Update fetch_and_read_URL

app.py

@@ -10,17 +10,18 @@ from tools.final_answer import FinalAnswerTool
 from Gradio_UI import GradioUI
 
 @tool
-def fetch_and_summarize_url(url:str, char_limit:int = 1500)-> dict: #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 fetches the content from a given URL, extracts the meaningful text, and returns a structured summary with the estimated reading time
+def fetch_and_summarize_url(url: str, char_limit: int = 1500) -> dict:
+    """A tool that fetches the content from a given URL, extracts the meaningful text,
+    and returns a structured summary with the estimated reading time.
+    
     Args:
-        url: the URL, where data will be fetched from
+        url: the URL where data will be fetched from.
         char_limit: Maximum number of characters (default 1500).
     """
     # STEP A - Fetch URL
     try:
         response = requests.get(url, timeout=10)
-        response.raise_for_status()  # triggers error for 4xx/5xx
+        response.raise_for_status()
         html_content = response.text
     except Exception as e:
         return {
@@ -28,45 +29,32 @@ def fetch_and_summarize_url(url:str, char_limit:int = 1500)-> dict: #it's import
             "reading_time_minutes": 0.0,
             "error": f"Failed to fetch URL: {str(e)}"
         }
- 
-    # STEP B — Extract text from HTML
-    soup = BeautifulSoup(html_content, "html.parser")
 
-    # Remove script, style, and other irrelevant tags
+    # STEP B - Extract text
+    soup = BeautifulSoup(html_content, "html.parser")
     for tag in soup(["script", "style", "header", "footer", "nav", "noscript"]):
         tag.extract()
+    raw_text = re.sub(r"\s+", " ", soup.get_text(separator=" ")).strip()
 
-    # Get raw text
-    raw_text = soup.get_text(separator=" ")
-
-    # Clean whitespace / newlines
-    raw_text = re.sub(r"\s+", " ", raw_text).strip()
-
-    # STEP C — Summarize using the LLM
+    # STEP C - Summarize
     try:
-        # Truncate text to avoid huge prompts
         truncated_text = raw_text[:char_limit]
-
-        # Ask the LLM to summarize
-        summary_prompt = f"Summarize the following text into 4–6 sentences:\n\n{truncated_text}"
-
-        # Use the agent model to generate the summary
+        summary_prompt = f"Summarize the following text into 4-6 sentences:\n\n{truncated_text}"
         summary = final_answer.run(summary_prompt).strip()
-
     except Exception as e:
         summary = f"Error summarizing text: {str(e)}"
 
-    # STEP D — Estimate reading time (words / 200 wpm)
+    # STEP D - Reading time
     try:
         word_count = len(raw_text.split())
         reading_time_minutes = round(word_count / 200, 2)
-    except Exception as e:
+    except:
         reading_time_minutes = 0.0
-    
+
     return {
-    "summary": summary,
-    "reading_time_minutes": reading_time_minutes
-}
+        "summary": summary,
+        "reading_time_minutes": reading_time_minutes
+    }
 
 @tool
 def get_current_time_in_timezone(timezone: str) -> str: