Prompting - Miscellaneous
Multiclass classification
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
Instructor - Advanced
- Context caching (structured output)
- Customize parameters of LLM driver
- 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
Instructor - Troubleshooting
Instructor - LLM API Support
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 dynamically
- Create tasks from meeting transcription
- Translating UI text fields
- Web page to PHP objects
Polyglot - LLM Basics
Polyglot - LLM Advanced
Polyglot - LLM Troubleshooting
Polyglot - LLM API Support
Polyglot - LLM Extras
Prompting - Zero-Shot Prompting
Prompting - Few-Shot Prompting
Prompting - Thought Generation
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
Prompting - Miscellaneous
Multiclass classification
Overview
We start by defining the structures.
For multi-label classification, we introduce a new enum class and a different PHP class to handle multiple labels.
<?php
require 'examples/boot.php';
use Cognesy\Instructor\Instructor;
/** Potential ticket labels */
enum Label : string {
case TECH_ISSUE = "tech_issue";
case BILLING = "billing";
case SALES = "sales";
case SPAM = "spam";
case OTHER = "other";
}
/** Represents analysed ticket data */
class TicketLabels {
/** @var Label[] */
public array $labels = [];
}
?>
Classifying Text
The function multi_classify
executes multi-label classification using LLM.
<?php
// Perform single-label classification on the input text.
function multi_classify(string $data) : TicketLabels {
return (new Instructor())->respond(
messages: [[
"role" => "user",
"content" => "Label following support ticket: {$data}",
]],
responseModel: TicketLabels::class,
);
}
?>
Testing and Evaluation
Finally, we test the multi-label classification function using a sample support ticket.
<?php
// Test single-label classification
$ticket = "My account is locked and I can't access my billing info.";
$prediction = multi_classify($ticket);
dump($prediction);
assert(in_array(Label::TECH_ISSUE, $prediction->labels));
assert(in_array(Label::BILLING, $prediction->labels));
?>
On this page