Prompting - Zero-Shot Prompting
Define Style
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 - Zero-Shot Prompting
Define Style
Overview
How can we constrain model outputs through prompting alone?
To constrain a model’s response to fit the boundaries of our task, we can specify a style.
Stylistic constraints can include:
- writing style: write a flowery description
- tone: write a dramatic description
- mood: write a happy description
- genre: write a journalistic description
Example
<?php
require 'examples/boot.php';
use Cognesy\Instructor\Extras\Sequence\Sequence;
use Cognesy\Instructor\Instructor;
use Cognesy\Utils\Arrays;
class Company {
public string $name;
public string $country;
public string $industry;
public string $websiteUrl;
public string $description;
}
class GenerateCompanyProfiles {
public function __invoke(array $criteria, array $styles) : array {
$criteriaStr = Arrays::toBullets($criteria);
$stylesStr = Arrays::toBullets($styles);
return (new Instructor)->respond(
messages: [
['role' => 'user', 'content' => "List companies meeting criteria:\n{$criteriaStr}\n\n"],
['role' => 'user', 'content' => "Use following styles for descriptions:\n{$stylesStr}\n\n"],
],
responseModel: Sequence::of(Company::class),
)->toArray();
}
}
$companies = (new GenerateCompanyProfiles)(
criteria: [
"insurtech",
"located in US, Canada or Europe",
"mentioned on ProductHunt"
],
styles: [
"brief", // "witty",
"journalistic", // "buzzword-filled",
]
);
dump($companies);
?>
References
On this page