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
from tools.visit_webpage import VisitWebpageTool

from Gradio_UI import GradioUI
import arxiv
from transformers import pipeline

# Initialize a summarization pipeline using a pre-trained model.
summarizer = pipeline("summarization")

def _search_arxiv(query: str, max_results: int = 5) -> list[dict[str, str | list[str]]]:
    """
    Search for research articles on arXiv based on the given query.
    
    Args:
        query (str): The search query.
        max_results (int): Maximum number of results to retrieve.
    
    Returns:
        list[dict[str, str | list[str]]]: Each dict contains title, authors, summary, publication date, and URL.
    """
    search = arxiv.Search(
        query=query,
        max_results=max_results,
        sort_by=arxiv.SortCriterion.SubmittedDate
    )
    results = []
    for result in search.results():
        results.append({
            'title': result.title,
            'authors': [author.name for author in result.authors],
            'summary': result.summary,
            'published': result.published.strftime("%Y-%m-%d"),
            'url': result.entry_id
        })
    return results

def _summarize_text(text: str) -> str:
    """
    Summarize the provided text using the Hugging Face summarization pipeline.
    
    Args:
        text (str): The text to summarize.
    
    Returns:
        str: The summarized text.
    """
    # For longer texts, consider chunking before summarizing.
    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
    return summary[0]['summary_text']


@tool
def personalized_research_assistant(query: str) -> str:
    """A tool that fetches relevant articles from arxiv and provides the information.
    
    Args:
        query: The research query to search for in arxiv.
    """
    response = ""
    articles = _search_arxiv(query)
    for idx, article in enumerate(articles):
        response += f"\nArticle {idx+1}:\n"
        response += f"\nTitle: {article['title']}\n"
        response += f"Authors: {', '.join(article['authors'])}\n"
        response += f"Published on: {article['published']}\n"
        response += f"URL: {article['url']}\n"
        response += "Abstract Summary:\n"
        response += f"{summarize_text(article['summary'])}\n"
        response += "-" * 80
    return response
    

@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()
model = HfApiModel(
max_tokens=2096,
temperature=0.5,
model_id='https://wxknx1kg971u7k1n.us-east-1.aws.endpoints.huggingface.cloud',# 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, image_generation_tool, DuckDuckGoSearchTool(), VisitWebpageTool(), 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()