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 \ Polyglot \ LLM Extras
Prompt Templates
Overview
Template
class in Instructor PHP provides a way to define and use
prompt templates using Twig, Blade or custom ‘arrowpipe’ template syntax.
Example
Copy
<?php
require 'examples/boot.php';
use Cognesy\Polyglot\LLM\Inference;
use Cognesy\Template\Template;
use Cognesy\Utils\Str;
// EXAMPLE 1: Define prompt template inline (don't use files) and use short syntax
$prompt = Template::twig()
->from('What is capital of {{country}}')
->with(['country' => 'Germany'])
->toText();
$answer = (new Inference)->create(
messages: $prompt
)->toText();
echo "EXAMPLE 1: prompt = $prompt\n";
echo "ASSISTANT: $answer\n";
echo "\n";
assert(Str::contains($answer, 'Berlin'));
// EXAMPLE 2: Load prompt from file
// use default template language, prompt files are in /prompts/twig/<prompt>.twig
$prompt = Template::text(
pathOrDsn: 'demo-twig:capital',
variables: ['country' => 'Germany'],
);
$answer = (new Inference)->create(messages: $prompt)->toText();
echo "EXAMPLE 2: prompt = $prompt\n";
echo "ASSISTANT: $answer\n";
echo "\n";
assert(Str::contains($answer, 'Berlin'));
?>
Assistant
Responses are generated using AI and may contain mistakes.