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 \ LLM API Support
Together.ai
Overview
Together.ai hosts a number of language models and offers inference API with support for chat completion, JSON completion, and tools call. You can use Instructor with Together.ai as demonstrated below.
Please note that some Together.ai models support OutputMode::Tools or OutputMode::Json, which are much more reliable than OutputMode::MdJson.
Mode compatibility:
- OutputMode::Tools - supported for selected models
- OutputMode::Json - supported for selected models
- OutputMode::MdJson - fallback mode
Example
<?php
require 'examples/boot.php';
use Cognesy\Instructor\Instructor;
use Cognesy\Polyglot\LLM\Enums\OutputMode;
enum UserType : string {
case Guest = 'guest';
case User = 'user';
case Admin = 'admin';
}
class User {
public int $age;
public string $name;
public string $username;
public UserType $role;
/** @var string[] */
public array $hobbies;
}
// Get Instructor with specified LLM client connection
// See: /config/llm.php to check or change LLM client connection configuration details
$instructor = (new Instructor)->withConnection('together');
$user = $instructor
->respond(
messages: "Jason (@jxnlco) is 25 years old and is the admin of this project. He likes playing football and reading books.",
responseModel: User::class,
examples: [[
'input' => 'Ive got email Frank - their developer, who\'s 30. He asked to come back to him frank@hk.ch. Btw, he plays on drums!',
'output' => ['age' => 30, 'name' => 'Frank', 'username' => 'frank@hk.ch', 'role' => 'developer', 'hobbies' => ['playing drums'],],
],[
'input' => 'We have a meeting with John, our new user. He is 30 years old - check his profile: @jx90.',
'output' => ['name' => 'John', 'role' => 'admin', 'hobbies' => [], 'username' => 'jx90', 'age' => 30],
]],
//model: 'meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo',
//options: ['stream' => true ]
mode: OutputMode::Tools,
);
print("Completed response model:\n\n");
dump($user);
assert(isset($user->name));
assert(isset($user->role));
assert(isset($user->age));
assert(isset($user->hobbies));
assert(isset($user->username));
assert(is_array($user->hobbies));
assert(count($user->hobbies) > 0);
assert($user->role === UserType::Admin);
assert($user->age === 25);
assert($user->name === 'Jason');
assert(in_array($user->username, ['jxnlco', '@jxnlco']));
?>
Assistant
Responses are generated using AI and may contain mistakes.