Skip to main content

​
GoogleLLM

Google Gemini LLM provider. Supports both the Gemini API (via apiKey) and Vertex AI (set vertexai: true with projectId and service-account credentials).

​
Constructor

​
apiKey
string | null
Google AI (Gemini) API key. Falls back to the GOOGLE_API_KEY environment variable, then null. Not used for Vertex AI auth.
​
model
GoogleLLMModel | string
Gemini model id. Default 'gemini-2.5-flash-lite'.
​
temperature
number
Sampling temperature controlling randomness. Default 0.7.
​
maxOutputTokens
number
Maximum number of tokens to generate in the response. Default 8192.
​
thinkingBudget
number | null
Token budget for Gemini “thinking” (reasoning). 0 disables thinking. Default 0.
​
includeThoughts
boolean
Whether to include the model’s thought/reasoning content in responses. Default false.
​
safetySettings
Array<Record<string, string>> | null
Gemini safety/content-filter settings, as an array of category/threshold maps. Default null (provider defaults).
​
topP
number | null
Nucleus sampling probability mass. Default null (model default).
​
topK
number | null
Top-K sampling cutoff. Default null (model default).
​
presencePenalty
number | null
Presence penalty discouraging repeated topics. Default null (model default).
​
frequencyPenalty
number | null
Frequency penalty discouraging repeated tokens. Default null (model default).
​
seed
number | null
Seed for reproducible sampling. Default null (non-deterministic).
​
vertexai
boolean
Route requests through Vertex AI instead of the Gemini API. When true, projectId is required. Default false.
​
projectId
string | null
Google Cloud project id for Vertex AI auth. Required when vertexai is true; falls back to GOOGLE_CLOUD_PROJECT. Default null.
​
location
string
Vertex AI region. Default 'us-central1'. Only used when vertexai is true.
​
serviceAccountJson
string | Record<string, any> | null
Vertex AI service-account credentials, as a JSON string or parsed object. Used when vertexai is true. Default null.
​
serviceAccountPath
string | null
Path to a Vertex AI service-account JSON file. Used when vertexai is true; falls back to GOOGLE_APPLICATION_CREDENTIALS. Default null.

​
cancelCurrentGeneration

Cancel the in-flight generation for the current session, if any.

​
chat

Stream a completion for the given messages, yielding LLMResponse chunks.
​
returns
AsyncIterator<LLMResponse>

​
close

Release any resources held by the provider.

​
closeEmitter

Close the emitter: drop all handlers and stop emitting. Waits up to 2 seconds for in-flight async handlers to settle before returning.

​
emit

​
event
string
required

​
getRuntimeConfig

​
returns
Record<string, any>

​
listenerCount

​
event
string
required
​
returns
number

​
off

​
event
string
required
​
handler
EventHandler
required

​
on

​
event
string
required
​
handler
EventHandler
required
​
returns
EventHandler

​
once

​
event
string
required
​
handler
EventHandler
required
​
returns
EventHandler

​
removeAllListeners

​
event
string

​
GoogleLLMModel

Supported Google Gemini LLM model ids.