AI prompts
base on TypeScript/JavaScript SDK for Gemini and Vertex AI. # Google Gen AI SDK for TypeScript and JavaScript
[](https://www.npmjs.com/package/@google/genai)
[](https://www.npmjs.com/package/@google/genai)
----------------------
**Documentation:** https://googleapis.github.io/js-genai/
----------------------
The Google Gen AI JavaScript SDK is designed for
TypeScript and JavaScript developers to build applications powered by Gemini. The SDK
supports both the [Gemini Developer API](https://ai.google.dev/gemini-api/docs)
and [Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/overview).
The Google Gen AI SDK is designed to work with Gemini 2.0 features.
> [!CAUTION]
> **API Key Security:** Avoid exposing API keys in client-side code.
> Use server-side implementations in production environments.
## Prerequisites
1. Node.js version 20 or later
### The following are required for Vertex AI users (excluding Vertex AI Studio)
1. [Select](https://console.cloud.google.com/project) or [create](https://cloud.google.com/resource-manager/docs/creating-managing-projects#creating_a_project) a Google Cloud project.
1. [Enable billing for your project](https://cloud.google.com/billing/docs/how-to/modify-project).
1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).
1. [Configure authentication](https://cloud.google.com/docs/authentication) for your project.
* [Install the gcloud CLI](https://cloud.google.com/sdk/docs/install).
* [Initialize the gcloud CLI](https://cloud.google.com/sdk/docs/initializing).
* Create local authentication credentials for your user account:
```sh
gcloud auth application-default login
```
A list of accepted authentication options are listed in [GoogleAuthOptions](https://github.com/googleapis/google-auth-library-nodejs/blob/3ae120d0a45c95e36c59c9ac8286483938781f30/src/auth/googleauth.ts#L87) interface of google-auth-library-node.js GitHub repo.
## Installation
To install the SDK, run the following command:
```shell
npm install @google/genai
```
## Quickstart
The simplest way to get started is to use an API key from
[Google AI Studio](https://aistudio.google.com/apikey):
```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-2.0-flash-001',
contents: 'Why is the sky blue?',
});
console.log(response.text);
}
main();
```
## Initialization
The Google Gen AI SDK provides support for both the
[Google AI Studio](https://ai.google.dev/gemini-api/docs) and
[Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/overview)
implementations of the Gemini API.
### Gemini Developer API
For server-side applications, initialize using an API key, which can
be acquired from [Google AI Studio](https://aistudio.google.com/apikey):
```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'});
```
### Vertex AI
Sample code for VertexAI initialization:
```typescript
import { GoogleGenAI } from '@google/genai';
const ai = new GoogleGenAI({
vertexai: true,
project: 'your_project',
location: 'your_location',
});
```
### (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 API in Vertex AI.
**Gemini Developer API:** Set `GOOGLE_API_KEY` as shown below:
```bash
export GOOGLE_API_KEY='your-api-key'
```
**Gemini API on Vertex AI:** Set `GOOGLE_GENAI_USE_VERTEXAI`,
`GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION`, as shown below:
```bash
export GOOGLE_GENAI_USE_VERTEXAI=true
export GOOGLE_CLOUD_PROJECT='your-project-id'
export GOOGLE_CLOUD_LOCATION='us-central1'
```
```typescript
import {GoogleGenAI} from '@google/genai';
const ai = new GoogleGenAI();
```
## API Selection
By default, the SDK uses the beta API endpoints provided by Google to support
preview features in the APIs. The stable API endpoints can be selected by
setting the API version to `v1`.
To set the API version use `apiVersion`. For example, to set the API version to
`v1` for Vertex AI:
```typescript
const ai = new GoogleGenAI({
vertexai: true,
project: 'your_project',
location: 'your_location',
apiVersion: 'v1'
});
```
To set the API version to `v1alpha` for the Gemini Developer API:
```typescript
const ai = new GoogleGenAI({
apiKey: 'GEMINI_API_KEY',
apiVersion: 'v1alpha'
});
```
## GoogleGenAI overview
All API features are accessed through an instance of the `GoogleGenAI` classes.
The submodules bundle together related API methods:
- [`ai.models`](https://googleapis.github.io/js-genai/release_docs/classes/models.Models.html):
Use `models` to query models (`generateContent`, `generateImages`, ...), or
examine their metadata.
- [`ai.caches`](https://googleapis.github.io/js-genai/release_docs/classes/caches.Caches.html):
Create and manage `caches` to reduce costs when repeatedly using the same
large prompt prefix.
- [`ai.chats`](https://googleapis.github.io/js-genai/release_docs/classes/chats.Chats.html):
Create local stateful `chat` objects to simplify multi turn interactions.
- [`ai.files`](https://googleapis.github.io/js-genai/release_docs/classes/files.Files.html):
Upload `files` to the API and reference them in your prompts.
This reduces bandwidth if you use a file many times, and handles files too
large to fit inline with your prompt.
- [`ai.live`](https://googleapis.github.io/js-genai/release_docs/classes/live.Live.html):
Start a `live` session for real time interaction, allows text + audio + video
input, and text or audio output.
## Samples
More samples can be found in the
[github samples directory](https://github.com/googleapis/js-genai/tree/main/sdk-samples).
### Streaming
For quicker, more responsive API interactions use the `generateContentStream`
method which yields chunks as they're generated:
```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.generateContentStream({
model: 'gemini-2.0-flash-001',
contents: 'Write a 100-word poem.',
});
for await (const chunk of response) {
console.log(chunk.text);
}
}
main();
```
### Function Calling
To let Gemini to interact with external systems, you can provide provide
`functionDeclaration` objects as `tools`. To use these tools it's a 4 step
1. **Declare the function name, description, and parameters**
2. **Call `generateContent` with function calling enabled**
3. **Use the returned `FunctionCall` parameters to call your actual function**
3. **Send the result back to the model (with history, easier in `ai.chat`)
as a `FunctionResponse`**
```typescript
import {GoogleGenAI, FunctionCallingConfigMode, FunctionDeclaration, Type} from '@google/genai';
const GEMINI_API_KEY = process.env.GEMINI_API_KEY;
async function main() {
const controlLightDeclaration: FunctionDeclaration = {
name: 'controlLight',
parameters: {
type: Type.OBJECT,
description: 'Set the brightness and color temperature of a room light.',
properties: {
brightness: {
type: Type.NUMBER,
description:
'Light level from 0 to 100. Zero is off and 100 is full brightness.',
},
colorTemperature: {
type: Type.STRING,
description:
'Color temperature of the light fixture which can be `daylight`, `cool`, or `warm`.',
},
},
required: ['brightness', 'colorTemperature'],
},
};
const ai = new GoogleGenAI({apiKey: GEMINI_API_KEY});
const response = await ai.models.generateContent({
model: 'gemini-2.0-flash-001',
contents: 'Dim the lights so the room feels cozy and warm.',
config: {
toolConfig: {
functionCallingConfig: {
// Force it to call any function
mode: FunctionCallingConfigMode.ANY,
allowedFunctionNames: ['controlLight'],
}
},
tools: [{functionDeclarations: [controlLightDeclaration]}]
}
});
console.log(response.functionCalls);
}
main();
```
### Generate Content
#### How to structure `contents` argument for `generateContent`
The SDK allows you to specify the following types in the `contents` parameter:
#### Content
- `Content`: The SDK will wrap the singular `Content` instance in an array which
contains only the given content instance
- `Content[]`: No transformation happens
#### Part
Parts will be aggregated on a singular Content, with role 'user'.
- `Part | string`: The SDK will wrap the `string` or `Part` in a `Content`
instance with role 'user'.
- `Part[] | string[]`: The SDK will wrap the full provided list into a single
`Content` with role 'user'.
**_NOTE:_** This doesn't apply to `FunctionCall` and `FunctionResponse` parts,
if you are specifying those, you need to explicitly provide the full
`Content[]` structure making it explicit which Parts are 'spoken' by the model,
or the user. The SDK will throw an exception if you try this.
## How is this different from the other Google AI SDKs
This SDK (`@google/genai`) is Google Deepmind’s "vanilla" SDK for its generative
AI offerings, and is where Google Deepmind adds new AI features.
Models hosted either on the [Vertex AI platform](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/overview) or the [Gemini Developer platform](https://ai.google.dev/gemini-api/docs) are accessible through this SDK.
Other SDKs may be offering additional AI frameworks on top of this SDK, or may
be targeting specific project environments (like Firebase).
The `@google/generative_language` and `@google-cloud/vertexai` SDKs are previous
iterations of this SDK and are no longer receiving new Gemini 2.0+ features.
", Assign "at most 3 tags" to the expected json: {"id":"13455","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"