Class v1beta.DiscussServiceClient (2.6.0)

An API for using Generative Language Models (GLMs) in dialog applications.

Also known as large language models (LLMs), this API provides models that are trained for multi-turn dialog. v1beta

Package

Constructors

(constructor)(opts, gaxInstance)

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

Construct an instance of DiscussServiceClient.

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 DiscussServiceClient({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;

discussServiceStub

discussServiceStub?: 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

cachedContentPath(id)

cachedContentPath(id: string): string;

Return a fully-qualified cachedContent resource name string.

Parameter
Name	Description
`id`	`string`

Returns
Type	Description
`string`	{string} Resource name string.

chunkPath(corpus, document, chunk)

chunkPath(corpus: string, document: string, chunk: string): string;

Return a fully-qualified chunk resource name string.

Parameters
Name	Description
`corpus`	`string`
`document`	`string`
`chunk`	`string`

Returns
Type	Description
`string`	{string} Resource name string.

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.

corpusPath(corpus)

corpusPath(corpus: string): string;

Return a fully-qualified corpus resource name string.

Parameter
Name	Description
`corpus`	`string`

Returns
Type	Description
`string`	{string} Resource name string.

corpusPermissionPath(corpus, permission)

corpusPermissionPath(corpus: string, permission: string): string;

Return a fully-qualified corpusPermission resource name string.

Parameters
Name	Description
`corpus`	`string`
`permission`	`string`

Returns
Type	Description
`string`	{string} Resource name string.

countMessageTokens(request, options)

countMessageTokens(request?: protos.google.ai.generativelanguage.v1beta.ICountMessageTokensRequest, options?: CallOptions): Promise<[
        protos.google.ai.generativelanguage.v1beta.ICountMessageTokensResponse,
        (protos.google.ai.generativelanguage.v1beta.ICountMessageTokensRequest | undefined),
        {} | undefined
    ]>;

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

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

Returns
Type	Description
`Promise<[ protos.google.ai.generativelanguage.v1beta.ICountMessageTokensResponse, (protos.google.ai.generativelanguage.v1beta.ICountMessageTokensRequest \| undefined), {} \| undefined ]>`	{Promise} - The promise which resolves to an array. The first element of the array is an object representing CountMessageTokensResponse. 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 prompt, whose token count is to be returned.
   */
  // const prompt = {}

  // Imports the Generativelanguage library
  const {DiscussServiceClient} = require('@google-ai/generativelanguage').v1beta;

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

  async function callCountMessageTokens() {
    // Construct request
    const request = {
      model,
      prompt,
    };

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

  callCountMessageTokens();

countMessageTokens(request, options, callback)

countMessageTokens(request: protos.google.ai.generativelanguage.v1beta.ICountMessageTokensRequest, options: CallOptions, callback: Callback<protos.google.ai.generativelanguage.v1beta.ICountMessageTokensResponse, protos.google.ai.generativelanguage.v1beta.ICountMessageTokensRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
`request`	`ICountMessageTokensRequest`
`options`	`CallOptions`
`callback`	`Callback<protos.google.ai.generativelanguage.v1beta.ICountMessageTokensResponse, protos.google.ai.generativelanguage.v1beta.ICountMessageTokensRequest \| null \| undefined, {} \| null \| undefined>`

Returns
Type	Description
`void`

countMessageTokens(request, callback)

countMessageTokens(request: protos.google.ai.generativelanguage.v1beta.ICountMessageTokensRequest, callback: Callback<protos.google.ai.generativelanguage.v1beta.ICountMessageTokensResponse, protos.google.ai.generativelanguage.v1beta.ICountMessageTokensRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
`request`	`ICountMessageTokensRequest`
`callback`	`Callback<protos.google.ai.generativelanguage.v1beta.ICountMessageTokensResponse, protos.google.ai.generativelanguage.v1beta.ICountMessageTokensRequest \| null \| undefined, {} \| null \| undefined>`

Returns
Type	Description
`void`

documentPath(corpus, document)

documentPath(corpus: string, document: string): string;

Return a fully-qualified document resource name string.

Parameters
Name	Description
`corpus`	`string`
`document`	`string`

Returns
Type	Description
`string`	{string} Resource name string.

filePath(file)

filePath(file: string): string;

Return a fully-qualified file resource name string.

Parameter
Name	Description
`file`	`string`

Returns
Type	Description
`string`	{string} Resource name string.

generateMessage(request, options)

generateMessage(request?: protos.google.ai.generativelanguage.v1beta.IGenerateMessageRequest, options?: CallOptions): Promise<[
        protos.google.ai.generativelanguage.v1beta.IGenerateMessageResponse,
        (protos.google.ai.generativelanguage.v1beta.IGenerateMessageRequest | undefined),
        {} | undefined
    ]>;

Generates a response from the model given an input MessagePrompt.

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

Returns
Type	Description
`Promise<[ protos.google.ai.generativelanguage.v1beta.IGenerateMessageResponse, (protos.google.ai.generativelanguage.v1beta.IGenerateMessageRequest \| undefined), {} \| undefined ]>`	{Promise} - The promise which resolves to an array. The first element of the array is an object representing GenerateMessageResponse. 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.
   *  Format: `name=models/{model}`.
   */
  // const model = 'abc123'
  /**
   *  Required. The structured textual input given to the model as a prompt.
   *  Given a
   *  prompt, the model will return what it predicts is the next message in the
   *  discussion.
   */
  // const prompt = {}
  /**
   *  Optional. Controls the randomness of the output.
   *  Values can range over `[0.0,1.0]`,
   *  inclusive. A value closer to `1.0` will produce responses that are more
   *  varied, while a value closer to `0.0` will typically result in
   *  less surprising responses from the model.
   */
  // const temperature = 1234
  /**
   *  Optional. The number of generated response messages to return.
   *  This value must be between
   *  `[1, 8]`, inclusive. If unset, this will default to `1`.
   */
  // const candidateCount = 1234
  /**
   *  Optional. The maximum cumulative probability of tokens to consider when
   *  sampling.
   *  The model uses combined Top-k and nucleus sampling.
   *  Nucleus sampling considers the smallest set of tokens whose probability
   *  sum is at least `top_p`.
   */
  // const topP = 1234
  /**
   *  Optional. The maximum number of tokens to consider when sampling.
   *  The model uses combined Top-k and nucleus sampling.
   *  Top-k sampling considers the set of `top_k` most probable tokens.
   */
  // const topK = 1234

  // Imports the Generativelanguage library
  const {DiscussServiceClient} = require('@google-ai/generativelanguage').v1beta;

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

  async function callGenerateMessage() {
    // Construct request
    const request = {
      model,
      prompt,
    };

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

  callGenerateMessage();

generateMessage(request, options, callback)

generateMessage(request: protos.google.ai.generativelanguage.v1beta.IGenerateMessageRequest, options: CallOptions, callback: Callback<protos.google.ai.generativelanguage.v1beta.IGenerateMessageResponse, protos.google.ai.generativelanguage.v1beta.IGenerateMessageRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
`request`	`IGenerateMessageRequest`
`options`	`CallOptions`
`callback`	`Callback<protos.google.ai.generativelanguage.v1beta.IGenerateMessageResponse, protos.google.ai.generativelanguage.v1beta.IGenerateMessageRequest \| null \| undefined, {} \| null \| undefined>`

Returns
Type	Description
`void`

generateMessage(request, callback)

generateMessage(request: protos.google.ai.generativelanguage.v1beta.IGenerateMessageRequest, callback: Callback<protos.google.ai.generativelanguage.v1beta.IGenerateMessageResponse, protos.google.ai.generativelanguage.v1beta.IGenerateMessageRequest | null | undefined, {} | null | undefined>): void;

Parameters
Name	Description
`request`	`IGenerateMessageRequest`
`callback`	`Callback<protos.google.ai.generativelanguage.v1beta.IGenerateMessageResponse, protos.google.ai.generativelanguage.v1beta.IGenerateMessageRequest \| 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.

matchChunkFromChunkName(chunkName)

matchChunkFromChunkName(chunkName: string): string | number;

Parse the chunk from Chunk resource.

Parameter
Name	Description
`chunkName`	`string` A fully-qualified path representing Chunk resource.

Returns
Type	Description
`string \| number`	{string} A string representing the chunk.

matchCorpusFromChunkName(chunkName)

matchCorpusFromChunkName(chunkName: string): string | number;

Parse the corpus from Chunk resource.

Parameter
Name	Description
`chunkName`	`string` A fully-qualified path representing Chunk resource.

Returns
Type	Description
`string \| number`	{string} A string representing the corpus.

matchCorpusFromCorpusName(corpusName)

matchCorpusFromCorpusName(corpusName: string): string | number;

Parse the corpus from Corpus resource.

Parameter
Name	Description
`corpusName`	`string` A fully-qualified path representing Corpus resource.

Returns
Type	Description
`string \| number`	{string} A string representing the corpus.

matchCorpusFromCorpusPermissionName(corpusPermissionName)

matchCorpusFromCorpusPermissionName(corpusPermissionName: string): string | number;

Parse the corpus from CorpusPermission resource.

Parameter
Name	Description
`corpusPermissionName`	`string` A fully-qualified path representing corpus_permission resource.

Returns
Type	Description
`string \| number`	{string} A string representing the corpus.

matchCorpusFromDocumentName(documentName)

matchCorpusFromDocumentName(documentName: string): string | number;

Parse the corpus from Document resource.

Parameter
Name	Description
`documentName`	`string` A fully-qualified path representing Document resource.

Returns
Type	Description
`string \| number`	{string} A string representing the corpus.

matchDocumentFromChunkName(chunkName)

matchDocumentFromChunkName(chunkName: string): string | number;

Parse the document from Chunk resource.

Parameter
Name	Description
`chunkName`	`string` A fully-qualified path representing Chunk resource.

Returns
Type	Description
`string \| number`	{string} A string representing the document.

matchDocumentFromDocumentName(documentName)

matchDocumentFromDocumentName(documentName: string): string | number;

Parse the document from Document resource.

Parameter
Name	Description
`documentName`	`string` A fully-qualified path representing Document resource.

Returns
Type	Description
`string \| number`	{string} A string representing the document.

matchFileFromFileName(fileName)

matchFileFromFileName(fileName: string): string | number;

Parse the file from File resource.

Parameter
Name	Description
`fileName`	`string` A fully-qualified path representing File resource.

Returns
Type	Description
`string \| number`	{string} A string representing the file.

matchIdFromCachedContentName(cachedContentName)

matchIdFromCachedContentName(cachedContentName: string): string | number;

Parse the id from CachedContent resource.

Parameter
Name	Description
`cachedContentName`	`string` A fully-qualified path representing CachedContent resource.

Returns
Type	Description
`string \| number`	{string} A string representing the id.

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.

matchPermissionFromCorpusPermissionName(corpusPermissionName)

matchPermissionFromCorpusPermissionName(corpusPermissionName: string): string | number;

Parse the permission from CorpusPermission resource.

Parameter
Name	Description
`corpusPermissionName`	`string` A fully-qualified path representing corpus_permission resource.

Returns
Type	Description
`string \| number`	{string} A string representing the permission.

matchPermissionFromTunedModelPermissionName(tunedModelPermissionName)

matchPermissionFromTunedModelPermissionName(tunedModelPermissionName: string): string | number;

Parse the permission from TunedModelPermission resource.

Parameter
Name	Description
`tunedModelPermissionName`	`string` A fully-qualified path representing tuned_model_permission resource.

Returns
Type	Description
`string \| number`	{string} A string representing the permission.

matchTunedModelFromTunedModelName(tunedModelName)

matchTunedModelFromTunedModelName(tunedModelName: string): string | number;

Parse the tuned_model from TunedModel resource.

Parameter
Name	Description
`tunedModelName`	`string` A fully-qualified path representing TunedModel resource.

Returns
Type	Description
`string \| number`	{string} A string representing the tuned_model.

matchTunedModelFromTunedModelPermissionName(tunedModelPermissionName)

matchTunedModelFromTunedModelPermissionName(tunedModelPermissionName: string): string | number;

Parse the tuned_model from TunedModelPermission resource.

Parameter
Name	Description
`tunedModelPermissionName`	`string` A fully-qualified path representing tuned_model_permission resource.

Returns
Type	Description
`string \| number`	{string} A string representing the tuned_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.

tunedModelPath(tunedModel)

tunedModelPath(tunedModel: string): string;

Return a fully-qualified tunedModel resource name string.

Parameter
Name	Description
`tunedModel`	`string`

Returns
Type	Description
`string`	{string} Resource name string.

tunedModelPermissionPath(tunedModel, permission)

tunedModelPermissionPath(tunedModel: string, permission: string): string;

Return a fully-qualified tunedModelPermission resource name string.

Parameters
Name	Description
`tunedModel`	`string`
`permission`	`string`

Returns
Type	Description
`string`	{string} Resource name string.