Interface representing the input to the Google Vertex AI model.

interface GoogleVertexAITextInput {
    apiVersion?: string;
    authOptions?: WebGoogleAuthOptions;
    cache?: boolean | BaseCache<Generation[]>;
    callbackManager?: CallbackManager;
    callbacks?: Callbacks;
    concurrency?: number;
    customModelURL?: string;
    endpoint?: string;
    location?: string;
    maxConcurrency?: number;
    maxOutputTokens?: number;
    maxRetries?: number;
    metadata?: Record<string, unknown>;
    model?: string;
    onFailedAttempt?: FailedAttemptHandler;
    tags?: string[];
    temperature?: number;
    topK?: number;
    topP?: number;
    verbose?: boolean;
}

Hierarchy

  • GoogleVertexAIBaseLLMInput<WebGoogleAuthOptions>
    • GoogleVertexAITextInput

Properties

apiVersion?: string

The version of the API functions. Part of the path.

authOptions?: WebGoogleAuthOptions
cache?: boolean | BaseCache<Generation[]>
callbackManager?: CallbackManager

Use callbacks instead

callbacks?: Callbacks
concurrency?: number

Use maxConcurrency instead

customModelURL?: string

If you are planning to connect to a model that lives under a custom endpoint provide the "customModelURL" which will override the automatic URL building

This is necessary in cases when you want to point to a fine-tuned model or a model that has been hidden under VertexAI Endpoints.

In those cases, specifying the GoogleVertexAIModelParams.model param will not be necessary and will be ignored.

GoogleVertexAILLMConnection.buildUrl

endpoint?: string

Hostname for the API call

location?: string

Region where the LLM is stored

maxConcurrency?: number

The maximum number of concurrent calls that can be made. Defaults to Infinity, which means no limit.

maxOutputTokens?: number

Maximum number of tokens to generate in the completion.

maxRetries?: number

The maximum number of retries that can be made for a single call, with an exponential backoff between each attempt. Defaults to 6.

metadata?: Record<string, unknown>
model?: string

Model to use

onFailedAttempt?: FailedAttemptHandler

Custom handler to handle failed attempts. Takes the originally thrown error object as input, and should itself throw an error if the input error is not retryable.

tags?: string[]
temperature?: number

Sampling temperature to use

topK?: number

Top-k changes how the model selects tokens for output.

A top-k of 1 means the selected token is the most probable among all tokens in the model’s vocabulary (also called greedy decoding), while a top-k of 3 means that the next token is selected from among the 3 most probable tokens (using temperature).

topP?: number

Top-p changes how the model selects tokens for output.

Tokens are selected from most probable to least until the sum of their probabilities equals the top-p value.

For example, if tokens A, B, and C have a probability of .3, .2, and .1 and the top-p value is .5, then the model will select either A or B as the next token (using temperature).

verbose?: boolean