base_url=self.base_url,
+            timeout=timeout_sec,
+        )
+
+        # 构建消息内容（文本 + 图片）
+        # Kimi 支持 image_url 格式，使用 base64 编码
+        content_parts = [{"type": "text", "text": prompt}]
+        
+        for img_path in image_paths:
+            try:
+                with open(img_path, "rb") as f:
+                    img_data = f.read()
+                b64_str = base64.b64encode(img_data).decode("utf-8")
+                
+                # 根据文件扩展名判断 MIME 类型
+                if img_path.lower().endswith((".jpg", ".jpeg")):
+                    mime = "image/jpeg"
+                elif img_path.lower().endswith(".png"):
+                    mime = "image/png"
+                else:
+                    mime = "image/jpeg"  # 默认
+                
+                data_uri = f"data:{mime};base64,{b64_str}"
+                content_parts.append({
+                    "type": "image_url",
+                    "image_url": {"url": data_uri}
+                })
+            except Exception as e:
+                print(f"[Kimi] Warning: Failed to load image {img_path}: {e}")
+                continue
+
+        # 调用 API
+        t0 = time.time()
+        try:
+            completion = client.chat.completions.create(
+                model=self.model,
+                messages=[
+                    {
+                        "role": "user",
+                        "content": content_parts,
+                    }
+                ],
+                temperature=temperature,
+            )
+
+            dt = time.time() - t0
+            text = completion.choices[0].message.content or ""
+            
+            result = text.replace("\n", " ")
+            print(f"[Kimi] Response elapsed={dt:.2f}s length={len(text)} preview={result}")
+
+            if not text:
+                raise RuntimeError("Kimi 返回内容为空")
+
+            return text
+
+        except Exception as e:
+            dt = time.time() - t0
+            print(f"[Kimi][Error] during request elapsed={dt:.2f}s: {e}")
+            raise
+
+    def __repr__(self):
+        return f"<KimiProvider model={self.model} base_url={self.base_url}>"
@@ -0,0 +1,61 @@
+"""
+Ollama VLM Provider
+支持本地/自建 Ollama 服务
+"""
+
+import os
+from typing import List
+
+from .base import VLMProvider
+
+
+class OllamaProvider(VLMProvider):
+    """
+    Ollama 本地/自建服务提供商
+    使用 OpenAI-compatible API (/v1/chat/completions)
+    """
+
+    def __init__(
+        self,
+        ollama_url: str = None,
+        model: str = None,
+    ):
+        """
+        Args:
+            ollama_url: Ollama 服务地址，默认从环境变量 OLLAMA_URL 读取
+            model: 模型名称，默认从环境变量 VLM_MODEL 读取
+        """
+        self.ollama_url = ollama_url or os.getenv("OLLAMA_URL", "http://192.168.1.250:11434")
+        self.model = model or os.getenv("VLM_MODEL", "qwen2.5vl:32b")
+
+    def chat_vision(
+        self,
+        prompt: str,
+        image_paths: List[str],
+        temperature: float = 0.1,
+        timeout_sec: int = 120,
+    ) -> str:
+        """调用 Ollama 服务进行视觉推理"""
+        # 导入原有的 ollama_client 逻辑（复用代码）
+        from .. import ollama_client
+
+        # 临时覆盖模块常量（确保使用实例配置）
+        original_url = ollama_client.OLLAMA_URL
+        original_model = ollama_client.DEFAULT_MODEL
+        try:
+            ollama_client.OLLAMA_URL = self.ollama_url
+            ollama_client.DEFAULT_MODEL = self.model
+            return ollama_client.chat_vision(
+                prompt=prompt,
+                image_paths=image_paths,
+                temperature=temperature,
+                model=self.model,
+                timeout_sec=timeout_sec,
+            )
+        finally:
+            # 恢复原始值
+            ollama_client.OLLAMA_URL = original_url
+            ollama_client.DEFAULT_MODEL = original_model
+
+    def __repr__(self):
+        return f"<OllamaProvider url={self.ollama_url} model={self.model}>"