new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

heroku/setup

6 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Heroku app creation command

To create a test app in Heroku, run: heroku create

Heroku model deployment command

To deploy an inference model (e.g., claude-3-5-haiku) to a Heroku app, run: heroku ai:models:create -a $APP_NAME claude-3-5-haiku

Heroku provider installation package

The Heroku provider is available via the @ai-sdk/openai-compatible module and can be installed with: npm install @ai-sdk/openai-compatible

Heroku required environment variables

Three environment variables are required for Heroku setup: INFERENCE_KEY (API authentication key), INFERENCE_MODEL_ID (model identifier), and INFERENCE_URL (base URL for the inference service).

createOpenAICompatible function for Heroku

To create a Heroku provider instance, import createOpenAICompatible from @ai-sdk/openai-compatible and call it with name set to 'heroku', baseURL set to process.env.INFERENCE_URL + '/v1', and apiKey set to process.env.INFERENCE_KEY.

Heroku provider instantiation code example

import { createOpenAICompatible } from '@ai-sdk/openai-compatible'; const heroku = createOpenAICompatible({ name: 'heroku', baseURL: process.env.INFERENCE_URL + '/v1', apiKey: process.env.INFERENCE_KEY, });

Give your agent this brain