File size: 3,292 Bytes
2e6775a
 
c02e3db
71a8799
9b5b26a
2e6775a
c02e3db
 
8c94cc1
73e52d4
 
8c94cc1
2e6775a
c02e3db
 
 
 
0f668a0
c02e3db
 
 
 
 
 
 
 
 
0f668a0
c02e3db
0f668a0
2e6775a
0f668a0
2e6775a
 
bb8d29a
2e6775a
 
 
 
 
 
 
 
 
c02e3db
2e6775a
 
c02e3db
2e6775a
 
 
 
 
c02e3db
2e6775a
 
 
71a8799
73e52d4
bb8d29a
 
73e52d4
 
 
 
c02e3db
bb8d29a
 
73e52d4
c02e3db
 
 
 
bb8d29a
 
 
 
71a8799
 
 
c02e3db
71a8799
 
 
c02e3db
71a8799
9b5b26a
bb8d29a
 
71a8799
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
from smolagents import CodeAgent, HfApiModel, load_tool, tool
import yaml
import feedparser
import gradio as gr

@tool
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 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 = []
        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,
)

with open("prompts.yaml", 'r') as stream:
    prompt_templates = yaml.safe_load(stream)

agent = CodeAgent(
    model=model,
    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 arXiv based on user-defined keywords and filters.",
    prompt_templates=prompt_templates
)

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 a simple Gradio interface
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...")

demo.launch()