Crate genai_rs 

genai-rs

A Rust client library for Google’s Generative AI (Gemini) API using the Interactions API.

Quick Start

use genai_rs::Client;

#[tokio::main]
async fn main() -> Result<(), genai_rs::GenaiError> {
    let client = Client::new(
        std::env::var("GEMINI_API_KEY").expect("GEMINI_API_KEY not set")
    );

    let response = client
        .interaction()
        .with_model(genai_rs::DEFAULT_MODEL)
        .with_text("Hello, Gemini!")
        .create()
        .await?;

    println!("{}", response.as_text().unwrap_or("No response"));
    Ok(())
}

Features

• Fluent Builder API: Chain methods for readable request construction
• Streaming: Real-time response streaming with create_stream()
• Function Calling: Automatic function discovery and execution via macros
• Built-in Tools: Google Search, Code Execution, URL Context
• Multimodal: Images, audio, video, and document inputs
• Thinking Mode: Access model reasoning with configurable levels

API Stability & Forward Compatibility

This library is designed for forward compatibility with evolving APIs:

• #[non_exhaustive] enums: Match statements require wildcard arms (_ => ...)
• Unknown variants: Unrecognized API types are captured, not rejected
• Graceful degradation: New API features won’t break existing code

When Google adds new features, your code continues to work. Unknown content types and tools are preserved for inspection via helper methods like has_unknown().

Module Organization

• Client: Main entry point for API interactions
• InteractionBuilder: Fluent builder for configuring requests
• interactions_api: Helper functions for constructing content
• function_calling: Function registration and execution

Re-exports

pub use errors::GenaiError;

pub use content::Annotation;

pub use content::CodeExecutionLanguage;

pub use content::Content;

pub use content::FileSearchResultItem;

pub use content::GoogleMapsResultItem;

pub use content::GoogleSearchResultItem;

pub use content::Place;

pub use content::Resolution;

pub use content::ReviewSnippet;

pub use content::UrlContextResultItem;

pub use steps::FunctionResultPayload;

pub use steps::Step;

pub use steps::StepDelta;

pub use steps::StepError;

pub use request::AgentConfig;

pub use request::AntigravityConfig;

pub use request::DeepResearchConfig;

pub use request::DynamicConfig;

pub use request::GenerationConfig;

pub use request::ImageAspectRatio;

pub use request::ImageConfig;

pub use request::ImageSize;

pub use request::InteractionInput;

pub use request::InteractionRequest;

pub use request::Role;

pub use request::ServiceTier;

pub use request::SpeechConfig;

pub use request::ThinkingLevel;

pub use request::ThinkingSummaries;

pub use request::TranscriptionConfig;

pub use request::TurnContent;

pub use request::VideoConfig;

pub use request::VideoTask;

pub use request::Visualization;

pub use response_format::ResponseDelivery;

pub use response_format::ResponseFormat;

pub use response_format::ResponseFormatSpec;

pub use environment::AllowlistEntry;

pub use environment::EnvironmentSource;

pub use environment::EnvironmentSpec;

pub use environment::NetworkConfig;

pub use environment::RemoteEnvironment;

pub use environment::SourceType;

pub use triggers::Trigger;

pub use triggers::TriggerCreateParams;

pub use triggers::TriggerExecution;

pub use triggers::TriggerExecutionListResponse;

pub use triggers::TriggerExecutionStatus;

pub use triggers::TriggerListResponse;

pub use triggers::TriggerStatus;

pub use triggers::TriggerUpdate;

pub use environments::CreateEnvironmentRequest;

pub use environments::Environment;

pub use environments::EnvironmentListResponse;

pub use environments::EnvironmentStatus;

pub use safety::HarmCategory;

pub use safety::SafetyMethod;

pub use safety::SafetySetting;

pub use safety::SafetyThreshold;

pub use agents::Agent;

pub use agents::AgentListResponse;

pub use webhooks::RevocationBehavior;

pub use webhooks::RotateSigningSecretResponse;

pub use webhooks::SigningSecret;

pub use webhooks::Webhook;

pub use webhooks::WebhookConfig;

pub use webhooks::WebhookEvent;

pub use webhooks::WebhookListResponse;

pub use webhooks::WebhookState;

pub use webhooks::WebhookUpdate;

pub use response::AudioInfo;

pub use response::CodeExecutionCallInfo;

pub use response::CodeExecutionResultInfo;

pub use response::FunctionCallInfo;

pub use response::FunctionResultInfo;

pub use response::GoogleMapsResultInfo;

pub use response::GroundingToolCount;

pub use response::ImageInfo;

pub use response::InteractionResponse;

pub use response::InteractionStatus;

pub use response::ModalityTokens;

pub use response::OwnedFunctionCallInfo;

pub use response::StepSummary;

pub use response::UrlContextResultInfo;

pub use response::UsageMetadata;

pub use tools::AllowedTools;

pub use tools::ComputerUseConfig;

pub use tools::ExaAiSearchConfig;

pub use tools::FileSearchConfig;

pub use tools::FunctionCallingMode;

pub use tools::FunctionDeclaration;

pub use tools::FunctionDeclarationBuilder;

pub use tools::FunctionParameters;

pub use tools::GoogleMapsConfig;

pub use tools::GoogleSearchConfig;

pub use tools::HybridSearchConfig;

pub use tools::McpServerConfig;

pub use tools::ParallelAiSearchConfig;

pub use tools::RagFilter;

pub use tools::RagRanking;

pub use tools::RagResource;

pub use tools::RagRetrievalConfig;

pub use tools::RagStoreConfig;

pub use tools::RetrievalConfig;

pub use tools::RetrievalType;

pub use tools::SearchType;

pub use tools::Tool;

pub use tools::ToolChoice;

pub use tools::VertexAiSearchConfig;

pub use wire_streaming::InteractionStreamEvent;

pub use wire_streaming::StreamChunk;

pub use wire_streaming::StreamEvent;

pub use wire_streaming::StreamMetadata;

pub use client::Client;

pub use client::ClientBuilder;

pub use request_builder::ConversationBuilder;

pub use request_builder::InteractionBuilder;

pub use function_calling::CallableFunction;

pub use function_calling::FunctionError;

pub use function_calling::ToolService;

pub use streaming::AutoFunctionResult;

pub use streaming::AutoFunctionResultAccumulator;

pub use streaming::AutoFunctionStreamChunk;

pub use streaming::AutoFunctionStreamEvent;

pub use streaming::FunctionExecutionResult;

pub use streaming::PendingFunctionCall;

pub use multimodal::audio_from_file;

pub use multimodal::audio_from_file_with_mime;

pub use multimodal::detect_mime_type;

pub use multimodal::document_from_file;

pub use multimodal::document_from_file_with_mime;

pub use multimodal::image_from_file;

pub use multimodal::image_from_file_with_mime;

pub use multimodal::video_from_file;

pub use multimodal::video_from_file_with_mime;

Modules

agents

Agent resource types for the /v1beta/agents API.

antigravity

Native client for Google’s Antigravity localharness agent runtime.

client

content

Content types for the Interactions API.

environment

Environment types for the environment request field and the Agents resource’s base_environment.

environments

Environments resource (/v1beta/environments).

errors

function_calling

interactions_api

multimodal

Multimodal content utilities for file loading and MIME type detection.

request

Request types for creating interactions.

request_builder

response

Response types for the Interactions API.

response_format

Typed response_format union for interaction requests.

safety

Safety settings for interaction requests.

steps

Step types for the Interactions API (revision 2026-05-20).

streaming

Streaming types for automatic function calling.

tools

triggers

Triggers resource (/v1beta/triggers) — server-side scheduled interactions.

webhooks

Webhook types for the /v1beta/webhooks resource and the per-request webhook_config field.

wire

Wire-level inspection of HTTP traffic.

wire_streaming

Streaming types for SSE responses (API revision 2026-05-20).

Structs

FileError

Error information for failed file operations.

FileMetadata

Represents an uploaded file in the Files API.

ListFilesResponse

Response from listing files.

ResumableUpload

Handle to a resumable upload session.

VideoMetadata

Metadata for video files.

Enums

FileState

Processing state of an uploaded file.

Constants

DEFAULT_CHUNK_SIZE

Default chunk size for chunked uploads (8 MB).

DEFAULT_IMAGE_MODEL

The model to use for image generation.

DEFAULT_MODEL

The model this crate is developed and verified against.

DEFAULT_TTS_MODEL

The model to use for text-to-speech.

INLINE_VIDEO_MODEL

A model that accepts inline (base64) video bytes, which DEFAULT_MODEL does not.

MINIMAL_THINKING_MODEL

A model that supports ThinkingLevel::Minimal, which DEFAULT_MODEL does not.