Basics
Automatic correction based on validation results
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
Advanced
- Context caching
- Context caching (Anthropic)
- Customize parameters of OpenAI client
- Custom prompts
- 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
Troubleshooting
LLM API Support
Extras
- Extraction of complex objects
- Extraction of complex objects (Anthropic)
- Extraction of complex objects (Cohere)
- Extraction of complex objects (Gemini)
- Embeddings
- Image processing - car damage detection
- Image to data (OpenAI)
- Image to data (Anthropic)
- Image to data (Gemini)
- 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
- Inference and tool use
- Working directly with LLMs and JSON - Tools mode
- Prompts
- Generating JSON Schema from PHP classes
- Generating JSON Schema dynamically
- Simple content summary
- Create tasks from meeting transcription
- Translating UI text fields
- Web page to PHP objects
Basics
Automatic correction based on validation results
Overview
Instructor uses validation errors to inform LLM on the problems identified in the response, so that LLM can try self-correcting in the next attempt.
In case maxRetries parameter is provided and LLM response does not meet validation criteria, Instructor will make subsequent inference attempts until results meet the requirements or maxRetries is reached.
Example
<?php
$loader = require 'vendor/autoload.php';
$loader->add('Cognesy\\Instructor\\', __DIR__.'../../src/');
use Cognesy\Instructor\Events\HttpClient\RequestSentToLLM;
use Cognesy\Instructor\Events\Response\ResponseValidated;
use Cognesy\Instructor\Events\Response\ResponseValidationAttempt;
use Cognesy\Instructor\Events\Response\ResponseValidationFailed;
use Cognesy\Instructor\Instructor;
use Symfony\Component\Validator\Constraints as Assert;
class UserDetails
{
public string $name;
#[Assert\Email]
public string $email;
}
$text = "you can reply to me via jason wp.pl -- Jason";
print("INPUT:\n$text\n\n");
print("RESULTS:\n");
$user = (new Instructor)
->onEvent(RequestSentToLLM::class, fn($event) => print("[ ] Requesting LLM response...\n"))
->onEvent(ResponseValidationAttempt::class, fn($event) => print("[?] Validating:\n ".json_encode($event->response)."\n"))
->onEvent(ResponseValidationFailed::class, fn($event) => print("[!] Validation failed:\n $event\n"))
->onEvent(ResponseValidated::class, fn($event) => print("[ ] Validation succeeded.\n"))
->respond(
messages: $text,
responseModel: UserDetails::class,
maxRetries: 3,
);
print("\nOUTPUT:\n");
dump($user);
assert($user->email === "jason@wp.pl");
?>