The multimodal agent has been basically completed.

MediaEngine/agent.py

@@ -19,7 +19,7 @@ from .nodes import (
     ReportFormattingNode
 )
 from .state import State
-from .tools import TavilyNewsAgency, TavilyResponse
+from .tools import BochaMultimodalSearch, BochaResponse
 from .utils import Config, load_config, format_search_results_for_prompt
 
 
@@ -40,7 +40,7 @@ class DeepSearchAgent:
         self.llm_client = self._initialize_llm()
         
         # 初始化搜索工具集
-        self.search_agency = TavilyNewsAgency(api_key=self.config.tavily_api_key)
+        self.search_agency = BochaMultimodalSearch(api_key=self.config.bocha_api_key)
         
         # 初始化节点
         self._initialize_nodes()
@@ -53,7 +53,7 @@ class DeepSearchAgent:
         
         print(f"Deep Search Agent 已初始化")
         print(f"使用LLM: {self.llm_client.get_model_info()}")
-        print(f"搜索工具集: TavilyNewsAgency (支持6种搜索工具)")
+        print(f"搜索工具集: BochaMultimodalSearch (支持5种多模态搜索工具)")
     
     def _initialize_llm(self) -> BaseLLM:
         """初始化LLM客户端"""
@@ -103,46 +103,40 @@ class DeepSearchAgent:
         except ValueError:
             return False
     
-    def execute_search_tool(self, tool_name: str, query: str, **kwargs) -> TavilyResponse:
+    def execute_search_tool(self, tool_name: str, query: str, **kwargs) -> BochaResponse:
         """
         执行指定的搜索工具
         
         Args:
             tool_name: 工具名称，可选值：
-                - "basic_search_news": 基础新闻搜索（快速、通用）
-                - "deep_search_news": 深度新闻分析
-                - "search_news_last_24_hours": 24小时内最新新闻
-                - "search_news_last_week": 本周新闻
-                - "search_images_for_news": 新闻图片搜索
-                - "search_news_by_date": 按日期范围搜索新闻
+                - "comprehensive_search": 全面综合搜索（默认）
+                - "web_search_only": 纯网页搜索
+                - "search_for_structured_data": 结构化数据查询
+                - "search_last_24_hours": 24小时内最新信息
+                - "search_last_week": 本周信息
             query: 搜索查询
-            **kwargs: 额外参数（如start_date, end_date, max_results）
+            **kwargs: 额外参数（如max_results）
             
         Returns:
-            TavilyResponse对象
+            BochaResponse对象
         """
         print(f"  → 执行搜索工具: {tool_name}")
         
-        if tool_name == "basic_search_news":
-            max_results = kwargs.get("max_results", 7)
-            return self.search_agency.basic_search_news(query, max_results)
-        elif tool_name == "deep_search_news":
-            return self.search_agency.deep_search_news(query)
-        elif tool_name == "search_news_last_24_hours":
-            return self.search_agency.search_news_last_24_hours(query)
-        elif tool_name == "search_news_last_week":
-            return self.search_agency.search_news_last_week(query)
-        elif tool_name == "search_images_for_news":
-            return self.search_agency.search_images_for_news(query)
-        elif tool_name == "search_news_by_date":
-            start_date = kwargs.get("start_date")
-            end_date = kwargs.get("end_date")
-            if not start_date or not end_date:
-                raise ValueError("search_news_by_date工具需要start_date和end_date参数")
-            return self.search_agency.search_news_by_date(query, start_date, end_date)
+        if tool_name == "comprehensive_search":
+            max_results = kwargs.get("max_results", 10)
+            return self.search_agency.comprehensive_search(query, max_results)
+        elif tool_name == "web_search_only":
+            max_results = kwargs.get("max_results", 15)
+            return self.search_agency.web_search_only(query, max_results)
+        elif tool_name == "search_for_structured_data":
+            return self.search_agency.search_for_structured_data(query)
+        elif tool_name == "search_last_24_hours":
+            return self.search_agency.search_last_24_hours(query)
+        elif tool_name == "search_last_week":
+            return self.search_agency.search_last_week(query)
         else:
-            print(f"  ⚠️  未知的搜索工具: {tool_name}，使用默认基础搜索")
-            return self.search_agency.basic_search_news(query)
+            print(f"  ⚠️  未知的搜索工具: {tool_name}，使用默认综合搜索")
+            return self.search_agency.comprehensive_search(query)
     
     def research(self, query: str, save_report: bool = True) -> str:
         """
@@ -231,7 +225,7 @@ class DeepSearchAgent:
         print("  - 生成搜索查询...")
         search_output = self.first_search_node.run(search_input)
         search_query = search_output["search_query"]
-        search_tool = search_output.get("search_tool", "basic_search_news")  # 默认工具
+        search_tool = search_output.get("search_tool", "comprehensive_search")  # 默认工具
         reasoning = search_output["reasoning"]
         
         print(f"  - 搜索查询: {search_query}")
@@ -241,41 +235,27 @@ class DeepSearchAgent:
         # 执行搜索
         print("  - 执行网络搜索...")
         
-        # 处理search_news_by_date的特殊参数
+        # 处理特殊参数（新的工具集不需要日期参数处理）
         search_kwargs = {}
-        if search_tool == "search_news_by_date":
-            start_date = search_output.get("start_date")
-            end_date = search_output.get("end_date")
-            
-            if start_date and end_date:
-                # 验证日期格式
-                if self._validate_date_format(start_date) and self._validate_date_format(end_date):
-                    search_kwargs["start_date"] = start_date
-                    search_kwargs["end_date"] = end_date
-                    print(f"  - 时间范围: {start_date} 到 {end_date}")
-                else:
-                    print(f"  ⚠️  日期格式错误（应为YYYY-MM-DD），改用基础搜索")
-                    print(f"      提供的日期: start_date={start_date}, end_date={end_date}")
-                    search_tool = "basic_search_news"
-            else:
-                print(f"  ⚠️  search_news_by_date工具缺少时间参数，改用基础搜索")
-                search_tool = "basic_search_news"
+        if search_tool in ["comprehensive_search", "web_search_only"]:
+            # 这些工具支持max_results参数
+            search_kwargs["max_results"] = 10
         
         search_response = self.execute_search_tool(search_tool, search_query, **search_kwargs)
         
         # 转换为兼容格式
         search_results = []
-        if search_response and search_response.results:
+        if search_response and search_response.webpages:
             # 每种搜索工具都有其特定的结果数量，这里取前10个作为上限
-            max_results = min(len(search_response.results), 10)
-            for result in search_response.results[:max_results]:
+            max_results = min(len(search_response.webpages), 10)
+            for result in search_response.webpages[:max_results]:
                 search_results.append({
-                    'title': result.title,
+                    'title': result.name,
                     'url': result.url,
-                    'content': result.content,
-                    'score': result.score,
-                    'raw_content': result.raw_content,
-                    'published_date': result.published_date  # 新增字段
+                    'content': result.snippet,
+                    'score': None,  # Bocha API不提供score
+                    'raw_content': result.snippet,
+                    'published_date': result.date_last_crawled  # 使用爬取日期
                 })
         
         if search_results:
@@ -324,7 +304,7 @@ class DeepSearchAgent:
             # 生成反思搜索查询
             reflection_output = self.reflection_node.run(reflection_input)
             search_query = reflection_output["search_query"]
-            search_tool = reflection_output.get("search_tool", "basic_search_news")  # 默认工具
+            search_tool = reflection_output.get("search_tool", "comprehensive_search")  # 默认工具
             reasoning = reflection_output["reasoning"]
             
             print(f"    反思查询: {search_query}")
@@ -332,41 +312,27 @@ class DeepSearchAgent:
             print(f"    反思推理: {reasoning}")
             
             # 执行反思搜索
-            # 处理search_news_by_date的特殊参数
+            # 处理特殊参数
             search_kwargs = {}
-            if search_tool == "search_news_by_date":
-                start_date = reflection_output.get("start_date")
-                end_date = reflection_output.get("end_date")
-                
-                if start_date and end_date:
-                    # 验证日期格式
-                    if self._validate_date_format(start_date) and self._validate_date_format(end_date):
-                        search_kwargs["start_date"] = start_date
-                        search_kwargs["end_date"] = end_date
-                        print(f"    时间范围: {start_date} 到 {end_date}")
-                    else:
-                        print(f"    ⚠️  日期格式错误（应为YYYY-MM-DD），改用基础搜索")
-                        print(f"        提供的日期: start_date={start_date}, end_date={end_date}")
-                        search_tool = "basic_search_news"
-                else:
-                    print(f"    ⚠️  search_news_by_date工具缺少时间参数，改用基础搜索")
-                    search_tool = "basic_search_news"
+            if search_tool in ["comprehensive_search", "web_search_only"]:
+                # 这些工具支持max_results参数
+                search_kwargs["max_results"] = 10
             
             search_response = self.execute_search_tool(search_tool, search_query, **search_kwargs)
             
             # 转换为兼容格式
             search_results = []
-            if search_response and search_response.results:
+            if search_response and search_response.webpages:
                 # 每种搜索工具都有其特定的结果数量，这里取前10个作为上限
-                max_results = min(len(search_response.results), 10)
-                for result in search_response.results[:max_results]:
+                max_results = min(len(search_response.webpages), 10)
+                for result in search_response.webpages[:max_results]:
                     search_results.append({
-                        'title': result.title,
+                        'title': result.name,
                         'url': result.url,
-                        'content': result.content,
-                        'score': result.score,
-                        'raw_content': result.raw_content,
-                        'published_date': result.published_date
+                        'content': result.snippet,
+                        'score': None,  # Bocha API不提供score
+                        'raw_content': result.snippet,
+                        'published_date': result.date_last_crawled
                     })
             
             if search_results: