Implement DuckDuckGo search (#1432)

* Implement DuckDuckGo search

* docs: add DuckDuckGo web search to config example

backend/packages/harness/deerflow/community/ddg_search/__init__.py

@@ -0,0 +1,3 @@
+from .tools import web_search_tool
+
+__all__ = ["web_search_tool"]

backend/packages/harness/deerflow/community/ddg_search/tools.py

@@ -0,0 +1,95 @@
+"""
+Web Search Tool - Search the web using DuckDuckGo (no API key required).
+"""
+
+import json
+import logging
+
+from langchain.tools import tool
+
+from deerflow.config import get_app_config
+
+logger = logging.getLogger(__name__)
+
+
+def _search_text(
+    query: str,
+    max_results: int = 5,
+    region: str = "wt-wt",
+    safesearch: str = "moderate",
+) -> list[dict]:
+    """
+    Execute text search using DuckDuckGo.
+
+    Args:
+        query: Search keywords
+        max_results: Maximum number of results
+        region: Search region
+        safesearch: Safe search level
+
+    Returns:
+        List of search results
+    """
+    try:
+        from ddgs import DDGS
+    except ImportError:
+        logger.error("ddgs library not installed. Run: pip install ddgs")
+        return []
+
+    ddgs = DDGS(timeout=30)
+
+    try:
+        results = ddgs.text(
+            query,
+            region=region,
+            safesearch=safesearch,
+            max_results=max_results,
+        )
+        return list(results) if results else []
+
+    except Exception as e:
+        logger.error(f"Failed to search web: {e}")
+        return []
+
+
+@tool("web_search", parse_docstring=True)
+def web_search_tool(
+    query: str,
+    max_results: int = 5,
+) -> str:
+    """Search the web for information. Use this tool to find current information, news, articles, and facts from the internet.
+
+    Args:
+        query: Search keywords describing what you want to find. Be specific for better results.
+        max_results: Maximum number of results to return. Default is 5.
+    """
+    config = get_app_config().get_tool_config("web_search")
+
+    # Override max_results from config if set
+    if config is not None and "max_results" in config.model_extra:
+        max_results = config.model_extra.get("max_results", max_results)
+
+    results = _search_text(
+        query=query,
+        max_results=max_results,
+    )
+
+    if not results:
+        return json.dumps({"error": "No results found", "query": query}, ensure_ascii=False)
+
+    normalized_results = [
+        {
+            "title": r.get("title", ""),
+            "url": r.get("href", r.get("link", "")),
+            "content": r.get("body", r.get("snippet", "")),
+        }
+        for r in results
+    ]
+
+    output = {
+        "query": query,
+        "total_results": len(normalized_results),
+        "results": normalized_results,
+    }
+
+    return json.dumps(output, indent=2, ensure_ascii=False)

config.example.yaml

@@ -231,12 +231,18 @@ tool_groups:
 # Configure available tools for the agent to use
 
 tools:
-  # Web search tool (requires Tavily API key)
+  # Web search tool (uses DuckDuckGo, no API key required)
   - name: web_search
     group: web
-    use: deerflow.community.tavily.tools:web_search_tool
+    use: deerflow.community.ddg_search.tools:web_search_tool
     max_results: 5
-    # api_key: $TAVILY_API_KEY  # Set if needed
+
+  # Web search tool (requires Tavily API key)
+  # - name: web_search
+  #   group: web
+  #   use: deerflow.community.tavily.tools:web_search_tool
+  #   max_results: 5
+  #   # api_key: $TAVILY_API_KEY  # Set if needed
 
   # Web search tool (uses InfoQuest, requires InfoQuest API key)
   # - name: web_search