Libraries tagged by structured output

AI-powered actions for Filament v5 — streaming modal, structured output, intelligent table actions

Go to Download

Validate, retry, and type-cast structured AI output against Laravel validation rules or JSON schemas.

Go to Download

Transcribe long recordings and pull structured fields out of them, inside a Laravel application.

Go to Download

Production-ready PHP library for LLMs - OpenAI, Anthropic, Google, Mistral, xAI, OpenRouter, Ollama. One interface, all providers, zero vendor lock-in.

Go to Download

PHP port of charmbracelet/log — minimal, colorful leveled logging with structured human-readable output, text/JSON/logfmt formatters, and stdlog adapter.

Go to Download

Automatic canonical and hreflang output for Laravel 5.4

Go to Download

Job postings for TYPO3: filterable list, detail view and standards-compliant schema.org/JobPosting JSON-LD output for Google for Jobs.

Go to Download

Extends the phpinfo function and provides a structured output format using JSON.

Go to Download

PHP SDK for writing MCP (Model Context Protocol) handlers served by the roxy proxy. Object model, typed builders, elicitation and structured output support.

Go to Download

A production-ready Laravel package to integrate with the Google Gemini API. Supports text, image, video, audio, long-context, structured output, files, caching, function-calling and understanding capabilities.

Go to Download

Scores every newly submitted comment for toxicity and spam with one AI call that returns a strict JSON verdict, then routes that verdict through ordinary ECA conditions into one of three exits: publish, hold for review, or block. The thresholds are two "Token: set value" actions in the model, not numbers in the prompt, so the policy can be changed without touching the prompt. Every run writes both scores, both thresholds and the exit taken to the eca_comment_verdict log channel, and a failed or undecodable AI response holds the comment instead of publishing it. Requires the ai_integration_eca and eca_tamper contributed modules, and a chat model that supports structured output has to be selected in the "Ask AI to score the comment" action.

Go to Download

Adds an AI-powered button to the Event node form. "Extract the event details" sends the node title and the description to a chat model with a strict JSON schema and fills the compound Event details field, a Custom Field whose columns hold the venue, the city, the capacity, the ticket price, whether the event is online, a contact address and a registration link. Custom Field columns are defined by the site builder, so the mapping the fill action returns is keyed by those column names, and the typed columns cast the strings the schema asks for. After applying the recipe, select a chat model that supports structured output in the chat action. Requires ECA Field Widget Actions 1.0.x-dev at or after commit c7c3edb, because both the compound fill and the recognition of the custom_field field type are unreleased. The recipe ships the Event content type with its Event details field.

Go to Download

Sends the article text to an AI chat model on presave and writes the structured answer into real node fields: SEO meta description, reading time, sentiment and Tags terms. Triggered by node entity presave, guarded so that each article is enriched only once. Includes the library's Article tags recipe, which provides the Article content type with its body and Tags fields and the Tags vocabulary. Requires the ai_integration_eca and eca_tamper contributed modules. After applying the recipe, select a chat model that supports structured output in the "Ask AI for structured enrichment data" action.

Go to Download

Structured outputs for LLMs using Spatie Data objects.

Go to Download

AI-native PHPUnit reporter: structured JSON output mapped to the production source under test.

Go to Download