diff --git a/README.md b/README.md
index e69de29..a7f047e 100644
--- a/README.md
+++ b/README.md
@@ -0,0 +1,118 @@
+# The Joomla! AI Package
+
+## Installation via Composer
+
+Add `"joomla/ai": "~4.0"` to the require block in your composer.json and then run `composer install`.
+
+```json
+{
+	"require": {
+		"joomla/ai": "~4.0"
+	}
+}
+```
+
+Alternatively, you can simply run the following from the command line:
+
+```sh
+composer require joomla/ai "~4.0"
+```
+
+If you want to include the test sources and docs, use
+
+```sh
+composer require --prefer-source joomla/ai "~4.0"
+```
+
+## Using the AI Framework
+The AI Framework provides a straightforward, provider-agnostic interface for working with three main AI providers: OpenAI, Anthropic and Ollama. Instead of writing separate code for each provider’s SDK, developers write once and simply switch providers by changing configuration.
+
+You can find the official provider APIs documentation here:
+- OpenAI API: https://platform.openai.com/docs/api-reference
+- Anthropic API: https://docs.anthropic.com/claude/docs
+- Ollama API: https://github.com/ollama/ollama/blob/main/docs/api.md
+
+The AI framework is built upon the Http package which provides an easy way to consume URLs and web services in a transport independent way. Joomla\Http currently supports streams, sockets and cURL. The framework centralizes HTTP handling in the Abstract Provider. Providers encapsulate:
+- Base URLs, headers, and auth (API keys/tokens)
+- Request building (JSON/multipart)
+- Response normalization and error mapping into framework exceptions
+
+## Instantiating a Provider
+
+Each provider is instantiated with its configuration (API key, defaults such as model or base URL). You can override these defaults per call when needed.
+
+### OpenAI:
+```php
+use Joomla\AI\AIFactory;
+
+$openai = AIFactory::getAI('openai', [
+  'api_key' => getenv('OPENAI_API_KEY'),
+  // Optional defaults:
+  // 'model' => 'gpt-4o',
+  // 'base_url' => 'https://api.openai.com/v1',
+]);
+```
+
+### Anthropic:
+```php
+use Joomla\AI\AIFactory;
+
+$anthropic = AIFactory::getAI('anthropic', [
+  'api_key' => getenv('ANTHROPIC_API_KEY'),
+  // 'model' => 'claude-3-5-sonnet',
+]);
+```
+
+### Ollama (local):
+```php
+use Joomla\AI\AIFactory;
+
+$ollama = AIFactory::getAI('ollama', [
+  // 'base_url' => 'http://localhost:11434',
+  // 'model' => 'llama3',
+]);
+```
+
+## Supported Methods
+
+| Provider | Methods |
+| --- | --- |
+| OpenAI | `chat`, `vision`, `generateImage`, `createImageVariation`, `editImage`, `speech`, `transcribe`, `translate`, `createEmbeddings`, `moderate`, `isContentFlagged`|
+| Anthropic | `chat`, `vision`, `getModel`|
+| Ollama | `chat`, `generate`, `pullModel`, `copyModel`, `deleteModel`, `checkModelExists`, `getRunningModels`|
+
+Not all providers implement every capability. The framework exposes capabilities via interfaces (e.g. ChatInterface, ImageInterface). Developers can use what each provider supports.
+
+## Making your first request
+All providers implement a shared set of capability interfaces (e.g., Chat, Images, Audio). Invoke these methods directly, passing per-call options to override defaults.
+
+```php
+// Chat example (OpenAI)
+$response = $openai->chat("Write a haiku about Joomla.", [
+  'model' => 'gpt-4o-mini', // overrides constructor default if set
+]);
+echo $response->getContent();           // primary content (e.g. text)
+$meta = $response->getMetadata();       // metadata content (e.g. model, usage)
+```
+
+## Error handling
+Provider HTTP errors are mapped to framework exceptions (e.g. auth, rate limit, invalid arguments). Catch and handle them as needed.
+```php
+try {
+  $response = $openai->chat("Hello!");
+} catch (\Throwable $e) {
+  // Log and surface a friendly message
+}
+```
+
+## Documentation
+
+- **[Overview](docs/overview.md)**  
+  Architecture & goals  
+
+- **[Getting Started](docs/getting-started.md)**  
+  Install, configure, first provider  
+
+- **[Guides](providers/)**  
+  Provider-specific guides with code examples
+---
diff --git a/Tests/FactoryTest.php b/Tests/FactoryTest.php
new file mode 100644
index 0000000..d6eaedb
--- /dev/null
+++ b/Tests/FactoryTest.php
@@ -0,0 +1,96 @@
+<?php
+
+require_once '../vendor/autoload.php';
+
+use Joomla\AI\AIFactory;
+use Joomla\AI\Exception\ProviderException;
+
+$configFile = __DIR__ . '/../config.json';
+$config = json_decode(file_get_contents($configFile), true);
+$api_key = $config['openai_api_key'] ?? null;
+$anthropic_api_key = $config['anthropic_api_key'] ?? null;
+
+echo "=== AI Factory Test Suite ===\n\n";
+
+// Test Case 1: Invalid Provider
+echo "1. Testing invalid provider 'abcd':\n";
+try {
+    $options = [
+        'api_key' => $anthropic_api_key
+    ];
+    
+    $ai = AIFactory::getAI('abcd', $options);
+    $response = $ai->chat("Hey");
+    echo $response->getContent();
+
+} catch (ProviderException $e) {
+    echo "Caught expected exception: " . $e->getMessage() . "\n";
+}
+echo "\n";
+
+// Test Case 2: Valid Provider Creation
+echo "2. Testing valid provider creation (anthropic):\n";
+try {
+    $options = [
+        'api_key' => $anthropic_api_key
+    ];
+    
+    $ai = AIFactory::getAI('anthropic', $options);
+    echo "Provider name: " . $ai->getProvider()->getName() . "\n";
+    $response = $ai->chat("Hey");
+    echo $response->getContent();
+} catch (Exception $e) {
+    echo "Failed to create Anthropic provider: " . $e->getMessage() . "\n";
+}
+echo "\n";
+
+// Test Case 3: Non-existent Method Call
+echo "3. Testing non-existent method call:\n";
+try {
+    $options = [
+        'api_key' => $anthropic_api_key
+    ];
+    
+    $ai = AIFactory::getAI('anthropic', $options);
+    $response = $ai->nonExistentMethod("test");
+    echo $response->getContent();
+} catch (ProviderException $e) {
+    echo "Caught expected Exception for non-existent method: " . $e->getMessage() . "\n";
+}
+echo "\n";
+
+// Test Case 4: Available Providers
+echo "4. Testing available providers:\n";
+try {
+    $availableProviders = AIFactory::getAvailableProviders();
+    echo "Available providers: " . implode(', ', $availableProviders) . "\n";
+    
+    // Test each provider availability
+    foreach ($availableProviders as $provider) {
+        $isAvailable = AIFactory::isProviderAvailable($provider);
+        echo "Provider '$provider' is available: " . ($isAvailable ? 'Yes' : 'No') . "\n";
+    }
+    
+    // Test non-existent provider
+    $isAvailable = AIFactory::isProviderAvailable('non-existent');
+    echo "Provider 'non-existent' is available: " . ($isAvailable ? 'Yes' : 'No') . "\n";
+} catch (Exception $e) {
+    echo "Failed to get available providers: " . $e->getMessage() . "\n";
+}
+echo "\n";
+
+// Test Case 5: Valid Method Call
+echo "5. Testing valid method calls:\n";
+try {
+    $options = [
+        'api_key' => $anthropic_api_key
+    ];
+
+    $ai = AIFactory::getAI('anthropic', $options);
+    $response = $ai->chat("Hey");
+    echo $response->getContent();
+} catch (Exception $e) {
+    echo "Test Failed: " . $e->getMessage() . "\n";
+}
+
+echo "\n=== Test Suite Complete ===\n";
\ No newline at end of file
diff --git a/docs/getting-started.md b/docs/getting-started.md
new file mode 100644
index 0000000..2ddd2b7
--- /dev/null
+++ b/docs/getting-started.md
@@ -0,0 +1,257 @@
+# Getting Started
+
+This guide will help you install the AI Framework and make your first request in just a few minutes.
+
+## Requirements
+
+- PHP 8.3.0 or higher
+- Composer
+- API keys for the providers you want to use
+
+## Installation
+
+### Via Composer
+
+Add the AI package to your project:
+
+```json
+{
+    "require": {
+        "joomla/ai": "~4.0"
+    }
+}
+```
+
+Then run:
+```bash
+composer install
+```
+
+Alternatively, install directly:
+```bash
+composer require joomla/ai "~4.0"
+```
+
+For development with test sources:
+```bash
+composer require --prefer-source joomla/ai "~4.0"
+```
+
+## Configuration
+
+### API Keys
+
+You will need API keys from the providers you want to use:
+
+- **OpenAI**: Get your key at https://platform.openai.com/api-keys
+- **Anthropic**: Get your key at https://console.anthropic.com/
+- **Ollama**: Runs locally, no API key needed
+
+### Storing API Keys
+
+You should not hardcode your API keys into your program code. Make them configurable via for example a registry object or by storing them in environment variables. **Never commit API keys to version control.**
+
+## Your First Request
+
+### Basic Chat Example
+
+```php
+<?php
+require_once 'vendor/autoload.php';
+
+use Joomla\AI\AIFactory;
+
+// Create provider instance
+$openai = AIFactory::getAI('openai', [
+    'api_key' => getenv('OPENAI_API_KEY')
+]);
+
+// Make your first chat request
+$response = $openai->chat("Hello! Tell me about Joomla in one sentence.");
+
+// Display the result
+echo "Response: " . $response->getContent() . "\n";
+echo "Model used: " . $response->getMetadata()['model'] . "\n";
+echo "Provider: " . $response->getProvider() . "\n";
+```
+
+### Multi-Provider Example
+
+```php
+<?php
+require_once 'vendor/autoload.php';
+
+use Joomla\AI\AIFactory;
+
+// Configure multiple providers
+$providers = [
+    'openai' => $openai = AIFactory::getAI('openai', ['api_key' => getenv('OPENAI_API_KEY')]),
+    'anthropic' => nAIFactory::getAI('anthropic', ['api_key' => getenv('ANTHROPIC_API_KEY')]),
+    'ollama' => AIFactory::getAI('ollama', []) // Local server, no API key needed
+];
+
+$question = "What is Joomla?";
+
+foreach ($providers as $name => $provider) {
+    try {
+        $response = $provider->chat($question);
+        echo "\n=== {$name} ===\n";
+        echo $response->getContent() . "\n";
+    } catch (Exception $e) {
+        echo "{$name}: Error - " . $e->getMessage() . "\n";
+    }
+}
+```
+
+## Working with Different Capabilities
+
+### Image Generation
+
+```php
+use Joomla\AI\AIFactory;
+
+$openai = AIFactory::getAI('openai', ['api_key' => getenv('OPENAI_API_KEY')]);
+
+// Generate an image
+$image = $openai->generateImage("A beautiful sunset over mountains", [
+    'model' => 'dall-e-3',
+    'size' => '1024x1024',
+    'response_format' => 'b64_json'
+]);
+
+// Save the image
+$image->saveFile('my_sunset.png');
+echo "Image saved as my_sunset.png\n";
+```
+
+### Text-to-Speech
+
+```php
+$audio = $openai->speech("Welcome to Joomla! This is a text-to-speech demo.", [
+    'model' => 'tts-1',
+    'voice' => 'alloy',
+    'response_format' => 'mp3'
+]);
+
+$audio->saveFile('welcome.mp3');
+echo "Audio saved as welcome.mp3\n";
+```
+
+### Vision (Image Analysis)
+
+```php
+$vision = $openai->vision(
+    "What do you see in this image?",
+    "https://example.com/your-image.jpg"
+);
+
+echo "Vision analysis: " . $vision->getContent() . "\n";
+```
+
+## Setting Default Models
+
+Avoid repeating model names by setting defaults:
+
+```php
+$openai = AIFactory::getAI('openai', ['api_key' => getenv('OPENAI_API_KEY')]);
+
+// Set a default model for all chat requests
+$openai->setDefaultModel('gpt-4o-mini');
+
+// These will use gpt-4o-mini
+$response1 = $openai->chat("Hello!");
+$response2 = $openai->chat("How are you?");
+
+// Override the default for one request
+$response3 = $openai->chat("Complex task", ['model' => 'gpt-4o']);
+
+// Back to default
+$response4 = $openai->chat("Simple task");
+
+// Clear the default
+$openai->unsetDefaultModel();
+```
+
+## Error Handling
+
+The framework provides specific exceptions that are inherited from [`AIException`](../src/Exception/AIException.php):
+
+```php
+use Joomla\AI\Exception\AuthenticationException;
+use Joomla\AI\Exception\RateLimitException;
+use Joomla\AI\Exception\QuotaExceededException;
+use Joomla\AI\Exception\InvalidArgumentException;
+use Joomla\AI\Exception\ProviderException;
+
+try {
+    $response = $openai->chat("Hello!");
+    echo $response->getContent();
+} catch (AuthenticationException $e) {
+    echo "Authentication failed: Check your API key\n";
+} catch (RateLimitException $e) {
+    echo "Rate limited: Please wait before trying again\n";
+} catch (QuotaExceededException $e) {
+    echo "Quota exceeded: Check your billing\n";
+} catch (InvalidArgumentException $e) {
+    echo "Invalid input: " . $e->getMessage() . "\n";
+} catch (ProviderException $e) {
+    echo "Provider error: " . $e->getMessage() . "\n";
+} catch (Exception $e) {
+    echo "Unexpected error: " . $e->getMessage() . "\n";
+}
+```
+
+## Local Development with Ollama
+
+For local AI without API costs:
+
+1. **Install Ollama**: Download from https://ollama.ai/
+2. **Pull a model**: `ollama pull llama3`
+3. **Use in your code**:
+
+```php
+use Joomla\AI\AIFactory;
+
+$ollama = AIFactory::getAI('ollama');
+
+$response = $ollama->chat("Hello!", ['model' => 'llama3']);
+echo $response->getContent();
+```
+
+## Response Object
+
+All methods return a unified [`Response`](../src/Response/Response.php) object:
+
+```php
+$response = $provider->chat("Hello!");
+
+// Primary content
+echo $response->getContent();
+
+// Provider metadata (model, usage, etc.)
+$metadata = $response->getMetadata();
+print_r($metadata);
+
+// Provider name
+echo $response->getProvider(); // "OpenAI", "Anthropic", or "Ollama"
+
+// Save files (for images, audio)
+$response->saveFile('output.png');
+```
+
+## Next Steps
+
+Now that you have the basics working:
+
+- **[Provider Guides](providers/)** - Provider-specific features and limitations
+
+## Troubleshooting
+
+**API Key Issues:**
+- Ensure environment variables are set correctly
+- Restart your terminal/web server after setting environment variables
+- Check that your API keys have sufficient credits/permissions
+
+**Model Issues:**
+- Verify the model name is correct and available
+- Some models may require special access or billing setup
diff --git a/docs/index.md b/docs/index.md
index c87f1b4..f795495 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -1 +1,5 @@
 * [Overview](overview.md)
+* [Getting Started](getting-started.md)
+* [Open AI Provider](providers/openai.md)
+* [Anthropic Provider](providers/anthropic.md)
+* [Ollama Provider](providers/ollama.md)
diff --git a/docs/overview.md b/docs/overview.md
index 063f86f..5589ef2 100644
--- a/docs/overview.md
+++ b/docs/overview.md
@@ -1,3 +1,115 @@
 ## Overview
 
-The AI package provides an abstraction layer to access the services of several AI providers.
+The AI package provides an abstraction layer to access the services of several AI providers. It provides a unified, provider-agnostic interface for integrating multiple AI services into your applications. Instead of learning different SDKs and handling varying response formats, you write code once and switch providers by changing configuration.
+
+Official provider API references:
+- OpenAI: https://platform.openai.com/docs/api-reference
+- Anthropic: https://docs.anthropic.com/claude/docs
+- Ollama: https://github.com/ollama/ollama/blob/main/docs/api.md
+
+## Supported Providers
+
+| Provider | Chat | Vision | Images | Audio | Embeddings | Moderation | Models |
+|----------|------|--------|---------|-------|------------|------------|---------|
+| **OpenAI** | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
+| **Anthropic** | ✓ | ✓ | - | - | - | - | ✓ |
+| **Ollama** | ✓ | - | - | - | - | - | ✓ |
+
+## Architecture
+
+### Core Components
+
+**Interfaces** (`/src/Interface/`)
+Define the interfaces that providers implement:
+- [`ProviderInterface`](../src/Interface/ProviderInterface.php) - Base provider contract
+- [`ChatInterface`](../src/Interface/ChatInterface.php) - Text conversation
+- [`ImageInterface`](../src/Interface/ImageInterface.php) - Image generation, editing, variations
+- [`AudioInterface`](../src/Interface/AudioInterface.php) - Speech synthesis, transcription, translation
+- [`EmbeddingInterface`](../src/Interface/EmbeddingInterface.php) - Vector embeddings
+- [`ModelInterface`](../src/Interface/ModelInterface.php) - Model management and capabilities
+- [`ModerationInterface`](../src/Interface/ModerationInterface.php) - Content safety
+
+**Abstract Provider** (`/src/AbstractProvider.php`)
+Centralizes common functionality:
+- HTTP client management (GET, POST, DELETE, multipart)
+- Error mapping (401→Auth, 429→RateLimit/Quota, etc.)
+- JSON response parsing
+
+**AI Factory** (`/src/AIFactory.php`)
+Centralized provider instantiation and management:
+- `getAI($provider, $options)` - Creates provider instances by name
+- Provider registry with supported providers ('openai', 'anthropic', 'ollama')
+- Simplifies provider switching and configuration management
+
+**AI Class** (`/src/AI.php`)
+- Wrapper providing access to all AI capabilities.
+
+**Response Object** (`/src/Response/Response.php`)
+Unified response wrapper that extends Joomla's HttpResponse:
+- `getContent()` - Primary result (text, base64 image, binary audio)
+- `getMetadata()` - Normalized provider details (model, usage, formats)
+- `getProvider()` - Provider name ("OpenAI", "Anthropic", "Ollama")
+- `saveFile($path)` - Method to save the generated output
+
+**Providers** (`/src/Provider/`)
+- [`OpenAIProvider`](../src/Provider/OpenAIProvider.php) - Implements methods related to OpenAI
+- [`AnthropicProvider`](../src/Provider/AnthropicProvider.php) - Implements methods related to Anthropic
+- [`OllamaProvider`](../src/Provider/OllamaProvider.php) - Implements methods related to Ollama
+
+### Exception Hierarchy
+
+All exceptions inherit from [`AIException`](../src/Exception/AIException.php):
+- [`AuthenticationException`](../src/Exception/AuthenticationException.php)
+- [`RateLimitException`](../src/Exception/RateLimitException.php)
+- [`QuotaExceededException`](../src/Exception/QuotaExceededException.php)
+- [`ProviderException`](../src/Exception/ProviderException.php)
+- [`InvalidArgumentException`](../src/Exception/InvalidArgumentException.php)
+- [`UnserializableResponseException`](../src/Exception/UnserializableResponseException.php)
+
+## Key Design Principles
+
+### Provider Abstraction
+```php
+// Same interface, different providers
+$openai = AIFactory::getAI('openai', ['api_key' => $key]);
+$anthropic = AIFactory::getAI('anthropic', ['api_key' => $anthropic_key]);
+
+// Identical usage
+$response1 = $openai->chat("Hello!");
+$response2 = $anthropic->chat("Hello!");
+```
+
+### Unified Response Format
+```php
+$response = $provider->chat("Hello!");
+echo $response->getContent();      // "Hello! How can I help you today?"
+echo $response->getProvider();     // "OpenAI"
+$metadata = $response->getMetadata();
+echo $metadata['model'];           // "gpt-4o"
+
+```
+
+### Default Model Management
+Flexible precedence system for model selection with four levels of fallback:
+
+1. **Per-call `options['model']`** - Highest priority
+2. **Provider default via `setDefaultModel()`** - Session-level default
+3. **Constructor option `'model'`** - Provider-level configuration
+4. **Method-specific fallback** - Built-in defaults per capability
+
+### File Handling
+Streamlined output persistence:
+```php
+// Images
+$image = $provider->generateImage("A sunset");
+$image->saveFile('sunset.png');
+
+// Audio
+$audio = $provider->speech("Hello world");
+$audio->saveFile('greeting.mp3');
+```
+
+## Next Steps
+
+- **[Getting Started](getting-started.md)** - Installation and first requests
+- **[Provider Guides](providers/)** - Provider-specific documentation
diff --git a/docs/providers/anthropic.md b/docs/providers/anthropic.md
new file mode 100644
index 0000000..eb8bab0
--- /dev/null
+++ b/docs/providers/anthropic.md
@@ -0,0 +1,143 @@
+# Anthropic Provider
+
+The Anthropic Provider ([`AnthropicProvider`](../../src/Provider/AnthropicProvider.php)) focuses on conversational AI using Claude models, offering superior reasoning capabilities.
+
+## Capabilities Overview
+
+| Feature | Description |
+|---------|-------------|
+| **Chat** | Advanced text conversation with Claude models |
+| **Vision** | Image analysis and description using Claude's vision capabilities |
+| **Model Management** | List available models and retrieve model information |
+
+## Configuration
+
+```php
+use Joomla\AI\AIFactory;
+
+$anthropic = AIFactory::getAI('anthropic', [
+    'api_key' => getenv('ANTHROPIC_API_KEY'),
+    'model' => 'claude-3-5-sonnet' // Optional: default model
+]);
+```
+
+## Chat Completions
+
+### Basic Chat
+```php
+$response = $anthropic->chat("Explain the advantages of Joomla over other CMS platforms.");
+echo $response->getContent();
+```
+
+### Advanced Chat with options
+```php
+$response = $anthropic->chat("How do I optimize database queries in Joomla?", [
+    'model' => 'claude-3-5-sonnet',
+    'max_tokens' => 1000,
+    'temperature' => 0.3
+]);
+
+$metadata = $response->getMetadata();
+echo "Model used: " . $metadata['model'] . "\n";
+echo "Tokens used: " . $metadata['usage']['input_tokens'] + $metadata['usage']['output_tokens'] . "\n";
+```
+
+### Message History
+```php
+$response = $anthropic->chat("", [
+    'messages' => [
+        ['role' => 'user', 'content' => 'What is Joomla?'],
+        ['role' => 'assistant', 'content' => 'Joomla is a free, open-source content management system...'],
+        ['role' => 'user', 'content' => 'How does it compare to WordPress?']
+    ],
+    'system' => 'You are a helpful web development consultant.'
+]);
+
+echo $response->getContent();
+```
+
+## Vision
+
+Analyze images with Claude's vision capabilities:
+
+### URL Image Analysis
+```php
+$response = $anthropic->vision(
+    "Analyze this website design and suggest improvements for user experience",
+    "https://example.com/website-screenshot.jpg"
+);
+
+echo $response->getContent();
+```
+
+### Base64 Image Analysis
+```php
+$imageData = base64_encode(file_get_contents('ui-mockup.png'));
+$response = $anthropic->vision(
+    "Review this UI mockup and provide detailed feedback on the design principles",
+    "data:image/png;base64," . $imageData,
+    [
+        'model' => 'claude-3-5-sonnet',
+        'max_tokens' => 1500
+    ]
+);
+
+echo $response->getContent();
+```
+
+## Model Management
+
+### List Available Models
+```php
+$models = $anthropic->getAvailableModels();
+echo "Available Models: " . implode(', ', $models) . "\n";
+```
+
+## Default Model Management
+
+Set defaults for consistent model usage:
+
+```php
+// Set a default model
+$anthropic->setDefaultModel('claude-3-5-sonnet');
+
+// These will use the default
+$chat1 = $anthropic->chat("What is web accessibility?");
+$vision1 = $anthropic->vision("Describe this image", $imageUrl);
+
+// Override for specific calls
+$detailed = $anthropic->chat("Provide a comprehensive analysis", [
+    'model' => 'claude-3-opus',
+    'max_tokens' => 2000
+]);
+
+// Clear the default
+$anthropic->unsetDefaultModel();
+```
+
+## Error Handling
+
+Anthropic-specific error patterns:
+
+```php
+use Joomla\AI\Exception\AuthenticationException;
+use Joomla\AI\Exception\RateLimitException;
+use Joomla\AI\Exception\InvalidArgumentException;
+
+try {
+    $response = $anthropic->chat("Hello", [
+        'max_tokens' => 500000 // Exceeds model limit
+    ]);
+} catch (InvalidArgumentException $e) {
+    echo "Parameter error: " . $e->getMessage();
+} catch (AuthenticationException $e) {
+    echo "Authentication failed: Check your API key";
+} catch (RateLimitException $e) {
+    echo "Rate limited: " . $e->getMessage();
+}
+```
+
+## Next Steps
+
+- **[OpenAI Provider](openai.md)**
+- **[Ollama Provider](ollama.md)**
diff --git a/docs/providers/index.md b/docs/providers/index.md
new file mode 100644
index 0000000..fc689e9
--- /dev/null
+++ b/docs/providers/index.md
@@ -0,0 +1,3 @@
+* [Open AI Provider](openai.md)
+* [Anthropic Provider](anthropic.md)
+* [Ollama Provider](ollama.md)
diff --git a/docs/providers/ollama.md b/docs/providers/ollama.md
new file mode 100644
index 0000000..fdabaa2
--- /dev/null
+++ b/docs/providers/ollama.md
@@ -0,0 +1,190 @@
+# Ollama Provider
+
+The Ollama Provider ([`OllamaProvider`](../../src/Provider/OllamaProvider.php)) enables local AI inference without API costs, offering privacy-focused processing and offline capabilities.
+
+## Capabilities Overview
+
+| Feature | Description |
+|---------|-------------|
+| **Chat** | Text conversation with locally-hosted models |
+| **Generate** | Text generation and completion tasks |
+| **Model Management** | Pull, copy, delete, and list local models |
+| **Model Availability** | Automatic model pulling and status checking |
+
+## Configuration
+
+```php
+use Joomla\AI\AIFactory;
+
+$ollama = AIFactory::getAI('ollama', [
+    'base_url' => 'http://localhost:11434', // Default Ollama server
+    'model' => 'llama3' // Optional: default model
+]);
+```
+
+## Prerequisites
+
+### Install Ollama
+1. Download from https://ollama.ai/
+2. Install and start the Ollama service
+3. Pull your first model:
+```bash
+ollama pull llama3
+```
+
+## Chat Completions
+
+### Basic Chat
+```php
+$response = $ollama->chat("Explain what Joomla CMS is and its main features.");
+echo $response->getContent();
+```
+
+### Chat with Model Selection
+```php
+$response = $ollama->chat("Write a PHP function for Joomla component development", [
+    'model' => 'codellama:7b',
+    'temperature' => 0.1 // More focused for code generation
+]);
+
+echo $response->getContent();
+```
+
+## Text Generation
+
+### Basic Generation
+```php
+$response = $ollama->generate("Complete this Joomla tutorial: To create a custom module, first you need to", [
+    'model' => 'llama3'
+]);
+
+echo $response->getContent();
+```
+
+### Generation with Parameters
+```php
+$response = $ollama->generate("Write a Joomla plugin that", [
+    'model' => 'codellama:13b',
+    'max_tokens' => 500,
+    'temperature' => 0.3,
+    'top_p' => 0.9,
+]);
+
+echo $response->getContent();
+```
+
+## Model Management
+
+### List Available Models (Local)
+```php
+$models = $ollama->getAvailableModels();
+echo "Available Models: " . implode(', ', $models) . "\n";
+```
+
+### List Running Models
+```php
+$running = $ollama->getRunningModels();
+echo $running;
+```
+
+### Pull a Model
+```php
+// Pull model if not already available
+$ollama->pullModel('mistral:7b');
+echo "Mistral 7B model is now available\n";
+```
+
+### Copy a Model
+```php
+// Create a copy with a custom name
+$ollama->copyModel('llama3', 'llama3-joomla-tuned');
+echo "Model copied for Joomla-specific use\n";
+```
+
+### Delete a Model
+```php
+$ollama->deleteModel('old-model:tag');
+echo "Model removed to free up space\n";
+```
+
+### Check Model Availability
+```php
+if ($ollama->checkModelExists('llama3')) {
+    echo "Llama3 is available locally\n";
+} else {
+    echo "Pulling Llama3...\n";
+    $ollama->pullModel('llama3');
+}
+```
+
+## Default Model Management
+
+```php
+// Set a default model for all operations
+$ollama->setDefaultModel('llama3');
+
+// These will use the default
+$chat = $ollama->chat("Hello!");
+$generate = $ollama->generate("Complete this: ");
+
+// Override for specific calls
+$code = $ollama->generate("Write PHP code:", ['model' => 'codellama:7b']);
+
+// Clear the default
+$ollama->unsetDefaultModel();
+```
+
+### Custom Parameters
+```php
+$response = $ollama->generate("Explain Joomla architecture", [
+    'model' => 'llama3',
+    'temperature' => 0.7,
+    'top_k' => 40,
+    'top_p' => 0.9,
+    'repeat_penalty' => 1.1,
+    'seed' => 42, // For reproducible results
+    'num_predict' => 100
+]);
+```
+
+## Error Handling
+
+```php
+use Joomla\AI\Exception\ProviderException;
+use Joomla\AI\Exception\InvalidArgumentException;
+
+try {
+    $response = $ollama->chat("Hello", ['model' => 'nonexistent-model']);
+} catch (ProviderException $e) {
+    echo "Model not available. \n";
+} catch (InvalidArgumentException $e) {
+    echo "Parameter error: " . $e->getMessage();
+}
+```
+
+## Troubleshooting
+
+### Connection Issues
+```php
+// Test Ollama server connectivity
+try {
+    $models = $ollama->getAvailableModels();
+    echo "Ollama server is responding\n";
+} catch (Exception $e) {
+    echo "Ollama server not accessible. Check if it's running on localhost:11434\n";
+}
+```
+
+### Model Issues
+```php
+// Verify model availability before use
+$modelName = 'llama3';
+if (!$ollama->checkModelExists($modelName)) {
+    echo "Model $modelName not found. Available models:\n";
+}
+```
+
+## Next Steps
+
+- **[OpenAI Provider](openai.md)**
+- **[Anthropic Provider](anthropic.md)**
diff --git a/docs/providers/openai.md b/docs/providers/openai.md
new file mode 100644
index 0000000..b938e63
--- /dev/null
+++ b/docs/providers/openai.md
@@ -0,0 +1,390 @@
+# OpenAI Provider
+
+The OpenAI Provider ([`OpenAIProvider`](../../src/Provider/OpenAIProvider.php)) offers the most comprehensive feature set in the framework, supporting chat, vision, image generation, audio processing, embeddings, and content moderation.
+
+## Capabilities Overview
+
+| Feature | Description |
+|---------|-------------|
+| **Chat** | Standard text conversation with GPT models |
+| **Vision** | Image analysis and description using vision-enabled models |
+| **Audio Chat** | Experimental audio responses with gpt-4o-audio-preview |
+| **Image Generation** | Text-to-image generation with DALL-E 2, DALL-E 3, and GPT-Image-1 models |
+| **Image Editing** | Edit existing images with masks and prompts |
+| **Image Variations** | Create variations of existing images (DALL-E 2 only) |
+| **Text-to-Speech** | Convert text to speech with multiple voices and audio formats |
+| **Transcription** | Convert audio to text using Whisper and GPT transcription models |
+| **Translation** | Translate audio from any language to English |
+| **Embeddings** | Generate vector embeddings for text similarity and search |
+| **Moderation** | Content safety checking and flagging inappropriate content |
+
+## Configuration
+
+```php
+use Joomla\AI\AIFactory;
+
+$openai = AIFactory::getAI('openai', [
+    'api_key' => getenv('OPENAI_API_KEY'),
+    'base_url' => 'https://api.openai.com/v1', // Optional: custom endpoint
+    'model' => 'gpt-4o-mini' // Optional: default model
+]);
+```
+
+## Chat Completions
+
+### Basic Chat
+```php
+$response = $openai->chat("Explain Joomla CMS in one paragraph.");
+echo $response->getContent();
+```
+
+### Advanced Chat Options
+```php
+$response = $openai->chat("Write a technical article outline", [
+    'model' => 'gpt-4o',
+    'max_tokens' => 1000,
+    'temperature' => 0.7,
+    'n' => 2 // Generate 2 response choices
+]);
+
+$metadata = $response->getMetadata();
+echo "Used model: " . $metadata['model'] . "\n";
+echo "Tokens used: " . $metadata['usage']['total_tokens'] . "\n";
+```
+
+### Message History
+```php
+$response = $openai->chat("", [
+    'messages' => [
+        ['role' => 'system', 'content' => 'You are a Joomla expert.'],
+        ['role' => 'user', 'content' => 'How do I create a custom component?'],
+        ['role' => 'assistant', 'content' => 'To create a custom component...'],
+        ['role' => 'user', 'content' => 'What about adding database tables?']
+    ]
+]);
+```
+
+### Audio Chat (Experimental)
+```php
+$response = $openai->chat("Say hello in a friendly voice", [
+    'model' => 'gpt-4o-audio-preview',
+    'modalities' => ['text', 'audio'],
+    'audio' => [
+        'voice' => 'alloy',
+        'format' => 'wav'
+    ]
+]);
+
+// Save audio
+$metadata = $response->getMetadata();
+if (isset($metadata['choices'][0]['message']['audio']['data'])) {
+    file_put_contents('hello.wav', base64_decode($metadata['choices'][0]['message']['audio']['data']));
+}
+```
+
+## Vision
+
+Analyze images with text prompts:
+
+```php
+// URL image
+$response = $openai->vision(
+    "Describe this website screenshot in detail",
+    "https://example.com/screenshot.jpg"
+);
+
+// Base64 image
+$imageData = base64_encode(file_get_contents('local-image.jpg'));
+$response = $openai->vision(
+    "What coding framework is shown in this image?",
+    "data:image/jpeg;base64," . $imageData
+);
+
+echo $response->getContent();
+```
+
+## Image Generation
+
+### DALL-E 2
+```php
+$image = $openai->generateImage("A futuristic Joomla logo in space", [
+    'model' => 'dall-e-2',
+    'size' => '1024x1024',
+    'n' => 4, // Generate 4 variations
+    'response_format' => 'b64_json'
+]);
+
+$image->saveFile('joomla-space-logo.png');
+```
+
+### DALL-E 3
+```php
+$image = $openai->generateImage("Minimalist Joomla CMS dashboard design", [
+    'model' => 'dall-e-3',
+    'quality' => 'hd',
+    'style' => 'vivid', // or 'natural'
+    'response_format' => 'url'
+]);
+
+echo "Image URL: " . $image->getContent();
+```
+
+### GPT-Image-1
+```php
+$image = $openai->generateImage("Professional web development workspace", [
+    'model' => 'gpt-image-1',
+    'background' => 'transparent',
+    'output_format' => 'png',
+    'output_compression' => 80
+]);
+
+$image->saveFile('workspace.png');
+```
+
+## Image Editing
+
+### Edit with Mask (DALL-E 2)
+```php
+$edited = $openai->editImage(
+    'original-logo.png',
+    "Change the background to a gradient blue",
+    [
+        'model' => 'dall-e-2',
+        'mask' => 'logo-mask.png',
+        'size' => '1024x1024',
+        'n' => 2
+    ]
+);
+
+$edited->saveFile('logo-blue-bg.png');
+```
+
+### Multi-Image Edit (GPT-Image-1)
+```php
+$edited = $openai->editImage(
+    ['image1.png', 'image2.png', 'image3.png'],
+    "Combine these into a cohesive collage",
+    [
+        'model' => 'gpt-image-1',
+        'background' => 'auto',
+        'quality' => 'high'
+    ]
+);
+
+$edited->saveFile('collage.png');
+```
+
+## Image Variations
+
+Create variations of existing images (DALL-E 2 only):
+
+```php
+$variations = $openai->createImageVariation('base-design.png', [
+    'model' => 'dall-e-2',
+    'n' => 3,
+    'size' => '512x512',
+    'response_format' => 'b64_json'
+]);
+
+$variations->saveFile('design-variation.png');
+```
+
+## Text-to-Speech
+
+### Basic TTS
+```php
+$audio = $openai->speech("Welcome to our Joomla website!", [
+    'model' => 'tts-1',
+    'voice' => 'nova',
+    'response_format' => 'mp3'
+]);
+
+$audio->saveFile('welcome.mp3');
+```
+
+### High-Quality TTS
+```php
+$audio = $openai->speech("Professional announcement text", [
+    'model' => 'tts-1-hd',
+    'response_format' => 'wav',
+    'speed' => 1.25 // 0.25 to 4.0
+]);
+
+$audio->saveFile('announcement.wav');
+```
+
+### Advanced TTS with Instructions
+```php
+$audio = $openai->speech("Say this with enthusiasm!", [
+    'model' => 'gpt-4o-mini-tts',
+    'voice' => 'alloy',
+    'response_format' => 'mp3',
+    'instructions' => 'Speak with high energy and excitement',
+    'speed' => 1.1
+]);
+
+$audio->saveFile('enthusiastic.mp3');
+```
+
+## Audio Transcription
+
+### Basic Transcription
+```php
+$transcript = $openai->transcribe('meeting-recording.wav', [
+    'model' => 'whisper-1',
+    'response_format' => 'json',
+    'language' => 'en'
+]);
+
+echo "Transcript: " . $transcript->getContent();
+```
+
+### Subtitle Generation
+```php
+$subtitles = $openai->transcribe('video-audio.wav', [
+    'model' => 'whisper-1',
+    'response_format' => 'srt' // or 'vtt'
+]);
+
+$subtitles->saveFile('video-subtitles.srt');
+```
+
+## Audio Translation
+
+Translate audio to English:
+
+```php
+$translation = $openai->translate('spanish-audio.mp3', [
+    'model' => 'whisper-1',
+    'response_format' => 'json',
+]);
+
+echo "English translation: " . $translation->getContent();
+```
+
+## Embeddings
+
+### Basic Embeddings
+```php
+$embeddings = $openai->createEmbeddings(
+    "Joomla is a content management system",
+    'text-embedding-3-small'
+);
+
+$vectors = json_decode($embeddings->getContent());
+echo "Vector dimensions: " . count($vectors) . "\n";
+```
+
+## Content Moderation
+
+### Basic Moderation
+```php
+$result = $openai->moderate("Some text to check for safety");
+
+if ($openai->isContentFlagged($result)) {
+    echo "Content was flagged\n";
+    print_r($result['results'][0]['categories']);
+} else {
+    echo "Content passed moderation\n";
+}
+```
+
+## Model Management
+
+### List Available Models
+```php
+$allModels = $openai->getAvailableModels();
+echo "Available models: " . implode(', ', $allModels) . "\n";
+```
+
+## Default Model Management
+
+Set defaults to avoid repeating model names:
+
+```php
+// Set defaults for different capabilities
+$openai->setDefaultModel('gpt-4o-mini');
+
+// All these use the default
+$chat = $openai->chat("Hello");
+$vision = $openai->vision("Describe this", $imageUrl);
+
+// Override for specific calls
+$premium = $openai->chat("Complex analysis", ['model' => 'gpt-4o']);
+
+// Clear defaults
+$openai->unsetDefaultModel();
+```
+
+## Error Handling
+
+OpenAI-specific error patterns:
+
+```php
+use Joomla\AI\Exception\InvalidArgumentException;
+use Joomla\AI\Exception\QuotaExceededException;
+
+try {
+    $response = $openai->generateImage("A simple logo", [
+        'model' => 'dall-e-3',
+        'style' => 'invalid-style' // This will throw InvalidArgumentException
+    ]);
+} catch (InvalidArgumentException $e) {
+    echo "Parameter error: " . $e->getMessage();
+} catch (QuotaExceededException $e) {
+    echo "Quota exceeded - check your billing";
+}
+```
+
+## Important Constraints
+
+### Model-Specific Limitations
+
+**DALL-E 2:**
+- Image variations: requires square PNG, max 4MB
+- Sizes: 256x256, 512x512, 1024x1024 only
+- Max 10 images per request
+
+**DALL-E 3:**
+- Only 1 image per request (`n=1`)
+- Sizes: 1024x1024, 1792x1024, 1024x1792 only
+- Style parameter: `vivid` or `natural`
+
+**GPT-Image-1:**
+- Always returns base64 (no `response_format` parameter)
+- Supports multiple input images for editing
+- Max 16 images for editing
+- Advanced parameters: background, output_format, compression
+
+**TTS Models:**
+- Text limit: 4096 characters
+- `instructions` parameter: only `gpt-4o-mini-tts`
+- Speed range: 0.25 to 4.0
+
+**Transcription:**
+- File size limit: 25MB
+- Formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm
+- `gpt-4o-transcribe`/`gpt-4o-mini-transcribe`: only JSON response format
+
+**Embeddings:**
+- `dimensions` parameter: only text-embedding-3-large (max 3072) and text-embedding-3-small (max 1536)
+
+### Content Safety
+
+The framework automatically applies moderation to:
+- Chat messages (before sending)
+- Image generation prompts
+- TTS text input
+- Image editing prompts
+
+Content flagged by moderation will throw an exception before the API call.
+
+## Best Practices
+
+1. **Use appropriate models**: Choose the right model for your use case (cost vs capability)
+2. **Handle rate limits**: Implement exponential backoff for production use
+
+## Next Steps
+
+- **[Anthropic Provider](anthropic.md)**
+- **[Ollama Provider](ollama.md)**
diff --git a/phpunit.xml.dist b/phpunit.xml.dist
index a4fd6ec..03184cc 100644
--- a/phpunit.xml.dist
+++ b/phpunit.xml.dist
@@ -1,29 +1,8 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<phpunit bootstrap="Tests/bootstrap.php" colors="false">
-	<php>
-		<env name="JOOMLA_TEST_DB_DRIVER" value="mysqli" />
-		<env name="JOOMLA_TEST_DB_HOST" value="mysqli" />
-		<env name="JOOMLA_TEST_DB_PORT" value="3306" />
-		<env name="JOOMLA_TEST_DB_USER" value="root" />
-		<env name="JOOMLA_TEST_DB_PASSWORD" value="" />
-		<env name="JOOMLA_TEST_DB_DATABASE" value="joomla_ut" />
-		<env name="JOOMLA_TEST_DB_PREFIX" value="" />
-
-		<env name="SYMFONY_DEPRECATIONS_HELPER" value="weak" />
-	</php>
+<phpunit bootstrap="vendor/autoload.php" colors="false">
 	<testsuites>
-		<testsuite name="Unit">
-			<directory>Tests/Command</directory>
-			<directory>Tests/Monitor</directory>
-			<directory>Tests/Query</directory>
-			<directory>Tests/Service</directory>
-			<file>Tests/AbstractDatabaseDriverTestCase.php</file>
-			<file>Tests/DatabaseAwareTraitTest.php</file>
-			<file>Tests/DatabaseExporterTest.php</file>
-			<file>Tests/DatabaseFactoryTest.php</file>
-			<file>Tests/DatabaseImporterTest.php</file>
-			<file>Tests/DatabaseIteratorTest.php</file>
-			<file>Tests/DatabaseQueryTest.php</file>
+		<testsuite name="default">
+			<directory>Tests</directory>
 		</testsuite>
 	</testsuites>
 </phpunit>
diff --git a/src/AI.php b/src/AI.php
new file mode 100644
index 0000000..b3dd06d
--- /dev/null
+++ b/src/AI.php
@@ -0,0 +1,73 @@
+<?php
+
+/**
+ * Part of the Joomla Framework AI Package
+ *
+ * @copyright  Copyright (C) 2025 Open Source Matters, Inc. All rights reserved.
+ * @license    GNU General Public License version 2 or later; see LICENSE
+ */
+
+namespace Joomla\AI;
+
+use Joomla\AI\Exception\ProviderException;
+
+/**
+ * AI client class.
+ *
+ * @since  __DEPLOY_VERSION__
+ */
+class AI
+{
+    /**
+     * The AI provider object to use for AI requests.
+     *
+     * @var AbstractProvider
+     * @since  __DEPLOY_VERSION__
+     */
+    protected AbstractProvider $provider;
+
+    /**
+     * Constructor.
+     *
+     * @param   AbstractProvider  $provider  The AI provider object.
+     *
+     * @since   __DEPLOY_VERSION__
+     */
+    public function __construct(AbstractProvider $provider)
+    {
+        $this->provider = $provider;
+    }
+
+    /**
+     * Magic method to delegate all calls to the provider.
+     *
+     * @param   string  $method     The method name being called
+     * @param   array   $arguments  The arguments passed to the method
+     *
+     * @return  mixed
+     * @throws  ProviderException  If the provider doesn't have the method
+     * @since   __DEPLOY_VERSION__
+     */
+    public function __call(string $method, array $arguments)
+    {
+        if (method_exists($this->provider, $method)) {
+            return $this->provider->$method(...$arguments);
+        }
+
+        throw new ProviderException(
+            $this->provider->getName(),
+            ['message' => 'Method ' . $method . ' is not supported by ' . $this->provider->getName()],
+        );
+    }
+
+    /**
+     * Get the underlying provider instance.
+     *
+     * @return  AbstractProvider
+     * @since   __DEPLOY_VERSION__
+     */
+    public function getProvider(): AbstractProvider
+    {
+        return $this->provider;
+    }
+}
diff --git a/src/AIFactory.php b/src/AIFactory.php
new file mode 100644
index 0000000..3a8d58c
--- /dev/null
+++ b/src/AIFactory.php
@@ -0,0 +1,107 @@
+<?php
+
+/**
+ * Part of the Joomla Framework AI Package
+ *
+ * @copyright  Copyright (C) 2025 Open Source Matters, Inc. All rights reserved.
+ * @license    GNU General Public License version 2 or later; see LICENSE
+ */
+
+namespace Joomla\AI;
+
+use Joomla\AI\Provider\OpenAIProvider;
+use Joomla\AI\Provider\AnthropicProvider;
+use Joomla\AI\Provider\OllamaProvider;
+use Joomla\AI\Exception\InvalidArgumentException;
+use Joomla\AI\Exception\ProviderException;
+
+/**
+ * AI Factory class for creating AI instances
+ *
+ * @since  __DEPLOY_VERSION__
+ */
+class AIFactory
+{
+    /**
+     * Available AI providers
+     *
+     * @var array
+     * @since  __DEPLOY_VERSION__
+     */
+    private const PROVIDERS = [
+        'openai' => OpenAIProvider::class,
+        'anthropic' => AnthropicProvider::class,
+        'ollama' => OllamaProvider::class,
+    ];
+
+    /**
+     * Create an AI instance with the specified provider
+     *
+     * @param   string  $provider  The provider name (openai, anthropic, ollama)
+     * @param   array   $options   Provider configuration options
+     *
+     * @return  AI
+     * @throws  InvalidArgumentException
+     * @throws  ProviderException
+     * @since   __DEPLOY_VERSION__
+     */
+    public static function getAI(string $provider, array $options = []): AI
+    {
+        $provider = strtolower($provider);
+
+        if (!isset(self::PROVIDERS[$provider])) {
+            throw new ProviderException(
+                $provider,
+                [
+                    'message' => 'Unknown AI provider: ' . $provider . '. Available providers: ' . implode(', ', array_keys(self::PROVIDERS)),
+                    'requested_provider' => $provider,
+                    'available_providers' => array_keys(self::PROVIDERS)
+                ],
+                null,
+                'INVALID_PROVIDER'
+            );
+        }
+
+        $providerClass = self::PROVIDERS[$provider];
+
+        try {
+            $providerInstance = new $providerClass($options);
+            return new AI($providerInstance);
+        } catch (\Exception $e) {
+            throw new ProviderException(
+                $provider,
+                [
+                    'message' => 'Failed to create ' . $provider . ' provider: ' . $e->getMessage(),
+                    'provider' => $provider,
+                    'original_error' => $e->getMessage()
+                ],
+                null,
+                'PROVIDER_CREATION_FAILED'
+            );
+        }
+    }
+
+    /**
+     * Get available provider names
+     *
+     * @return  array
+     * @since   __DEPLOY_VERSION__
+     */
+    public static function getAvailableProviders(): array
+    {
+        return array_keys(self::PROVIDERS);
+    }
+
+    /**
+     * Check if a provider is available
+     *
+     * @param   string  $provider  The provider name
+     *
+     * @return  bool
+     * @since   __DEPLOY_VERSION__
+     */
+    public static function isProviderAvailable(string $provider): bool
+    {
+        return isset(self::PROVIDERS[strtolower($provider)]);
+    }
+}
diff --git a/src/AbstractProvider.php b/src/AbstractProvider.php
index 65b35e7..e504411 100644
--- a/src/AbstractProvider.php
+++ b/src/AbstractProvider.php
@@ -52,7 +52,7 @@ abstract class AbstractProvider implements ProviderInterface
     /**
      * Constructor.
      *
-     * @param   array|\ArrayAccess  $options  Provider options array.
+     * @param   mixed         $options      Provider options array.
      * @param   HttpFactory   $httpFactory  The http factory
      *
      * @throws  \InvalidArgumentException
diff --git a/src/Interface/ImageInterface.php b/src/Interface/ImageInterface.php
index 80a5d92..1d494f7 100644
--- a/src/Interface/ImageInterface.php
+++ b/src/Interface/ImageInterface.php
@@ -39,7 +39,7 @@ public function generateImage(string $prompt, array $options = []): Response;
      * @return  Response
      * @since   __DEPLOY_VERSION__
      */
-    // public function editImage(string $imagePath, string $prompt, array $options = []): Response;
+    public function editImage(string $imagePath, string $prompt, array $options = []): Response;
 
     /**
      * Create alternative versions of an image from the text prompt given to the AI provider.
@@ -50,5 +50,5 @@ public function generateImage(string $prompt, array $options = []): Response;
      * @return  Response
      * @since   __DEPLOY_VERSION__
      */
-    // public function createImageVariations(string $imagePath, array $options = []): Response;
+    public function createImageVariation(string $imagePath, array $options = []): Response;
 }
diff --git a/src/Interface/ModelInterface.php b/src/Interface/ModelInterface.php
index d88beb8..b29591b 100644
--- a/src/Interface/ModelInterface.php
+++ b/src/Interface/ModelInterface.php
@@ -16,38 +16,6 @@
  */
 interface ModelInterface
 {
-    /**
-     * Get all available models for this provider.
-     *
-     * @return  array  Array of available model names
-     * @since   __DEPLOY_VERSION__
-     */
-    public function getAvailableModels(): array;
-
-    /**
-     * Get models that support chat capability.
-     *
-     * @return  array  Array of chat capable model names
-     * @since   __DEPLOY_VERSION__
-     */
-    public function getChatModels(): array;
-
-    /**
-     * Get models that support vision capability.
-     *
-     * @return  array  Array of vision capable model names
-     * @since   __DEPLOY_VERSION__
-     */
-    public function getVisionModels(): array;
-
-    /**
-     * Get models that support image generation capability.
-     *
-     * @return  array  Array of image capable model names
-     * @since   __DEPLOY_VERSION__
-     */
-    // public function getImageModels(): array;
-
     /**
      * Check if a model supports a specific capability.
      *
diff --git a/src/Interface/ProviderInterface.php b/src/Interface/ProviderInterface.php
index 03d8ca4..abd825f 100644
--- a/src/Interface/ProviderInterface.php
+++ b/src/Interface/ProviderInterface.php
@@ -9,8 +9,6 @@
 
 namespace Joomla\AI\Interface;
 
-use Joomla\AI\Response\Response;
-
 /**
  * AI provider class interface.
  *
@@ -34,15 +32,11 @@ public static function isSupported(): bool;
      */
     public function getName(): string;
 
-    // Should be a smart router in future versions.
     /**
-     * Send a prompt to the AI provider and return a Response object with the response.
-     *
-     * @param   string  $prompt     The prompt to send to the AI provider.
-     * @param   array   $options    An associative array of options to send with the request.
+     * Get all available models for this provider.
      *
-     * @return  Response
-     * @since  __DEPLOY_VERSION__
+     * @return  array  Array of available model names
+     * @since   __DEPLOY_VERSION__
      */
-    // public function prompt(string $prompt, array $options = []): Response;
+    public function getAvailableModels(): array;
 }
diff --git a/src/Provider/AnthropicProvider.php b/src/Provider/AnthropicProvider.php
index c033ad0..600e8d7 100644
--- a/src/Provider/AnthropicProvider.php
+++ b/src/Provider/AnthropicProvider.php
@@ -10,7 +10,6 @@
 namespace Joomla\AI\Provider;
 
 use Joomla\AI\AbstractProvider;
-use Joomla\AI\Provider\OpenAIProvider;
 use Joomla\AI\Exception\AuthenticationException;
 use Joomla\AI\Exception\InvalidArgumentException;
 use Joomla\AI\Exception\ProviderException;
diff --git a/src/Provider/OllamaProvider.php b/src/Provider/OllamaProvider.php
index f0c2e85..433a20b 100644
--- a/src/Provider/OllamaProvider.php
+++ b/src/Provider/OllamaProvider.php
@@ -6,6 +6,7 @@
 use Joomla\AI\Exception\AuthenticationException;
 use Joomla\AI\Exception\InvalidArgumentException;
 use Joomla\AI\Exception\ProviderException;
+use Joomla\AI\Interface\ProviderInterface;
 use Joomla\AI\Response\Response;
 use Joomla\Http\HttpFactory;
 
@@ -14,7 +15,7 @@
  *
  * @since  __DEPLOY_VERSION__
  */
-class OllamaProvider extends AbstractProvider
+class OllamaProvider extends AbstractProvider implements ProviderInterface
 {
     /**
      * Custom base URL for API requests
diff --git a/src/Provider/OpenAIProvider.php b/src/Provider/OpenAIProvider.php
index 2027908..0b25a44 100644
--- a/src/Provider/OpenAIProvider.php
+++ b/src/Provider/OpenAIProvider.php
@@ -13,8 +13,10 @@
 use Joomla\AI\Exception\AuthenticationException;
 use Joomla\AI\Exception\InvalidArgumentException;
 use Joomla\AI\Exception\ProviderException;
+use Joomla\AI\Interface\ProviderInterface;
 use Joomla\AI\Interface\AudioInterface;
 use Joomla\AI\Interface\ChatInterface;
+use Joomla\AI\Interface\EmbeddingInterface;
 use Joomla\AI\Interface\ImageInterface;
 use Joomla\AI\Interface\ModelInterface;
 use Joomla\AI\Interface\ModerationInterface;
@@ -26,7 +28,7 @@
  *
  * @since  __DEPLOY_VERSION__
  */
-class OpenAIProvider extends AbstractProvider implements ChatInterface, ModelInterface, ImageInterface, AudioInterface, ModerationInterface
+class OpenAIProvider extends AbstractProvider implements ProviderInterface, ChatInterface, ModelInterface, ImageInterface, EmbeddingInterface, AudioInterface, ModerationInterface
 {
     /**
      * Custom base URL for API requests
diff --git a/src/Response/Response.php b/src/Response/Response.php
index c2c7030..8767273 100644
--- a/src/Response/Response.php
+++ b/src/Response/Response.php
@@ -100,13 +100,13 @@ public function saveFile(string $filename)
             $baseName = pathinfo($filename, PATHINFO_FILENAME);
             $ext = pathinfo($filename, PATHINFO_EXTENSION) ?: 'png';
 
-            $data = json_decode($content, true);
-            if ($imageCount === 1 && is_string($content)) {
+            if ($imageCount === 1) {
                 $decodedContent = base64_decode($content);
                 if (File::write($filename, $decodedContent)) {
                     $savedFiles[] = $filename;
                 }
-            } elseif (is_array($data)) {
+            } else {
+                $data = json_decode($content, true);
                 foreach ($data as $index => $b64) {
                     $file = Path::clean($dir . '/' . $baseName . '_' . ($index + 1) . '.' . $ext);
                     $decodedContent = base64_decode($b64);
@@ -124,7 +124,7 @@ public function saveFile(string $filename)
             $data = json_decode($content, true);
 
             $lines = [];
-            if ($imageCount === 1 && is_string($content)) {
+            if ($imageCount === 1) {
                 $lines[] = "  Image URL: " . $content;
             } elseif (is_array($data)) {
                 foreach ($data as $index => $url) {
@@ -150,7 +150,7 @@ public function saveFile(string $filename)
         }
 
         // For all other content
-        if ($content !== null) {
+        if ($content !== '') {
             if (File::write($filename, $content)) {
                 return [$filename];
             }