Project Description

This project implements an AI agent that can interact with Google's Gemini model, fetch summaries from Wikipedia, and retrieve news articles.

Features

• Gemini Integration: Uses Google's Gemini model to answer prompts and generate text.
• Wikipedia Lookup: Fetches summaries from Wikipedia based on a given topic.
• News Retrieval: Retrieves recent news articles related to a specified keyword using the News API.
• Task History: Keeps track of executed tasks and their responses.

Prerequisites

• Python 3.7 or higher
• Install the required packages:

  pip install -r requirements.txt

• Set the following environment variables:
  • GOOGLE_API_KEY: Your Google Gemini API key.
  • NEWS_API_KEY: Your News API key (optional, for news functionality).

Running the Application

1. Clone the repository (if applicable).
2. Navigate to the project directory.
3. Create a .env file in the project root and add your API keys:

   GOOGLE_API_KEY=YOUR_GOOGLE_API_KEY
   NEWS_API_KEY=YOUR_NEWS_API_KEY
   

4. Run the main script:

   python main.py

File Changes in main.py

• Import Statements: Added necessary import statements for google.generativeai, requests, json, datetime, os, sys, dotenv, and typing.
• Environment Variable Loading: Implemented loading of environment variables using dotenv to securely store API keys.
• AdvancedAgent Class:
  • Added a class AdvancedAgent to encapsulate the AI agent's functionality.
  • Includes methods for interacting with Gemini (ask_gemini), fetching Wikipedia summaries (fetch_wikipedia_summary), fetching news articles (fetch_news), and executing tasks (execute_task).
  • Includes a task_log to store executed tasks and their responses.
  • Includes a _manage_memory method to manage the agent's memory.
• Main Function:
  • Initializes the AI agent and handles user input.
  • Provides a command-line interface for interacting with the agent.
  • Handles exceptions and provides informative error messages.
• Error Handling: Implemented comprehensive error handling throughout the code to catch potential issues with API requests, environment variables, and user input.