Skip to main content

remote::vertexai

Description

Google Vertex AI inference provider enables you to use Google's Gemini models through Google Cloud's Vertex AI platform, providing several advantages:

• Enterprise-grade security: Uses Google Cloud's security controls and IAM • Better integration: Seamless integration with other Google Cloud services • Advanced features: Access to additional Vertex AI features like model tuning and monitoring • Authentication: Uses Google Cloud Application Default Credentials (ADC) instead of API keys

Configuration:

  • Set VERTEX_AI_PROJECT environment variable (required)
  • Set VERTEX_AI_LOCATION environment variable (optional, defaults to global)
  • Use Google Cloud Application Default Credentials or service account key

Authentication Setup: Option 1 (Recommended): gcloud auth application-default login Option 2: Set GOOGLE_APPLICATION_CREDENTIALS to service account key path

Available Models:

  • vertex_ai/gemini-2.0-flash
  • vertex_ai/gemini-2.5-flash
  • vertex_ai/gemini-2.5-pro

Configuration

FieldTypeRequiredDefaultDescription
allowed_modelslist[str] | NoneNoList of models that should be registered with the model registry. If None, all models are allowed.
refresh_modelsboolNoFalseWhether to refresh models periodically from the provider
networkNetworkConfig | NoneNoNetwork configuration including TLS, proxy, and timeout settings.
network.tlsTLSConfig | NoneNoTLS/SSL configuration for secure connections.
network.tls.verifybool | PathNoTrueWhether to verify TLS certificates. Can be a boolean or a path to a CA certificate file.
network.tls.min_versionLiteral[TLSv1.2, TLSv1.3] | NoneNoMinimum TLS version to use. Defaults to system default if not specified.
network.tls.cipherslist[str] | NoneNoList of allowed cipher suites (e.g., ['ECDHE+AESGCM', 'DHE+AESGCM']).
network.tls.client_certPath | NoneNoPath to client certificate file for mTLS authentication.
network.tls.client_keyPath | NoneNoPath to client private key file for mTLS authentication.
network.proxyProxyConfig | NoneNoProxy configuration for HTTP connections.
network.proxy.urlHttpUrl | NoneNoSingle proxy URL for all connections (e.g., 'http://proxy.example.com:8080').
network.proxy.httpHttpUrl | NoneNoProxy URL for HTTP connections.
network.proxy.httpsHttpUrl | NoneNoProxy URL for HTTPS connections.
network.proxy.cacertPath | NoneNoPath to CA certificate file for verifying the proxy's certificate. Required for proxies in interception mode.
network.proxy.no_proxylist[str] | NoneNoList of hosts that should bypass the proxy (e.g., ['localhost', '127.0.0.1', '.internal.corp']).
network.timeoutfloat | TimeoutConfig | NoneNoTimeout configuration. Can be a float (for both connect and read) or a TimeoutConfig object with separate connect and read timeouts.
network.timeout.connectfloat | NoneNoConnection timeout in seconds.
network.timeout.readfloat | NoneNoRead timeout in seconds.
network.headersdict[str, str] | NoneNoAdditional HTTP headers to include in all requests.
projectstrNoGoogle Cloud project ID for Vertex AI
locationstrNoglobalGoogle Cloud location for Vertex AI

Sample Configuration

project: ${env.VERTEX_AI_PROJECT:=}
location: ${env.VERTEX_AI_LOCATION:=global}