增加Kimi多模态Api,这样可以灵活选择！

exp_multimodal/exp_multimodal_gui.py

@@ -15,7 +15,7 @@ from tkinterdnd2 import DND_FILES, TkinterDnD
 from exp_multimodal.labels import build_labels, _normalize, _base_ingredient
 from exp_multimodal.vlm_classifier import classify_image
 from exp_multimodal.ollama_client import OLLAMA_URL as DEFAULT_OLLAMA_URL, DEFAULT_MODEL as DEFAULT_VLM_MODEL
-from exp_multimodal import ollama_client as _ollama_mod
+from exp_multimodal.vlm_providers import VLMProvider, OllamaProvider, KimiProvider
 
 
 ctk.set_appearance_mode("System")
@@ -38,8 +38,15 @@ class MultiModalFoodApp:
 
         # 配置
         self.mode_var = ctk.StringVar(value="dish")  # dish | whole | processed
+        
+        # VLM Provider 配置
+        self.provider_var = ctk.StringVar(value="ollama")  # ollama | kimi
         self.ollama_url_var = ctk.StringVar(value=DEFAULT_OLLAMA_URL)
         self.vlm_model_var = ctk.StringVar(value=DEFAULT_VLM_MODEL)
+        self.kimi_api_key_var = ctk.StringVar(value="")
+        self.kimi_base_url_var = ctk.StringVar(value="https://api.moonshot.cn/v1")
+        self.kimi_model_var = ctk.StringVar(value="moonshot-v1-32k-vision-preview")
+        
         self.alias_map_path: Optional[str] = None
 
         # Fewshot 可视化编辑（C 方案）: dict[label] = hint
@@ -58,6 +65,9 @@ class MultiModalFoodApp:
 
         # UI
         self.create_widgets()
+        
+        # 加载保存的配置
+        self.load_config()
 
     # -------------------- 图像加载工具 --------------------
     def load_image_with_chinese_path(self, file_path: str):
@@ -323,14 +333,58 @@ class MultiModalFoodApp:
             rb = ctk.CTkRadioButton(mode_frame, text=text, variable=self.mode_var, value=val)
             rb.pack(side="left", padx=8, pady=8)
 
-        # 服务配置
-        ctk.CTkLabel(panel, text="VLM 服务配置", font=("Arial", 14, "bold")).pack(anchor="w", pady=(10, 6))
-        svc = ctk.CTkFrame(panel)
-        svc.pack(fill="x", pady=(0, 10))
-        ctk.CTkLabel(svc, text="OLLAMA_URL:").pack(side="left", padx=6, pady=8)
-        ctk.CTkEntry(svc, textvariable=self.ollama_url_var, width=320).pack(side="left", padx=4, pady=8)
-        ctk.CTkLabel(svc, text="VLM_MODEL:").pack(side="left", padx=12, pady=8)
-        ctk.CTkEntry(svc, textvariable=self.vlm_model_var, width=220).pack(side="left", padx=4, pady=8)
+        # VLM 服务提供商选择
+        ctk.CTkLabel(panel, text="VLM 服务提供商", font=("Arial", 14, "bold")).pack(anchor="w", pady=(10, 6))
+        provider_frame = ctk.CTkFrame(panel)
+        provider_frame.pack(fill="x", pady=(0, 10))
+        
+        for val, text in [("ollama", "Ollama (本地/自建)"), ("kimi", "Kimi 1.5 (厂商API)")]:
+            rb = ctk.CTkRadioButton(
+                provider_frame, 
+                text=text, 
+                variable=self.provider_var, 
+                value=val,
+                command=self.on_provider_change
+            )
+            rb.pack(side="left", padx=8, pady=8)
+
+        # Ollama 配置区域
+        self.ollama_config_frame = ctk.CTkFrame(panel)
+        self.ollama_config_frame.pack(fill="x", pady=(0, 10))
+        ctk.CTkLabel(self.ollama_config_frame, text="Ollama 配置", font=("Arial", 12, "bold")).pack(anchor="w", pady=(4, 4))
+        
+        ollama_row1 = ctk.CTkFrame(self.ollama_config_frame)
+        ollama_row1.pack(fill="x", pady=(0, 4))
+        ctk.CTkLabel(ollama_row1, text="OLLAMA_URL:").pack(side="left", padx=6, pady=4)
+        ctk.CTkEntry(ollama_row1, textvariable=self.ollama_url_var, width=420).pack(side="left", padx=4, pady=4)
+        
+        ollama_row2 = ctk.CTkFrame(self.ollama_config_frame)
+        ollama_row2.pack(fill="x", pady=(0, 4))
+        ctk.CTkLabel(ollama_row2, text="MODEL:").pack(side="left", padx=6, pady=4)
+        ctk.CTkEntry(ollama_row2, textvariable=self.vlm_model_var, width=420).pack(side="left", padx=4, pady=4)
+
+        # Kimi 配置区域
+        self.kimi_config_frame = ctk.CTkFrame(panel)
+        self.kimi_config_frame.pack(fill="x", pady=(0, 10))
+        ctk.CTkLabel(self.kimi_config_frame, text="Kimi 配置", font=("Arial", 12, "bold")).pack(anchor="w", pady=(4, 4))
+        
+        kimi_row1 = ctk.CTkFrame(self.kimi_config_frame)
+        kimi_row1.pack(fill="x", pady=(0, 4))
+        ctk.CTkLabel(kimi_row1, text="API_KEY:").pack(side="left", padx=6, pady=4)
+        ctk.CTkEntry(kimi_row1, textvariable=self.kimi_api_key_var, width=420, show="*").pack(side="left", padx=4, pady=4)
+        
+        kimi_row2 = ctk.CTkFrame(self.kimi_config_frame)
+        kimi_row2.pack(fill="x", pady=(0, 4))
+        ctk.CTkLabel(kimi_row2, text="BASE_URL:").pack(side="left", padx=6, pady=4)
+        ctk.CTkEntry(kimi_row2, textvariable=self.kimi_base_url_var, width=420).pack(side="left", padx=4, pady=4)
+        
+        kimi_row3 = ctk.CTkFrame(self.kimi_config_frame)
+        kimi_row3.pack(fill="x", pady=(0, 4))
+        ctk.CTkLabel(kimi_row3, text="MODEL:").pack(side="left", padx=6, pady=4)
+        ctk.CTkEntry(kimi_row3, textvariable=self.kimi_model_var, width=420).pack(side="left", padx=4, pady=4)
+
+        # 初始化显示状态
+        self.on_provider_change()
 
         # Alias Map
         alias = ctk.CTkFrame(panel)
@@ -385,6 +439,16 @@ class MultiModalFoodApp:
         self.refresh_extra_labels_view()
         self.refresh_fewshot_view()
 
+        # 配置保存/加载
+        cfg_manage = ctk.CTkFrame(panel)
+        cfg_manage.pack(fill="x", pady=(10, 10))
+        ctk.CTkLabel(cfg_manage, text="配置管理", font=("Arial", 14, "bold")).pack(anchor="w", pady=(0, 6))
+        cfg_row = ctk.CTkFrame(cfg_manage)
+        cfg_row.pack(fill="x")
+        ctk.CTkButton(cfg_row, text="保存当前配置", command=self.save_config, width=140, fg_color="blue", hover_color="darkblue").pack(side="left", padx=6)
+        ctk.CTkButton(cfg_row, text="加载配置", command=self.load_config_from_file, width=140).pack(side="left", padx=6)
+        ctk.CTkLabel(cfg_row, text="(自动保存到 config.json)", font=("Arial", 10), text_color="gray").pack(side="left", padx=12)
+
     def pick_alias_file(self):
         path = filedialog.askopenfilename(title="选择 alias_map.json", filetypes=[("JSON 文件", "*.json"), ("所有文件", "*.*")])
         if path:
@@ -395,6 +459,16 @@ class MultiModalFoodApp:
         self.alias_map_path = None
         self.alias_label_var.set("未选择")
 
+    def on_provider_change(self):
+        """切换 Provider 时显示/隐藏对应的配置区域"""
+        provider = self.provider_var.get()
+        if provider == "ollama":
+            self.ollama_config_frame.pack(fill="x", pady=(0, 10), before=self.kimi_config_frame)
+            self.kimi_config_frame.pack_forget()
+        elif provider == "kimi":
+            self.kimi_config_frame.pack(fill="x", pady=(0, 10), before=self.ollama_config_frame)
+            self.ollama_config_frame.pack_forget()
+
     # 额外标签编辑
     def refresh_extra_labels_view(self):
         self.extra_labels_listbox.configure(state="normal")
@@ -562,12 +636,13 @@ class MultiModalFoodApp:
             labels = self._build_final_labels(mode)
             ingredient_only = (mode in {"whole", "processed"})
             use_hints = self.fewshot_hints if self.fewshot_enabled_var.get() else None
-            # 环境覆盖（仅对运行时生效，不修改模块常量）
-            os.environ["OLLAMA_URL"] = self.ollama_url_var.get().strip() or DEFAULT_OLLAMA_URL
-            os.environ["VLM_MODEL"] = self.vlm_model_var.get().strip() or DEFAULT_VLM_MODEL
-            # 同时覆盖已导入模块中的运行时常量，确保 classify 调用使用最新配置
-            _ollama_mod.OLLAMA_URL = os.environ["OLLAMA_URL"]
-            _ollama_mod.DEFAULT_MODEL = os.environ["VLM_MODEL"]
+
+            # 创建 VLM Provider
+            provider = self._create_vlm_provider()
+            if provider is None:
+                self.root.after(0, lambda: messagebox.showerror("错误", "Provider 配置错误，请检查配置"))
+                self.root.after(0, self.recognition_completed)
+                return
 
             self.current_results.clear()
             for i, img in enumerate(self.uploaded_images):
@@ -575,12 +650,13 @@ class MultiModalFoodApp:
                     result = classify_image(
                         image_path=img['path'],
                         labels=labels,
+                        provider=provider,
                         fewshot_hints=use_hints,
                         ingredient_only=ingredient_only,
                     )
                     pred = result.get("label", "Unknown")
                     conf = result.get("confidence", 0.0)
-                    # 若非数值，后续展示为 N/A
+                    # 若非数值,后续展示为 N/A
                     if not isinstance(conf, (int, float)):
                         try:
                             conf = float(conf)
@@ -619,6 +695,33 @@ class MultiModalFoodApp:
             self.root.after(0, lambda: messagebox.showerror("错误", f"识别过程中出错: {e}"))
             self.root.after(0, self.recognition_completed)
 
+    def _create_vlm_provider(self) -> Optional[VLMProvider]:
+        """根据配置创建 VLM Provider"""
+        provider_type = self.provider_var.get()
+        
+        try:
+            if provider_type == "ollama":
+                url = self.ollama_url_var.get().strip() or DEFAULT_OLLAMA_URL
+                model = self.vlm_model_var.get().strip() or DEFAULT_VLM_MODEL
+                return OllamaProvider(ollama_url=url, model=model)
+            
+            elif provider_type == "kimi":
+                api_key = self.kimi_api_key_var.get().strip()
+                if not api_key:
+                    messagebox.showerror("错误", "Kimi API Key 不能为空")
+                    return None
+                base_url = self.kimi_base_url_var.get().strip() or "https://api.moonshot.cn/v1"
+                model = self.kimi_model_var.get().strip() or "moonshot-v1-32k-vision-preview"
+                return KimiProvider(api_key=api_key, base_url=base_url, model=model)
+            
+            else:
+                messagebox.showerror("错误", f"未知的 Provider 类型: {provider_type}")
+                return None
+                
+        except Exception as e:
+            messagebox.showerror("错误", f"创建 Provider 失败: {e}")
+            return None
+
     def update_progress(self, current: int, total: int):
         self.recognize_button.configure(text=f"识别中... ({current}/{total})")
         self.update_images_display()
@@ -631,6 +734,142 @@ class MultiModalFoodApp:
         self.update_stats()
         messagebox.showinfo("完成", f"所有图片识别完成！耗时: {self.recognition_duration:.2f}秒")
 
+    # -------------------- 配置管理 --------------------
+    def get_config_path(self) -> str:
+        """获取配置文件路径（项目根目录下的 config.json）"""
+        return os.path.join(os.path.dirname(os.path.dirname(__file__)), "vlm_config.json")
+
+    def save_config(self):
+        """保存当前配置到 JSON 文件"""
+        config = {
+            "mode": self.mode_var.get(),
+            "provider": self.provider_var.get(),
+            "ollama": {
+                "url": self.ollama_url_var.get(),
+                "model": self.vlm_model_var.get(),
+            },
+            "kimi": {
+                "api_key": self.kimi_api_key_var.get(),
+                "base_url": self.kimi_base_url_var.get(),
+                "model": self.kimi_model_var.get(),
+            },
+            "alias_map_path": self.alias_map_path,
+            "fewshot_enabled": self.fewshot_enabled_var.get(),
+            "fewshot_hints": self.fewshot_hints,
+            "fewshot_file_path": self.fewshot_file_path,
+            "extra_labels": self.extra_labels,
+            "extra_labels_file_path": self.extra_labels_file_path,
+        }
+        
+        try:
+            config_path = self.get_config_path()
+            with open(config_path, "w", encoding="utf-8") as f:
+                json.dump(config, f, ensure_ascii=False, indent=2)
+            messagebox.showinfo("成功", f"配置已保存到 {os.path.basename(config_path)}")
+        except Exception as e:
+            messagebox.showerror("错误", f"保存配置失败: {e}")
+
+    def load_config(self):
+        """自动加载配置（启动时调用）"""
+        config_path = self.get_config_path()
+        if not os.path.exists(config_path):
+            return
+        
+        try:
+            with open(config_path, "r", encoding="utf-8") as f:
+                config = json.load(f)
+            
+            # 恢复配置
+            if "mode" in config:
+                self.mode_var.set(config["mode"])
+            if "provider" in config:
+                self.provider_var.set(config["provider"])
+            
+            if "ollama" in config:
+                self.ollama_url_var.set(config["ollama"].get("url", DEFAULT_OLLAMA_URL))
+                self.vlm_model_var.set(config["ollama"].get("model", DEFAULT_VLM_MODEL))
+            
+            if "kimi" in config:
+                self.kimi_api_key_var.set(config["kimi"].get("api_key", ""))
+                self.kimi_base_url_var.set(config["kimi"].get("base_url", "https://api.moonshot.cn/v1"))
+                self.kimi_model_var.set(config["kimi"].get("model", "moonshot-v1-32k-vision-preview"))
+            
+            if "alias_map_path" in config and config["alias_map_path"]:
+                self.alias_map_path = config["alias_map_path"]
+                self.alias_label_var.set(os.path.basename(self.alias_map_path))
+            
+            if "fewshot_enabled" in config:
+                self.fewshot_enabled_var.set(config["fewshot_enabled"])
+            if "fewshot_hints" in config:
+                self.fewshot_hints = config["fewshot_hints"]
+            if "fewshot_file_path" in config:
+                self.fewshot_file_path = config["fewshot_file_path"]
+            
+            if "extra_labels" in config:
+                self.extra_labels = config["extra_labels"]
+            if "extra_labels_file_path" in config:
+                self.extra_labels_file_path = config["extra_labels_file_path"]
+            
+            self.refresh_extra_labels_view()
+            self.refresh_fewshot_view()
+            self.on_provider_change()
+            
+            print(f"[Config] 配置已从 {config_path} 加载")
+        except Exception as e:
+            print(f"[Config] 加载配置失败: {e}")
+
+    def load_config_from_file(self):
+        """从用户选择的文件加载配置"""
+        path = filedialog.askopenfilename(
+            title="选择配置文件",
+            filetypes=[("JSON 文件", "*.json"), ("所有文件", "*.*")]
+        )
+        if not path:
+            return
+        
+        try:
+            with open(path, "r", encoding="utf-8") as f:
+                config = json.load(f)
+            
+            # 恢复配置（同上）
+            if "mode" in config:
+                self.mode_var.set(config["mode"])
+            if "provider" in config:
+                self.provider_var.set(config["provider"])
+            
+            if "ollama" in config:
+                self.ollama_url_var.set(config["ollama"].get("url", DEFAULT_OLLAMA_URL))
+                self.vlm_model_var.set(config["ollama"].get("model", DEFAULT_VLM_MODEL))
+            
+            if "kimi" in config:
+                self.kimi_api_key_var.set(config["kimi"].get("api_key", ""))
+                self.kimi_base_url_var.set(config["kimi"].get("base_url", "https://api.moonshot.cn/v1"))
+                self.kimi_model_var.set(config["kimi"].get("model", "moonshot-v1-32k-vision-preview"))
+            
+            if "alias_map_path" in config and config["alias_map_path"]:
+                self.alias_map_path = config["alias_map_path"]
+                self.alias_label_var.set(os.path.basename(self.alias_map_path))
+            
+            if "fewshot_enabled" in config:
+                self.fewshot_enabled_var.set(config["fewshot_enabled"])
+            if "fewshot_hints" in config:
+                self.fewshot_hints = config["fewshot_hints"]
+            if "fewshot_file_path" in config:
+                self.fewshot_file_path = config["fewshot_file_path"]
+            
+            if "extra_labels" in config:
+                self.extra_labels = config["extra_labels"]
+            if "extra_labels_file_path" in config:
+                self.extra_labels_file_path = config["extra_labels_file_path"]
+            
+            self.refresh_extra_labels_view()
+            self.refresh_fewshot_view()
+            self.on_provider_change()
+            
+            messagebox.showinfo("成功", f"配置已从 {os.path.basename(path)} 加载")
+        except Exception as e:
+            messagebox.showerror("错误", f"加载配置失败: {e}")
+
 
 def main():
     root = TkinterDnD.Tk()  # 必须使用 TkinterDnD.Tk 以支持拖拽