LLM API Support
Together.ai
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
- 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
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 Mode::Tools or Mode::Json, which are much more reliable than Mode::MdJson.
Mode compatibility:
- Mode::Tools - supported for selected models
- Mode::Json - supported for selected models
- Mode::MdJson - fallback mode
Example
<?php
$loader = require 'vendor/autoload.php';
$loader->add('Cognesy\\Instructor\\', __DIR__ . '../../src/');
use Cognesy\Instructor\Enums\Mode;
use Cognesy\Instructor\Instructor;
use Cognesy\Instructor\Utils\Debug\Debug;
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 = $instructor
->respond(
messages: "Jason (@jxnlco) is 25 years old and is the admin of this project. He likes playing football and reading books.",
responseModel: User::class,
examples: [[
'input' => 'Ive got email Frank - their developer, who\'s 30. He asked to come back to him frank@hk.ch. Btw, he plays on drums!',
'output' => ['age' => 30, 'name' => 'Frank', 'username' => 'frank@hk.ch', 'role' => 'developer', 'hobbies' => ['playing drums'],],
],[
'input' => 'We have a meeting with John, our new user. He is 30 years old - check his profile: @jx90.',
'output' => ['name' => 'John', 'role' => 'admin', 'hobbies' => [], 'username' => 'jx90', 'age' => 30],
]],
model: 'meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo',
//options: ['stream' => true ]
mode: Mode::Tools,
);
print("Completed response model:\n\n");
dump($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']));
?>