Update app.py

app.py

@@ -1,4 +1,9 @@
 from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
+import xml.etree.ElementTree as ET
+import matplotlib.pyplot as plt
+from wordcloud import WordCloud
+from collections import Counter
+import re
 import datetime
 import requests
 import pytz
@@ -9,31 +14,71 @@ from Gradio_UI import GradioUI
 
 # Below is an example of a tool that does nothing. Amaze us with your creativity !
 @tool
-def search_arxiv(query: str) -> str:
-    """Searches arXiv for academic papers.
+def search_arxiv(query: str):
+    """Searches arXiv for academic papers and returns structured results.
 
     Args:
         query (str): The topic or keywords to search for.
 
-        
     Returns:
-        str: A formatted list of found papers with titles, summaries, and links.
+        list: A list of tuples containing titles, summaries, and links.
     """
-    max_results=5
+    max_results = 5
     url = f"http://export.arxiv.org/api/query?search_query={query}&max_results={max_results}"
     response = requests.get(url)
 
     if response.status_code == 200:
         papers = []
-        for entry in response.text.split("<entry>")[1:max_results+1]:
-            title = entry.split("<title>")[1].split("</title>")[0].strip()
-            summary = entry.split("<summary>")[1].split("</summary>")[0].strip()
-            link = entry.split("<id>")[1].split("</id>")[0].strip()
-            papers.append(f"Title: {title}\nSummary: {summary}\nLink: {link}\n")
-
-        return "\n\n".join(papers)
+        root = ET.fromstring(response.text)
+        for entry in root.findall("{http://www.w3.org/2005/Atom}entry"):
+            title = entry.find("{http://www.w3.org/2005/Atom}title").text
+            summary = entry.find("{http://www.w3.org/2005/Atom}summary").text
+            link = entry.find("{http://www.w3.org/2005/Atom}id").text
+            papers.append((title, summary, link))
+
+        return papers
+
+    return []
+
+def generate_visuals(query):
+    results = search_arxiv(query)
+    if not results:
+        return "No papers found.", None, None
+
+    # Extract text data
+    titles = [title for title, _, _ in results]
+    summaries = " ".join(summary for _, summary, _ in results)
+
+    # Generate Bar Chart for Keyword Frequency in Titles
+    words = [word.lower() for title in titles for word in re.findall(r'\b\w+\b', title) if len(word) > 3]
+    word_counts = Counter(words).most_common(10)
+
+    plt.figure(figsize=(8, 5))
+    plt.bar(*zip(*word_counts), color='skyblue')
+    plt.xticks(rotation=45)
+    plt.title("Top Keywords in Titles")
+    plt.xlabel("Keywords")
+    plt.ylabel("Frequency")
+    plt.tight_layout()
+    bar_chart_path = "bar_chart.png"
+    plt.savefig(bar_chart_path)
+    plt.close()
+
+    # Generate Word Cloud for Summary Text
+    wordcloud = WordCloud(width=500, height=300, background_color="white").generate(summaries)
+    plt.figure(figsize=(8, 5))
+    plt.imshow(wordcloud, interpolation="bilinear")
+    plt.axis("off")
+    wordcloud_path = "wordcloud.png"
+    plt.savefig(wordcloud_path)
+    plt.close()
+
+    # Display Search Results as Clickable Links
+    markdown_text = "\n\n".join(
+        [f"**[{title}]({link})**\n\n{summary}" for title, summary, link in results]
+    )
 
-    return "No papers found."
+    return markdown_text, bar_chart_path, wordcloud_path
 
 
 @tool
@@ -96,5 +141,15 @@ agent = CodeAgent(
     prompt_templates=prompt_templates
 )
 
+iface = gr.Interface(
+    fn=generate_visuals,
+    inputs="text",
+    outputs=["markdown", "image", "image"],
+    title="🔎 arXiv Research Paper Search",
+    description="Enter a topic or keywords to search for academic papers on arXiv. Get a list of papers with visual analysis.",
+    examples=[["Machine Learning"], ["Quantum Computing"], ["Climate Change"]]
+)
+
+iface.launch()
 
 GradioUI(agent).launch()