Generative Language API: Node.js Client

Generative Language API client for Node.js

A comprehensive list of changes in each version may be found in the CHANGELOG.

• [Generative Language API Node.js Client API Reference][client-docs]
• [Generative Language API Documentation][product-docs]
• github.com/googleapis/google-cloud-node/packages/google-ai-generativelanguage

Read more about the client libraries for Cloud APIs, including the older Google APIs Client Libraries, in Client Libraries Explained.

Table of contents:

• Quickstart
  • Before you begin
  • Installing the client library
  • Using the client library
• Samples
• Versioning
• Contributing
• License

Quickstart

Before you begin

1. [Select or create a Cloud Platform project][projects].
2. [Enable billing for your project][billing].
3. [Enable the Generative Language API API][enable_api].
4. [Set up authentication][auth] so you can access the API from your local workstation.

Installing the client library

npm install @google-ai/generativelanguage

Using the client library

/**
 * 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 name to use with the format name=models/{model}.
 */
// const model = 'abc123'
/**
 *  Required. The free-form input text given to the model as a prompt.
 *  Given a prompt, the model will generate a TextCompletion response it
 *  predicts as the completion of the input text.
 */
// const prompt = {
//  text: 'abc123'
// }
/**
 *  Controls the randomness of the output.
 *  Note: The default value varies by model, see the `Model.temperature`
 *  attribute of the `Model` returned the `getModel` function.
 *  Values can range from 0.0,1.0,
 *  inclusive. A value closer to 1.0 will produce responses that are more
 *  varied and creative, while a value closer to 0.0 will typically result in
 *  more straightforward responses from the model.
 */
// const temperature = 1234
/**
 *  Number of generated responses to return.
 *  This value must be between 1, 8, inclusive. If unset, this will default
 *  to 1.
 */
// const candidateCount = 1234
/**
 *  The maximum number of tokens to include in a candidate.
 *  If unset, this will default to 64.
 */
// const maxOutputTokens = 1234
/**
 *  The maximum cumulative probability of tokens to consider when sampling.
 *  The model uses combined Top-k and nucleus sampling.
 *  Tokens are sorted based on their assigned probabilities so that only the
 *  most liekly tokens are considered. Top-k sampling directly limits the
 *  maximum number of tokens to consider, while Nucleus sampling limits number
 *  of tokens based on the cumulative probability.
 *  Note: The default value varies by model, see the `Model.top_p`
 *  attribute of the `Model` returned the `getModel` function.
 */
// const topP = 1234
/**
 *  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.
 *  Defaults to 40.
 *  Note: The default value varies by model, see the `Model.top_k`
 *  attribute of the `Model` returned the `getModel` function.
 */
// const topK = 1234
/**
 *  The set of character sequences (up to 5) that will stop output generation.
 *  If specified, the API will stop at the first appearance of a stop
 *  sequence. The stop sequence will not be included as part of the response.
 */
// const stopSequences = 'abc123'

// Imports the Generativelanguage library
const {TextServiceClient} = require('@google-ai/generativelanguage').v1beta2;

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

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

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

callGenerateText();

Samples

Samples are in the samples/ directory. Each sample's README.md has instructions for running its sample.

Changelog

3.2.0 (2025-05-09)

Features

• [generativelanguage] add CODE_RETRIEVAL_QUERY embedding task type (#6307) (484c6e0)
• [generativelanguage] add support for live API (https://togithub.com/googleapis/go-genai/issues/275) (484c6e0)
• Add CODE_RETRIEVAL_QUERY embedding task type (484c6e0)
• Add language_code to speech config (484c6e0)
• Add minimum, maximum, any_of, property_ordering, default and null type to Schema (484c6e0)
• Add seed to GenerationConfig (484c6e0)
• Add support for ModalityTokenCounts in UsageMetadata responses (484c6e0)
• Add support for ModalityTokenCounts in UsageMetadata responses (484c6e0)
• Add support for Veo: PredictLongRunning and generated/downloadable files (484c6e0)
• Add ThinkingConfig, MediaResolution, and seed to GenerationConfig (484c6e0)

3.1.0 (2025-03-19)

Features

• [Many APIs] await/catch promises, and update listOperationsAsync return type (#6182) (c41ff07)

3.0.0 (2025-03-18)

⚠ BREAKING CHANGES

• upgrade to Node 18 (#6096)

Features

• [Many APIs] add request/response debug logging to gapics, update templates to gax 5 (54a73fe)

Miscellaneous Chores

• Upgrade to Node 18 (#6096) (eadae64)

2.9.1 (2025-02-12)

Bug Fixes

• [Many APIs] finalize fixing typings for headers in generator (#6011) (ee865ff)

2.9.0 (2025-01-11)

Features

• [generativelanguage] Add GoogleSearch tool type (#5929) (e5a665a)

2.8.0 (2024-11-21)

Features

• [generativelanguage] Adds search grounding (#5828) (0b27dc2)

2.7.0 (2024-10-10)

Features

• [generativelanguage] Add GoogleSearchRetrieval tool and candidate.grounding_metadata (#5699) (3eb6375)

2.6.0 (2024-06-26)

Features

• [generativelanguage] Add code execution (#5506) (13034af)
• [generativelanguage] Add content caching (#5451) (75c026f)

2.5.0 (2024-05-21)

Features

• [generativelanguage] Add video metadata to files API (#5359) (4185d57)
• [Many APIs] update Nodejs generator to send API versions in headers for GAPICs (#5350) (6c03873)
• [Many APIs] update Nodejs generator to send API versions in headers for GAPICs (#5351) (01f48fc)
• [Many APIs] update Nodejs generator to send API versions in headers for GAPICs (#5354) (a9784ed)

2.4.0 (2024-05-08)

Features

• Add FileState to File (#5312) (01f4b53)

2.3.0 (2024-04-18)

Features

• [generativelanguage] Add rest binding for tuned models (#5228) (b0ddbbe)

2.2.0 (2024-04-05)

Features

• [generativelanguage] Add system instructions (#5208) (54c5762)

2.1.1 (2024-03-26)

Bug Fixes

• [generativelanguage] make learning rate a one-of (#5142) (b2a5f9d)

2.1.0 (2024-02-09)

Features

• Trusted Private Cloud support, use the universeDomain parameter (#5022) (b6498d8)

2.0.1 (2024-01-23)

Bug Fixes

• [generativelanguage] improve retry logic for streaming API calls (#4955) (cafe82f)

2.0.0 (2023-12-11)

Features

• [generativelanguage] Add v1 and v1beta, adds GenerativeService and RetrievalService (#4879) (d98f897).
• BREAKING CHANGE: version v1beta is now the default version.

1.1.0 (2023-09-20)

Features

• [generativelanguage] Upgrade to API v1beta3 (#4681) (bf0f0e2)

1.0.1 (2023-09-06)

Bug Fixes

• [Many APIs] simplify logic for HTTP/1.1 REST fallback option (#4583) (c3ddba8)

1.0.0 (2023-08-06)

⚠ BREAKING CHANGES

• migrate to Node 14 (#4443)

Bug Fixes

• [Many APIs] fix typings for IAM methods (#4459) (1d510be)

Miscellaneous Chores

• Migrate to Node 14 (#4443) (2260f12)

0.2.1 (2023-07-04)

Bug Fixes

• [generativelanguage] Update safety protos (#4382) (d06c733)

0.2.0 (2023-05-06)

Features

• [generativelanguage] Add safety settings (#4248) (76b2df7)

0.1.1 (2023-05-04)

Bug Fixes

• docs: Fix sample links in README (#4236) (d852042)

0.1.0 (2023-05-02)

Features

• Add initial files for google.ai.generativelanguage.v1beta2 (#4224) (8db807a)