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

google-vertex/setup

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

Google Vertex provider installation

The Google Vertex provider is installed via the `@ai-sdk/google-vertex` module.

Google Vertex provider instance import

Import the default provider instance `googleVertex` from `@ai-sdk/google-vertex`.

Google Vertex Node.js runtime authentication

Node.js runtime supports all standard Google Cloud authentication options through the `google-auth-library`. Typical use involves setting a path to a json credentials file in the `GOOGLE_APPLICATION_CREDENTIALS` environment variable. The credentials file can be obtained from the Google Cloud Console.

Google Vertex Edge runtime authentication

Edge runtimes support Google's Application Default Credentials through environment variables. Set GOOGLE_CLIENT_EMAIL, GOOGLE_PRIVATE_KEY, and optionally GOOGLE_PRIVATE_KEY_ID from a service account JSON file from the Google Cloud Console.

Google Vertex Edge runtime provider import

Import the default provider instance `googleVertex` from `@ai-sdk/google-vertex/edge`. The /edge sub-module is included in the `@ai-sdk/google-vertex` package and does not need separate installation.

Google Vertex Edge runtime optional provider settings

Optional settings for Edge runtime: project (string, uses GOOGLE_VERTEX_PROJECT env var by default), location (string, e.g. us-central1, uses GOOGLE_VERTEX_LOCATION env var by default), googleCredentials (object with clientEmail, privateKey, privateKeyId properties), headers (Resolvable<Record<string, string | undefined>>), fetch (custom fetch implementation).

Google Vertex Express Mode authentication

Express mode uses an API key instead of OAuth or service account credentials. When using express mode, project and location settings are not required. Pass apiKey parameter or set GOOGLE_VERTEX_API_KEY environment variable.

Google Vertex transcription authentication

Transcription models use standard Google Cloud credentials (OAuth, Application Default Credentials, or service account). Express Mode API keys are not supported for transcription models.

Google Vertex transcription model region configuration

Set GOOGLE_VERTEX_LOCATION or providerOptions.googleVertex.region to a Speech-to-Text region. For Chirp: chirp_2 available in us-central1, europe-west4, asia-southeast1; chirp_3 in us and eu multi-regions. Chirp not available in global location. telephony availability depends on selected region and language.

Create customized Google Vertex providers

There are two Google Vertex providers: 1. **Google Vertex Anthropic provider**: Import `createVertexAnthropic` from `@ai-sdk/google-vertex/anthropic` and create a provider instance with settings like project and location. 2. **Google Vertex provider**: Import `createGoogleVertex` from `@ai-sdk/google-vertex` and create a provider instance with settings like project and location. Both providers support configuration options including project and location settings.

Give your agent this brain