Instructor for PHP

Structured data processing in PHP, powered by LLMs. Designed for simplicity, transparency, and control.

Introduction

Start processing your data with LLMs in under 5 minutes

Quickstart

Set up Instructor in your project and start processing data with LLMs

Setup

Why use Instructor?

Managing and rendering prompts in Instructor

Prompt Templates

Response model defines the structure of results returned by LLM.

Response Models

Configure your environment for Instructor

Environment

How to set up location of Instructor configuration directory for your project

Configuration Path

Instructor supports a number of LLM API providers.

LLM API Providers

Running and viewing cookbooks with Instructor Hub tool

Instructor Cookbooks

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

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

Debugging

Receive specific internal event with onEvent()

Tracking token usage via events

Receive all internal events with wiretap()

Anthropic

Azure OpenAI

Cerebras

Cohere

DeepSeek

Fireworks.ai

Google Gemini

Groq

Minimaxi

Mistral AI

MoonshotAI

Local / Ollama

OpenAI

OpenRouter

SambaNova

Together.ai

xAI / Grok

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

Assign a Role

Auto-Refine The Prompt

Clarify Ambiguous Information

Define Style

Emotional Stimuli

Generate Follow-Up Questions

Ask Model to Repeat the Query

Simulate a Perspective

Generate In-Context Examples

Analogical Prompting

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 is a PHP library that provides a unified API to access various LLM API providers.

Overview

Start working with LLMs in under 5 minutes

Upgrade

Overview of Inference

Learn how to create requests to LLM providers using Polyglot.

Creating Requests

Learn how to handle responses from Polyglot.

Response Handling

How to use the Inference class in Polyglot for LLM requests

Inference Class

Learn how to customize request options for LLM inference in Polyglot.

Request Options

Learn how to work with streaming responses in Polyglot.

Overview of Streaming

How to use advanced stream processing features in Polyglot

Advanced Stream Processing

Learn how to work with different output modes in Polyglot.

Overview of Output Modes

Learn how to use text mode in Polyglot for LLM responses.

Text Mode

Learn how to use JSON mode in Polyglot for structured LLM responses.

JSON Mode

Learn how to use JSON Schema mode in Polyglot for structured and validated LLM responses.

JSON Schema Mode

Learn how to use Markdown JSON mode in Polyglot for structured LLM responses.

MdJSON Mode

Learn how to use tools mode in Polyglot for LLM function calling.

Tools Mode

Embeddings are a way to represent data (text, images, audio) in a continuous vector space.

Overview of Embeddings

Learn how to work with vector embeddings in Polyglot.

Working with Embeddings

Learn how to troubleshoot issues with Polyglot.

Overview of Troubleshooting

Learn how to troubleshoot authentication errors when using Polyglot.

Authentication

Learn how to troubleshoot connection issues when using Polyglot.

Connection

Learn how to troubleshoot streaming issues when using Polyglot.

Learn how to handle rate limiting issues when using Polyglot.

Rate Limits

Learn how to troubleshoot model-specific issues when using Polyglot.

Model-Specific Issues

Learn how to troubleshoot provider-specific issues when using Polyglot.

Provider-Specific Issues

How to troubleshoot provider configurations in Polyglot

Connection Configurations

Debugging LLM interactions is essential for troubleshooting and optimizing your applications.

Debugging Requests and Responses

Context Caching

Connection Management

Learn how to configure different LLM providers and models in Polyglot.

Configuration Deep Dive

Learn how to use custom HTTP clients in Polyglot.

Customizing HTTP Client

Learn how to extend Polyglot with custom providers and middleware.

Extending Polyglot

A detailed look at Polyglot's internal architecture

Overview of Architecture

Explore the public API layer of Polyglot, including the Inference and Embeddings classes.

Public API Layer

Learn about the request and response objects used in Polyglot.

Request and Response Objects

Learn about the internal request/response lifecycle in Polyglot.

Request/Response Lifecycle

Learn about the provider abstraction layer in Polyglot.

Provider Abstraction Layer

Learn about the adapters used in Polyglot for LLM providers.

Adapters

Understanding the HTTP client layer in Polyglot

HTTP Client Layer

Understanding the configuration layer of Polyglot for LLM and Embeddings.

Configuration Layer

Learn about the events system in Polyglot.

Events System

Working directly with LLMs

Working directly with LLMs and JSON - JSON mode

Working directly with LLMs and JSON - JSON Schema mode

Working directly with LLMs and JSON - MdJSON mode

Working directly with LLMs and JSON - Tools mode

Context caching (text inference)

Embeddings

Parallel Calls

Reasoning Content Access

Debugging HTTP Calls

Chat with summary

Simple content summary

Inference and tool use

Unified HTTP client API for PHP, designed for LLM interactions. Framework agnostic, middleware support, and streaming capabilities.

Learn how to use the unified HTTP client API in your PHP project.

Getting Started

Learn how to create and send HTTP requests using the unified HTTP client API.

Making HTTP Requests

Learn how to handle HTTP responses using the unified HTTP client API.

Handling Responses

Learn how to handle streaming responses using the unified HTTP client API.

Instructor Guide

Concepts

Essentials

Advanced Features

Practical Techniques

Internals

More

Release Notes

Instructor Hub

V0.12.6