Class GeminiProvider

GeminiProvider: Concrete BaseProvider implementation for Google Gemini models.

Responsibilities:

Owns the GoogleGenAI SDK client
Initializes provider-level configuration
Registers supported capabilities
Delegates execution to capability-specific implementations

Implements chat, embedding, image, and moderation capabilities for Gemini.

Template: TChatInput

Input type for chat requests

Template: TEmbedInput

Input type for embedding requests

Template: TImageInput

Input type for image generation requests

Template: TModerationInput

Input type for moderation requests

Hierarchy (View Summary)

BaseProvider
- GeminiProvider

Implements

Constructors

constructor

new GeminiProvider(): GeminiProvider
Returns GeminiProvider
Overrides BaseProvider.constructor
- Defined in src/providers/gemini/GeminiProvider.ts:124

Properties

`Protected`capabilities

capabilities: Partial<CapabilityMap> = {}

Support provider capabilities

`Protected`config

config: ProviderConnectionConfig | null = null

Current connection config

`Protected` `Optional`executors

executors?: Map<CapabilityKeyType, CapabilityExecutor<any, any, any>>

`Readonly`providerType

providerType: AIProviderType

Type of this provider (OpenAI, Anthropic, Gemini, etc.)

Methods

analyzeImage

analyzeImage(
    req: AIRequest<ClientImageAnalysisRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedImageAnalysis[]>>
Execute an image analysis request
Parameters
- req: AIRequest<ClientImageAnalysisRequest>
  Unified AI request containing Image analysis input and options
- executionContext: MultiModalExecutionContext
  Execution context
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation
Returns Promise<AIResponse<NormalizedImageAnalysis[]>>
AIResponse containing normalized image analysis results
Implementation of ImageAnalysisCapability.analyzeImage
- Defined in src/providers/gemini/GeminiProvider.ts:362

analyzeImageStream

analyzeImageStream(
    req: AIRequest<ClientImageAnalysisRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): AsyncGenerator<AIResponseChunk<NormalizedImageAnalysis[]>>
Execute a streaming image analysis request.
Parameters
- req: AIRequest<ClientImageAnalysisRequest>
  Unified AI request containing image analysis input and options
- executionContext: MultiModalExecutionContext
  Execution context
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation
Returns AsyncGenerator<AIResponseChunk<NormalizedImageAnalysis[]>>
Async iterable emitting streamed response chunks
Implementation of ImageAnalysisStreamCapability.analyzeImageStream
- Defined in src/providers/gemini/GeminiProvider.ts:382

analyzeVideo

analyzeVideo(
    req: AIRequest<ClientVideoAnalysisRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedVideoAnalysis[]>>
Execute a non-streaming video analysis request.
Parameters
- req: AIRequest<ClientVideoAnalysisRequest>
- executionContext: MultiModalExecutionContext
- Optionalsignal: AbortSignal
Returns Promise<AIResponse<NormalizedVideoAnalysis[]>>
Implementation of VideoAnalysisCapability.analyzeVideo
- Defined in src/providers/gemini/GeminiProvider.ts:396

chat

chat(
    req: AIRequest<ClientChatRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedChatMessage>>
Execute a non-streaming chat request.
Parameters
- req: AIRequest<ClientChatRequest>
  Unified AI request containing chat input and options
- executionContext: MultiModalExecutionContext
  Execution context
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation
Returns Promise<AIResponse<NormalizedChatMessage>>
AIResponse containing generated text
Implementation of ChatCapability.chat
- Defined in src/providers/gemini/GeminiProvider.ts:242

chatStream

chatStream(
    req: AIRequest<ClientChatRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): AsyncGenerator<AIResponseChunk<NormalizedChatMessage>>
Execute a streaming chat request.
Parameters
- req: AIRequest<ClientChatRequest>
  Unified AI request containing chat input and options
- executionContext: MultiModalExecutionContext
  Execution context
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation
Returns AsyncGenerator<AIResponseChunk<NormalizedChatMessage>>
Async iterable emitting streamed response chunks
Implementation of ChatStreamCapability.chatStream
- Defined in src/providers/gemini/GeminiProvider.ts:262

downloadVideo

downloadVideo(
    req: AIRequest<ClientVideoDownloadRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedVideo[]>>
Execute a non-streaming video download request.
Parameters
- req: AIRequest<ClientVideoDownloadRequest>
- executionContext: MultiModalExecutionContext
- Optionalsignal: AbortSignal
Returns Promise<AIResponse<NormalizedVideo[]>>
Implementation of VideoDownloadCapability.downloadVideo
- Defined in src/providers/gemini/GeminiProvider.ts:438

embed

embed(
    req: AIRequest<ClientEmbeddingRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedEmbedding[]>>
Execute an embedding request.
Parameters
- req: AIRequest<ClientEmbeddingRequest>
  Unified AI request containing embedding input
- executionContext: MultiModalExecutionContext
  Execution context
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation
Returns Promise<AIResponse<NormalizedEmbedding[]>>
AIResponse containing embedding vector(s)
Implementation of EmbedCapability.embed
- Defined in src/providers/gemini/GeminiProvider.ts:302

ensureInitialized

ensureInitialized(): void
Ensures that the provider has been initialized before use.

Returns void
Throws
Error if not initialized
Inherited from BaseProvider.ensureInitialized
- Defined in src/core/provider/BaseProvider.ts:291

extendVideo

extendVideo(
    req: AIRequest<ClientVideoExtendRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedVideo[]>>
Execute a non-streaming video extension request.
Parameters
- req: AIRequest<ClientVideoExtendRequest>
- executionContext: MultiModalExecutionContext
- Optionalsignal: AbortSignal
Returns Promise<AIResponse<NormalizedVideo[]>>
Implementation of VideoExtendCapability.extendVideo
- Defined in src/providers/gemini/GeminiProvider.ts:424

generateImage

generateImage(
    req: AIRequest<ClientImageGenerationRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedImage[]>>
Execute an image generation request.
Parameters
- req: AIRequest<ClientImageGenerationRequest>
  Unified AI request containing image generation input
- executionContext: MultiModalExecutionContext
  Execution context
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation
Returns Promise<AIResponse<NormalizedImage[]>>
AIResponse containing normalized generated images
Implementation of ImageGenerationCapability.generateImage
- Defined in src/providers/gemini/GeminiProvider.ts:322

generateImageStream

generateImageStream(
    req: AIRequest<ClientImageGenerationRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): AsyncGenerator<AIResponseChunk<NormalizedImage[]>>
Execute a streaming image generation request.
Parameters
- req: AIRequest<ClientImageGenerationRequest>
  Unified AI request containing image generation input
- executionContext: MultiModalExecutionContext
  Execution context
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation
Returns AsyncGenerator<AIResponseChunk<NormalizedImage[]>>
Async iterable emitting image generation chunks
Implementation of ImageGenerationStreamCapability.generateImageStream
- Defined in src/providers/gemini/GeminiProvider.ts:342

generateVideo

generateVideo(
    req: AIRequest<ClientVideoGenerationRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedVideo[]>>
Execute a non-streaming video generation request.
Parameters
- req: AIRequest<ClientVideoGenerationRequest>
- executionContext: MultiModalExecutionContext
- Optionalsignal: AbortSignal
Returns Promise<AIResponse<NormalizedVideo[]>>
Implementation of VideoGenerationCapability.generateVideo
- Defined in src/providers/gemini/GeminiProvider.ts:410

getCapabilities

getCapabilities(): Partial<CapabilityMap>
Returns Partial<CapabilityMap>
Inherited from BaseProvider.getCapabilities
- Defined in src/core/provider/BaseProvider.ts:79

getCapability

getCapability<C extends CapabilityKeyType>(
capability: C,
): C extends keyof CapabilityMap ? CapabilityMap[C] : ProviderCapability
Type Parameters
- C extends CapabilityKeyType
Parameters
- capability: C
Returns C extends keyof CapabilityMap ? CapabilityMap[C] : ProviderCapability
Inherited from BaseProvider.getCapability
- Defined in src/core/provider/BaseProvider.ts:102

getMergedOptions

getMergedOptions(
capability: string,
runtimeOptions?: any,
): { generalParams: any; model: any; modelParams: any; providerParams: any }
Resolve and merge configuration for a capability.

Merge precedence (low → high):
1. providerDefaults (global provider-level defaults)
2. model capability defaults (models[modelName][capability])
3. runtimeOptions (request-level overrides)
Model resolution fallback: runtimeOptions.model → config.defaultModels[capability] → config.defaultModel
Parameters
- capability: string
  Name of the capability
- runtimeOptions: any = {}
  Request-level override options
Returns { generalParams: any; model: any; modelParams: any; providerParams: any }
Merged configuration with keys: model, modelParams, providerParams, generalParams

Throws
Error if a model cannot be resolved for this capability
Inherited from BaseProvider.getMergedOptions
- Defined in src/core/provider/BaseProvider.ts:228

getProviderType

getProviderType(): AIProviderType
Returns AIProviderType
Inherited from BaseProvider.getProviderType
- Defined in src/core/provider/BaseProvider.ts:75

hasCapability

hasCapability<C extends CapabilityKeyType>(capability: C): boolean
Type-safe runtime check for a capability. Allows safe casting after confirming the capability is registered.
Type Parameters
- C extends CapabilityKeyType
  Capability key
Parameters
- capability: C
  Capability symbol
Returns boolean
True if the capability is registered
Inherited from BaseProvider.hasCapability
- Defined in src/core/provider/BaseProvider.ts:116

init

init(config: ProviderConnectionConfig): void
Initializes the Gemini provider and registers supported capabilities.
Parameters
- config: ProviderConnectionConfig
  Provider connection configuration
Returns void
Throws
Error if API key is missing or invalid
Overrides BaseProvider.init
- Defined in src/providers/gemini/GeminiProvider.ts:134

isInitialized

isInitialized(): boolean
Check if the provider has been initialized.

Returns boolean
True if initialized, false otherwise
Inherited from BaseProvider.isInitialized
- Defined in src/core/provider/BaseProvider.ts:71

`Protected`mergeOptions

mergeOptions(...sources: any[]): any
Deep-merge multiple objects. Arrays override completely, objects are recursively merged, primitives override. Used for merging provider defaults, model configurations, and runtime options.
Parameters
- ...sources: any[]
  Objects to merge
Returns any
Deep-merged object
Inherited from BaseProvider.mergeOptions
- Defined in src/core/provider/BaseProvider.ts:148

moderation

moderation(
    req: AIRequest<ClientModerationRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedModeration[]>>
Execute a moderation request.
Parameters
- req: AIRequest<ClientModerationRequest>
  Unified AI request containing moderation input
- executionContext: MultiModalExecutionContext
  Execution context
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation
Returns Promise<AIResponse<NormalizedModeration[]>>
AIResponse containing moderation result(s)
Implementation of ModerationCapability.moderation
- Defined in src/providers/gemini/GeminiProvider.ts:282

`Protected`registerCapability

registerCapability<C extends BuiltInCapabilityKey>(
capability: C,
impl: CapabilityMap[C],
): void
Register a capability implementation. Called by concrete providers to declare support for a capability.
Type Parameters
- C extends BuiltInCapabilityKey
  Capability key
Parameters
- capability: C
  Capability symbol
- impl: CapabilityMap[C]
  Implementation of the capability
Returns void
Inherited from BaseProvider.registerCapability
- Defined in src/core/provider/BaseProvider.ts:129
registerCapability(
capability: CustomCapabilityKey,
impl: ProviderCapability,
): void
Register a capability implementation. Called by concrete providers to declare support for a capability.
Parameters
- capability: CustomCapabilityKey
  Capability symbol
- impl: ProviderCapability
  Implementation of the capability
Returns void
Inherited from BaseProvider.registerCapability
- Defined in src/core/provider/BaseProvider.ts:130

setClientExecutors

setClientExecutors(
executors: Map<CapabilityKeyType, CapabilityExecutor<any, any, any>>,
): void
Parameters
- executors: Map<CapabilityKeyType, CapabilityExecutor<any, any, any>>
Returns void
Inherited from BaseProvider.setClientExecutors
- Defined in src/core/provider/BaseProvider.ts:136

textToSpeech

textToSpeech(
    req: AIRequest<ClientTextToSpeechRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedAudio[]>>
Execute a non-streaming text-to-speech request.
Parameters
- req: AIRequest<ClientTextToSpeechRequest>
  Unified AI request containing input text and TTS options.
- executionContext: MultiModalExecutionContext
  Execution context.
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation.
Returns Promise<AIResponse<NormalizedAudio[]>>
AIResponse containing normalized synthesized audio artifact(s).
Implementation of TextToSpeechCapability.textToSpeech
- Defined in src/providers/gemini/GeminiProvider.ts:514

textToSpeechStream

textToSpeechStream(
    req: AIRequest<ClientTextToSpeechRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): AsyncGenerator<AIResponseChunk<NormalizedAudio[]>>
Execute a streaming text-to-speech request.
Parameters
- req: AIRequest<ClientTextToSpeechRequest>
  Unified AI request containing input text and TTS options.
- executionContext: MultiModalExecutionContext
  Execution context.
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation.
Returns AsyncGenerator<AIResponseChunk<NormalizedAudio[]>>
Async iterable emitting incremental synthesized audio chunks.
Implementation of TextToSpeechStreamCapability.textToSpeechStream
- Defined in src/providers/gemini/GeminiProvider.ts:533

transcribeAudio

transcribeAudio(
    req: AIRequest<ClientAudioTranscriptionRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedChatMessage[]>>
Execute a non-streaming audio transcription request.
Parameters
- req: AIRequest<ClientAudioTranscriptionRequest>
  Unified AI request containing audio input and transcription options.
- executionContext: MultiModalExecutionContext
  Execution context.
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation.
Returns Promise<AIResponse<NormalizedChatMessage[]>>
AIResponse containing normalized transcription artifact(s).
Implementation of AudioTranscriptionCapability.transcribeAudio
- Defined in src/providers/gemini/GeminiProvider.ts:457

transcribeAudioStream

transcribeAudioStream(
    req: AIRequest<ClientAudioTranscriptionRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): AsyncGenerator<AIResponseChunk<NormalizedChatMessage[]>>
Execute a streaming audio transcription request.
Parameters
- req: AIRequest<ClientAudioTranscriptionRequest>
  Unified AI request containing audio input and transcription options.
- executionContext: MultiModalExecutionContext
  Execution context.
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation.
Returns AsyncGenerator<AIResponseChunk<NormalizedChatMessage[]>>
Async iterable emitting incremental transcription chunks.
Implementation of AudioTranscriptionStreamCapability.transcribeAudioStream
- Defined in src/providers/gemini/GeminiProvider.ts:476

translateAudio

translateAudio(
    req: AIRequest<ClientAudioTranslationRequest>,
    executionContext: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedChatMessage[]>>
Execute a non-streaming audio translation request.
Parameters
- req: AIRequest<ClientAudioTranslationRequest>
  Unified AI request containing source audio and translation options.
- executionContext: MultiModalExecutionContext
  Execution context.
- Optionalsignal: AbortSignal
  AbortSignal for request cancellation.
Returns Promise<AIResponse<NormalizedChatMessage[]>>
AIResponse containing normalized translated transcript artifact(s).
Implementation of AudioTranslationCapability.translateAudio
- Defined in src/providers/gemini/GeminiProvider.ts:495

Class GeminiProvider

Template: TChatInput

Template: TEmbedInput

Template: TImageInput

Template: TModerationInput

Hierarchy (View Summary)

Implements

Index

Constructors

Properties

Methods

Constructors

constructor

Returns GeminiProvider

Properties

Protectedcapabilities

Protectedconfig

Protected Optionalexecutors

ReadonlyproviderType

Methods

analyzeImage

Parameters

Returns Promise<AIResponse<NormalizedImageAnalysis[]>>

analyzeImageStream

Parameters

Returns AsyncGenerator<AIResponseChunk<NormalizedImageAnalysis[]>>

analyzeVideo

Parameters

Returns Promise<AIResponse<NormalizedVideoAnalysis[]>>

chat

Parameters

Returns Promise<AIResponse<NormalizedChatMessage>>

chatStream

Parameters

Returns AsyncGenerator<AIResponseChunk<NormalizedChatMessage>>

downloadVideo

Parameters

Returns Promise<AIResponse<NormalizedVideo[]>>

embed

Parameters

Returns Promise<AIResponse<NormalizedEmbedding[]>>

ensureInitialized

Returns void

Throws

extendVideo

Parameters

Returns Promise<AIResponse<NormalizedVideo[]>>

generateImage

Parameters

Returns Promise<AIResponse<NormalizedImage[]>>

generateImageStream

Parameters

Returns AsyncGenerator<AIResponseChunk<NormalizedImage[]>>

generateVideo

Parameters

Returns Promise<AIResponse<NormalizedVideo[]>>

getCapabilities

Returns Partial<CapabilityMap>

getCapability

Type Parameters

Parameters

Returns C extends keyof CapabilityMap ? CapabilityMap[C] : ProviderCapability

getMergedOptions

Parameters

Returns { generalParams: any; model: any; modelParams: any; providerParams: any }

Throws

getProviderType

Returns AIProviderType

hasCapability

Type Parameters

Parameters

Returns boolean

init

Parameters

Returns void

Throws

isInitialized

Returns boolean

ProtectedmergeOptions

Parameters

`Protected`capabilities

`Protected`config

`Protected` `Optional`executors

`Readonly`providerType

`Protected`mergeOptions

`Protected`registerCapability