Updated app.y to arxiv API

app.py

@@ -1,60 +1,38 @@
 from smolagents import CodeAgent, HfApiModel, load_tool, tool
-import datetime
-import requests
-import pytz
 import yaml
-from tools.final_answer import FinalAnswerTool
-from scholarly import scholarly
+import feedparser
 import gradio as gr
 
 @tool
-def fetch_latest_research_papers(keywords: list, num_results: int = 1) -> list:
-    """Fetches the latest research papers from Google Scholar based on provided keywords.
+def fetch_latest_arxiv_papers(keywords: list, num_results: int = 1) -> list:
+    """Fetches the latest research papers from arXiv based on provided keywords.
     Args:
         keywords: A list of keywords to search for relevant papers.
         num_results: The number of papers to fetch (default is 5).
     """
     try:
-        print(f"DEBUG: Searching papers with keywords: {keywords}")  # Debug input
-        query = " ".join([kw.strip() for kw in keywords if kw.strip()])  # Ensure clean query
-        search_results = scholarly.search_pubs(query)
-        papers = []
-        for _ in range(num_results):  # Fetch extra papers to ensure we get recent ones
-            paper = next(search_results, None)
-            if paper:
-                scholarly.fill(paper)  # Fetch additional metadata
-                pub_year = paper['bib'].get('pub_year', 'Unknown Year')
-
-                # Ensure year is an integer
-                if pub_year != 'Unknown Year':
-                    try:
-                        pub_year = int(pub_year)
-                    except ValueError:
-                        pub_year = 0  # Handle invalid years
-
-                print(f"DEBUG: Found paper - {paper['bib'].get('title', 'No Title')} ({pub_year})")
+        print(f"DEBUG: Searching arXiv papers with keywords: {keywords}")  # Debug input
+        query = "+".join(keywords)
+        url = f"http://export.arxiv.org/api/query?search_query=all:{query}&start=0&max_results={num_results}&sortBy=submittedDate&sortOrder=descending"
+        feed = feedparser.parse(url)
 
-                papers.append({
-                    "title": paper['bib'].get('title', 'No Title'),
-                    "authors": paper['bib'].get('author', 'Unknown Authors'),
-                    "year": pub_year,
-                    "abstract": paper['bib'].get('abstract', 'No Abstract Available'),
-                    "link": paper.get('pub_url', 'No Link Available')
-                })
-
-        # Sort by the latest publication year
-        papers = sorted(papers, key=lambda x: x["year"] if isinstance(x["year"], int) else 0, reverse=True)
+        papers = []
+        for entry in feed.entries:
+            papers.append({
+                "title": entry.title,
+                "authors": ", ".join(author.name for author in entry.authors),
+                "year": entry.published[:4],  # Extract year
+                "abstract": entry.summary,
+                "link": entry.link
+            })
 
-        # Return only the latest `num_results` papers
-        return papers[:num_results]
+        return papers
 
     except Exception as e:
         print(f"ERROR: {str(e)}")  # Debug errors
         return [f"Error fetching research papers: {str(e)}"]
 
 
-final_answer = FinalAnswerTool()
-
 model = HfApiModel(
     max_tokens=2096,
     temperature=0.5,
@@ -64,16 +42,16 @@ model = HfApiModel(
 
 with open("prompts.yaml", 'r') as stream:
     prompt_templates = yaml.safe_load(stream)
-    
+
 agent = CodeAgent(
     model=model,
-    tools=[final_answer, fetch_latest_research_papers],
+    tools=[fetch_latest_arxiv_papers],
     max_steps=6,
     verbosity_level=1,
     grammar=None,
     planning_interval=None,
     name="ScholarAgent",
-    description="An AI agent that fetches the latest research papers from Google Scholar based on user-defined keywords and filters.",
+    description="An AI agent that fetches the latest research papers from arXiv based on user-defined keywords and filters.",
     prompt_templates=prompt_templates
 )
 
@@ -85,11 +63,14 @@ def search_papers(user_input):
         print("DEBUG: No valid keywords provided.")
         return "Error: Please enter at least one valid keyword."
     
-    results = fetch_latest_research_papers(keywords, num_results=1)
+    results = fetch_latest_arxiv_papers(keywords, num_results=3)  # Fetch 3 results
     print(f"DEBUG: Results received - {results}")  # Debug function output
     
     if isinstance(results, list) and results and isinstance(results[0], dict):
-        return "\n\n".join([f"**Title:** {paper['title']}\n**Authors:** {paper['authors']}\n**Year:** {paper['year']}\n**Abstract:** {paper['abstract']}\n[Read More]({paper['link']})" for paper in results])
+        return "\n\n".join([
+            f"**Title:** {paper['title']}\n**Authors:** {paper['authors']}\n**Year:** {paper['year']}\n**Abstract:** {paper['abstract']}\n[Read More]({paper['link']})"
+            for paper in results
+        ])
     
     print("DEBUG: No results found.")
     return "No results found. Try different keywords."
@@ -97,14 +78,13 @@ def search_papers(user_input):
 
 # Create a simple Gradio interface
 with gr.Blocks() as demo:
-    gr.Markdown("# Google Scholar Research Paper Fetcher")
+    gr.Markdown("# arXiv Research Paper Fetcher")
     keyword_input = gr.Textbox(label="Enter keywords (comma-separated)", placeholder="e.g., deep learning, reinforcement learning")
     output_display = gr.Markdown()
     search_button = gr.Button("Search")
-    
+
     search_button.click(search_papers, inputs=[keyword_input], outputs=[output_display])
 
-    
     print("DEBUG: Gradio UI is running. Waiting for user input...")
 
 demo.launch()