Basic constructor

Basic get set

Basic private vs public fields

Basic via mixin

Fluent API

Handling errors with `Maybe` helper class

Mixed Type Property

Making some fields optional

Automatic correction based on validation results

Using attributes

Using LLM API connection presets from config file

Validation custom

Validation mixin

Validation with LLM

Use custom configuration providers

Context caching

Context caching oai

Custom client parameters

Use custom HTTP client instance

Use custom HTTP client instance - Laravel

Custom prompts

Function arguments

Manual Schema Building

Partial updates

Providing examples

Extracting scalar values

Extracting sequences of objects

Laravel Logging Integration

Monolog Logging with Functional Pipeline

PSR-3 Logging with Functional Pipeline

Symfony Logging Integration

Receive specific internal event with onEvent()

Modifying Settings Path

Token usage

Receive all internal events with wiretap()

Azure oai

Deep seek

Fireworks ai

Gemini oai

Hugging face

Local / Ollama

Open ai

Open router

Samba nova

Together ai

X ai

Extraction of complex objects

Extraction of complex objects (Anthropic)

Extraction of complex objects (Cohere)

Extraction of complex objects (Gemini)

Custom Content Extractors

Data inputs

Image processing - car damage detection

Image to data (OpenAI)

Image to data (Anthropic)

Image to data (Gemini)

Json schema

Return extracted data as array

Use different class for schema and output

Streaming with array output format

Pure Array Processing (No Classes)

Generating JSON Schema from PHP classes

Generating JSON Schema dynamically

Create tasks from meeting transcription

Translating UI text fields

Web page to PHP objects

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

Llm with schema helper

Llm with tools helper

Customize configuration providers of LLM driver

Context caching (text inference)

Context cache llmoai

Custom client parameters

Custom embeddings driver

Using custom LLM driver

Embeddings utils

Work directly with HTTP client facade

Parallel Calls

Reasoning Content Access

Debugging HTTP Calls

Logging laravel embeddings

Logging laravel inference

Logging monolog

Logging symfony

Azure oai

Deep seek

Fireworks ai

Gemini oai

Local / Ollama

Open ai

Open router

Samba nova

Together ai

X ai

Basic Agent Usage

Basic Agent Control Usage

Agent Control Events & Monitoring

Agent Control Streaming

Agent Control Runtime Switching

Agent file sys

Agent-Driven Codebase Search

Agent self critic

Agent with Structured Output Extraction

Agent Subagent Orchestration

Multi-Participant AI Chat Panel Discussion

Chat with summary

Claude code

Claude Code CLI - Agentic Search

OpenAI Codex CLI - Basic

OpenAI Codex CLI - Streaming

Metrics collection

Open code basic

Open code streaming

Prompt template

Summary llm

Inference and tool use

Tool use re act

Assign a Role

Auto-Refine The Prompt

Clarify Ambiguous Information

Define Style

Emotional language

Generate Follow-Up Questions

Ask Model to Repeat the Query

Simulate a Perspective

Consistency based examples

Example ordering

Generate In-Context Examples

Select effective samples

Analogical Prompting

Automate Example Selection

Prioritize Complex Examples

Examine The Context

Higher level context

Include Incorrect Examples

Use Majority Voting

Generate Prompt Variations

Structure The Reasoning

Uncertain examples

Combine Multiple Reasoning Chains

Use LLMs to Combine Different Responses

Combine specialized ll ms

Prioritize Consistent Examples

Use Distinct Example Subsets

Use Ensembles To Test Prompts

Generate Multiple Candidate Responses

Use Task Specific Evaluation Metrics

Use Translation for Paraphrasing

Verify Responses over Majority Voting

Break Down Reasoning Into Multiple Steps

Determine Uncertainty of Reasoning Chain

Improve With Feedback

Reconstruct Prompt from Reasoning Steps

Self-Verify Responses

Independently Verify Responses

Break Down Complex Tasks

Ditch Vanilla Chain Of Thought

Generate Code for Intermediate Steps

Generate in Parallel

Solve Simpler Subproblems

Leverage Task Specific Systems

Arbitrary props

Arbitrary props consistency

Chain of Summaries

Chain of Thought

Single label classification

Multiclass classification

Entity relationship extraction

Handling errors

Http client streaming

HTTP Middleware (Hooks + Conditional Decoration)

HTTP Middleware (Stream)

HTTP Middleware (Sync)

Http pool

Limiting length of lists

Reflection Prompting

Restating instructions

Rewriting instructions

Search criteria

Time range

Time range with cot