Class GoogleLlm

Integration for Gemini models.

Hierarchy (view full)

BaseLlm
- GoogleLlm

Index

Constructors

Properties

Accessors

apiClient apiBackend trackingHeaders liveApiVersion liveApiClient

Methods

generateContentAsync maybeAppendUserContent supportedModels generateContentAsyncImpl connect

Constructors

constructor

new GoogleLlm(model?): GoogleLlm
Constructor for Gemini
Parameters
- model: string = "gemini-2.5-flash"
Returns GoogleLlm
Overrides BaseLlm.constructor
- Defined in packages/adk/src/models/google-llm.ts:36

Properties

model

model: string

The name of the LLM, e.g. gemini-2.5-flash or gemini-2.5-flash-001.

`Protected`logger

logger: Logger = ...

Accessors

apiClient

get apiClient(): GoogleGenAI
Provides the api client.

Returns GoogleGenAI
- Defined in packages/adk/src/models/google-llm.ts:217

apiBackend

get apiBackend(): GoogleLLMVariant
Gets the API backend type.

Returns GoogleLLMVariant
- Defined in packages/adk/src/models/google-llm.ts:248

trackingHeaders

get trackingHeaders(): Record<string, string>
Gets the tracking headers.

Returns Record<string, string>
- Defined in packages/adk/src/models/google-llm.ts:262

liveApiVersion

get liveApiVersion(): string
Gets the live API version.

Returns string
- Defined in packages/adk/src/models/google-llm.ts:282

liveApiClient

get liveApiClient(): GoogleGenAI
Gets the live API client.

Returns GoogleGenAI
- Defined in packages/adk/src/models/google-llm.ts:291

Methods

generateContentAsync

generateContentAsync(llmRequest, stream?): AsyncGenerator<LlmResponse, void, unknown>
Generates one content from the given contents and tools.
Parameters
- llmRequest: LlmRequest
  LlmRequest, the request to send to the LLM.
- Optionalstream: boolean
  bool = false, whether to do streaming call.
Returns AsyncGenerator<LlmResponse, void, unknown>
a generator of LlmResponse.

For non-streaming call, it will only yield one LlmResponse.

For streaming call, it may yield more than one response, but all yielded responses should be treated as one response by merging the parts list.
Inherited from BaseLlm.generateContentAsync
- Defined in packages/adk/src/models/base-llm.ts:46

`Protected`maybeAppendUserContent

maybeAppendUserContent(llmRequest): void
Appends a user content, so that model can continue to output.
Parameters
- llmRequest: LlmRequest
  LlmRequest, the request to send to the LLM.
Returns void
Inherited from BaseLlm.maybeAppendUserContent
- Defined in packages/adk/src/models/base-llm.ts:216

`Static`supportedModels

supportedModels(): string[]
Provides the list of supported models.

Returns string[]
Overrides BaseLlm.supportedModels
- Defined in packages/adk/src/models/google-llm.ts:43

`Protected`generateContentAsyncImpl

generateContentAsyncImpl(llmRequest, stream?): AsyncGenerator<LlmResponse, void, unknown>
Main content generation method - handles both streaming and non-streaming
Parameters
- llmRequest: LlmRequest
- stream: boolean = false
Returns AsyncGenerator<LlmResponse, void, unknown>
Overrides BaseLlm.generateContentAsyncImpl
- Defined in packages/adk/src/models/google-llm.ts:56

connect

connect(_llmRequest): BaseLLMConnection
Connects to the Gemini model and returns an llm connection.
Parameters
- _llmRequest: LlmRequest
Returns BaseLLMConnection
Overrides BaseLlm.connect
- Defined in packages/adk/src/models/google-llm.ts:159