Prompting - Miscellaneous
Entity relationship extraction
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
Entity relationship extraction
Overview
In cases where relationships exist between entities, it’s vital to define them explicitly in the model.
Following example demonstrates how to define relationships between users by
incorporating an $id
and $coworkers
fields.
Example
<?php
require 'examples/boot.php';
use Cognesy\Instructor\Instructor;
class UserDetail
{
/** Unique identifier for each user. */
public int $id;
public int $age;
public string $name;
public string $role;
/**
* @var int[] Correct and complete list of coworker IDs, representing
* collaboration between users.
*/
public array $coworkers;
}
class UserRelationships
{
/**
* @var UserDetail[] Collection of users, correctly capturing the
* relationships among them.
*/
public array $users;
}
$text = "Jason is 25 years old. He is a Python programmer of Apex website.\
Amanda is a contractor working with Jason on Apex website. John is 40yo\
and he's CEO - Jason reports to him.";
$relationships = (new Instructor)->respond(
messages: [['role' => 'user', 'content' => $text]],
responseModel: UserRelationships::class,
);
dump($relationships);
assert(!empty($relationships->users));
?>