Polyglot - LLM Advanced
Embeddings
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 Advanced
Embeddings
Overview
Embeddings
class offers access to embeddings APIs and convenient methods
to find top K vectors or documents most similar to provided query.
Embeddings
class supports following embeddings providers:
- Azure
- Cohere
- Gemini
- Jina
- Mistral
- OpenAI
Embeddings providers access details can be found and modified via
/config/embed.php
.
Example
<?php
require 'examples/boot.php';
use Cognesy\Polyglot\Embeddings\Embeddings;
$documents = [
'Computer vision models are used to analyze images and videos.',
'The bakers at the Nashville Bakery baked 200 loaves of bread on Monday morning.',
'The new movie starring Tom Hanks is now playing in theaters.',
'Famous soccer player Lionel Messi has arrived in town.',
'News about the latest iPhone model has been leaked.',
'New car model by Tesla is now available for pre-order.',
'Philip K. Dick is an author of many sci-fi novels.',
];
$query = "technology news";
$connections = [
'azure',
'cohere1',
'gemini',
'jina',
'mistral',
//'ollama',
'openai'
];
foreach($connections as $connection) {
$bestMatches = (new Embeddings)->withConnection($connection)->findSimilar(
query: $query,
documents: $documents,
topK: 3
);
echo "\n[$connection]\n";
dump($bestMatches);
}
?>