Prompting - Miscellaneous
Using CoT to improve interpretation of component data
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
Using CoT to improve interpretation of component data
Overview
You can reuse the same component for different contexts within a model. In this
example, the TimeRange component is used for both $workTime
and $leisureTime
.
We’re additionally starting the data structure with a Chain of Thought field to elicit LLM reasoning for the time range calculation, which can improve the accuracy of the response.
Example
<?php
require 'examples/boot.php';
use Cognesy\Instructor\Instructor;
class TimeRange
{
/** Step by step reasoning to get the correct time range */
public string $chainOfThought;
/** The start time in hours (0-23 format) */
public int $startTime;
/** The end time in hours (0-23 format) */
public int $endTime;
}
$timeRange = (new Instructor)->respond(
messages: [['role' => 'user', 'content' => "Workshop with Apex Industries started 9 and it took us 6 hours to complete."]],
responseModel: TimeRange::class,
maxRetries: 2
);
dump($timeRange);
assert($timeRange->startTime === 9);
assert($timeRange->endTime === 15);
?>