LocatAI.NET 1.0.1

LocatAI.NET

LocatAI.NET is an AI-powered Selenium WebDriver extension that uses OpenAI to intelligently locate web elements using natural language descriptions. Version 1.0.0 brings a stable, production-ready implementation with comprehensive caching, logging, and configuration options.

Features

• AI-powered element location using natural language descriptions
• Built-in caching system for successful locators with performance tracking
• Multiple API key configuration options
• Comprehensive logging and performance monitoring
• Full .NET Standard 2.0 and .NET 6.0+ support
• Configurable OpenAI model selection (default: gpt-4)
• Seamless integration with existing Selenium WebDriver code

Installation

Install via NuGet Package Manager:

Install-Package LocatAI.NET -Version 1.0.0

Or via .NET CLI:

dotnet add package LocatAI.NET --version 1.0.0

Getting Started

1. Install the Package Follow the installation instructions above to add LocatAI.NET to your project.

2. Create Configuration File Create a new file named appsettings.json in your project's root directory with the following content:

   {
     "LocatAI": {
       "OpenAIApiKey": "your-api-key",
       "OpenAIModel": "gpt-4o-mini-2024-07-18",
       "DefaultWaitTimeoutSeconds": 10,
       "Cache": {
         "MaxSize": 100,
         "ExpirySeconds": 3600,
         "MinAttemptsForEviction": 5,
         "MinSuccessRateForEviction": 0.6,
         "MaxFailuresForEviction": 3,
         "CacheDirectory": "Cache"
       }
     }
   }
   

3. Configure API Key Replace "your-api-key" with your actual OpenAI API key using one of these methods (in order of precedence):

   1. Set programmatically in code:

   settings.SetApiKey("your-api-key");
   

   2. Use environment variable:

   set OPENAI_API_KEY=your-api-key
   

   3. In appsettings.json (as shown above)

4. Start Using LocatAI

   using LocatAI.NET;
   
   // Use AI to find elements
   var loginButton = await driver.FindElementByAIAsync("the login button");
   var emailField = await driver.FindElementByAIAsync("email input field");
   
   // Regular Selenium actions
   emailField.SendKeys("test@example.com");
   loginButton.Click();
   

Configuration Options

Basic Settings

• OpenAIApiKey: Your OpenAI API key
• OpenAIModel: Model to use (defaults to "gpt-4")
• DefaultWaitTimeoutSeconds: Default timeout for element searches (default: 10)

Cache Settings

"Cache": {
  "MaxSize": 100,          // Maximum number of cached locators
  "ExpirySeconds": 3600,   // Cache entry lifetime
  "MinAttemptsForEviction": 5,
  "MinSuccessRateForEviction": 0.6,
  "MaxFailuresForEviction": 3,
  "CacheDirectory": "Cache" // Directory for cache files
}

Advanced Usage

Custom API Key Provider

public class CustomApiKeyProvider : IApiKeyProvider 
{
    public string GetApiKey() => "your-custom-key";
    public Task<string> GetApiKeyAsync() => Task.FromResult("your-custom-key");
}

var settings = new LocatAISettings(new CustomApiKeyProvider());

Usage Tracking

// Get usage statistics
var report = AIUsageTracker.Instance.GetReport();
Console.WriteLine($"API Success Rate: {report.ApiSuccessRate:P2}");
Console.WriteLine($"Cache Hit Rate: {report.CacheHitRate:P2}");
Console.WriteLine($"Estimated Cost: ${report.EstimatedCost:F2}");

Documentation

For detailed documentation and examples, visit our GitHub repository.

Version History

See CHANGELOG.md for version history and release notes.

License

This project is licensed under the MIT License - see the LICENSE file for details.