Polyglot - LLM Basics
Working directly with LLMs and JSON - Tools mode
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
Polyglot - LLM Basics
Working directly with LLMs and JSON - Tools mode
Overview
While working with Inference
class, you can also generate JSON output
from the model inference. This is useful for example when you need to
process the response in a structured way or when you want to store the
elements of the response in a database.
Example
In this example we will use OpenAI tools mode, in which model will generate a JSON containing arguments for a function call. This way we can make the model generate a JSON object with specific structure of parameters.
<?php
require 'examples/boot.php';
use Cognesy\Polyglot\LLM\Enums\Mode;
use Cognesy\Polyglot\LLM\Inference;
$data = (new Inference)
->withConnection('openai')
->create(
messages: [['role' => 'user', 'content' => 'What is capital of France? \
Respond with function call.']],
tools: [[
'type' => 'function',
'function' => [
'name' => 'extract_data',
'description' => 'Extract city data',
'parameters' => [
'type' => 'object',
'description' => 'City information',
'properties' => [
'name' => [
'type' => 'string',
'description' => 'City name',
],
'founded' => [
'type' => 'integer',
'description' => 'Founding year',
],
'population' => [
'type' => 'integer',
'description' => 'Current population',
],
],
'required' => ['name', 'founded', 'population'],
'additionalProperties' => false,
],
],
]],
toolChoice: [
'type' => 'function',
'function' => [
'name' => 'extract_data'
]
],
options: ['max_tokens' => 64],
mode: Mode::Tools,
)
->toJson();
echo "USER: What is capital of France\n";
echo "ASSISTANT:\n";
dump($data);
?>