tools/rss_get_papers.py

import re
from typing import Any, Optional
from smolagents.tools import Tool
import requests
import markdownify
import smolagents

from tools.feed_processor import  DailyHFRSSParser, RSSFeedProcessor

class HFDaylyPapperTool(Tool):
    name = "get_actual_ai_news"
    description = "Return actual news about AI today."
    output_type = "string"
    inputs = {'number': {'type': 'integer', 'description': 'How much paper you want research.'}}
    
    def __init__(self, max_results=10, **kwargs):
        super().__init__()
        self.rss_processor = RSSFeedProcessor()
        self.rss_processor.register_feed(
            "HuggingFace Daily pappers",
            "https://jamesg.blog/hf-papers.xml",
            DailyHFRSSParser(),
        )

    def forward(self, number: int) -> str:
        try:
            from markdownify import markdownify
            from smolagents.utils import truncate_content
            
        except ImportError as e:
            raise ImportError(
                "You must install packages `markdownify` and `requests` to run this tool: for instance run `pip install markdownify requests`."
            ) from e
            
        try:
            response = self.rss_processor.get_latest_articles(["HuggingFace Daily pappers"], number)[0]
            
            result = ""
            for article in response:
                result+=self.pretty_str_paper(article)
                
            markdown_content = markdownify(result).strip()
            markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)

            return truncate_content(markdown_content, 10000)

        except Exception as e:
            return f"An unexpected error occurred: {str(e)}"

    def pretty_str_paper(self, article):
        return     f"*{article.title}*\n" \
                   f"_Источник_: {article.source}\n" \
                   f"_Авторы_: {article.authors}\n" \
                   f"_Опубликовано_: {article.published}\n" \
                   f"_Описание_: {article.summary}\n\n"