Update app.py

app.py

@@ -7,16 +7,59 @@ from tools.final_answer import FinalAnswerTool
 
 from Gradio_UI import GradioUI
 
-# Below is an example of a tool that does nothing. Amaze us with your creativity !
 @tool
-def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
-    #Keep this format for the description / args / args description but feel free to modify the tool
-    """A tool that does nothing yet 
+def summarize_webpage(url: str, max_length: int = 300) -> str:
+    """A tool that fetches a webpage and provides a concise summary of its content.
+    
     Args:
-        arg1: the first argument
-        arg2: the second argument
+        url: The URL of the webpage to summarize
+        max_length: Maximum length of the summary in characters
     """
-    return "What magic will you build ?"
+    try:
+        import requests
+        from bs4 import BeautifulSoup
+        import re
+        
+        # Fetch the webpage
+        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'}
+        response = requests.get(url, headers=headers, timeout=10)
+        response.raise_for_status()
+        
+        # Parse HTML content
+        soup = BeautifulSoup(response.content, 'html.parser')
+        
+        # Remove script and style elements
+        for script in soup(["script", "style", "header", "footer", "nav"]):
+            script.extract()
+            
+        # Get text and clean it
+        text = soup.get_text()
+        lines = (line.strip() for line in text.splitlines())
+        chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
+        text = '\n'.join(chunk for chunk in chunks if chunk)
+        
+        # Remove excessive newlines and whitespace
+        text = re.sub(r'\n+', '\n', text)
+        text = re.sub(r'\s+', ' ', text)
+        
+        # Truncate to avoid overwhelming the model
+        text = text[:10000] if len(text) > 10000 else text
+        
+        # Get title
+        title = soup.title.string if soup.title else "Unknown Title"
+        
+        # For the summarization, we'll use our agent's model directly
+        # Note: This assumes the agent will handle the summarization part
+        
+        return {
+            "title": title,
+            "url": url,
+            "content": text,
+            "summary_request": f"Please summarize the above webpage content in no more than {max_length} characters."
+        }
+        
+    except Exception as e:
+        return f"Error fetching or processing webpage: {str(e)}"
 
 @tool
 def get_current_time_in_timezone(timezone: str) -> str: