app.py

from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool, LiteLLMModel
import datetime
import requests
import pytz
import yaml
import os 
from dotenv import load_dotenv
import json
import xml.etree.ElementTree as ET
from tools.final_answer import FinalAnswerTool

from Gradio_UI import GradioUI
load_dotenv()
api_key = os.environ.get("GOOGLE_API_KEY")

@tool
def search_arxiv_papers(topic: str, max_results: int = 10) -> str:
    """Searches arXiv for papers related to the given topic and returns results as JSON.
    Args:
        topic: The search query for arXiv.
        max_results: Maximum number of results to return (default 10).
    """
    try:
        url = 'http://export.arxiv.org/api/query'
        params = {
            'search_query': f'all:{topic}',
            'start': 0,
            'max_results': max_results,
            'sortBy': 'submittedDate',
            'sortOrder': 'descending'
        }
        headers = {'User-Agent': 'Mozilla/5.0'}  # arXiv requires user agent
        response = requests.get(url, params=params)
        response.raise_for_status()
        
        root = ET.fromstring(response.content)
        entries = root.findall('{http://www.w3.org/2005/Atom}entry')
        papers = []
        
        for entry in entries:
            title = entry.find('{http://www.w3.org/2005/Atom}title').text.strip()
            authors = [author.find('{http://www.w3.org/2005/Atom}name').text 
                      for author in entry.findall('{http://www.w3.org/2005/Atom}author')]
            summary = entry.find('{http://www.w3.org/2005/Atom}summary').text.strip()
            link = entry.find('{http://www.w3.org/2005/Atom}id').text
            
            papers.append({
                'title': title,
                'authors': authors,
                'summary': summary,
                'link': link
            })
            
        return json.dumps(papers)
    except Exception as e:
        return f"Error searching arXiv: {str(e)}"

@tool
def save_papers_to_folder(papers_json: str, folder: str = "downloads") -> str:
    """Saves papers data to specified folder as text files.
    Args:
        papers_json: JSON string containing papers data.
        folder: Target folder path (default 'downloads').
    """
    try:
        os.makedirs(folder, exist_ok=True)
        papers = json.loads(papers_json)
        
        for idx, paper in enumerate(papers, 1):
            # Handle missing fields gracefully
            title = paper.get('title', f'Untitled_{idx}')
            authors = paper.get('authors', ['Unknown'])
            link = paper.get('link', 'No link available')
            summary = paper.get('summary', 'No summary available')
            
            # Improved filename sanitization
            clean_title = "".join([c if c.isalnum() else "_" for c in title])[:50]
            filename = os.path.join(folder, f"{clean_title or f'paper_{idx}'}.txt")  
            print("Current working directory:", os.getcwd())
            print("Absolute path to downloads:", os.path.abspath("downloads"))
            print(filename)
            with open(filename, 'w') as f:
                f.write(f"Title: {paper['title']}\n")
                f.write(f"Authors: {', '.join(paper['authors'])}\n")
                f.write(f"Link: {paper['link']}\n")
                f.write(f"Summary: {paper['summary']}\n\n")
                
        return f"Saved {len(papers)} papers to {folder} directory."
    except Exception as e:
        return f"Error saving papers: {str(e)}"



# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def my_custom_tool(arg1:str, arg2: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
    """A tool that does nothing yet 
    Args:
        arg1: the first argument
        arg2: the second argument
    """
    return "What magic will you build ?"

@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
#model_id='google/gemma-3-1b-it',
#custom_role_conversions=None,
#)
#model=LiteLLMModel(
#    model_id = "ollama/qwen2:7b",
#    api_base="http://0.0.0.0:11434",
#    num_ctx=8192,
#)
model=LiteLLMModel(
    model_id = "gemini/gemini-2.0-flash-lite",
    #api_base = "https://generativelanguage.googleapis.com/v1beta/models",
    api_key = api_key,
    num_ctx=8192,
)


# 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, search_arxiv_papers, save_papers_to_folder], ## 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()