Merge pull request #549 from Kingtous/main

feat: add Baidu, DuckDuckGo search tool and optional config

app/agent/manus.py

@@ -7,8 +7,9 @@ from app.prompt.manus import NEXT_STEP_PROMPT, SYSTEM_PROMPT
 from app.tool import Terminate, ToolCollection
 from app.tool.browser_use_tool import BrowserUseTool
 from app.tool.file_saver import FileSaver
-from app.tool.google_search import GoogleSearch
+from app.tool.web_search import WebSearch
 from app.tool.python_execute import PythonExecute
+from app.config import config
 
 
 class Manus(ToolCallAgent):
@@ -34,7 +35,7 @@ class Manus(ToolCallAgent):
     # Add general-purpose tools to the tool collection
     available_tools: ToolCollection = Field(
         default_factory=lambda: ToolCollection(
-            PythonExecute(), GoogleSearch(), BrowserUseTool(), FileSaver(), Terminate()
+            PythonExecute(), WebSearch(), BrowserUseTool(), FileSaver(), Terminate()
         )
     )
 

app/config.py

@@ -30,6 +30,8 @@ class ProxySettings(BaseModel):
     username: Optional[str] = Field(None, description="Proxy username")
     password: Optional[str] = Field(None, description="Proxy password")
 
+class SearchSettings(BaseModel):
+    engine: str = Field(default='Google', description="Search engine the llm to use")
 
 class BrowserSettings(BaseModel):
     headless: bool = Field(False, description="Whether to run browser in headless mode")
@@ -58,6 +60,9 @@ class AppConfig(BaseModel):
     browser_config: Optional[BrowserSettings] = Field(
         None, description="Browser configuration"
     )
+    search_config: Optional[SearchSettings] = Field(
+        None, description="Search configuration"
+    )
 
     class Config:
         arbitrary_types_allowed = True
@@ -149,6 +154,11 @@ class Config:
             if valid_browser_params:
                 browser_settings = BrowserSettings(**valid_browser_params)
 
+        search_config = raw_config.get("search", {})
+        search_settings = None
+        if search_config:
+            search_settings = SearchSettings(**search_config)
+
         config_dict = {
             "llm": {
                 "default": default_settings,
@@ -158,6 +168,7 @@ class Config:
                 },
             },
             "browser_config": browser_settings,
+            "search_config": search_settings,
         }
 
         self._config = AppConfig(**config_dict)
@@ -170,5 +181,9 @@ class Config:
     def browser_config(self) -> Optional[BrowserSettings]:
         return self._config.browser_config
     
+    @property
+    def search_config(self) -> Optional[SearchSettings]:
+        return self._config.search_config
+
 
 config = Config()

app/prompt/manus.py

@@ -8,7 +8,7 @@ FileSaver: Save files locally, such as txt, py, html, etc.
 
 BrowserUseTool: Open, browse, and use web browsers.If you open a local HTML file, you must provide the absolute path to the file.
 
-GoogleSearch: Perform web information retrieval
+WebSearch: Perform web information retrieval
 
 Terminate: End the current interaction when the task is complete or when you need additional information from the user. Use this tool to signal that you've finished addressing the user's request or need clarification before proceeding further.
 

app/tool/search/__init__.py

@@ -0,0 +1,12 @@
+from app.tool.search.base import WebSearchEngine
+from app.tool.search.baidu_search import BaiduSearchEngine
+from app.tool.search.duckduckgo_search import DuckDuckGoSearchEngine
+from app.tool.search.google_search import GoogleSearchEngine
+
+
+__all__ = [
+    "WebSearchEngine",
+    "BaiduSearchEngine",
+    "DuckDuckGoSearchEngine",
+    "GoogleSearchEngine",
+]

app/tool/search/baidu_search.py

@@ -0,0 +1,9 @@
+from baidusearch.baidusearch import search
+from app.tool.search.base import WebSearchEngine
+
+
+class BaiduSearchEngine(WebSearchEngine):
+    
+    def perform_search(self, query, num_results = 10, *args, **kwargs):
+        """Baidu search engine."""
+        return search(query, num_results=num_results)

app/tool/search/base.py

@@ -0,0 +1,15 @@
+class WebSearchEngine(object):
+    def perform_search(self, query: str, num_results: int = 10, *args, **kwargs) -> list[dict]:
+        """
+        Perform a web search and return a list of URLs.
+
+        Args:
+            query (str): The search query to submit to the search engine.
+            num_results (int, optional): The number of search results to return. Default is 10.
+            args: Additional arguments.
+            kwargs: Additional keyword arguments.
+
+        Returns:
+            List: A list of dict matching the search query.
+        """
+        raise NotImplementedError

app/tool/search/duckduckgo_search.py

@@ -0,0 +1,9 @@
+from duckduckgo_search import DDGS
+from app.tool.search.base import WebSearchEngine
+
+
+class DuckDuckGoSearchEngine(WebSearchEngine):
+    
+    async def perform_search(self, query, num_results = 10, *args, **kwargs):
+        """DuckDuckGo search engine."""
+        return DDGS.text(query, num_results=num_results)

app/tool/search/google_search.py

@@ -0,0 +1,8 @@
+from app.tool.search.base import WebSearchEngine
+from googlesearch import search
+
+class GoogleSearchEngine(WebSearchEngine):
+    
+    def perform_search(self, query, num_results = 10, *args, **kwargs):
+        """Google search engine."""
+        return search(query, num_results=num_results)

app/tool/web_search.py

@@ -1,14 +1,14 @@
 import asyncio
 from typing import List
 
-from googlesearch import search
-
 from app.tool.base import BaseTool
+from app.config import config
+from app.tool.search import WebSearchEngine, BaiduSearchEngine, GoogleSearchEngine, DuckDuckGoSearchEngine
 
 
-class GoogleSearch(BaseTool):
+class WebSearch(BaseTool):
-    name: str = "google_search"
+    name: str = "web_search"
-    description: str = """Perform a Google search and return a list of relevant links.
+    description: str = """Perform a web search and return a list of relevant links.
 Use this tool when you need to find information on the web, get up-to-date data, or research specific topics.
 The tool returns a list of URLs that match the search query.
 """
@@ -17,7 +17,7 @@ The tool returns a list of URLs that match the search query.
         "properties": {
             "query": {
                 "type": "string",
-                "description": "(required) The search query to submit to Google.",
+                "description": "(required) The search query to submit to the search engine.",
             },
             "num_results": {
                 "type": "integer",
@@ -27,13 +27,18 @@ The tool returns a list of URLs that match the search query.
         },
         "required": ["query"],
     }
+    _search_engine: dict[str, WebSearchEngine] = {
+        "google": GoogleSearchEngine(),
+        "baidu": BaiduSearchEngine(),
+        "duckduckgo": DuckDuckGoSearchEngine(),
+    }
 
     async def execute(self, query: str, num_results: int = 10) -> List[str]:
         """
-        Execute a Google search and return a list of URLs.
+        Execute a Web search and return a list of URLs.
 
         Args:
-            query (str): The search query to submit to Google.
+            query (str): The search query to submit to the search engine.
             num_results (int, optional): The number of search results to return. Default is 10.
 
         Returns:
@@ -41,8 +46,18 @@ The tool returns a list of URLs that match the search query.
         """
         # Run the search in a thread pool to prevent blocking
         loop = asyncio.get_event_loop()
+        search_engine = self.get_search_engine()
         links = await loop.run_in_executor(
-            None, lambda: list(search(query, num_results=num_results))
+            None, lambda: list(search_engine.perform_search(query, num_results=num_results))
         )
 
         return links
+
+    def get_search_engine(self) -> WebSearchEngine:
+        """Determines the search engine to use based on the configuration."""
+        default_engine = self._search_engine.get("google")
+        if config.search_config is None:
+            return default_engine
+        else:
+            engine = config.search_config.engine.lower()
+            return self._search_engine.get(engine, default_engine)

config/config.example.toml

@@ -42,3 +42,8 @@ api_key = "sk-..."
 # server = "http://proxy-server:port"
 # username = "proxy-username"
 # password = "proxy-password"
+
+# Optional configuration, Search settings.
+# [search]
+# Search engine for agent to use. Default is "Google", can be set to "Baidu" or "DuckDuckGo".
+#engine = "Google"

requirements.txt

@@ -15,6 +15,8 @@ uvicorn~=0.34.0
 unidiff~=0.7.5
 browser-use~=0.1.40
 googlesearch-python~=1.3.0
+baidusearch~=1.0.3
+duckduckgo_search~=7.5.1
 
 aiofiles~=24.1.0
 pydantic_core~=2.27.2