Update tools/web_search.py

tools/web_search.py

@@ -1,27 +1,96 @@
-from typing import Any, Optional
+from typing import List
 from smolagents.tools import Tool
-import duckduckgo_search
+
 
 class DuckDuckGoSearchTool(Tool):
+    """
+    Performs a DuckDuckGo web search and returns formatted search results.
+    """
+
     name = "web_search"
-    description = "Performs a duckduckgo web search based on your query (think a Google search) then returns the top search results."
-    inputs = {'query': {'type': 'string', 'description': 'The search query to perform.'}}
+
+    description = (
+        "Searches the web using DuckDuckGo and returns the most relevant "
+        "search results. Use this whenever factual or current information "
+        "is required."
+    )
+
+    inputs = {
+        "query": {
+            "type": "string",
+            "description": "Search query."
+        }
+    }
+
     output_type = "string"
 
-    def __init__(self, max_results=10, **kwargs):
+    def __init__(self, max_results: int = 5):
+
         super().__init__()
+
         self.max_results = max_results
+
         try:
-            from duckduckgo_search import DDGS
+
+            from ddgs import DDGS
+
+            self.ddgs = DDGS()
+
         except ImportError as e:
+
             raise ImportError(
-                "You must install package `duckduckgo_search` to run this tool: for instance run `pip install duckduckgo-search`."
+                "Install ddgs using:\n\npip install ddgs"
             ) from e
-        self.ddgs = DDGS(**kwargs)
 
     def forward(self, query: str) -> str:
-        results = self.ddgs.text(query, max_results=self.max_results)
-        if len(results) == 0:
-            raise Exception("No results found! Try a less restrictive/shorter query.")
-        postprocessed_results = [f"[{result['title']}]({result['href']})\n{result['body']}" for result in results]
-        return "## Search Results\n\n" + "\n\n".join(postprocessed_results)
+
+        try:
+
+            results = list(
+                self.ddgs.text(
+                    query,
+                    max_results=self.max_results
+                )
+            )
+
+        except Exception as e:
+
+            return f"Search failed.\nReason: {e}"
+
+        if not results:
+
+            return "No search results found."
+
+        formatted = []
+
+        seen_urls = set()
+
+        for i, result in enumerate(results, start=1):
+
+            title = result.get("title", "No title")
+
+            url = result.get("href", "")
+
+            snippet = result.get("body", "")
+
+            if url in seen_urls:
+                continue
+
+            seen_urls.add(url)
+
+            formatted.append(
+                f"""
+Result {i}
+
+Title:
+{title}
+
+URL:
+{url}
+
+Snippet:
+{snippet}
+"""
+            )
+
+        return "\n".join(formatted)