app.py

from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
from tools.final_answer import FinalAnswerTool
import xml.etree.ElementTree as ET
import os
from Gradio_UI import GradioUI

HF_SECRET = os.getenv("HF_TOKEN")


# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def paper_finder(topics:list, max_paper:int)-> str: #it's import to specify the return type
    #Keep this format for the description / args / args description but feel free to modify the tool
    """
        Searches arxiv.org for the most recently updated research papers on specified topics.
        Args:
          topics: A list of topic keywords or phrases (e.g., ['Computer Vision', 'NLP']) to guide the search.
          max_paper: The maximum number of papers to retrieve for each topic.
    """

    results = []

    for topic in topics:
        # request to the arxiv page
        query = requests.utils.quote(topic)
        url = f"http://export.arxiv.org/api/query?search_query=all:{query}&sortBy=lastUpdatedDate&sortOrder=descending&max_results={max_paper}"
        
        try:
            response = requests.get(url)
            response.raise_for_status()
            
            # parsing element tree as text
            root = ET.fromstring(response.text)

            # extract paper information
            papers = []
            
            # arxiv returns responses in Atom 1.0 format "https://info.arxiv.org/help/api/user-manual.html#32-the-api-response"
            namespace = {"atom": 'http://www.w3.org/2005/Atom'}

            # list of the returned Atom results
            for entry in root.findall('atom:entry', namespace):
                title = entry.find('atom:title', namespace).text.strip()
                summary = entry.find('atom:summary', namespace).text.strip()
                published = entry.find('atom:published', namespace).text.strip()[:10]
                link = entry.find('./atom:link[@title="pdf"]', namespace)
                if link is not None:
                    pdf_url = link.get('href')
                else:
                    pdf_url = "No PDF link available"

                # Authors of the paper
                authors = []
                for author in entry.findall('atom:author/atom:name', namespace):
                    authors.append(author.text.strip())

                # Adding paper
                papers.append({
                    "title": title,
                    "authors": ", ".join(authors[:3]) + ("..." if len(authors) > 3 else ""),
                    "published": published,
                    "summary": summary[:150] + "..." if len(summary) > 150 else summary,
                    "pdf_url": pdf_url
                })

            # Format the results for this topic
            topic_results = f"\n## Latest papers on {topic} ({len(papers)})\n\n"

            for i, paper in enumerate(papers, 1):
                topic_results += f"{i}. {paper['title']}\n"
                topic_results += f"   Authors: {paper['authors']}\n"
                topic_results += f"   Published: {paper['published']}\n"
                topic_results += f"   Summary: {paper['summary']}\n"
                topic_results += f"   PDF: {paper['pdf_url']}\n\n"

            results.append(topic_results)
    
        except Exception as e:
            results.append(f"\n## Error searching for {topic}: {str(e)}\n")
        
    return "\n".join(results) if results else "No papers found for the given topics. Try different search terms."

@tool
def get_current_time_in_timezone(timezone: str) -> str:
    """A tool that fetches the current local time in a specified timezone.
    Args:
        timezone: A string representing a valid timezone (e.g., 'America/New_York').
    """
    try:
        # Create timezone object
        tz = pytz.timezone(timezone)
        # Get current time in that timezone
        local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
        return f"The current local time in {timezone} is: {local_time}"
    except Exception as e:
        return f"Error fetching time for timezone '{timezone}': {str(e)}"


final_answer = FinalAnswerTool()

# If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 

model = HfApiModel(
    max_tokens=2096,
    temperature=0.5,
    model_id="Qwen/Qwen2.5-Coder-32B-Instruct" ,# it is possible that this model may be overloaded
    custom_role_conversions=None,
    )


# Import tool from Hub
image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)

with open("prompts.yaml", 'r') as stream:
    prompt_templates = yaml.safe_load(stream)
    
agent = CodeAgent(
    model=model,
    tools=[final_answer, paper_finder, get_current_time_in_timezone], ## add your tools here (don't remove final answer)
    max_steps=6,
    verbosity_level=1,
    grammar=None,
    planning_interval=None,
    name=None,
    description=None,
    prompt_templates=prompt_templates
)

GradioUI(agent).launch()