Class v1.GenerativeServiceClient (2.4.0)

Version latest

• 2.4.0 (latest)
• 2.3.0

API for using Large Models that generate multimodal content and have additional capabilities beyond text generation. v1

Package

@google-ai/generativelanguage

Constructors

(constructor)(opts, gaxInstance)

constructor(opts?: ClientOptions, gaxInstance?: typeof gax | typeof gax.fallback);

Construct an instance of GenerativeServiceClient.

Parameters
Name	Description
opts	ClientOptions
gaxInstance	typeof gax | typeof fallback : loaded instance of google-gax. Useful if you need to avoid loading the default gRPC version and want to use the fallback HTTP implementation. Load only fallback version and pass it to the constructor: ``` const gax = require('google-gax/build/src/fallback'); // avoids loading google-gax with gRPC const client = new GenerativeServiceClient({fallback: true}, gax); ```

Properties

apiEndpoint

get apiEndpoint(): string;

The DNS address for this API service.

apiEndpoint

static get apiEndpoint(): string;

The DNS address for this API service - same as servicePath.

auth

auth: gax.GoogleAuth;

descriptors

descriptors: Descriptors;

generativeServiceStub

generativeServiceStub?: Promise<{
        [name: string]: Function;
    }>;

innerApiCalls

innerApiCalls: {
        [name: string]: Function;
    };

pathTemplates

pathTemplates: {
        [name: string]: gax.PathTemplate;
    };

port

static get port(): number;

The port for this API service.

scopes

static get scopes(): never[];

The scopes needed to make gRPC calls for every method defined in this service.

servicePath

static get servicePath(): string;

The DNS address for this API service.

universeDomain

get universeDomain(): string;

warn

warn: (code: string, message: string, warnType?: string) => void;

Methods

batchEmbedContents(request, options)

batchEmbedContents(request?: protos.google.ai.generativelanguage.v1.IBatchEmbedContentsRequest, options?: CallOptions): Promise<[
        protos.google.ai.generativelanguage.v1.IBatchEmbedContentsResponse,
        (protos.google.ai.generativelanguage.v1.IBatchEmbedContentsRequest | undefined),
        {} | undefined
    ]>;

Generates multiple embeddings from the model given input text in a synchronous call.

Parameters
Name	Description
request	IBatchEmbedContentsRequest The request object that will be sent.
options	CallOptions Call options. See CallOptions for more details.

Returns
Type	Description
Promise<[ protos.google.ai.generativelanguage.v1.IBatchEmbedContentsResponse, (protos.google.ai.generativelanguage.v1.IBatchEmbedContentsRequest | undefined), {} | undefined ]>	{Promise} - The promise which resolves to an array. The first element of the array is an object representing BatchEmbedContentsResponse. Please see the documentation for more details and examples.

Example

  /**
   * This snippet has been automatically generated and should be regarded as a code template only.
   * It will require modifications to work.
   * It may require correct/in-range values for request initialization.
   * TODO(developer): Uncomment these variables before running the sample.
   */
  /**
   *  Required. The model's resource name. This serves as an ID for the Model to
   *  use.
   *  This name should match a model name returned by the `ListModels` method.
   *  Format: `models/{model}`
   */
  // const model = 'abc123'
  /**
   *  Required. Embed requests for the batch. The model in each of these requests
   *  must match the model specified `BatchEmbedContentsRequest.model`.
   */
  // const requests = [1,2,3,4]

  // Imports the Generativelanguage library
  const {GenerativeServiceClient} = require('@google-ai/generativelanguage').v1;

  // Instantiates a client
  const generativelanguageClient = new GenerativeServiceClient();

  async function callBatchEmbedContents() {
    // Construct request
    const request = {
      model,
      requests,
    };

    // Run request
    const response = await generativelanguageClient.batchEmbedContents(request);
    console.log(response);
  }

  callBatchEmbedContents();

batchEmbedContents(request, options, callback)

batchEmbedContents(request: protos.google.ai.generativelanguage.v1.IBatchEmbedContentsRequest, options: CallOptions, callback: Callback<protos.google.ai.generativelanguage.v1.IBatchEmbedContentsResponse, protos.google.ai.generativelanguage.v1.IBatchEmbedContentsRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
request	IBatchEmbedContentsRequest
options	CallOptions
callback	Callback<protos.google.ai.generativelanguage.v1.IBatchEmbedContentsResponse, protos.google.ai.generativelanguage.v1.IBatchEmbedContentsRequest | null | undefined, {} | null | undefined>

Returns
Type	Description
void

batchEmbedContents(request, callback)

batchEmbedContents(request: protos.google.ai.generativelanguage.v1.IBatchEmbedContentsRequest, callback: Callback<protos.google.ai.generativelanguage.v1.IBatchEmbedContentsResponse, protos.google.ai.generativelanguage.v1.IBatchEmbedContentsRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
request	IBatchEmbedContentsRequest
callback	Callback<protos.google.ai.generativelanguage.v1.IBatchEmbedContentsResponse, protos.google.ai.generativelanguage.v1.IBatchEmbedContentsRequest | null | undefined, {} | null | undefined>

Returns
Type	Description
void

close()

close(): Promise<void>;

Terminate the gRPC channel and close the client.

The client will no longer be usable and all future behavior is undefined.

Returns
Type	Description
Promise<void>	{Promise} A promise that resolves when the client is closed.

countTokens(request, options)

countTokens(request?: protos.google.ai.generativelanguage.v1.ICountTokensRequest, options?: CallOptions): Promise<[
        protos.google.ai.generativelanguage.v1.ICountTokensResponse,
        protos.google.ai.generativelanguage.v1.ICountTokensRequest | undefined,
        {} | undefined
    ]>;

Runs a model's tokenizer on input content and returns the token count.

Parameters
Name	Description
request	ICountTokensRequest The request object that will be sent.
options	CallOptions Call options. See CallOptions for more details.

Returns
Type	Description
Promise<[ protos.google.ai.generativelanguage.v1.ICountTokensResponse, protos.google.ai.generativelanguage.v1.ICountTokensRequest | undefined, {} | undefined ]>	{Promise} - The promise which resolves to an array. The first element of the array is an object representing CountTokensResponse. Please see the documentation for more details and examples.

Example

  /**
   * This snippet has been automatically generated and should be regarded as a code template only.
   * It will require modifications to work.
   * It may require correct/in-range values for request initialization.
   * TODO(developer): Uncomment these variables before running the sample.
   */
  /**
   *  Required. The model's resource name. This serves as an ID for the Model to
   *  use.
   *  This name should match a model name returned by the `ListModels` method.
   *  Format: `models/{model}`
   */
  // const model = 'abc123'
  /**
   *  Required. The input given to the model as a prompt.
   */
  // const contents = [1,2,3,4]

  // Imports the Generativelanguage library
  const {GenerativeServiceClient} = require('@google-ai/generativelanguage').v1;

  // Instantiates a client
  const generativelanguageClient = new GenerativeServiceClient();

  async function callCountTokens() {
    // Construct request
    const request = {
      model,
      contents,
    };

    // Run request
    const response = await generativelanguageClient.countTokens(request);
    console.log(response);
  }

  callCountTokens();

countTokens(request, options, callback)

countTokens(request: protos.google.ai.generativelanguage.v1.ICountTokensRequest, options: CallOptions, callback: Callback<protos.google.ai.generativelanguage.v1.ICountTokensResponse, protos.google.ai.generativelanguage.v1.ICountTokensRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
request	ICountTokensRequest
options	CallOptions
callback	Callback<protos.google.ai.generativelanguage.v1.ICountTokensResponse, protos.google.ai.generativelanguage.v1.ICountTokensRequest | null | undefined, {} | null | undefined>

Returns
Type	Description
void

countTokens(request, callback)

countTokens(request: protos.google.ai.generativelanguage.v1.ICountTokensRequest, callback: Callback<protos.google.ai.generativelanguage.v1.ICountTokensResponse, protos.google.ai.generativelanguage.v1.ICountTokensRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
request	ICountTokensRequest
callback	Callback<protos.google.ai.generativelanguage.v1.ICountTokensResponse, protos.google.ai.generativelanguage.v1.ICountTokensRequest | null | undefined, {} | null | undefined>

Returns
Type	Description
void

embedContent(request, options)

embedContent(request?: protos.google.ai.generativelanguage.v1.IEmbedContentRequest, options?: CallOptions): Promise<[
        protos.google.ai.generativelanguage.v1.IEmbedContentResponse,
        protos.google.ai.generativelanguage.v1.IEmbedContentRequest | undefined,
        {} | undefined
    ]>;

Generates an embedding from the model given an input Content.

Parameters
Name	Description
request	IEmbedContentRequest The request object that will be sent.
options	CallOptions Call options. See CallOptions for more details.

Returns
Type	Description
Promise<[ protos.google.ai.generativelanguage.v1.IEmbedContentResponse, protos.google.ai.generativelanguage.v1.IEmbedContentRequest | undefined, {} | undefined ]>	{Promise} - The promise which resolves to an array. The first element of the array is an object representing EmbedContentResponse. Please see the documentation for more details and examples.

Example

  /**
   * This snippet has been automatically generated and should be regarded as a code template only.
   * It will require modifications to work.
   * It may require correct/in-range values for request initialization.
   * TODO(developer): Uncomment these variables before running the sample.
   */
  /**
   *  Required. The model's resource name. This serves as an ID for the Model to
   *  use.
   *  This name should match a model name returned by the `ListModels` method.
   *  Format: `models/{model}`
   */
  // const model = 'abc123'
  /**
   *  Required. The content to embed. Only the `parts.text` fields will be
   *  counted.
   */
  // const content = {}
  /**
   *  Optional. Optional task type for which the embeddings will be used. Can
   *  only be set for `models/embedding-001`.
   */
  // const taskType = {}
  /**
   *  Optional. An optional title for the text. Only applicable when TaskType is
   *  `RETRIEVAL_DOCUMENT`.
   *  Note: Specifying a `title` for `RETRIEVAL_DOCUMENT` provides better quality
   *  embeddings for retrieval.
   */
  // const title = 'abc123'
  /**
   *  Optional. Optional reduced dimension for the output embedding. If set,
   *  excessive values in the output embedding are truncated from the end.
   *  Supported by `models/text-embedding-latest`.
   */
  // const outputDimensionality = 1234

  // Imports the Generativelanguage library
  const {GenerativeServiceClient} = require('@google-ai/generativelanguage').v1;

  // Instantiates a client
  const generativelanguageClient = new GenerativeServiceClient();

  async function callEmbedContent() {
    // Construct request
    const request = {
      model,
      content,
    };

    // Run request
    const response = await generativelanguageClient.embedContent(request);
    console.log(response);
  }

  callEmbedContent();

embedContent(request, options, callback)

embedContent(request: protos.google.ai.generativelanguage.v1.IEmbedContentRequest, options: CallOptions, callback: Callback<protos.google.ai.generativelanguage.v1.IEmbedContentResponse, protos.google.ai.generativelanguage.v1.IEmbedContentRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
request	IEmbedContentRequest
options	CallOptions
callback	Callback<protos.google.ai.generativelanguage.v1.IEmbedContentResponse, protos.google.ai.generativelanguage.v1.IEmbedContentRequest | null | undefined, {} | null | undefined>

Returns
Type	Description
void

embedContent(request, callback)

embedContent(request: protos.google.ai.generativelanguage.v1.IEmbedContentRequest, callback: Callback<protos.google.ai.generativelanguage.v1.IEmbedContentResponse, protos.google.ai.generativelanguage.v1.IEmbedContentRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
request	IEmbedContentRequest
callback	Callback<protos.google.ai.generativelanguage.v1.IEmbedContentResponse, protos.google.ai.generativelanguage.v1.IEmbedContentRequest | null | undefined, {} | null | undefined>

Returns
Type	Description
void

generateContent(request, options)

generateContent(request?: protos.google.ai.generativelanguage.v1.IGenerateContentRequest, options?: CallOptions): Promise<[
        protos.google.ai.generativelanguage.v1.IGenerateContentResponse,
        (protos.google.ai.generativelanguage.v1.IGenerateContentRequest | undefined),
        {} | undefined
    ]>;

Generates a response from the model given an input GenerateContentRequest.

Parameters
Name	Description
request	IGenerateContentRequest The request object that will be sent.
options	CallOptions Call options. See CallOptions for more details.

Returns
Type	Description
Promise<[ protos.google.ai.generativelanguage.v1.IGenerateContentResponse, (protos.google.ai.generativelanguage.v1.IGenerateContentRequest | undefined), {} | undefined ]>	{Promise} - The promise which resolves to an array. The first element of the array is an object representing . Please see the documentation for more details and examples.

Example

  /**
   * This snippet has been automatically generated and should be regarded as a code template only.
   * It will require modifications to work.
   * It may require correct/in-range values for request initialization.
   * TODO(developer): Uncomment these variables before running the sample.
   */
  /**
   *  Required. The name of the `Model` to use for generating the completion.
   *  Format: `name=models/{model}`.
   */
  // const model = 'abc123'
  /**
   *  Required. The content of the current conversation with the model.
   *  For single-turn queries, this is a single instance. For multi-turn queries,
   *  this is a repeated field that contains conversation history + latest
   *  request.
   */
  // const contents = [1,2,3,4]
  /**
   *  Optional. A list of unique `SafetySetting` instances for blocking unsafe
   *  content.
   *  This will be enforced on the `GenerateContentRequest.contents` and
   *  `GenerateContentResponse.candidates`. There should not be more than one
   *  setting for each `SafetyCategory` type. The API will block any contents and
   *  responses that fail to meet the thresholds set by these settings. This list
   *  overrides the default settings for each `SafetyCategory` specified in the
   *  safety_settings. If there is no `SafetySetting` for a given
   *  `SafetyCategory` provided in the list, the API will use the default safety
   *  setting for that category. Harm categories HARM_CATEGORY_HATE_SPEECH,
   *  HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_DANGEROUS_CONTENT,
   *  HARM_CATEGORY_HARASSMENT are supported.
   */
  // const safetySettings = [1,2,3,4]
  /**
   *  Optional. Configuration options for model generation and outputs.
   */
  // const generationConfig = {}

  // Imports the Generativelanguage library
  const {GenerativeServiceClient} = require('@google-ai/generativelanguage').v1;

  // Instantiates a client
  const generativelanguageClient = new GenerativeServiceClient();

  async function callGenerateContent() {
    // Construct request
    const request = {
      model,
      contents,
    };

    // Run request
    const response = await generativelanguageClient.generateContent(request);
    console.log(response);
  }

  callGenerateContent();

generateContent(request, options, callback)

generateContent(request: protos.google.ai.generativelanguage.v1.IGenerateContentRequest, options: CallOptions, callback: Callback<protos.google.ai.generativelanguage.v1.IGenerateContentResponse, protos.google.ai.generativelanguage.v1.IGenerateContentRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
request	IGenerateContentRequest
options	CallOptions
callback	Callback<protos.google.ai.generativelanguage.v1.IGenerateContentResponse, protos.google.ai.generativelanguage.v1.IGenerateContentRequest | null | undefined, {} | null | undefined>

Returns
Type	Description
void

generateContent(request, callback)

generateContent(request: protos.google.ai.generativelanguage.v1.IGenerateContentRequest, callback: Callback<protos.google.ai.generativelanguage.v1.IGenerateContentResponse, protos.google.ai.generativelanguage.v1.IGenerateContentRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
request	IGenerateContentRequest
callback	Callback<protos.google.ai.generativelanguage.v1.IGenerateContentResponse, protos.google.ai.generativelanguage.v1.IGenerateContentRequest | null | undefined, {} | null | undefined>

Returns
Type	Description
void

getProjectId()

getProjectId(): Promise<string>;

Returns
Type	Description
Promise<string>

getProjectId(callback)

getProjectId(callback: Callback<string, undefined, undefined>): void;

Parameter
Name	Description
callback	Callback<string, undefined, undefined>

Returns
Type	Description
void

initialize()

initialize(): Promise<{
        [name: string]: Function;
    }>;

Initialize the client. Performs asynchronous operations (such as authentication) and prepares the client. This function will be called automatically when any class method is called for the first time, but if you need to initialize it before calling an actual method, feel free to call initialize() directly.

You can await on this method if you want to make sure the client is initialized.

Returns
Type	Description
Promise<{ [name: string]: Function; }>	{Promise} A promise that resolves to an authenticated service stub.

matchModelFromModelName(modelName)

matchModelFromModelName(modelName: string): string | number;

Parse the model from Model resource.

Parameter
Name	Description
modelName	string A fully-qualified path representing Model resource.

Returns
Type	Description
string | number	{string} A string representing the model.

modelPath(model)

modelPath(model: string): string;

Return a fully-qualified model resource name string.

Parameter
Name	Description
model	string

Returns
Type	Description
string	{string} Resource name string.

streamGenerateContent(request, options)

streamGenerateContent(request?: protos.google.ai.generativelanguage.v1.IGenerateContentRequest, options?: CallOptions): gax.CancellableStream;

Generates a streamed response from the model given an input GenerateContentRequest.

Parameters
Name	Description
request	IGenerateContentRequest The request object that will be sent.
options	CallOptions Call options. See CallOptions for more details.

Returns
Type	Description
gax.CancellableStream	{Stream} An object stream which emits on 'data' event. Please see the documentation for more details and examples.

Example

  /**
   * This snippet has been automatically generated and should be regarded as a code template only.
   * It will require modifications to work.
   * It may require correct/in-range values for request initialization.
   * TODO(developer): Uncomment these variables before running the sample.
   */
  /**
   *  Required. The name of the `Model` to use for generating the completion.
   *  Format: `name=models/{model}`.
   */
  // const model = 'abc123'
  /**
   *  Required. The content of the current conversation with the model.
   *  For single-turn queries, this is a single instance. For multi-turn queries,
   *  this is a repeated field that contains conversation history + latest
   *  request.
   */
  // const contents = [1,2,3,4]
  /**
   *  Optional. A list of unique `SafetySetting` instances for blocking unsafe
   *  content.
   *  This will be enforced on the `GenerateContentRequest.contents` and
   *  `GenerateContentResponse.candidates`. There should not be more than one
   *  setting for each `SafetyCategory` type. The API will block any contents and
   *  responses that fail to meet the thresholds set by these settings. This list
   *  overrides the default settings for each `SafetyCategory` specified in the
   *  safety_settings. If there is no `SafetySetting` for a given
   *  `SafetyCategory` provided in the list, the API will use the default safety
   *  setting for that category. Harm categories HARM_CATEGORY_HATE_SPEECH,
   *  HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_DANGEROUS_CONTENT,
   *  HARM_CATEGORY_HARASSMENT are supported.
   */
  // const safetySettings = [1,2,3,4]
  /**
   *  Optional. Configuration options for model generation and outputs.
   */
  // const generationConfig = {}

  // Imports the Generativelanguage library
  const {GenerativeServiceClient} = require('@google-ai/generativelanguage').v1;

  // Instantiates a client
  const generativelanguageClient = new GenerativeServiceClient();

  async function callStreamGenerateContent() {
    // Construct request
    const request = {
      model,
      contents,
    };

    // Run request
    const stream = await generativelanguageClient.streamGenerateContent(request);
    stream.on('data', (response) => { console.log(response) });
    stream.on('error', (err) => { throw(err) });
    stream.on('end', () => { /* API call completed */ });
  }

  callStreamGenerateContent();