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 \ Instructor \ Basics
Validation across multiple fields
Overview
Sometimes property level validation is not enough - you may want to check values of multiple properties and based on the combination of them decide to accept or reject the response. Or the assertions provided by Symfony may not be enough for your use case.
In such case you can easily add custom validation code to your response model by:
- using
ValidationMixin
- and defining validation logic in
validate()
method.
In this example LLM should be able to correct typo in the message (graduation year we provided
is 1010
instead of 2010
) and respond with correct graduation year.
Example
<?php
require 'examples/boot.php';
use Cognesy\Instructor\Features\Validation\Traits\ValidationMixin;
use Cognesy\Instructor\Features\Validation\ValidationResult;
use Cognesy\Instructor\Instructor;
class UserDetails
{
use ValidationMixin;
public string $name;
public int $birthYear;
public int $graduationYear;
public function validate() : ValidationResult {
if ($this->graduationYear > $this->birthYear) {
return ValidationResult::valid();
}
return ValidationResult::fieldError(
field: 'graduationYear',
value: $this->graduationYear,
message: "Graduation year has to be bigger than birth year."
);
}
}
$user = (new Instructor)
->wiretap(fn($e) => $e->print())
->respond(
messages: [['role' => 'user', 'content' => 'Jason was born in 2000 and graduated in 23.']],
responseModel: UserDetails::class,
model: 'gpt-3.5-turbo',
maxRetries: 2,
);
dump($user);
assert($user->graduationYear === 2023);
?>
Assistant
Responses are generated using AI and may contain mistakes.