Spaces:
Running
Running
| import feedparser | |
| import urllib.parse | |
| import yaml | |
| import gradio as gr | |
| from smolagents import CodeAgent, HfApiModel, tool | |
| def fetch_latest_arxiv_papers(keywords: list, num_results: int = 3) -> list: | |
| """ | |
| Fetches the latest research papers from arXiv based on provided keywords. | |
| Args: | |
| keywords (list): A list of keywords to search for relevant papers. | |
| num_results (int): The number of papers to fetch (default is 3). | |
| Returns: | |
| list: A list of dictionaries, each containing: | |
| - "title": The paper title | |
| - "authors": A string of authors | |
| - "year": Year of publication | |
| - "abstract": Summary of the paper | |
| - "link": URL to the full paper | |
| """ | |
| try: | |
| print(f"DEBUG: Searching arXiv papers with keywords: {keywords}") # Debug input | |
| # ✅ Properly format query with +AND+ for multiple keywords | |
| query = "+AND+".join([f"all:{kw}" for kw in keywords]) | |
| query_encoded = urllib.parse.quote(query) # Encode spaces and special characters | |
| url = f"http://export.arxiv.org/api/query?search_query={query_encoded}&start=0&max_results={num_results}&sortBy=submittedDate&sortOrder=descending" | |
| print(f"DEBUG: Query URL - {url}") # Debug URL | |
| feed = feedparser.parse(url) | |
| 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 papers | |
| except Exception as e: | |
| print(f"ERROR: {str(e)}") # Debug errors | |
| return [f"Error fetching research papers: {str(e)}"] | |
| model = HfApiModel( | |
| max_tokens=2096, | |
| temperature=0.5, | |
| model_id='Qwen/Qwen2.5-Coder-32B-Instruct', | |
| custom_role_conversions=None, | |
| ) | |
| # Load prompt templates | |
| with open("prompts.yaml", 'r') as stream: | |
| prompt_templates = yaml.safe_load(stream) | |
| # Create the AI Agent | |
| agent = CodeAgent( | |
| model=model, | |
| tools=[fetch_latest_arxiv_papers], # Properly registered tool | |
| max_steps=6, | |
| verbosity_level=1, | |
| grammar=None, | |
| planning_interval=None, | |
| name="ScholarAgent", | |
| description="An AI agent that fetches the latest research papers from arXiv based on user-defined keywords and filters.", | |
| prompt_templates=prompt_templates | |
| ) | |
| # Define Gradio Search Function | |
| def search_papers(user_input): | |
| keywords = [kw.strip() for kw in user_input.split(",") if kw.strip()] # Ensure valid keywords | |
| print(f"DEBUG: Received input keywords - {keywords}") # Debug user input | |
| if not keywords: | |
| print("DEBUG: No valid keywords provided.") | |
| return "Error: Please enter at least one valid keyword." | |
| 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 | |
| ]) | |
| print("DEBUG: No results found.") | |
| return "No results found. Try different keywords." | |
| # Create Gradio UI | |
| with gr.Blocks() as demo: | |
| 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...") | |
| # Launch Gradio App | |
| demo.launch() | |