Crate gemini_rust 

gemini-rust

A Rust client library for Google’s Gemini API.

Crate Organization

This crate is organized into domain-specific modules that align with the Gemini API’s capabilities:

• interactions - Interactions API (recommended) — unified interface for models and agents
• generation - Legacy generateContent API (deprecated, still available)
• embedding - Text embedding generation for semantic analysis
• batch - Batch processing for multiple requests
• files - File upload and management
• cache - Content caching for reusable contexts
• safety - Content moderation and safety settings
• tools - Function calling and tool integration
• file_search - Retrieval augmented generation (RAG)
• models - Core primitive types shared across modules
• prelude - Convenient re-exports of commonly used types

Quick Start

For most use cases, import from the prelude:

use gemini_rust::prelude::*;

For more specialized types, import them directly from the crate root or their respective modules.

Interactions API (Recommended)

The Interactions API is the simplest and best way to use Gemini models and agents:

let interaction = client.create_interaction()
    .with_model("gemini-2.5-flash")
    .with_text("Hello, world!")
    .execute()
    .await?;

println!("{}", interaction.output_text());

Re-exports

pub use client::Error as ClientError;

pub use client::Gemini;

pub use client::GeminiBuilder;

pub use client::GenerationStream;

pub use client::Model;

pub use generation::builder::ContentBuilder;Deprecated

pub use generation::model::BlockReason;

pub use generation::model::Candidate;

pub use generation::model::CitationMetadata;

pub use generation::model::CitationSource;

pub use generation::model::CountTokensResponse;

pub use generation::model::FinishReason;

pub use generation::model::GenerateContentRequest;Deprecated

pub use generation::model::GenerationConfig;Deprecated

pub use generation::model::GenerationResponse;Deprecated

pub use generation::model::GroundingChunk;

pub use generation::model::GroundingMetadata;

pub use generation::model::GroundingSegment;

pub use generation::model::GroundingSupport;

pub use generation::model::MapsGroundingChunk;

pub use generation::model::MediaResolution;

pub use generation::model::MediaResolutionLevel;

pub use generation::model::MultiSpeakerVoiceConfig;

pub use generation::model::PrebuiltVoiceConfig;

pub use generation::model::PromptFeedback;

pub use generation::model::PromptTokenDetails;

pub use generation::model::SpeakerVoiceConfig;

pub use generation::model::SpeechConfig;

pub use generation::model::ThinkingConfig;

pub use generation::model::ThinkingLevel;

pub use generation::model::UsageMetadata;

pub use generation::model::VoiceConfig;

pub use generation::model::WebGroundingChunk;

pub use interactions::InteractionBuilder;

pub use interactions::InteractionEvent;

pub use interactions::InteractionHandle;

pub use interactions::InteractionStream;

pub use interactions::StepDeltaData;

pub use embedding::builder::EmbedBuilder;

pub use embedding::model::BatchContentEmbeddingResponse;

pub use embedding::model::BatchEmbedContentsRequest;

pub use embedding::model::ContentEmbedding;

pub use embedding::model::ContentEmbeddingResponse;

pub use embedding::model::EmbedContentRequest;

pub use embedding::model::TaskType;

pub use safety::model::HarmBlockThreshold;

pub use safety::model::HarmCategory;

pub use safety::model::HarmProbability;

pub use safety::model::SafetyRating;

pub use safety::model::SafetySetting;

pub use tools::model::CodeExecutionConfig;

pub use tools::model::CodeExecutionOutcome;

pub use tools::model::CodeExecutionResult;

pub use tools::model::CodeLanguage;

pub use tools::model::ExecutableCode;

pub use tools::model::FunctionCall;

pub use tools::model::FunctionCallingConfig;

pub use tools::model::FunctionCallingMode;

pub use tools::model::FunctionDeclaration;

pub use tools::model::FunctionResponse;

pub use tools::model::GoogleMapsConfig;

pub use tools::model::LatLng;

pub use tools::model::RetrievalConfig;

pub use tools::model::Tool;

pub use tools::model::ToolConfig;

pub use batch::builder::BatchBuilder;

pub use batch::handle::BatchGenerationResponseItem;

pub use batch::handle::BatchHandle;

pub use batch::handle::BatchHandle as Batch;

pub use batch::handle::BatchStatus;

pub use batch::handle::Error as BatchHandleError;

pub use batch::model::BatchConfig;

pub use batch::model::BatchGenerateContentRequest;

pub use batch::model::BatchOperation;

pub use batch::model::BatchStats;

pub use batch::model::IndividualRequestError;

pub use batch::model::RequestMetadata;

pub use batch::Error as BatchError;

pub use files::builder::FileBuilder;

pub use files::handle::FileHandle;

pub use files::model::File;

pub use files::model::FileState;

pub use files::Error as FilesError;

pub use cache::builder::CacheBuilder;

pub use cache::handle::CachedContentHandle;

pub use cache::model::CacheExpirationRequest;

pub use cache::model::CacheExpirationResponse;

pub use cache::model::CachedContent;

pub use cache::model::CreateCachedContentRequest;

pub use file_search::model::ChunkingConfig;

pub use file_search::model::CustomMetadata;

pub use file_search::model::CustomMetadataValue;

pub use file_search::model::Document;

pub use file_search::model::DocumentState;

pub use file_search::model::FileSearchStore;

pub use file_search::model::Operation;

pub use file_search::model::OperationResult;

pub use file_search::model::Status;

pub use file_search::model::StringList;

pub use file_search::model::WhiteSpaceConfig;

pub use file_search::DocumentBuilder;

pub use file_search::DocumentHandle;

pub use file_search::FileSearchStoreBuilder;

pub use file_search::FileSearchStoreHandle;

pub use file_search::ImportBuilder;

pub use file_search::OperationHandle;

pub use file_search::UploadBuilder;

pub use interactions::model::*;

Modules

batch

Batch processing for multiple generation requests

cache

Content caching for reusable contexts and system instructions

client

common

Common utilities and serialization helpers

embedding

Text embedding generation for semantic analysis

file_search

File search for retrieval augmented generation (RAG)

files

File upload and management

generation

Content generation including text, images, and audio

interactions

Interactions API — the modern interface for Gemini models and agents Interactions API — the modern interface for Gemini models and agents.

prelude

Convenient re-exports of commonly used types

safety

Content moderation and safety settings

tools

Function calling and tool integration

Structs

Blob

Core primitive types for building requests and parsing responses Blob for a message part

Content

Core primitive types for building requests and parsing responses Content of a message

FileData

Core primitive types for building requests and parsing responses Coordinates for a previously uploaded file.

Message

Core primitive types for building requests and parsing responses Message in a conversation

Enums

Modality

Core primitive types for building requests and parsing responses Content modality type - specifies the format of model output

Part

Core primitive types for building requests and parsing responses Content part that can be included in a message

Role

Core primitive types for building requests and parsing responses Role of a message in a conversation