### Quickstart Example

Source: https://googleapis.github.io/js-genai

A simple example demonstrating how to get started with the SDK using an API key from Google AI Studio.

```APIDOC
## Quickstart
The simplest way to get started is to use an API key from Google AI Studio:
```typescript
import {GoogleGenAI} from '@google/genai';  
const GEMINI_API_KEY = process.env.GEMINI_API_KEY;  
  
const ai = new GoogleGenAI({apiKey: GEMINI_API_KEY});  
  
async function main() {
  const response = await ai.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: 'Why is the sky blue?',
  });
  console.log(response.text);
}

main();
```
```

--------------------------------

### Quickstart: Generate Content with API Key

Source: https://googleapis.github.io/js-genai

A simple example to get started using an API key from Google AI Studio to generate content. Ensure your API key is stored in the GEMINI_API_KEY environment variable.

```typescript
import {GoogleGenAI} from '@google/genai';
const GEMINI_API_KEY = process.env.GEMINI_API_KEY;

const ai = new GoogleGenAI({apiKey: GEMINI_API_KEY});

async function main() {
  const response = await ai.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: 'Why is the sky blue?',
  });
  console.log(response.text);
}

main();
```

--------------------------------

### Quickstart: Generate Content with API Key

Source: https://googleapis.github.io/js-genai/release_docs/index.html

A simple example demonstrating how to initialize the SDK with an API key and generate content. This is suitable for quick testing and development.

```typescript
import {GoogleGenAI} from '@google/genai';
const GEMINI_API_KEY = process.env.GEMINI_API_KEY;

const ai = new GoogleGenAI({apiKey: GEMINI_API_KEY});

async function main() {
  const response = await ai.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: 'Why is the sky blue?',
  });
  console.log(response.text);
}

main();
Copy

```

--------------------------------

### Install @google/genai SDK

Source: https://googleapis.github.io/js-genai/release_docs/index.html

Install the Google Gen AI SDK using npm. Ensure Node.js version 20 or later is installed.

```bash
npm install @google/genai
Copy

```

--------------------------------

### Install @google/genai SDK

Source: https://googleapis.github.io/js-genai

Install the Google Gen AI SDK using npm. Ensure you have Node.js version 20 or later.

```bash
npm install @google/genai
```

--------------------------------

### gRPC Service Example with google.protobuf.Empty

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/interactions_client.GeminiNextGenAPIClient.Webhooks.WebhookDeleteResponse.html

This example demonstrates how to use google.protobuf.Empty as both the request and response type for a gRPC service method.

```proto
service Foo {
  rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);
}

```

--------------------------------

### Enum Schema Examples

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.Schema.html

Examples showing how to define enum constraints for string and integer types.

```json
{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}
```

```json
{type:INTEGER, format:enum, enum:["101", "201", "301"]}
```

--------------------------------

### ReinforcementTuningExample Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.ReinforcementTuningExample.html

Defines the structure for reinforcement tuning examples on Vertex AI.

```APIDOC
## Interface ReinforcementTuningExample
User-facing format for Gemini Reinforcement Tuning examples on Vertex.

### Properties
* `contents` (Content[]) - Optional - Multi-turn contents that represents the Prompt.
* `references` (Record<string, string>) - Optional - References for the given prompt. The key is the name of the reference, and the value is the reference itself.
* `systemInstruction` (Content) - Optional - Corresponds to `system_instruction` in user-facing GenerateContentRequest.
```

--------------------------------

### ToolCall Arguments Example

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.ToolCall.html

Example of the structure for the optional args property.

```json
{"arg1": "value1", "arg2": "value2"}
```

--------------------------------

### Example: FileSearch with Store Names

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.FileSearch.html

Specify the required file search store names when initializing the FileSearch tool. Example: `fileSearchStores/my-file-search-store-123`.

```typescript
fileSearchStoreNames: ["fileSearchStores/my-file-search-store-123"]
```

--------------------------------

### get

Source: https://googleapis.github.io/js-genai/release_docs/classes/filesearchstores.FileSearchStores.html

Gets a File Search Store.

```APIDOC
## get
  * get(params: GetFileSearchStoreParameters): Promise<FileSearchStore>
Gets a File Search Store.
#### Parameters
    * params: GetFileSearchStoreParameters
The parameters for getting a File Search Store.
#### Returns Promise<FileSearchStore>
FileSearchStore.
```

--------------------------------

### Interface ActivityStart

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.ActivityStart.html

Documentation for the ActivityStart interface, which marks the start of user activity when server-side detection is disabled.

```APIDOC
## Interface ActivityStart

### Description
Marks the start of user activity. This can only be sent if automatic (i.e. server-side) activity detection is disabled.
```

--------------------------------

### Initializing for Vertex AI API

Source: https://googleapis.github.io/js-genai/release_docs/classes/client.GoogleGenAI.html

Example of initializing the GoogleGenAI SDK for use with the Vertex AI API by specifying project and location details.

```APIDOC
import {GoogleGenAI} from '@google/genai';  
const ai = new GoogleGenAI({
  vertexai: true,  
  project: 'PROJECT_ID',  
  location: 'PROJECT_LOCATION'
});
```

--------------------------------

### get

Source: https://googleapis.github.io/js-genai/release_docs/classes/tunings.Tunings.html

Gets a specific TuningJob by its parameters. Note that this method is experimental.

```APIDOC
## get

### Description
Gets a TuningJob. This method is experimental and may change in future versions.

### Method
GET

### Endpoint
/v1beta/tunings/{name}

### Parameters
#### Path Parameters
- **name** (string) - Required - The resource name of the TuningJob to retrieve.

#### Query Parameters
None

#### Request Body
None

### Request Example
```json
{
  "name": "tunings/your-tuning-job-id"
}
```

### Response
#### Success Response (200)
- **TuningJob** (object) - A TuningJob object.

#### Response Example
```json
{
  "name": "tunings/your-tuning-job-id",
  "state": "SUCCEEDED",
  "createTime": "2023-10-27T10:00:00Z",
  "updateTime": "2023-10-27T10:05:00Z"
}
```
```

--------------------------------

### Example Usage of google.protobuf.Empty

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/interactions_client.GeminiNextGenAPIClient.Agents.AgentDeleteResponse.html

Illustrates how google.protobuf.Empty can be used as request and response types in service definitions.

```proto
service Foo {
  rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);
}

```

--------------------------------

### Integrate MCP Server with Model Context Protocol

Source: https://googleapis.github.io/js-genai

Utilize the experimental Model Context Protocol (MCP) support by passing a local MCP server as a tool. This example demonstrates setting up a client, connecting to an MCP server via stdio, and sending a request to the model with MCP tools.

```javascript
import { GoogleGenAI, FunctionCallingConfigMode , mcpToTool} from '@google/genai';
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

// Create server parameters for stdio connection
const serverParams = new StdioClientTransport({
  command: "npx", // Executable
  args: ["-y", "@philschmid/weather-mcp"] // MCP Server
});

const client = new Client(
  {
    name: "example-client",
    version: "1.0.0"
  }
);

// Configure the client
const ai = new GoogleGenAI({});

// Initialize the connection between client and server
await client.connect(serverParams);

// Send request to the model with MCP tools
const response = await ai.models.generateContent({
  model: "gemini-2.5-flash",
  contents: `What is the weather in London in ${new Date().toLocaleDateString()}?`,
  config: {
    tools: [mcpToTool(client)],  // uses the session, will automatically call the tool using automatic function calling
  },
});
console.log(response.text);

// Close the connection
await client.close();
```

--------------------------------

### Example Request Path

Source: https://googleapis.github.io/js-genai/release_docs/types/interactions_internal_request-options.RequestOptions.html

Specifies the URL path for a request. This is a common configuration when making API calls.

```string
"/v1/foo"
```

--------------------------------

### List Files with Pagination

Source: https://googleapis.github.io/js-genai/release_docs/classes/files.Files.html

Lists files with optional pagination. The example demonstrates how to set the page size and iterate through the returned files.

```typescript
const files = await ai.files.list({config: {'pageSize': 2}}); 
for await (const file of files) {
  console.log(file);
}
```

--------------------------------

### get

Source: https://googleapis.github.io/js-genai/release_docs/classes/files.Files.html

Retrieves the file information from the service.

```APIDOC
## get
  * get(params: GetFileParameters): Promise<File>
Retrieves the file information from the service.
#### Parameters
    * params: GetFileParameters
The parameters for the get request
#### Returns Promise<File>
The Promise that resolves to the types.File object requested.
#### Example
```
const config: GetFileParameters = {  
  name: fileName,  
};
file = await ai.files.get(config);  
console.log(file.name);
Copy
```
```

--------------------------------

### systemInstruction

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.GenerateContentConfig.html

Optional. Instructions provided to the model to guide its behavior and improve performance, such as setting a concise response style.

```APIDOC
### `Optional`systemInstruction
systemInstruction?: ContentUnion
Instructions for the model to steer it toward better performance. For example, "Answer as concisely as possible" or "Don't use technical terms in your response".
```

--------------------------------

### Manual Pagination Control

Source: https://googleapis.github.io/js-genai/release_docs/classes/pagers.Pager.html

This example demonstrates manual control over pagination. It fetches items page by page and checks for the existence of a next page before proceeding.

```javascript
const pager = await ai.files.list({config: {pageSize: 10}});  
let page = pager.page;  
while (true) {  
  for (const file of page) {  
    console.log(file.name);  
  }  
  if (!pager.hasNextPage()) {  
    break;  
  }  
  page = await pager.nextPage();  
}
```

--------------------------------

### Example: FileSearch with TopK

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.FileSearch.html

Set the optional topK parameter to control the number of semantic retrieval chunks to retrieve.

```typescript
topK: 5
```

--------------------------------

### Define TuningExample Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.TuningExample.html

Defines the structure for a single tuning example, including optional text input and the expected model output. Note that this interface is not supported in Vertex AI.

```typescript
interface TuningExample {
output?: string;
textInput?: string;
}
```

--------------------------------

### Error Handling Example

Source: https://googleapis.github.io/js-genai/release_docs/index.html

Demonstrates how to catch and handle errors raised by the API using the `ApiError` class.

```APIDOC
## Error Handling

This code snippet illustrates how to implement error handling for API calls using a try-catch block.

```javascript
import {GoogleGenAI} from '@google/genai';
const GEMINI_API_KEY = process.env.GEMINI_API_KEY;

const ai = new GoogleGenAI({apiKey: GEMINI_API_KEY});

async function main() {
  await ai.models.generateContent({
    model: 'non-existent-model',
    contents: 'Write a 100-word poem.',
  }).catch((e) => {
    console.error('error name: ', e.name);
    console.error('error message: ', e.message);
    console.error('error status: ', e.status);
  });
}

main();
```
```

--------------------------------

### Agents (Deep Research)

Source: https://googleapis.github.io/js-genai

Utilizes specialized agents, such as `deep-research-pro-preview-12-2025`, for complex tasks. This example demonstrates starting a research agent and polling for results.

```APIDOC
## Agents (Deep Research)

Uses specialized agents for complex tasks like deep research.

```javascript
function sleep(ms: number): Promise<void> {
  return new Promise(resolve => setTimeout(resolve, ms));
}

// 1. Start the Deep Research Agent
const initialInteraction = await ai.interactions.create({
  input:
      'Research the history of the Google TPUs with a focus on 2025 and 2026.',
  agent: 'deep-research-pro-preview-12-2025',
  background: true,
});

console.log(`Research started. Interaction ID: ${initialInteraction.id}`);

// 2. Poll for results
while (true) {
  const interaction = await ai.interactions.get(initialInteraction.id);
  console.log(`Status: ${interaction.status}`);

  if (interaction.status === 'completed') {
    console.debug('\nFinal Report:\n', interaction.outputs);
    break;
  } else if (['failed', 'cancelled'].includes(interaction.status)) {
    console.log(`Failed with status: ${interaction.status}`);
    break;
  }

  await sleep(10000); // Sleep for 10 seconds
}
```
```

--------------------------------

### LiveClientSetup Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.LiveClientSetup.html

The LiveClientSetup interface defines the configuration options available for a live streaming session. These options allow for customization of various aspects of the session, from model behavior to audio processing and safety settings.

```APIDOC
## Interface LiveClientSetup

Message contains configuration that will apply for the duration of the streaming session.

### Properties
- **avatarConfig** (AvatarConfig) - Optional - Configures the avatar model behavior.
- **contextWindowCompression** (ContextWindowCompressionConfig) - Optional - Configures context window compression mechanism. If included, server will compress context window to fit into given length.
- **explicitVadSignal** (boolean) - Optional - Configures the explicit VAD signal. If enabled, the client will send vad_signal to indicate the start and end of speech. This allows the server to process the audio more efficiently.
- **generationConfig** (GenerationConfig) - Optional - The generation configuration for the session. Note: only a subset of fields are supported.
- **inputAudioTranscription** (AudioTranscriptionConfig) - Optional - The transcription of the input aligns with the input audio language.
- **model** (string) - Optional - The fully qualified name of the publisher model or tuned model endpoint to use.
- **outputAudioTranscription** (AudioTranscriptionConfig) - Optional - The transcription of the output aligns with the language code specified for the output audio.
- **proactivity** (ProactivityConfig) - Optional - Configures the proactivity of the model. This allows the model to respond proactively to the input and to ignore irrelevant input.
- **realtimeInputConfig** (RealtimeInputConfig) - Optional - Configures the realtime input behavior in BidiGenerateContent.
- **safetySettings** (SafetySetting[]) - Optional - Safety settings in the request to block unsafe content in the response.
- **sessionResumption** (SessionResumptionConfig) - Optional - Configures session resumption mechanism. If included server will send SessionResumptionUpdate messages.
- **systemInstruction** (ContentUnion) - Optional - The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
- **tools** (ToolListUnion) - Optional - A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
```

--------------------------------

### get

Source: https://googleapis.github.io/js-genai/release_docs/classes/interactions_resources_webhooks.BaseWebhooks.html

Gets a specific Webhook.

```APIDOC
## get
  * get(
id: string,
params?:
| undefined
| null
| GeminiNextGenAPIClient.Webhooks.WebhookGetParams,
options?: RequestOptions,
): APIPromise<GeminiNextGenAPIClient.Webhooks.Webhook>
Gets a specific Webhook.
#### Parameters
    * id: string
    * params: undefined | null | GeminiNextGenAPIClient.Webhooks.WebhookGetParams = {}
    * `Optional`options: RequestOptions
#### Returns APIPromise<GeminiNextGenAPIClient.Webhooks.Webhook>
```

--------------------------------

### Initialize a client with specific resources

Source: https://googleapis.github.io/js-genai/release_docs/functions/interactions_tree-shakable.createClient.html

Use this to create a client instance containing only the required resource classes. Ensure resources are imported from the appropriate path.

```typescript
import { Interactions } from `gemini-next-gen-api/resources/interactions`;  
import { createClient } from `gemini-next-gen-api/tree-shakable`;  
  
const client = createClient({  
  resources: [Interactions],  
});
```

--------------------------------

### withOptions

Source: https://googleapis.github.io/js-genai/release_docs/classes/interactions_client.GeminiNextGenAPIClient-1.html

Creates a new client instance with the same options, allowing for overrides.

```APIDOC
## withOptions

### Description
Creates a new client instance re-using the same options given to the current client with optional overriding.

### Parameters
*   **options** (Partial<ClientOptions>) - Partial client options to override.

### Returns
this - A new client instance with the specified options.
```

--------------------------------

### get

Source: https://googleapis.github.io/js-genai/release_docs/classes/caches.Caches.html

Gets cached content configurations.

```APIDOC
## get
  * get(params: GetCachedContentParameters): Promise<CachedContent>
Gets cached content configurations.
#### Parameters
    * params: GetCachedContentParameters
The parameters for the get request.
#### Returns Promise<CachedContent>
The cached content.
#### Example
```javascript
await ai.caches.get({name: '...'}); // The server-generated resource name.
```
```

--------------------------------

### get

Source: https://googleapis.github.io/js-genai/release_docs/classes/interactions_client.GeminiNextGenAPIClient-1.html

Sends a GET request to the specified path.

```APIDOC
## get

### Description
Sends a GET request to the specified path.

### Method
GET

### Parameters
*   **path** (string) - The path for the request.
*   **opts** (PromiseOrValue<RequestOptions>) - Optional. Additional request options.

### Returns
APIPromise<Rsp> - A promise that resolves with the response.

### Type Parameters
*   **Rsp** - The expected response type.
```

--------------------------------

### constructor

Source: https://googleapis.github.io/js-genai/release_docs/classes/interactions_resources_webhooks.BaseWebhooks.html

Initializes a new instance of the BaseWebhooks class.

```APIDOC
## constructor
  * new BaseWebhooks(client: BaseGeminiNextGenAPIClient): BaseWebhooks
#### Parameters
    * client: BaseGeminiNextGenAPIClient
#### Returns BaseWebhooks
```

--------------------------------

### Live Class Constructor

Source: https://googleapis.github.io/js-genai/release_docs/classes/live.Live.html

Initializes the Live class with necessary API client, authentication, and WebSocket factory.

```APIDOC
## constructor Live

### Description
Initializes the Live class.

### Parameters
- **apiClient** (ApiClient) - The API client instance.
- **auth** (Auth) - The authentication object.
- **webSocketFactory** (WebSocketFactory) - The WebSocket factory instance.

### Returns
Live - An instance of the Live class.
```

--------------------------------

### Live.connect Method

Source: https://googleapis.github.io/js-genai/release_docs/classes/live.Live.html

Establishes a connection to a specified model with given configuration and returns a Session object.

```APIDOC
## POST /connect

### Description
Establishes a connection to the specified model with the given configuration and returns a Session object representing that connection. Built-in MCP support is an experimental feature and may change in future versions.

### Method
POST

### Endpoint
/connect

### Parameters
#### Request Body
- **params** (LiveConnectParameters) - Required - The parameters for establishing a connection to the model.
  - **model** (string) - Required - The name of the model to connect to.
  - **config** (object) - Optional - Configuration for the connection.
    - **responseModalities** (array) - Optional - Specifies the modalities for the response (e.g., [Modality.AUDIO]).
  - **callbacks** (object) - Optional - Callback functions for connection events.
    - **onopen** (function) - Called when the connection is opened.
    - **onmessage** (function) - Called when a message is received.
    - **onerror** (function) - Called when an error occurs.
    - **onclose** (function) - Called when the connection is closed.

### Response
#### Success Response (200)
- **session** (Session) - A live session object.

### Request Example
```javascript
let model;
if (GOOGLE_GENAI_USE_VERTEXAI) {
  model = 'gemini-2.0-flash-live-preview-04-09';
} else {
  model = 'gemini-live-2.5-flash-preview';
}
const session = await ai.live.connect({
  model: model,
  config: {
    responseModalities: [Modality.AUDIO],
  },
  callbacks: {
    onopen: () => {
      console.log('Connected to the socket.');
    },
    onmessage: (e) => {
      console.log('Received message from the server: %s\n', debug(e.data));
    },
    onerror: (e) => {
      console.log('Error occurred: %s\n', debug(e.error));
    },
    onclose: (e) => {
      console.log('Connection closed.');
    },
  },
});
```
```

--------------------------------

### Interface: PrebuiltVoiceConfig

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.PrebuiltVoiceConfig.html

Configuration for a prebuilt voice.

```APIDOC
## Interface PrebuiltVoiceConfig

### Description
Configuration for a prebuilt voice.

### Properties
#### voiceName
- **voiceName** (string) - Optional - The name of the prebuilt voice to use.
```

--------------------------------

### get

Source: https://googleapis.github.io/js-genai/release_docs/classes/models.Models.html

Fetches information about a model by name.

```APIDOC
## get

### Description
Fetches information about a model by name.

### Method
GET (assumed, based on typical API patterns for retrieval)

### Endpoint
`/v1beta/models/{model}` (example, actual endpoint may vary)

### Parameters
#### Path Parameters
- **model** (string) - Required - The name of the model to fetch information for.

#### Request Body
(Not applicable for GET requests)

### Request Example
```javascript
const modelInfo = await ai.models.get({model: 'gemini-2.0-flash'});
```

### Response
#### Success Response (200)
- **Model** - Information about the model.
```

--------------------------------

### Sample Class Methods

Source: https://googleapis.github.io/js-genai/release_docs/classes/cross_sentencepiece_sentencepiece_model.pb.sentencepiece.SelfTestData.Sample.html

Methods for creating, serializing, and verifying Sample objects.

```APIDOC
## Class: Sample

### Description
Represents a Sample object with input and expected fields.

### Properties
- **expected** (string) - Sample expected value.
- **input** (string) - Sample input value.

### Methods
- **constructor(properties?: ISample)**: Constructs a new Sample instance.
- **toJSON()**: Converts the Sample instance to a JSON object.
- **static create(properties?: ISample)**: Creates a new Sample instance.
- **static decode(reader: Uint8Array | Reader, length?: number)**: Decodes a Sample message.
- **static decodeDelimited(reader: Uint8Array | Reader)**: Decodes a length-delimited Sample message.
- **static encode(message: ISample, writer?: Writer)**: Encodes a Sample message.
- **static encodeDelimited(message: ISample, writer?: Writer)**: Encodes a length-delimited Sample message.
- **static fromObject(object: { [k: string]: any })**: Creates a Sample message from a plain object.
- **static getTypeUrl(typeUrlPrefix?: string)**: Gets the default type URL.
- **static toObject(message: Sample, options?: IConversionOptions)**: Creates a plain object from a Sample message.
- **static verify(message: { [k: string]: any })**: Verifies a Sample message; returns null if valid, or an error string.
```

--------------------------------

### get Method

Source: https://googleapis.github.io/js-genai/release_docs/classes/operations.Operations.html

Retrieves the status of a long-running operation.

```APIDOC
## GET /operations/{operationId}

### Description
Gets the status of a long-running operation.

### Method
GET

### Endpoint
/operations/{operationId}

### Parameters
#### Path Parameters
* **operationId** (string) - Required - The ID of the operation to retrieve.

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response (200)
- **T** (any) - The type of the operation's result.
- **U** (Operation<T>) - The type of the operation, extending Operation<T>.

#### Response Example
```json
{
  "name": "operations/12345",
  "metadata": {},
  "done": false,
  "error": null,
  "response": null
}
```
```

--------------------------------

### createClient Function

Source: https://googleapis.github.io/js-genai/release_docs/functions/interactions_tree-shakable.createClient.html

Creates a client with a subset of the available resources to reduce bundle size. Import the resource classes you need from `gemini-next-gen-api/resources/*`. Use the BaseResource variants if you do not need to use subresources.

```APIDOC
## Function createClient

### Description
Creates a client with a subset of the available resources to reduce bundle size. Import the resource classes you need from `gemini-next-gen-api/resources/*`. Use the BaseResource variants if you do not need to use subresources.

### Type Parameters
* `const T extends readonly typeof APIResource[]`

### Parameters
* `options`: `ClientOptions & { resources: T }`

### Returns
`PartialGeminiNextGenAPIClient<InferClientStructure<T>>`

### Example
```javascript
import { Interactions } from `gemini-next-gen-api/resources/interactions`;  
import { createClient } from `gemini-next-gen-api/tree-shakable`;  
  
const client = createClient({
  resources: [Interactions],
});
```
```

--------------------------------

### get Agent

Source: https://googleapis.github.io/js-genai/release_docs/classes/interactions_resources_agents.BaseAgents.html

Retrieves a specific Agent by its ID.

```APIDOC
## get
  * get(
id: string,
params?: undefined | null | GeminiNextGenAPIClient.Agents.AgentGetParams,
options?: RequestOptions,
): APIPromise<GeminiNextGenAPIClient.Agents.Agent>
Gets a specific Agent.
#### Parameters
    * id: string
    * params: undefined | null | GeminiNextGenAPIClient.Agents.AgentGetParams = {}
    * `Optional`options: RequestOptions
#### Returns APIPromise<GeminiNextGenAPIClient.Agents.Agent>
```

--------------------------------

### LiveMusicClientSetup Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.LiveMusicClientSetup.html

The LiveMusicClientSetup interface defines the structure for messages sent when connecting to the API. It includes an optional model property.

```APIDOC
## Interface LiveMusicClientSetup

Message to be sent by the system when connecting to the API.

### Properties

#### `model` (string) - Optional

The model's resource name. Format: `models/{model}`.
```

--------------------------------

### GET /documents/list

Source: https://googleapis.github.io/js-genai/release_docs/classes/documents.Documents.html

Lists documents available in the store.

```APIDOC
## GET /documents/list

### Description
Lists documents.

### Parameters
#### Query Parameters
- **params** (ListDocumentsParameters) - Required - The parameters for the list request.

### Response
#### Success Response (200)
- **Pager<Document>** - A pager of documents.

### Request Example
const documents = await ai.documents.list({parent:'rag_store_name', config: {'pageSize': 2}});
```

--------------------------------

### RequestInit

Source: https://googleapis.github.io/js-genai/release_docs/modules/interactions_internal_builtin-types.html

Represents the options that can be passed to the fetch function.

```APIDOC
## RequestInit

### Description
Represents the options that can be passed to the fetch function.

### Type Definition
```typescript
interface RequestInit {
    body?: BodyInit | null;
    cache?: RequestCache;
    credentials?: RequestCredentials;
    headers?: HeadersInit;
    integrity?: string;
    keepalive?: boolean;
    method?: string;
    mode?: RequestMode;
    redirect?: RequestRedirect;
    referrer?: string;
    referrerPolicy?: ReferrerPolicy;
    signal?: AbortSignal | null;
    window?: any;
}
```
```

--------------------------------

### GET /documents

Source: https://googleapis.github.io/js-genai/release_docs/classes/documents.Documents.html

Retrieves details of a specific document.

```APIDOC
## GET /documents

### Description
Gets a Document.

### Parameters
#### Query Parameters
- **params** (GetDocumentParameters) - Required - The parameters for getting a document.

### Response
#### Success Response (200)
- **Document** - The requested document object.
```

--------------------------------

### WebhookGetParams Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/interactions_client.GeminiNextGenAPIClient.Webhooks.WebhookGetParams.html

Defines the parameters for the Webhook GET request.

```APIDOC
## Interface WebhookGetParams

### Description
Defines the parameters for the Webhook GET request.

### Properties

#### Query Parameters
- **api_version** (string) - Optional - Which version of the API to use.
```

--------------------------------

### Define LiveClientSetup Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.LiveClientSetup.html

The interface structure for configuring a streaming session.

```typescript
interface LiveClientSetup {  
avatarConfig?: AvatarConfig;  
contextWindowCompression?: ContextWindowCompressionConfig;  
explicitVadSignal?: boolean;  
generationConfig?: GenerationConfig;  
inputAudioTranscription?: AudioTranscriptionConfig;  
model?: string;  
outputAudioTranscription?: AudioTranscriptionConfig;  
proactivity?: ProactivityConfig;  
realtimeInputConfig?: RealtimeInputConfig;  
safetySettings?: SafetySetting[];  
sessionResumption?: SessionResumptionConfig;  
systemInstruction?: ContentUnion;  
tools?: ToolListUnion;  
}
```

--------------------------------

### Batches API - get

Source: https://googleapis.github.io/js-genai/release_docs/classes/batches.Batches.html

Retrieves batch job configurations.

```APIDOC
## POST /v1/batches:get

### Description
Retrieves batch job configurations.

### Method
POST

### Endpoint
/v1/batches:get

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
- **params** (GetBatchJobParameters) - Required - The parameters for the get request.
  - **name** (string) - Required - The server-generated resource name of the batch job to retrieve.

### Request Example
```javascript
const batchJob = await ai.batches.get({name: 'projects/my-project/locations/us-central1/batches/my-batch-id'});
console.log(batchJob);
```

### Response
#### Success Response (200)
- **BatchJob** (object) - The batch job configuration.
  - **name** (string) - The resource name of the batch job.
  - **state** (string) - The current state of the batch job.
  - **model** (string) - The model used for the batch job.
  - **createTime** (string) - The timestamp when the batch job was created.
  - **updateTime** (string) - The timestamp when the batch job was last updated.
  - **error** (object) - Details about any errors encountered.

#### Response Example
```json
{
  "name": "projects/my-project/locations/us-central1/batches/my-batch-id",
  "state": "SUCCEEDED",
  "model": "gemini-2.0-flash",
  "createTime": "2023-10-27T10:00:00Z",
  "updateTime": "2023-10-27T10:05:00Z"
}
```
```

--------------------------------

### Interface: SpeakerVoiceConfig

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.SpeakerVoiceConfig.html

Configuration for a single speaker in a multi-speaker setup.

```APIDOC
## Interface SpeakerVoiceConfig

Configuration for a single speaker in a multi-speaker setup.

### Properties
- **speaker** (string) - Optional - The name of the speaker. This should be the same as the speaker name used in the prompt.
- **voiceConfig** (VoiceConfig) - Optional - The configuration for the voice of this speaker.
```

--------------------------------

### create

Source: https://googleapis.github.io/js-genai/release_docs/classes/filesearchstores.FileSearchStores.html

Creates a File Search Store.

```APIDOC
## create
  * create(params: CreateFileSearchStoreParameters): Promise<FileSearchStore>
Creates a File Search Store.
#### Parameters
    * params: CreateFileSearchStoreParameters
The parameters for creating a File Search Store.
#### Returns Promise<FileSearchStore>
FileSearchStore.
```

--------------------------------

### Get Library Version

Source: https://googleapis.github.io/js-genai/release_docs/variables/interactions_version.VERSION.html

Access the current version of the @google/genai library.

```APIDOC
## Get Library Version

### Description
Retrieves the current version of the @google/genai JavaScript library.

### Method
GET

### Endpoint
/interactions/version

### Parameters
None

### Request Example
None

### Response
#### Success Response (200)
- **version** (string) - The current version string of the library.

#### Response Example
{
  "version": "0.0.1"
}
```

--------------------------------

### OperationGetParameters Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.OperationGetParameters.html

Defines the parameters for the get method of the operations module.

```APIDOC
## Interface OperationGetParameters<T, U>

### Description
Parameters for the get method of the operations module.

### Type Parameters
* **T**
* **U** extends Operation<T>

### Properties
#### config (optional)
- **config** (GetOperationConfig) - Used to override the default configuration.

#### operation
- **operation** (U) - The operation to be retrieved.
```

--------------------------------

### Model Context Protocol (MCP) Support

Source: https://googleapis.github.io/js-genai/release_docs/index.html

Demonstrates how to use the experimental Model Context Protocol (MCP) support by passing a local MCP server as a tool.

```APIDOC
## Model Context Protocol (MCP) Support (Experimental)

### Description
Built-in MCP support is an experimental feature. You can pass a local MCP server as a tool directly.

### Method
`POST`

### Endpoint
`/v1beta/models/{model}:generateContent`

### Parameters
#### Request Body
```json
{
  "model": "gemini-2.5-flash",
  "contents": "What is the weather in London in [current date]?",
  "config": {
    "tools": [
      // MCP tool configuration would go here, e.g., using mcpToTool(client)
    ]
  }
}
```

### Example Usage
```javascript
import { GoogleGenAI, FunctionCallingConfigMode , mcpToTool} from '@google/genai';
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

// Create server parameters for stdio connection
const serverParams = new StdioClientTransport({
  command: "npx", // Executable
  args: ["-y", "@philschmid/weather-mcp"] // MCP Server
});

const client = new Client(
  {
    name: "example-client",
    version: "1.0.0"
  }
);

// Configure the client
const ai = new GoogleGenAI({});

// Initialize the connection between client and server
await client.connect(serverParams);

// Send request to the model with MCP tools
const response = await ai.models.generateContent({
  model: "gemini-2.5-flash",
  contents: `What is the weather in London in ${new Date().toLocaleDateString()}?`,
  config: {
    tools: [mcpToTool(client)],  // uses the session, will automatically call the tool using automatic function calling
  },
});
console.log(response.text);

// Close the connection
await client.close();
```
```

--------------------------------

### GetTuningJobParameters Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.GetTuningJobParameters.html

Defines the parameters for the get method related to tuning jobs.

```APIDOC
## Interface GetTuningJobParameters

Parameters for the get method.

### Properties
- **config** (GetTuningJobConfig) - Optional - Optional parameters for the request.
- **name** (string) - Required - The name of the tuning job.
```

--------------------------------

### get

Source: https://googleapis.github.io/js-genai/release_docs/classes/interactions_client.GeminiNextGenAPIClient.Webhooks-1.html

Retrieves a specific Webhook by its ID, with optional parameters and request options.

```APIDOC
## get
  * get(
id: string,
params?:  
| undefined  
| null  
| GeminiNextGenAPIClient.Webhooks.WebhookGetParams,
options?: RequestOptions,
): APIPromise<GeminiNextGenAPIClient.Webhooks.Webhook>
Gets a specific Webhook.
#### Parameters
    * id: string
    * params: undefined | null | GeminiNextGenAPIClient.Webhooks.WebhookGetParams = {}
    * `Optional`options: RequestOptions
#### Returns APIPromise<GeminiNextGenAPIClient.Webhooks.Webhook>
```

--------------------------------

### Define SpeakerVoiceConfig Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.SpeakerVoiceConfig.html

Interface definition for configuring a speaker in a multi-speaker setup.

```typescript
interface SpeakerVoiceConfig {  
speaker?: string;  
voiceConfig?: VoiceConfig;  
}
```

--------------------------------

### Initialize gcloud CLI for Authentication

Source: https://googleapis.github.io/js-genai

Use this command to create local authentication credentials for your user account when using the Gemini Enterprise Agent Platform.

```bash
gcloud auth application-default login
```

--------------------------------

### Initialize gcloud CLI for Authentication

Source: https://googleapis.github.io/js-genai/release_docs/index.html

Use this command to create local authentication credentials for your user account when using the Gemini Enterprise Agent Platform.

```bash
gcloud auth application-default login
Copy

```

--------------------------------

### Define OperationGetParameters Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.OperationGetParameters.html

Interface definition for the get method parameters in the operations module.

```typescript
interface OperationGetParameters<T, U extends Operation<T>> {  
config?: GetOperationConfig;  
operation: U;  
}
```

```typescript
config?: GetOperationConfig
```

```typescript
operation: U
```

--------------------------------

### GET /response/text

Source: https://googleapis.github.io/js-genai/release_docs/classes/types.GenerateContentResponse.html

Retrieves the concatenated text content from the first candidate of a model response.

```APIDOC
## GET /response/text

### Description
Returns the concatenation of all text parts from the first candidate in the response. If non-text parts exist, they are ignored, and a warning is logged.

### Returns
- **string | undefined** - The concatenated text content.

### Remarks
If multiple candidates exist, only the first is processed. Thought parts are excluded from the returned text.
```

--------------------------------

### GET /interactions/{id}

Source: https://googleapis.github.io/js-genai/release_docs/classes/interactions_client.GeminiNextGenAPIClient.Interactions-1.html

Retrieves the full details of a single interaction based on its ID.

```APIDOC
## GET /interactions/{id}

### Description
Retrieves the full details of a single interaction based on its Interaction.id. Supports both standard and streaming responses.

### Method
GET

### Endpoint
/interactions/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the interaction.

### Response
#### Success Response (200)
- **Interaction** (object) - The interaction details or a stream of SSE events.

### Response Example
{
  "api_version": "api_version"
}
```

--------------------------------

### Interface RagChunkPageSpan

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.RagChunkPageSpan.html

Defines the structure for specifying the start and end pages of a document chunk.

```APIDOC
## Interface RagChunkPageSpan

### Description
Represents where the chunk starts and ends in the document. This data type is not supported in Gemini API.

### Properties
- **firstPage** (number) - Optional - Page where chunk starts in the document. Inclusive. 1-indexed.
- **lastPage** (number) - Optional - Page where chunk ends in the document. Inclusive. 1-indexed.
```

--------------------------------

### NodeJS Environment Variables Initialization

Source: https://googleapis.github.io/js-genai

Initialize the SDK in NodeJS environments using environment variables.

```APIDOC
### (Optional) (NodeJS only) Using environment variables:
For NodeJS environments, you can create a client by configuring the necessary environment variables. Configuration setup instructions depends on whether you're using the Gemini Developer API or the Gemini Enterprise Agent Platform.
**Gemini Developer API:** Set `GOOGLE_API_KEY` as shown below:
```bash
export GOOGLE_API_KEY='your-api-key'
```

**Gemini Enterprise Agent Platform:** Set `GOOGLE_GENAI_USE_ENTERPRISE`, `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION`, as shown below:
```bash
export GOOGLE_GENAI_USE_ENTERPRISE=true  
export GOOGLE_CLOUD_PROJECT='your-project-id'
export GOOGLE_CLOUD_LOCATION='us-central1'
```
```typescript
import {GoogleGenAI} from '@google/genai';  

const ai = new GoogleGenAI();
```
```

--------------------------------

### Define startIndex Property

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.Citation.html

Represents the start index of the citation in the content. This is an output-only property.

```typescript
startIndex?: number
```

--------------------------------

### create

Source: https://googleapis.github.io/js-genai/release_docs/classes/interactions_resources_webhooks.BaseWebhooks.html

Creates a new Webhook.

```APIDOC
## create
  * create(
params: GeminiNextGenAPIClient.Webhooks.WebhookCreateParams,
options?: RequestOptions,
): APIPromise<GeminiNextGenAPIClient.Webhooks.Webhook>
Creates a new Webhook.
#### Parameters
    * params: GeminiNextGenAPIClient.Webhooks.WebhookCreateParams
    * `Optional`options: RequestOptions
#### Returns APIPromise<GeminiNextGenAPIClient.Webhooks.Webhook>
```

--------------------------------

### Define GetTuningJobParameters Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.GetTuningJobParameters.html

Represents the required parameters for the get method in tuning job operations.

```typescript
interface GetTuningJobParameters {  
config?: GetTuningJobConfig;  
name: string;  
}
```

--------------------------------

### GetOperationParameters Interface

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.GetOperationParameters.html

Defines the parameters available for the GET method, allowing customization of operation configurations.

```APIDOC
## Interface GetOperationParameters

### Description
Parameters for the GET method.

### Properties
- **config** (GetOperationConfig) - Optional - Used to override the default configuration.
- **operationName** (string) - Required - The server-assigned name for the operation.
```

--------------------------------

### Gemini Developer API Initialization

Source: https://googleapis.github.io/js-genai

Initialize the SDK for the Gemini Developer API using an API key.

```APIDOC
## Initialization
### Gemini Developer API
For server-side applications, initialize using an API key, which can be acquired from Google AI Studio:
```typescript
import { GoogleGenAI } from '@google/genai';  
const ai = new GoogleGenAI({apiKey: 'GEMINI_API_KEY'});
```
#### Browser
Caution
**API Key Security:** Avoid exposing API keys in client-side code. Use server-side implementations in production environments.
In the browser the initialization code is identical:
```typescript
import { GoogleGenAI } from '@google/genai';  
const ai = new GoogleGenAI({apiKey: 'GEMINI_API_KEY'});
```
```

--------------------------------

### Gemini Enterprise Agent Platform Initialization

Source: https://googleapis.github.io/js-genai

Initialize the SDK for the Gemini Enterprise Agent Platform.

```APIDOC
### Gemini Enterprise Agent Platform
Sample code for Gemini Enterprise Agent Platform initialization:
```typescript
import { GoogleGenAI } from '@google/genai';  

const ai = new GoogleGenAI({
    enterprise: true,  
    project: 'your_project',
    location: 'your_location',
});
```
```

--------------------------------

### GET /interactions (Non-Streaming)

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/interactions_client.GeminiNextGenAPIClient.Interactions.InteractionGetParamsNonStreaming.html

Retrieves interaction data without streaming, using the InteractionGetParamsNonStreaming interface.

```APIDOC
## GET /interactions

### Description
Retrieves interaction data from the Gemini Next Gen API client in a non-streaming format.

### Method
GET

### Endpoint
/interactions

### Parameters
#### Path Parameters
- **api_version** (string) - Optional - Which version of the API to use.

#### Query Parameters
- **include_input** (boolean) - Optional - If set to true, includes the input in the response.
- **last_event_id** (string) - Optional - If set, resumes the interaction stream from the next chunk after the event marked by the event id. Can only be used if `stream` is true.
- **stream** (boolean) - Optional - If set to true, the generated content will be streamed incrementally. Set to false for non-streaming.
```

--------------------------------

### GET /interactions/{id}

Source: https://googleapis.github.io/js-genai/release_docs/classes/interactions_resources_interactions.BaseInteractions.html

Retrieves the full details of a single interaction by its ID, with support for streaming.

```APIDOC
## GET /interactions/{id}

### Description
Retrieves the full details of a single interaction based on its ID. Supports both standard and streaming responses.

### Method
GET

### Endpoint
/interactions/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the interaction.

### Response
#### Success Response (200)
- **Interaction** (object) - The interaction details or a stream of SSE events.

### Response Example
{
  "api_version": "api_version"
}
```

--------------------------------

### Initialize Gemini Enterprise Agent Platform

Source: https://googleapis.github.io/js-genai

Sample code for initializing the Google Gen AI SDK for the Gemini Enterprise Agent Platform, requiring project and location details.

```typescript
import { GoogleGenAI } from '@google/genai';

const ai = new GoogleGenAI({
    enterprise: true,
    project: 'your_project',
    location: 'your_location',
});
```

--------------------------------

### Optional baseModel Property

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.CreateTuningJobParametersPrivate.html

Specify the base model for tuning, for example, 'gemini-2.5-flash'. This is an optional field.

```typescript
baseModel?: string
```

--------------------------------

### CreateTuningJobConfig

Source: https://googleapis.github.io/js-genai/release_docs/interfaces/types.CreateTuningJobConfig.html

The CreateTuningJobConfig interface defines the optional parameters for creating a fine-tuning job. It includes settings for model adaptation, training parameters, and output configuration.

```APIDOC
## Interface CreateTuningJobConfig
Fine-tuning job creation request - optional fields.

### Properties
abortSignal? adapterSize? baseTeacherModel? batchSize? beta? checkpointInterval? compositeRewardConfig? customBaseModel? description? encryptionSpec? epochCount? evaluateInterval? exportLastCheckpointOnly? httpOptions? labels? learningRate? learningRateMultiplier? maxOutputTokens? method? outputUri? preTunedModelCheckpointId? rewardConfig? samplesPerPrompt? sftLossWeightMultiplier? thinkingLevel? tunedModelDisplayName? tunedTeacherModelSource? tuningMode? validationDataset? validationDatasetUri?

### `Optional`abortSignal
abortSignal?: AbortSignal
Abort signal which can be used to cancel the request.
NOTE: AbortSignal is a client-only operation. Using it to cancel an operation will not cancel the request in the service. You will still be charged usage for any applicable operations.

### `Optional`adapterSize
adapterSize?: AdapterSize
Adapter size for tuning.

### `Optional`baseTeacherModel
baseTeacherModel?: string
The base teacher model that is being distilled. Distillation only.

### `Optional`batchSize
batchSize?: number
The batch size hyperparameter for tuning. This is only supported for OSS models in Gemini Enterprise Agent Platform.

### `Optional`beta
beta?: number
Weight for KL Divergence regularization, Preference Optimization tuning only.

### `Optional`checkpointInterval
checkpointInterval?: number
How often at steps to save checkpoints during training. Reinforcement tuning only.

### `Optional`compositeRewardConfig
compositeRewardConfig?: CompositeReinforcementTuningRewardConfig
Composite reward function configuration for reinforcement tuning. Reinforcement tuning only.

### `Optional`customBaseModel
customBaseModel?: string
Custom base model for tuning. This is only supported for OSS models in Gemini Enterprise Agent Platform.

### `Optional`description
description?: string
The description of the TuningJob

### `Optional`encryptionSpec
encryptionSpec?: EncryptionSpec
The encryption spec of the tuning job. Customer-managed encryption key options for a TuningJob. If this is set, then all resources created by the TuningJob will be encrypted with provided encryption key.

### `Optional`epochCount
epochCount?: number
Number of complete passes the model makes over the entire training dataset during training.

### `Optional`evaluateInterval
evaluateInterval?: number
How often at steps to evaluate the tuning job during training. Reinforcement tuning only.

### `Optional`exportLastCheckpointOnly
exportLastCheckpointOnly?: boolean
If set to true, disable intermediate checkpoints and only the last checkpoint will be exported. Otherwise, enable intermediate checkpoints.

### `Optional`httpOptions
httpOptions?: HttpOptions
Used to override HTTP request options.

### `Optional`labels
labels?: Record<string, string>
Optional. The labels with user-defined metadata to organize TuningJob and generated resources such as Model and Endpoint. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.

### `Optional`learningRate
learningRate?: number
The learning rate for tuning. OSS models only. Mutually exclusive with learning_rate_multiplier.

### `Optional`learningRateMultiplier
learningRateMultiplier?: number
Multiplier for adjusting the default learning rate. 1P models only. Mutually exclusive with learning_rate.

### `Optional`maxOutputTokens
maxOutputTokens?: number
The maximum number of tokens to generate per prompt. Reinforcement tuning only.
```

--------------------------------

### Initialize SDK using Environment Variables (NodeJS)

Source: https://googleapis.github.io/js-genai/release_docs/index.html

Initialize the Google Gen AI SDK in a NodeJS environment after configuring the necessary environment variables for either the Gemini Developer API or the Enterprise Agent Platform.

```typescript
import {GoogleGenAI} from '@google/genai';

const ai = new GoogleGenAI();
Copy

```