Docs
CommunityJev Integrations & Adapters
Laravel AI SDK Classification
The Laravel AI SDK's docs carry a Classification section covering classifying images, yes or no decisions, and choosing from collections, and list TYPESAFE_API_KEY among the provider credentials in config/ai.php.
- Format
- Docs
- Reading time
- 2 min
- Published by
- Community
- Author
- Laravel
- Last verified
- Oct 2026
- Languages
- PHP
- Capabilities
- Requires API key
Highlights
- Install with composer require laravel/ai, publish with php artisan vendor:publish, then run php artisan migrate.
- TYPESAFE_API_KEY sits in config/ai.php or .env with OpenAI, Anthropic, Gemini, Groq, Cohere, DeepSeek, xAI, and OpenRouter keys.
- The Classification section covers classifying images, yes or no decisions, and choosing from collections.
- Custom base URLs are supported for OpenAI, Anthropic, Gemini, Groq, Cohere, DeepSeek, xAI, and OpenRouter, for proxies such as LiteLLM.
- OpenAI-compatible drivers such as LM Studio, vLLM, Together, Fireworks, or a local gateway need a url, with the key optional as a bearer token.
Watch out
The captured documentation shows the SDK overview, installation, provider configuration, and the Classification section headings, but the classification examples themselves are outside the captured text, so this entry establishes the Jev key and section layout rather than exact classification APIs. No licence, pricing, or rate limits appear on the page.
Questions about this entry
Short answers drawn from the linked project or page.
A unified, expressive API for interacting with AI providers such as OpenAI, Anthropic, and Gemini. It covers agents with tools and structured output, images, TTS and STT, text summarization, embeddings, reranking, classification, files, and vector stores.
Run composer require laravel/ai, publish the SDK configuration and migrations with php artisan vendor:publish --provider=Laravel\Ai\AiServiceProvider, then php artisan migrate, which creates the agent_conversations and agent_conversation_messages tables.
In your application's config/ai.php configuration file or as an environment variable. The docs list TYPESAFE_API_KEY in .env alongside ANTHROPIC_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, and the other provider credentials.
Three topics: classifying images, yes or no decisions, and choosing from collections. The captured page shows the section and its subsections in the navigation but not the example bodies, and there is also a Testing section covering Classification.
Yes. Add a url parameter to a provider configuration; custom base URLs are supported for OpenAI, Anthropic, Gemini, Groq, Cohere, DeepSeek, xAI, and OpenRouter, and the docs name proxies such as LiteLLM and Azure OpenAI Gateway as use cases.
A driver for endpoints such as LM Studio, vLLM, Together, Fireworks, or a local gateway: url is required, key is optional and sent as a bearer token, custom headers are supported, and embeddings and transcription need default models configured.
The captured page does not show the classification calls or Jev specifics beyond the TYPESAFE_API_KEY entry and section headings, and it states no Jev pricing, model aliases, or rate limits, so behavior details must come from the SDK's classification docs.
More Jev resources like this
Freek Van der Herten describes replacing a fifteen-language subject-prefix list with Jev in There There's helpdesk: three questions in one call, header checks first, raw probabilities stored next to each thresholded verdict.
Jev Integrations & AdaptersArticle#community#php#laravel
Community
A follow-up on There There's Jev use: workflow conditions described in plain language become a Boolean question in the same inbound classification request, and Jev picks a ticket's assignee from a curated list.
Jev Integrations & AdaptersArticle#community#php#laravel
Community
Filament plugin that filters admin table rows by a plain-English statement: each row gets a Jev Noul probability that the statement is true, and rows at or above the threshold stay. Scores are cached by content, so reruns of the same statement are instant and free.
Jev Integrations & Adapters#community#laravel#filament
Community
vibefilter/filamentPHP
vibefilter/filamentPHPA PHP decision engine for Laravel that replaces open-ended prompts with typed primitives: Noul for binary likelihoods, Choice for categorical classification and Score for bounded ratings, each returning calibrated probabilities.
Jev Integrations & Adapters#community#github#php
Community
obelaw/systemonePHP
obelaw/systemonePHPA Claude Code plugin that adds five Jev tools — jev_choice, jev_noul, jev_score, jev_ask and jev_doctor — so small decisions like safety checks, tool choices and review verdicts come back as typed answers with calibrated confidence, labelled auto or escalate.
Jev Integrations & Adapters#community#catalog-import#logicrw
Community
darwintechlab/claude-jevJavaScript
darwintechlab/claude-jevJavaScriptLiteLLM serves decision models on two routes that share one provider list: /v1/decisions for OpenAI-format bodies and /v1/systemone for System One bodies, with Jev available as the typesafe/jev-latest provider.
Jev Integrations & AdaptersDocs#community#litellm#gateway
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.