interface BaseGoogleClassifierParamsCustom HTTP headers included with every request to the Gemini Decisions API.
Shared configuration parameters for BaseGoogleClassifier.
Custom ApiClient instance used to authenticate and send HTTP requests.
API version path segment. Defaults to "v1beta" for the Gemini Developer API
and "v1" for Vertex AI.
Optional callbacks attached to every invocation of this classifier.
Custom HTTP headers included with every request to the Gemini Decisions API.
OpenAI-compatible alias for input media detail ("auto", "low", "high").
If both mediaResolution and detail are provided, mediaResolution wins.
Custom API host or base URL override (e.g. "generativelanguage.googleapis.com"
or "http://localhost:8080").
Google Cloud region when targeting Vertex AI. Defaults to "global".
The maximum number of concurrent calls that can be made.
Defaults to Infinity, which means no limit.
The maximum number of retries that can be made for a single call, with an exponential backoff between each attempt. Defaults to 6.
Default media resolution applied to input image and video content blocks
that do not specify their own resolution ("low", "medium", "high", or
"ultra_high" for images).
Optional metadata attached to every invocation of this classifier.
Gemini Decisions model identifier (for example, "gemini-decision-1").
Custom handler to handle failed attempts. Takes the originally thrown error object as input, and should itself throw an error if the input error is not retryable.
Explicit Google platform selection ("gai" for Gemini Developer API,
"gcp" for Vertex AI).
Optional tags attached to every invocation of this classifier.
Shorthand to route requests to Vertex AI (platformType: "gcp").