All Classes and Interfaces
Class
Description
Request for creating cached content in Google GenAI.
Request for updating cached content in Google GenAI.
Represents cached content in Google GenAI for reusing large contexts across multiple
requests.
Service for managing cached content in Google GenAI.
Exception thrown when cached content operations fail.
Result of listing cached content with pagination support.
Google GenAI Chat Model implementation that provides access to Google's Gemini language
models.
Options for the Google GenAI Chat API.
Configures function calling behavior when tools are provided.
Controls how the model selects functions to call.
Constants for Google Gen AI.
Represents token count information for a specific modality (text, image, audio, video).
The GoogleGenAiRuntimeHints class is responsible for registering runtime hints for
Google GenAI classes.
Enum representing methods for evaluating harmful content.
Enum representing different threshold levels for blocking harmful content.
Enum representing different categories of harmful content.
The service tier to use for the request.
Enum representing the level of thinking tokens the model should generate.
Implementation of
ToolCallingManager specifically designed for Vertex AI
Gemini.Represents the traffic type for Google GenAI requests, indicating whether a request
consumes Pay-As-You-Go or Provisioned Throughput quota.
Extended usage metadata for Google GenAI responses that includes thinking tokens,
cached content, tool-use tokens, and modality breakdowns.
Utility class for converting JSON Schema to OpenAPI schema format.
Gemini supports the following MIME types:
image/gif
image/png
image/jpeg
video/mov
video/mpeg
video/mp4
video/mpg
video/avi
video/wmv
video/mpegps
video/flv
https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini