generated from kyegomez/Python-Package-Template
-
-
Notifications
You must be signed in to change notification settings - Fork 5
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
167 additions
and
0 deletions.
There are no files selected for viewing
167 changes: 167 additions & 0 deletions
167
cookbook/enterprise/marketing/news/Swarms_Cookbook_NewsAgent.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,167 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "1e7d476c", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "# Swarms Cookbook: NewsAgent - Real-Time News Aggregation and Summarization\n", | ||
| "\n", | ||
| "Welcome to the Swarms Cookbook! In this guide, we will walk through the steps of using **NewsAgent**, an enterprise-grade solution for real-time news aggregation, querying, and summarization.\n", | ||
| "\n", | ||
| "NewsAgent helps businesses stay informed by automating news monitoring from multiple sources, summarizing relevant content, and providing timely updates.\n", | ||
| "\n", | ||
| "### Key Features:\n", | ||
| "- **News Aggregation**: Fetch news from various sources via NewsAPI.\n", | ||
| "- **Advanced Summarization**: Leverages AI to generate concise summaries of complex news stories.\n", | ||
| "- **Enterprise-Grade**: Built with robust error handling and scalability for enterprise deployments.\n", | ||
| "\n", | ||
| "Follow this step-by-step guide to set up **NewsAgent** and integrate it into your news monitoring workflows.\n", | ||
| "\n", | ||
| "Be sure to visit the **[Swarms GitHub](https://github.com/kyegomez/swarms)**, **[Discord](https://discord.com/servers/agora-999382051935506503)**, and **[Swarms Marketplace](https://swarms.xyz)** for more resources and to connect with the community.\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "8e2c95c9", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Installation\n", | ||
| "\n", | ||
| "First, install the **NewsAgent** package by running the following command:\n", | ||
| "\n", | ||
| "```bash\n", | ||
| "pip3 install -U news-swarm\n", | ||
| "```\n", | ||
| "\n", | ||
| "Ensure that you have Python 3.10+ installed.\n", | ||
| "\n", | ||
| "You will also need to create a `.env` file with the following environment variables for API access:\n", | ||
| "\n", | ||
| "```bash\n", | ||
| "OPENAI_API_KEY=\"your-openai-api-key\"\n", | ||
| "NEWSAPI_API_KEY=\"your-newsapi-api-key\"\n", | ||
| "WORKSPACE_DIR=\"agent_workspace\"\n", | ||
| "```\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "id": "a9480d48", | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "# Import necessary libraries\n", | ||
| "import os\n", | ||
| "from dotenv import load_dotenv\n", | ||
| "from swarm_models import OpenAIChat\n", | ||
| "from swarms import Agent\n", | ||
| "from news_swarm.main import NewsAgent\n", | ||
| "\n", | ||
| "# Load environment variables from the .env file\n", | ||
| "load_dotenv()\n", | ||
| "\n", | ||
| "# Ensure API keys are loaded\n", | ||
| "openai_api_key = os.getenv(\"OPENAI_API_KEY\")\n", | ||
| "newsapi_api_key = os.getenv(\"NEWSAPI_API_KEY\")\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "948f87de", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Setting Up NewsAgent\n", | ||
| "\n", | ||
| "Now, let's initialize **NewsAgent** for real-time news aggregation and summarization. We will create an **OpenAIChat** instance for language model integration and set up the news agent to query and summarize the latest news from multiple sources.\n", | ||
| "\n", | ||
| "In this example, we'll fetch news related to **multi-agent collaboration** and display the results.\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "id": "7da9002b", | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "# Create an instance of OpenAIChat class for LLM integration\n", | ||
| "model = OpenAIChat(\n", | ||
| " openai_api_key=openai_api_key,\n", | ||
| " model_name=\"gpt-4o-mini\",\n", | ||
| " temperature=0.1\n", | ||
| ")\n", | ||
| "\n", | ||
| "# Initialize the base agent\n", | ||
| "base_agent = Agent(\n", | ||
| " agent_name=\"News-Agent-V1\",\n", | ||
| " llm=model,\n", | ||
| " max_loops=1,\n", | ||
| " autosave=True,\n", | ||
| " dashboard=False,\n", | ||
| " verbose=True,\n", | ||
| " dynamic_temperature_enabled=True,\n", | ||
| " saved_state_path=\"news_agent.json\",\n", | ||
| " user_name=\"swarms_corp\",\n", | ||
| " retry_attempts=1,\n", | ||
| " context_length=200000,\n", | ||
| ")\n", | ||
| "\n", | ||
| "# Create the NewsAgent instance\n", | ||
| "news_agent = NewsAgent(\n", | ||
| " agent_name=\"news-agent-v1\",\n", | ||
| " agent=base_agent,\n", | ||
| " newsapi_api_key=newsapi_api_key,\n", | ||
| " system_prompt=None,\n", | ||
| " return_json=True,\n", | ||
| ")\n", | ||
| "\n", | ||
| "# Run the agent to fetch news related to \"multi-agent collaboration\"\n", | ||
| "print(news_agent.run(\"multi-agent collaboration\"))\n", | ||
| "\n", | ||
| "# Fetch news for multiple topics concurrently\n", | ||
| "print(news_agent.run_concurrently([\"OpenAI\", \"Anthropic\"]))\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "ebaadd82", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## System Architecture\n", | ||
| "\n", | ||
| "**NewsAgent** operates by combining real-time data fetching from **NewsAPI** with advanced AI-based summarization. Here’s how it works:\n", | ||
| "\n", | ||
| "- **News Fetching**: NewsAgent queries **NewsAPI** to fetch the latest news articles based on the provided keywords or topics.\n", | ||
| "- **OpenAI Integration**: Uses **GPT-4** to summarize complex news stories into concise reports that are easy to understand and act upon.\n", | ||
| "- **Agent Framework**: Powered by the **Swarms** framework, NewsAgent is scalable, flexible, and reliable for enterprise use.\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "5f8c3abb", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Next Steps and Resources\n", | ||
| "\n", | ||
| "You've successfully set up and run a real-time news aggregation and summarization using **NewsAgent**!\n", | ||
| "\n", | ||
| "To explore more:\n", | ||
| "- Try different queries for a wide range of topics.\n", | ||
| "- Adjust the agent’s configuration for more tailored results.\n", | ||
| "- Integrate **NewsAgent** into your existing platforms for automated news monitoring.\n", | ||
| "\n", | ||
| "For more resources and to contribute, visit:\n", | ||
| "- **[Swarms GitHub](https://github.com/kyegomez/swarms)**\n", | ||
| "- **[Swarms Discord](https://discord.com/servers/agora-999382051935506503)**\n", | ||
| "- **[Swarms Marketplace](https://swarms.xyz)**\n", | ||
| "\n", | ||
| "Stay connected with the Swarms community and keep building advanced agents!\n" | ||
| ] | ||
| } | ||
| ], | ||
| "metadata": {}, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 5 | ||
| } |