Spaces:
Running
Running
| 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 gradio as gr | |
| def fetch_latest_research_papers(keywords: list, num_results: int = 1) -> list: | |
| """ | |
| Fetches the latest research papers from Google Scholar based on provided keywords. | |
| Args: | |
| keywords (list of str): A list of keywords to search for relevant papers. | |
| num_results (int): The number of papers to fetch. Default is 1. | |
| Returns: | |
| list: A list of dictionaries containing paper details. | |
| """ | |
| try: | |
| print(f"DEBUG: Searching papers with keywords: {keywords}") # Debug input | |
| query = " ".join(keywords) | |
| search_results = scholarly.search_pubs(query) | |
| papers = [] | |
| for i in range(num_results): | |
| paper = next(search_results, None) | |
| if paper: | |
| print(f"DEBUG: Found paper - {paper['bib'].get('title', 'No Title')}") # Debug result | |
| papers.append({ | |
| "title": paper['bib'].get('title', 'No Title'), | |
| "authors": paper['bib'].get('author', 'Unknown Authors'), | |
| "year": paper['bib'].get('pub_year', 'Unknown Year'), | |
| "abstract": paper['bib'].get('abstract', 'No Abstract Available'), | |
| "link": paper.get('pub_url', 'No Link Available') | |
| }) | |
| if not papers: | |
| print("DEBUG: No papers found.") | |
| 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, | |
| model_id='Qwen/Qwen2.5-Coder-32B-Instruct', | |
| custom_role_conversions=None, | |
| ) | |
| with open("prompts.yaml", 'r') as stream: | |
| prompt_templates = yaml.safe_load(stream) | |
| agent = CodeAgent( | |
| model=model, | |
| tools=[final_answer, fetch_latest_research_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.", | |
| prompt_templates=prompt_templates | |
| ) | |
| def search_papers(user_input): | |
| keywords = user_input.split(",") # Split input by commas for multiple keywords | |
| print(f"DEBUG: Received input keywords - {keywords}") # Debug user input | |
| results = fetch_latest_research_papers(keywords, num_results=1) | |
| print(f"DEBUG: Results received - {results}") # Debug function output | |
| if isinstance(results, list) and 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." | |
| # Create a simple Gradio interface | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# Google Scholar 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() | |