Cookbook
Cookbook \ Instructor \ Basics
- Basic use
- Specifying required and optional parameters via constructor
- Getters and setters
- Private vs public object field
- Basic use via mixin
- Fluent API
- Handling errors with `Maybe` helper class
- Mixed Type Property
- Modes
- Making some fields optional
- Automatic correction based on validation results
- Using attributes
- Using LLM API connection presets from config file
- Validation
- Custom validation using Symfony Validator
- Validation across multiple fields
- Validation with LLM
Cookbook \ Instructor \ Advanced
- Use custom configuration providers
- Context caching (structured output)
- Customize parameters of LLM driver
- Custom prompts
- Customize parameters via DSN
- Extracting arguments of function or method
- Logging monolog
- Logging psr
- Streaming partial updates during inference
- Providing example inputs and outputs
- Extracting scalar values
- Extracting sequences of objects
- Streaming
- Structures
Cookbook \ Instructor \ Troubleshooting
Cookbook \ Instructor \ LLM API Support
Cookbook \ Instructor \ Extras
- Extraction of complex objects
- Extraction of complex objects (Anthropic)
- Extraction of complex objects (Cohere)
- Extraction of complex objects (Gemini)
- Using structured data as an input
- Image processing - car damage detection
- Image to data (OpenAI)
- Image to data (Anthropic)
- Image to data (Gemini)
- Generating JSON Schema from PHP classes
- Generating JSON Schema from PHP classes
- Generating JSON Schema dynamically
- Create tasks from meeting transcription
- Translating UI text fields
- Web page to PHP objects
Cookbook \ Polyglot \ LLM Basics
- Working directly with LLMs
- Working directly with LLMs and JSON - JSON mode
- Working directly with LLMs and JSON - JSON Schema mode
- Working directly with LLMs and JSON - MdJSON mode
- Working directly with LLMs and JSON - Tools mode
- Generating JSON Schema from PHP classes
- Generating JSON Schema from PHP classes
Cookbook \ Polyglot \ LLM Advanced
Cookbook \ Polyglot \ LLM Troubleshooting
Cookbook \ Polyglot \ LLM API Support
Cookbook \ Polyglot \ LLM Extras
Cookbook \ Prompting \ Zero-Shot Prompting
Cookbook \ Prompting \ Few-Shot Prompting
Cookbook \ Prompting \ Thought Generation
Cookbook \ Prompting \ Miscellaneous
- Arbitrary properties
- Consistent values of arbitrary properties
- Chain of Summaries
- Chain of Thought
- Single label classification
- Multiclass classification
- Entity relationship extraction
- Handling errors
- Limiting the length of lists
- Reflection Prompting
- Restating instructions
- Ask LLM to rewrite instructions
- Expanding search queries
- Summary with Keywords
- Reusing components
- Using CoT to improve interpretation of component data
Cookbook \ Instructor \ Basics
Private vs public object field
Overview
Instructor only sets accessible fields of the object with the data provided by LLM.
Private and protected fields are left unchanged, unless:
- class has constructor with parameters matching one or more property names - in such situation object will be hydrated with data from LLM via constructor params,
- class has getXxx() and setXxx() methods with xxx matching one of the property names - in such situation object will be hydrated with data from LLM via setter methods
If you want to access them directly after extraction, provide default values for them.
Example
Copy
<?php
require 'examples/boot.php';
use Cognesy\Instructor\StructuredOutput;
$text = <<<TEXT
Jason is 25 years old. His password is '123admin'.
TEXT;
// CASE 1: Class with public fields
class User
{
public string $name;
public int $age;
public string $password = '';
}
$user = (new StructuredOutput)
->withMessages($text)
->withResponseClass(User::class)
->get();
echo "User with public fields\n";
dump($user);
assert($user->name === "Jason");
assert($user->age === 25);
assert($user->password === '123admin');
// CASE 2: Class with some private fields
class UserWithPrivateFields
{
public string $name;
private int $age = 0;
private string $password = '';
public function getAge() : int {
return $this->age;
}
public function getPassword(): string {
return $this->password;
}
}
$userPriv = (new StructuredOutput)
->withMessages($text)
->withResponseClass(UserWithPrivateFields::class)
->get();
echo "Private 'password' and 'age' fields are not hydrated by Instructor\n";
dump($userPriv);
assert($userPriv->name === "Jason");
assert($userPriv->getAge() === 0);
assert($userPriv->getPassword() === '');
?>
Assistant
Responses are generated using AI and may contain mistakes.