Skip to content

A simple yet powerful search tool that leverages Google's Gemini AI with Search Grounding to provide comprehensive, up-to-date information on any topic. Built with the latest Google Gen AI SDK.

License

Notifications You must be signed in to change notification settings

llegomark/google-search-grounding

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Grounding with Google Search

A simple yet powerful search tool that leverages Google's Gemini AI with Search Grounding to provide comprehensive, up-to-date information on any topic. Built with the latest Google Gen AI SDK (google-genai).

🌟 Features

  • Uses Gemini 2.0 Flash model for fast, accurate responses
  • Integrates Google Search grounding for real-time information
  • Generates conversational, easy-to-understand research results
  • Automatically saves results with unique identifiers
  • Includes Manila time (GMT+8) timestamps
  • Verifies search usage and grounding

🚀 Quick Start

Prerequisites

  • Python 3.9 or higher
  • Google AI Studio API key (Get it here)

Installation

  1. Clone the repository:
git clone https://github.com/llegomark/google-search-grounding.git
cd google-search-grounding
  1. Install the required packages:
pip install google-genai python-dotenv pytz
  1. Create a .env file in the project root and add your API key:
GOOGLE_API_KEY=your_api_key_here

Usage

Run the script:

python research_tool.py

Simply enter any topic you want to research, and the tool will:

  • Generate comprehensive research using Gemini AI
  • Ground the information using Google Search
  • Save results automatically to research_results/ directory
  • Display results in the console

About

A simple yet powerful search tool that leverages Google's Gemini AI with Search Grounding to provide comprehensive, up-to-date information on any topic. Built with the latest Google Gen AI SDK.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages