WIP: Add latest trend functionality

app.py

@@ -1,22 +1,63 @@
-from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel,load_tool,tool
+from smolagents import CodeAgent, DuckDuckGoSearchTool, VisitWebpageTool, HfApiModel, load_tool, tool
 import datetime
 import requests
 import pytz
 import yaml
+from typing import List
 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 !
+import re
+from typing import Dict
+
 @tool
-def parse_search_results(query_results: str)-> 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
-    """This tool parses the search results for a given search query result. This tool is suggested to
-    be used after the DuckDuckGoSearch tool.
+def parse_search_results(query_results: str) -> Dict[str, str]:
+    """
+    Parses search results text and extracts URLs along with their corresponding description.
+    
     Args:
-        query_results: A string representing the search results.
+        query_results: A string representing the search results. Each search result is expected to start with a URL,
+                       followed by one or more lines of description until the next URL is encountered.
+                       
+    Returns:
+        A dictionary where each key is a URL and the corresponding value is the description text.
     """
-    return query_results.lower()
+    results: Dict[str, str] = {}
+    current_url = None
+    current_desc = []
+    
+    # Split the input into lines
+    lines = query_results.splitlines()
+    
+    # Regex pattern to match a URL (starting with http:// or https://)
+    url_pattern = re.compile(r"^(https?://\S+)")
+    
+    for line in lines:
+        stripped_line = line.strip()
+        if not stripped_line:
+            continue  # Skip empty lines
+        
+        # Check if the line starts with a URL
+        url_match = url_pattern.match(stripped_line)
+        if url_match:
+            # Save the previous URL and its description if available
+            if current_url is not None:
+                results[current_url] = " ".join(current_desc).strip()
+            # Set the new URL and reset description accumulator
+            current_url = url_match.group(1)
+            current_desc = []
+        else:
+            # Accumulate description lines
+            current_desc.append(stripped_line)
+    
+    # Save the last URL and its description if any
+    if current_url is not None:
+        results[current_url] = " ".join(current_desc).strip()
+    
+    return results
+
 
 @tool
 def get_current_time_in_timezone(timezone: str) -> str:
@@ -55,7 +96,7 @@ with open("prompts.yaml", 'r') as stream:
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer, parse_search_results, DuckDuckGoSearchTool()], ## add your tools here (don't remove final answer)
+    tools=[final_answer, parse_search_results, DuckDuckGoSearchTool(), VisitWebpageTool()], ## add your tools here (don't remove final answer)
     max_steps=6,
     verbosity_level=1,
     grammar=None,