Cookbook
Cookbook \ Instructor \ Basics
- Basic use
- Basic use via mixin
- Handling errors with `Maybe` helper class
- Modes
- Making some fields optional
- Private vs public object field
- Automatic correction based on validation results
- Using attributes
- Using LLM API connections from config file
- Validation
- Custom validation using Symfony Validator
- Validation across multiple fields
- Validation with LLM
Cookbook \ Instructor \ Advanced
- Context caching (structured output)
- Customize parameters of LLM driver
- Custom prompts
- Customize parameters via DSN
- Using structured data as an input
- Extracting arguments of function or method
- 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)
- 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 \ Prompting \ Miscellaneous
Restating instructions
Overview
Make Instructor restate long or complex instructions and rules to improve inference accuracy.
Example
Copy
<?php
require 'examples/boot.php';
use Cognesy\Instructor\Instructor;
/**
* Identify what kind of job the user is doing.
* Typical roles we're working with are CEO, CTO, CFO, CMO.
* Sometimes user does not state their role directly - you will need
* to make a guess, based on their description.
*/
class UserRole
{
/** Restate instructions and rules, so you can correctly determine the title. */
public string $instructions;
/** Role description */
public string $description;
/* Guess job title */
public string $title;
}
/**
* Details of analyzed user. The key information we're looking for
* is appropriate role data.
*/
class UserDetail
{
public string $name;
public int $age;
public UserRole $role;
}
$text = <<<TEXT
I'm Jason, I'm 28 yo. I am the head of Apex Software, responsible for
driving growth of our company.
TEXT;
$instructor = new Instructor;
$user = ($instructor)->respond(
messages: [["role" => "user", "content" => $text]],
responseModel: UserDetail::class,
);
dump($user);
assert($user->name === "Jason");
assert($user->age === 28);
//assert(!empty($user->role->title));
?>
Assistant
Responses are generated using AI and may contain mistakes.