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 \ Advanced
Streaming partial updates during inference
Overview
Instructor can process LLM’s streamed responses to provide partial updates that you can use to update the model with new data as the response is being generated. You can use it to improve user experience by updating the UI with partial data before the full response is received.
Example
<?php
require 'examples/boot.php';
use Cognesy\Instructor\Instructor;
use Cognesy\Polyglot\LLM\Enums\OutputMode;
use Cognesy\Utils\Cli\Console;
class UserRole
{
/** Monotonically increasing identifier */
public int $id;
public string $title = '';
}
class UserDetail
{
public int $age;
public string $name;
public string $location;
/** @var UserRole[] */
public array $roles;
/** @var string[] */
public array $hobbies;
}
// This function will be called every time a new token is received
function partialUpdate($partial) {
// Clear the screen and move the cursor to the top
Console::clearScreen();
// Display the partial object
dump($partial);
// Wait a bit before clearing the screen to make partial changes slower.
// Don't use this in your application :)
//usleep(250000);
}
?>
Now we can use this data model to extract arbitrary properties from a text message.
As the tokens are streamed from LLM API, the partialUpdate
function will be called
with partially updated object of type UserDetail
that you can use, usually to update
the UI.
<?php
$text = <<<TEXT
Jason is 25 years old, he is an engineer and tech lead. He lives in
San Francisco. He likes to play soccer and climb mountains.
TEXT;
$user = (new Instructor)
->withConnection('openai')
->onPartialUpdate(partialUpdate(...))
->request(
messages: $text,
responseModel: UserDetail::class,
options: ['stream' => true],
mode: OutputMode::Json,
)->get();
echo "All tokens received, fully completed object available in `\$user` variable.\n";
echo '$user = '."\n";
dump($user);
assert(!empty($user->roles));
assert(!empty($user->hobbies));
assert($user->location === 'San Francisco');
assert($user->age == 25);
assert($user->name === 'Jason');
?>
Assistant
Responses are generated using AI and may contain mistakes.