Prompting - Zero-Shot Prompting
Generate Follow-Up Questions
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
Generate Follow-Up Questions
Overview
Models can sometimes correctly answer sub-problems but incorrectly answer the overall query. This is known as the compositionality gap1.
How can we encourage a model to use the answers to sub-problems to correctly generate the overall solution?
Self-Ask is a technique which use a single prompt to:
- decide if follow-up questions are required
- generate the follow-up questions
- answer the follow-up questions
- answer the main query
Example
<?php
require 'examples/boot.php';
use Cognesy\Instructor\Features\Schema\Attributes\Description;
use Cognesy\Instructor\Instructor;
class FollowUp {
#[Description("Follow-up question")]
public string $question;
#[Description("Answer to the follow-up question")]
public string $answer;
}
class Response {
public bool $followUpsRequired;
/** @var FollowUp[] */
public array $followUps;
public string $finalAnswer;
}
class RespondWithFollowUp {
private $prompt = <<<QUERY
Query: {query}
Are follow-up questions needed?
If so, generate follow-up questions, their answers, and then the final answer to the query.
QUERY;
public function __invoke(string $query) : Response {
return (new Instructor)->respond(
messages: str_replace('{query}', $query, $this->prompt),
responseModel: Response::class,
);
}
}
$response = (new RespondWithFollowUp)(
query: "Who succeeded the president of France ruling when Bulgaria joined EU?",
);
echo "Answer:\n";
dump($response);
?>
References
On this page