LocatAI 1.2.0-beta

LocatAI

LocatAI is an AI-powered element locator for Selenium WebDriver automation. It helps you find elements on web pages using natural language descriptions instead of brittle CSS/XPath selectors.

Features

• Natural Language Locators: Find elements using plain English descriptions
• Multiple AI Providers: Support for OpenAI, Anthropic Claude, Google Gemini, and Ollama
• Smart Caching: Reduce API calls and improve performance
• Confidence Scoring: Each locator comes with a confidence score
• Automatic Retry: Configurable retry mechanism for failed locators
• WebDriver Extension Methods: Simple integration with Selenium WebDriver

Installation

dotnet add package LocatAI

Quick Start

Step 1: Add an appsettings.json file to your project

{
  "AI": {
    "Provider": "openai",
    "ApiKey": "your-api-key-here",
    "Model": "gpt-4"
  },
  "Options": {
    "MinimumConfidence": 0.4,
    "MaxLocatorsToTry": 3,
    "EnableDetailedLogging": true,
    "TimeoutMilliseconds": 10000,
    "EnableLocatorRetry": true,
    "MaxRetryAttempts": 1
  }
}

Don't forget to set the Copy to Output Directory property to Copy if newer in your project settings.

Step 2: Initialize with the configuration

using Microsoft.Extensions.Configuration;
using LocatAI.Core;

// Load configuration from appsettings.json
var config = new ConfigurationBuilder()
    .SetBasePath(AppContext.BaseDirectory)
    .AddJsonFile("appsettings.json", optional: false, reloadOnChange: true)
    .Build();

// Initialize LocatAI with the configuration
ElementFinder.Initialize(config);

Step 3: Use in your tests

using OpenQA.Selenium;
using OpenQA.Selenium.Chrome;
using LocatAI.Core;

// Create a WebDriver instance
var driver = new ChromeDriver();
driver.Navigate().GoToUrl("https://example.com");

// Find elements using natural language
var loginButton = driver.FindElementByLocatAI("login button");
loginButton.Click();

var usernameField = driver.FindElementByLocatAI("username input field");
usernameField.SendKeys("your-username");

Advanced Configuration

If you need more control, you can also configure LocatAI programmatically:

using LocatAI.Core;
using LocatAI.Providers;
using LocatAI.Models;

// Initialize with a specific provider
var provider = AIProviderFactory.Create("openai", "your-api-key", "gpt-4");
ElementFinder.Initialize(provider);

// Or with custom options
var options = new LocatAIOptions
{
    MinimumConfidence = 0.5,
    MaxLocatorsToTry = 5,
    EnableDetailedLogging = true
};
ElementFinder.Initialize(provider, options);

License

MIT