update app.py

app.py

@@ -5,16 +5,17 @@ import pytz
 import yaml
 import os 
 import json
+import xml.etree.elementTree as ET
 from tools.final_answer import FinalAnswerTool
 
 from Gradio_UI import GradioUI
 
 @tool
-def search_arxiv_papers(topic: str, max_results: int = 5) -> str:
+def search_arxiv_papers(topic: str, max_results: int = 10) -> str:
     """Searches arXiv for papers related to the given topic and returns results as JSON.
     Args:
         topic: The search query for arXiv.
-        max_results: Maximum number of results to return (default 5).
+        max_results: Maximum number of results to return (default 10).
     """
     try:
         url = 'http://export.arxiv.org/api/query'
@@ -25,10 +26,11 @@ def search_arxiv_papers(topic: str, max_results: int = 5) -> str:
             'sortBy': 'submittedDate',
             'sortOrder': 'descending'
         }
+        headers = {'User-Agent': 'Mozilla/5.0'}  # arXiv requires user agent
         response = requests.get(url, params=params)
         response.raise_for_status()
         
-        root = xml.etree.ElementTree.fromstring(response.content)
+        root = ET.fromstring(response.content)
         entries = root.findall('{http://www.w3.org/2005/Atom}entry')
         papers = []
         
@@ -61,11 +63,16 @@ def save_papers_to_folder(papers_json: str, folder: str = "downloads") -> str:
         os.makedirs(folder, exist_ok=True)
         papers = json.loads(papers_json)
         
-        for paper in papers:
-            # Sanitize filename
-            title = "".join([c if c.isalnum() else "_" for c in paper['title']])[:50]
-            filename = os.path.join(folder, f"{title}.txt")
+        for idx, paper in enumerate(papers, 1):
+            # Handle missing fields gracefully
+            title = paper.get('title', f'Untitled_{idx}')
+            authors = paper.get('authors', ['Unknown'])
+            link = paper.get('link', 'No link available')
+            summary = paper.get('summary', 'No summary available')
             
+            # Improved filename sanitization
+            clean_title = "".join([c if c.isalnum() else "_" for c in title])[:50]
+            filename = os.path.join(folder, f"{clean_title or f'paper_{idx}'}.txt")    
             with open(filename, 'w') as f:
                 f.write(f"Title: {paper['title']}\n")
                 f.write(f"Authors: {', '.join(paper['authors'])}\n")