mkdir hnbot; cd hnbot/
poetry init

This command will guide you through creating your pyproject.toml config.


Would you like to define your main dependencies interactively? (yes/no) [yes] yes

Package to add or search for (leave blank to skip): novu
Add a package (leave blank to skip): beautifulsoup4


Do you confirm generation? (yes/no) [yes] yes

% mkdir hn_bot; cd hn_bot
% cd hn_bot 
% poetry shell
(hn-bot-py3.9) (base) % poetry install

# hn_scraper.py
from typing import Dict, List

import requests
from bs4 import BeautifulSoup

def scrape_page(page_number: str) -> List[Dict[str, str]]:
    response = requests.get(f"https://news.ycombinator.com/news?p={page_number}")
    yc_web_page = response.text
    soup = BeautifulSoup(yc_web_page, 'html.parser')

    articles = []

    for article_tag in soup.find_all(name="span", class_="titleline"):
        title = article_tag.getText()
        link = article_tag.find("a")["href"]
        articles.append({"title": title, "link": link})

    return articles

 % python hn_scraper.py
(['Linux Network Performance Parameters Explained (github.com/leandromoreira)', 'Double Commander – Changes in version 1.1.0 (github.com/doublecmd)', 'If You’ve Got a New Car, It’s a Data Privacy Nightmare (gizmodo.com)', 'Ask HN: I’m an FCC Commissioner proposing regulation of IoT security updates', 'Gcsfuse: A user-space file system for interacting with Google Cloud S

# llm_classifier.py
import requests
import json

def classify_post(title: str, interests: str) -> bool:

    url = "https://demo.agenta.ai/64f1d1aefeebd024bbdb1ea4/hn_bot/v1/generate"
    params = {
        "inputs": {
            "title": title,
            "interests": interests
        },
        "temperature": 0,
        "model": "gpt-3.5-turbo",
        "maximum_length": 100,
        "prompt_system": "You are an expert in classification. You answer only with True or False.",
        "prompt_human": "Classify whether this hackernews post is interesting for someone with the following interests:\nHacker news post title: {title}\nInterests: {interests}",
        "stop_sequence": "\n",
        "top_p": 1,
        "frequence_penalty": 0,
        "presence_penalty": 0
    }

    response = requests.post(url, json=params)

    data = response.json()

    return bool(data)

# novu_bot
from novu.config import NovuConfig
from novu.api import EventApi
from novu.api.subscriber import SubscriberApi
from novu.dto.subscriber import SubscriberDto

NovuConfig().configure("https://api.novu.co", "YOUR_API_KEY")
webhook_url = "..." # the webhook url we got from Discord

def send_message(msg):
    your_subscriber_id = "123"  # Replace this with a unique user ID.

    # Define a subscriber instance
    subscriber = SubscriberDto(
        subscriber_id=your_subscriber_id,
        email="abc@gmail.com",
        first_name="John",
        last_name="Doe"
    )

    SubscriberApi().create(subscriber)
    SubscriberApi().credentials(subscriber_id=your_subscriber_id,
                                provider_id="discord",

    EventApi().trigger(
        name="slackbot",  # The trigger ID of the workflow. It can be found on the workflow page.
        recipients=your_subscriber_id,
        payload={},  # Your Novu payload goes here
    )

from hn_bot import hn_scraper, llm_classifier, novu_bot
import schedule
import time

interests = "LLMs, LLMOps, Python, Infrastructure, Tennis, MLOps, Data science, AI, startups, Computational Biology"

def main():
    novu_bot.send_message("Interesting posts at HackerNews:\n")

    posts = hn_scraper.scrape_page("1")
    for title, url in posts:
        if llm_classifier.classify_post(title, interests) == "True":
            novu_bot.send_message(f"{title}\n{url}")

if __name__ == "__main__":
    main()

from hn_bot import hn_scraper, llm_classifier, novu_bot
from time import sleep
interests = "LLM, LLMOps, MLOps, Data science, AI, startups"

done_post_titles = []


def main():
    novu_bot.send_message("Interesting posts at HackerNews:\n")

    posts = []
    for i in range(1, 5):
        posts += hn_scraper.scrape_page(i)
    for post in posts:
        title = post["title"]
        url = post["link"]
        if llm_classifier.classify_post(title, interests) and title not in done_post_titles:
            done_post_titles.append(title)
            novu_bot.send_message(f"{title}\n{url}")


if __name__ == "__main__":
    while True:
        main()
        sleep(3600)