Generate content with the Gemini API

Use generateContent or streamGenerateContent to generate content with Gemini.

The Gemini model family includes models that work with multimodal prompt requests. The term multimodal indicates that you can use more than one modality, or type of input, in a prompt. Models that aren't multimodal accept prompts only with text. Modalities can include text, audio, video, and more.

Create a Google Cloud account to get started

To start using the Vertex AI API for Gemini, create a Google Cloud account.

After creating your account, use this document to review the Gemini model request body, model parameters, response body, and some sample requests.

When you're ready, see the Vertex AI API for Gemini quickstart to learn how to send a request to the Vertex AI Gemini API using a programming language SDK or the REST API.

Supported models

Model Version
Gemini 1.5 Flash gemini-1.5-flash-001
gemini-1.5-flash-002
Gemini 1.5 Pro gemini-1.5-pro-001
gemini-1.5-pro-002
Gemini 1.0 Pro Vision gemini-1.0-pro-001
gemini-1.0-pro-vision-001
Gemini 1.0 Pro gemini-1.0-pro
gemini-1.0-pro-001
gemini-1.0-pro-002

Example syntax

Syntax to generate a model response.

Non-streaming

curl

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \

https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/google/models/${MODEL_ID}:generateContent \
-d '{
  "contents": [{
    ...
  }],
  "generationConfig": {
    ...
  },
  "safetySettings": {
    ...
  }
  ...
}'

Python

gemini_model = GenerativeModel(MODEL_ID)
generation_config = GenerationConfig(...)

model_response = gemini_model.generate_content([...], generation_config, safety_settings={...})

Streaming

curl

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/google/models/${MODEL_ID}:streamGenerateContent \
  -d '{
    "contents": [{
      ...
    }],
    "generationConfig": {
      ...
    },
    "safetySettings": {
      ...
    }
    ...
  }'

Python

gemini_model = GenerativeModel(MODEL_ID)
model_response = gemini_model.generate_content([...], generation_config, safety_settings={...}, stream=True)

Parameter list

See examples for implementation details.

Request body

{
  "cachedContent": string,
  "contents": [
    {
      "role": string,
      "parts": [
        {
          // Union field data can be only one of the following:
          "text": string,
          "inlineData": {
            "mimeType": string,
            "data": string
          },
          "fileData": {
            "mimeType": string,
            "fileUri": string
          },
          // End of list of possible types for union field data.

          "videoMetadata": {
            "startOffset": {
              "seconds": integer,
              "nanos": integer
            },
            "endOffset": {
              "seconds": integer,
              "nanos": integer
            }
          }
        }
      ]
    }
  ],
  "systemInstruction": {
    "role": string,
    "parts": [
      {
        "text": string
      }
    ]
  },
  "tools": [
    {
      "functionDeclarations": [
        {
          "name": string,
          "description": string,
          "parameters": {
            object (OpenAPI Object Schema)
          }
        }
      ]
    }
  ],
  "safetySettings": [
    {
      "category": enum (HarmCategory),
      "threshold": enum (HarmBlockThreshold)
    }
  ],
  "generationConfig": {
    "temperature": number,
    "topP": number,
    "topK": number,
    "candidateCount": integer,
    "maxOutputTokens": integer,
    "presencePenalty": float,
    "frequencyPenalty": float,
    "stopSequences": [
      string
    ],
    "responseMimeType": string,
    "responseSchema": schema,
    "seed": integer,
    "responseLogprobs": boolean,
    "logprobs": integer,
    "audioTimestamp": boolean
  },
  "labels": {
    string: string
  }
}

The request body contains data with the following parameters:

Parameters

cachedContent

Optional: CachedContent

Cached content. You can use cached content in requests that contain repeated content.

contents

Required: Content

The content of the current conversation with the model.

For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history and the latest request.

systemInstruction

Optional: Content

Available for gemini-1.5-flash, gemini-1.5-pro, and gemini-1.0-pro-002.

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".

The text strings count toward the token limit.

The role field of systemInstruction is ignored and doesn't affect the performance of the model.

tools

Optional. 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. See Function calling.

toolConfig

Optional. See Function calling.

safetySettings

Optional: SafetySetting

Per request settings for blocking unsafe content.

Enforced on GenerateContentResponse.candidates.

generationConfig

Optional: GenerationConfig

Generation configuration settings.

labels

Optional: string

Metadata that you can add to the API call in the format of key-value pairs.

contents

The base structured data type containing multi-part content of a message.

This class consists of two main properties: role and parts. The role property denotes the individual producing the content, while the parts property contains multiple elements, each representing a segment of data within a message.

Parameters

role

Optional: string

The identity of the entity that creates the message. The following values are supported:

  • user: This indicates that the message is sent by a real person, typically a user-generated message.
  • model: This indicates that the message is generated by the model.

The model value is used to insert messages from the model into the conversation during multi-turn conversations.

For non-multi-turn conversations, this field can be left blank or unset.

parts

Part

A list of ordered parts that make up a single message. Different parts may have different IANA MIME types.

For limits on the inputs, such as the maximum number of tokens or the number of images, see the model specifications on the Google models page.

To compute the number of tokens in your request, see Get token count.

parts

A data type containing media that is part of a multi-part Content message.

Parameters

text

Optional: string

A text prompt or code snippet.

inlineData

Optional: Blob

Inline data in raw bytes.

For gemini-1.0-pro-vision, you can specify at most 1 image by using inlineData.To specify up to 16 images, use fileData.

fileData

Optional: fileData

Data stored in a file.

functionCall

Optional: FunctionCall.

It contains a string representing the FunctionDeclaration.name field and a structured JSON object containing any parameters for the function call predicted by the model.

See Function calling.

functionResponse

Optional: FunctionResponse.

The result output of a FunctionCall that contains a string representing the FunctionDeclaration.name field and a structured JSON object containing any output from the function call. It is used as context to the model.

See Function calling.

videoMetadata

Optional: VideoMetadata

For video input, the start and end offset of the video in Duration format. For example, to specify a 10 second clip starting at 1:00, set "startOffset": { "seconds": 60 } and "endOffset": { "seconds": 70 }.

The metadata should only be specified while the video data is presented in inlineData or fileData.

blob

Content blob. If possible send as text rather than raw bytes.

Parameters

mimeType

string

The media type of the file specified in the data or fileUri fields. Acceptable values include the following:

Click to expand MIME types

  • application/pdf
  • audio/mpeg
  • audio/mp3
  • audio/wav
  • image/png
  • image/jpeg
  • image/webp
  • text/plain
  • video/mov
  • video/mpeg
  • video/mp4
  • video/mpg
  • video/avi
  • video/wmv
  • video/mpegps
  • video/flv

For gemini-1.0-pro-vision, the maximum video length is 2 minutes.

For Gemini 1.5 Pro and Gemini 1.5 Flash, the maximum length of an audio file is 8.4 hours and the maximum length of a video file (without audio) is one hour. For more information, see Gemini 1.5 Pro media requirements.

Text files must be UTF-8 encoded. The contents of the text file count toward the token limit.

There is no limit on image resolution.

data

bytes

The base64 encoding of the image, PDF, or video to include inline in the prompt. When including media inline, you must also specify the media type (mimeType) of the data.

Size limit: 20MB

CachedContent

Used to update when a context cache expires. You must specify ttl or expireTime when you update CachedContent, but you can't specify both. For more information, see Use context caching.

Parameters

ttl

TTL

Used to specify the number of seconds and nanoseconds after a context cache is created or updated that the context cache lives before it expires.

expireTime

Timestamp

A timestamp that specifies when a context cache expires.

TTL

The time to live, or duration, after a context cache is created or updated before it expires.

Parameters

seconds

float

The seconds component of the duration before a context cache expires after it's created. The default value is 3,600 seconds.

nano

Optional: float

The nanoseconds component of the duration before a context cache expires after it's created.

FileData

URI or web-URL data.

Parameters

mimeType

string

IANA MIME type of the data.

fileUri

string

The URI or URL of the file to include in the prompt. Acceptable values include the following:

  • Cloud Storage bucket URI: The object must either be publicly readable or reside in the same Google Cloud project that's sending the request.
  • HTTP URL: The file URL must be publicly readable. You can specify one video file and up to 10 image files per request. Audio files and documents can't exceed 15 MB.
  • YouTube video URL:The YouTube video must be either owned by the account that you used to sign in to the Google Cloud console or is public. Only one YouTube video URL is supported per request.

When specifying a fileURI, you must also specify the media type (mimeType) of the file.

For gemini-1.5-pro and gemini-1.5-flash, the size limit is 2GB.

For gemini-1.0-pro-vision, the size limit is 20MB.

functionCall

A predicted functionCall returned from the model that contains a string representing the functionDeclaration.name and a structured JSON object containing the parameters and their values.

Parameters

name

string

The name of the function to call.

args

Struct

The function parameters and values in JSON object format.

See Function calling for parameter details.

functionResponse

The resulting output from a FunctionCall that contains a string representing the FunctionDeclaration.name. Also contains a structured JSON object with the output from the function (and uses it as context for the model). This should contain the result of a FunctionCall made based on model prediction.

Parameters

name

string

The name of the function to call.

response

Struct

The function response in JSON object format.

videoMetadata

Metadata describing the input video content.

Parameters

startOffset

Optional: google.protobuf.Duration

The start offset of the video.

endOffset

Optional: google.protobuf.Duration

The end offset of the video.

safetySetting

Safety settings.

Parameters

category

Optional: HarmCategory

The safety category to configure a threshold for. Acceptable values include the following:

Click to expand safety categories

  • HARM_CATEGORY_SEXUALLY_EXPLICIT
  • HARM_CATEGORY_HATE_SPEECH
  • HARM_CATEGORY_HARASSMENT
  • HARM_CATEGORY_DANGEROUS_CONTENT

threshold

Optional: HarmBlockThreshold

The threshold for blocking responses that could belong to the specified safety category based on probability.

  • OFF
  • BLOCK_NONE
  • BLOCK_LOW_AND_ABOVE
  • BLOCK_MEDIUM_AND_ABOVE
  • BLOCK_ONLY_HIGH

method

Optional: HarmBlockMethod

Specify if the threshold is used for probability or severity score. If not specified, the threshold is used for probability score.

harmCategory

Harm categories that block content.

Parameters

HARM_CATEGORY_UNSPECIFIED

The harm category is unspecified.

HARM_CATEGORY_HATE_SPEECH

The harm category is hate speech.

HARM_CATEGORY_DANGEROUS_CONTENT

The harm category is dangerous content.

HARM_CATEGORY_HARASSMENT

The harm category is harassment.

HARM_CATEGORY_SEXUALLY_EXPLICIT

The harm category is sexually explicit content.

harmBlockThreshold

Probability thresholds levels used to block a response.

Parameters

HARM_BLOCK_THRESHOLD_UNSPECIFIED

Unspecified harm block threshold.

BLOCK_LOW_AND_ABOVE

Block low threshold and higher (i.e. block more).

BLOCK_MEDIUM_AND_ABOVE

Block medium threshold and higher.

BLOCK_ONLY_HIGH

Block only high threshold (i.e. block less).

BLOCK_NONE

Block none.

OFF

Switches off safety if all categories are turned OFF

harmBlockMethod

A probability threshold that blocks a response based on a combination of probability and severity.

Parameters

HARM_BLOCK_METHOD_UNSPECIFIED

The harm block method is unspecified.

SEVERITY

The harm block method uses both probability and severity scores.

PROBABILITY

The harm block method uses the probability score.

generationConfig

Configuration settings used when generating the prompt.

Parameters

temperature

Optional: float

The temperature is used for sampling during response generation, which occurs when topP and topK are applied. Temperature controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a less open-ended or creative response, while higher temperatures can lead to more diverse or creative results. A temperature of 0 means that the highest probability tokens are always selected. In this case, responses for a given prompt are mostly deterministic, but a small amount of variation is still possible.

If the model returns a response that's too generic, too short, or the model gives a fallback response, try increasing the temperature.

  • Range for gemini-1.5-flash: 0.0 - 2.0 (default: 1.0)
  • Range for gemini-1.5-pro: 0.0 - 2.0 (default: 1.0)
  • Range for gemini-1.0-pro-vision: 0.0 - 1.0 (default: 0.4)
  • Range for gemini-1.0-pro-002: 0.0 - 2.0 (default: 1.0)
  • Range for gemini-1.0-pro-001: 0.0 - 1.0 (default: 0.9)

For more information, see Content generation parameters.

topP

Optional: float

If specified, nucleus sampling is used.

Top-P changes how the model selects tokens for output. Tokens are selected from the most (see top-K) to least probable until the sum of their probabilities equals the top-P value. For example, if tokens A, B, and C have a probability of 0.3, 0.2, and 0.1 and the top-P value is 0.5, then the model will select either A or B as the next token by using temperature and excludes C as a candidate.

Specify a lower value for less random responses and a higher value for more random responses.

  • Range: 0.0 - 1.0
  • Default for gemini-1.5-flash: 0.95
  • Default for gemini-1.5-pro: 0.95
  • Default for gemini-1.0-pro: 1.0
  • Default for gemini-1.0-pro-vision: 1.0

topK

Optional: Top-K changes how the model selects tokens for output. A top-K of 1 means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-K of 3 means that the next token is selected from among the three most probable tokens by using temperature.

For each token selection step, the top-K tokens with the highest probabilities are sampled. Then tokens are further filtered based on top-P with the final token selected using temperature sampling.

Specify a lower value for less random responses and a higher value for more random responses.

Range: 1-40

Supported by gemini-1.0-pro-vision only.

Default for gemini-1.0-pro-vision: 32

candidateCount

Optional: int

The number of response variations to return. For each request, you're charged for the output tokens of all candidates, but are only charged once for the input tokens.

Specifying multiple candidates is a Preview feature that works with generateContent (streamGenerateContent is not supported). The following models are supported:

  • Gemini 1.5 Flash: 1-8, default: 1
  • Gemini 1.5 Pro: 1-8, default: 1
  • Gemini 1.0 Pro: 1-8, default: 1

maxOutputTokens

Optional: int

Maximum number of tokens that can be generated in the response. A token is approximately four characters. 100 tokens correspond to roughly 60-80 words.

Specify a lower value for shorter responses and a higher value for potentially longer responses.

For more information, see Content generation parameters.

stopSequences

Optional: List[string]

Specifies a list of strings that tells the model to stop generating text if one of the strings is encountered in the response. If a string appears multiple times in the response, then the response truncates where it's first encountered. The strings are case-sensitive.

For example, if the following is the returned response when stopSequences isn't specified:

public static string reverse(string myString)

Then the returned response with stopSequences set to ["Str", "reverse"] is:

public static string

Maximum 5 items in the list.

For more information, see Content generation parameters.

presencePenalty

Optional: float

Positive penalties.

Positive values penalize tokens that already appear in the generated text, increasing the probability of generating more diverse content.

The maximum value for presencePenalty is up to, but not including, 2.0. Its minimum value is -2.0.

Supported by gemini-1.5-pro-002 and gemini-1.5-flash-002 only.

frequencyPenalty

Optional: float

Positive values penalize tokens that repeatedly appear in the generated text, decreasing the probability of repeating content.

This maximum value for frequencyPenalty is up to, but not including, 2.0. Its minimum value is -2.0.

Supported by gemini-1.5-pro-002 and gemini-1.5-flash-002 only.

responseMimeType

Optional: string (enum)

Available for the following models:

  • gemini-1.5-pro
  • gemini-1.5-flash

The output response MIME type of the generated candidate text.

The following MIME types are supported:

  • application/json: JSON response in the candidates.
  • text/plain (default): Plain text output.
  • text/x.enum: For classification tasks, output an enum value as defined in the response schema.

Specify the appropriate response type to avoid unintended behaviors. For example, if you require a JSON-formatted response, specify application/json and not text/plain.

responseSchema

Optional: schema

The schema that generated candidate text must follow. For more information, see Control generated output.

You must specify the responseMimeType parameter to use this parameter.

Available for the following models:

  • gemini-1.5-pro
  • gemini-1.5-flash

seed

Optional: int

When seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn't guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used.

This is a preview feature.

Available for the following models:

  • gemini-1.5-pro
  • gemini-1.5-flash
  • gemini-1.0-pro-002

responseLogprobs

Optional: boolean

If true, returns the log probabilities of the tokens that were chosen by the model at each step. By default, this parameter is set to false.

Available for the following models:

  • gemini-1.5-flash

This is a preview feature.

logprobs

Optional: int

Returns the log probabilities of the top candidate tokens at each generation step. The model's chosen tokens and log probabilities are always returned at each step, which might not appear in the list of top candidates. Specify the number of candidates to return by using an integer value in the range of 1-5.

You must enable response_logprobs to use this parameter.

This is a preview feature.

audioTimestamp

Optional: boolean

Available for the following models:

  • gemini-1.5-pro-002
  • gemini-1.5-flash-002

Enables timestamp understanding for audio-only files.

This is a preview feature.

Response body

{
  "candidates": [
    {
      "modelVersion": string,
      "content": {
        "parts": [
          {
            "text": string
          }
        ]
      },
      "finishReason": enum (FinishReason),
      "safetyRatings": [
        {
          "category": enum (HarmCategory),
          "probability": enum (HarmProbability),
          "blocked": boolean
        }
      ],
      "citationMetadata": {
        "citations": [
          {
            "startIndex": integer,
            "endIndex": integer,
            "uri": string,
            "title": string,
            "license": string,
            "publicationDate": {
              "year": integer,
              "month": integer,
              "day": integer
            }
          }
        ]
      },
      "avgLogprobs": double,
      "logprobsResult": {
        "topCandidates": [
          {
            "candidates": [
              {
                "token": string,
                "logProbability": float
              }
            ]
          }
        ],
        "chosenCandidates": [
          {
            "token": string,
            "logProbability": float
          }
        ]
      }
    }
  ],
  "usageMetadata": {
    "promptTokenCount": integer,
    "candidatesTokenCount": integer,
    "totalTokenCount": integer
  }
}
Response element Description
modelVersion The model and version used for generation. For example: gemini-1.5-flash-002.
text The generated text.
finishReason The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens. Because the response uses the prompt for context, it's not possible to change the behavior of how the model stops generating tokens.
  • FINISH_REASON_STOP: Natural stop point of the model or provided stop sequence.
  • FINISH_REASON_MAX_TOKENS: The maximum number of tokens as specified in the request was reached.
  • FINISH_REASON_SAFETY: Token generation was stopped because the response was flagged for safety reasons. Note that Candidate.content is empty if content filters block the output.
  • FINISH_REASON_RECITATION: The token generation was stopped because the response was flagged for unauthorized citations.
  • FINISH_REASON_BLOCKLIST: Token generation was stopped because the response includes blocked terms.
  • FINISH_REASON_PROHIBITED_CONTENT: Token generation was stopped because the response was flagged for prohibited content, such as child sexual abuse material (CSAM).
  • FINISH_REASON_SPII: Token generation was stopped because the response was flagged for sensitive personally identifiable information (SPII).
  • FINISH_REASON_MALFORMED_FUNCTION_CALL: Candidates were blocked because of malformed and unparsable function call.
  • FINISH_REASON_OTHER: All other reasons that stopped the token
  • FINISH_REASON_UNSPECIFIED: The finish reason is unspecified.
category The safety category to configure a threshold for. Acceptable values include the following:

Click to expand safety categories

  • HARM_CATEGORY_SEXUALLY_EXPLICIT
  • HARM_CATEGORY_HATE_SPEECH
  • HARM_CATEGORY_HARASSMENT
  • HARM_CATEGORY_DANGEROUS_CONTENT
probability The harm probability levels in the content.
  • HARM_PROBABILITY_UNSPECIFIED
  • NEGLIGIBLE
  • LOW
  • MEDIUM
  • HIGH
blocked A boolean flag associated with a safety attribute that indicates if the model's input or output was blocked.
startIndex An integer that specifies where a citation starts in the content.
endIndex An integer that specifies where a citation ends in the content.
url The URL of a citation source. Examples of a URL source might be a news website or a GitHub repository.
title The title of a citation source. Examples of source titles might be that of a news article or a book.
license The license associated with a citation.
publicationDate The date a citation was published. Its valid formats are YYYY, YYYY-MM, and YYYY-MM-DD.
avgLogprobs Average log probability of the candidate.
token Generative AI models break down text data into tokens for processing, which can be characters, words, or phrases.
logProbability A log probability value that indicates the model's confidence for a particular token.
promptTokenCount Number of tokens in the request.
candidatesTokenCount Number of tokens in the response(s).
totalTokenCount Number of tokens in the request and response(s).

Examples

Non-streaming text response

Generate a non-streaming model response from a text input.

REST

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • LOCATION: The region to process the request.
  • MODEL_ID: The model ID of the model that you want to use (for example, gemini-1.5-flash-002). See the list of supported models.
  • TEXT: The text instructions to include in the prompt.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:generateContent

Request JSON body:

{
  "contents": [{
    "role": "user",
    "parts": [{
      "text": "TEXT"
    }]
  }]
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:generateContent"

PowerShell

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:generateContent" | Select-Object -Expand Content

Python

import vertexai
from vertexai.generative_models import GenerativeModel

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

response = model.generate_content(
    "What's a good name for a flower shop that specializes in selling bouquets of dried flowers?"
)

print(response.text)
# Example response:
# **Emphasizing the Dried Aspect:**
# * Everlasting Blooms
# * Dried & Delightful
# * The Petal Preserve
# ...

NodeJS

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function generate_from_text_input(projectId = 'PROJECT_ID') {
  const vertexAI = new VertexAI({project: projectId, location: 'us-central1'});

  const generativeModel = vertexAI.getGenerativeModel({
    model: 'gemini-1.5-flash-001',
  });

  const prompt =
    "What's a good name for a flower shop that specializes in selling bouquets of dried flowers?";

  const resp = await generativeModel.generateContent(prompt);
  const contentResponse = await resp.response;
  console.log(JSON.stringify(contentResponse));
}

Java

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.ResponseHandler;

public class QuestionAnswer {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    String output = simpleQuestion(projectId, location, modelName);
    System.out.println(output);
  }

  // Asks a question to the specified Vertex AI Gemini model and returns the generated answer.
  public static String simpleQuestion(String projectId, String location, String modelName)
      throws Exception {
    // Initialize client that will be used to send requests.
    // This client only needs to be created once, and can be reused for multiple requests.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {
      String output;
      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      // Send the question to the model for processing.
      GenerateContentResponse response = model.generateContent("Why is the sky blue?");
      // Extract the generated text from the model's response.
      output = ResponseHandler.getText(response);
      return output;
    }
  }
}

Go

import (
	"context"
	"encoding/json"
	"fmt"
	"io"

	"cloud.google.com/go/vertexai/genai"
)

func generateContentFromText(w io.Writer, projectID string) error {
	location := "us-central1"
	modelName := "gemini-1.5-flash-001"

	ctx := context.Background()
	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("error creating client: %w", err)
	}
	gemini := client.GenerativeModel(modelName)
	prompt := genai.Text(
		"What's a good name for a flower shop that specializes in selling bouquets of dried flowers?")

	resp, err := gemini.GenerateContent(ctx, prompt)
	if err != nil {
		return fmt.Errorf("error generating content: %w", err)
	}
	// See the JSON response in
	// https://pkg.go.dev/cloud.google.com/go/vertexai/genai#GenerateContentResponse.
	rb, err := json.MarshalIndent(resp, "", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}
	fmt.Fprintln(w, string(rb))
	return nil
}

C#


using Google.Cloud.AIPlatform.V1;
using System;
using System.Threading.Tasks;

public class TextInputSample
{
    public async Task<string> TextInput(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-flash-001")
    {

        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();
        string prompt = @"What's a good name for a flower shop that specializes in selling bouquets of dried flowers?";

        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts =
                    {
                        new Part { Text = prompt }
                    }
                }
            }
        };

        GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);

        string responseText = response.Candidates[0].Content.Parts[0].Text;
        Console.WriteLine(responseText);

        return responseText;
    }
}

REST (OpenAI)

You can call the Inference API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • LOCATION: The region to process the request.
  • MODEL_ID: The name of the model to use.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions

Request JSON body:

{
  "model": "google/MODEL_ID",
  "messages": [{
    "role": "user",
    "content": "Write a story about a magic backpack."
  }]
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions"

PowerShell

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions" | Select-Object -Expand Content

Python (OpenAI)

You can call the Inference API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

import vertexai
import openai

from google.auth import default, transport

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
location = "us-central1"

vertexai.init(project=PROJECT_ID, location=location)

# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
auth_request = transport.requests.Request()
credentials.refresh(auth_request)

# # OpenAI Client
client = openai.OpenAI(
    base_url=f"https://{location}-aiplatform.googleapis.com/v1beta1/projects/{PROJECT_ID}/locations/{location}/endpoints/openapi",
    api_key=credentials.token,
)

response = client.chat.completions.create(
    model="google/gemini-1.5-flash-002",
    messages=[{"role": "user", "content": "Why is the sky blue?"}],
)

print(response.choices[0].message.content)
# Example response:
# The sky is blue due to a phenomenon called **Rayleigh scattering**.
# Sunlight is made up of all the colors of the rainbow.
# As sunlight enters the Earth's atmosphere ...

Non-streaming multi-modal response

Generate a non-streaming model response from a multi-modal input, such as text and an image.

REST

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • LOCATION: The region to process the request.
  • MODEL_ID: The model ID of the model that you want to use (for example, gemini-1.5-flash-002). See the list of supported models.
  • TEXT: The text instructions to include in the prompt.
  • FILE_URI: The Cloud Storage URI to the file storing the data.
  • MIME_TYPE: The IANA MIME type of the data.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:generateContent

Request JSON body:

{
  "contents": [{
    "role": "user",
    "parts": [
      {
        "text": "TEXT"
      },
      {
        "fileData": {
          "fileUri": "FILE_URI",
          "mimeType": "MIME_TYPE"
        }
      }
    ]
  }]
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:generateContent"

PowerShell

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:generateContent" | Select-Object -Expand Content

Python

import vertexai

from vertexai.generative_models import GenerativeModel, Part

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

response = model.generate_content(
    [
        Part.from_uri(
            "gs://cloud-samples-data/generative-ai/image/scones.jpg",
            mime_type="image/jpeg",
        ),
        "What is shown in this image?",
    ]
)

print(response.text)
# That's a lovely overhead shot of a rustic-style breakfast or brunch spread.
# Here's what's in the image:
# * **Blueberry scones:** Several freshly baked blueberry scones are arranged on parchment paper.
# They look crumbly and delicious.
# ...

NodeJS

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function createNonStreamingMultipartContent(
  projectId = 'PROJECT_ID',
  location = 'us-central1',
  model = 'gemini-1.5-flash-001',
  image = 'gs://generativeai-downloads/images/scones.jpg',
  mimeType = 'image/jpeg'
) {
  // Initialize Vertex with your Cloud project and location
  const vertexAI = new VertexAI({project: projectId, location: location});

  // Instantiate the model
  const generativeVisionModel = vertexAI.getGenerativeModel({
    model: model,
  });

  // For images, the SDK supports both Google Cloud Storage URI and base64 strings
  const filePart = {
    fileData: {
      fileUri: image,
      mimeType: mimeType,
    },
  };

  const textPart = {
    text: 'what is shown in this image?',
  };

  const request = {
    contents: [{role: 'user', parts: [filePart, textPart]}],
  };

  console.log('Prompt Text:');
  console.log(request.contents[0].parts[1].text);

  console.log('Non-Streaming Response Text:');

  // Generate a response
  const response = await generativeVisionModel.generateContent(request);

  // Select the text from the response
  const fullTextResponse =
    response.response.candidates[0].content.parts[0].text;

  console.log(fullTextResponse);
}

Java

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;
import com.google.cloud.vertexai.generativeai.ResponseHandler;

public class Multimodal {
  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    String output = nonStreamingMultimodal(projectId, location, modelName);
    System.out.println(output);
  }

  // Ask a simple question and get the response.
  public static String nonStreamingMultimodal(String projectId, String location, String modelName)
      throws Exception {
    // Initialize client that will be used to send requests.
    // This client only needs to be created once, and can be reused for multiple requests.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {
      GenerativeModel model = new GenerativeModel(modelName, vertexAI);

      String videoUri = "gs://cloud-samples-data/video/animals.mp4";
      String imgUri = "gs://cloud-samples-data/generative-ai/image/character.jpg";

      // Get the response from the model.
      GenerateContentResponse response = model.generateContent(
          ContentMaker.fromMultiModalData(
              PartMaker.fromMimeTypeAndData("video/mp4", videoUri),
              PartMaker.fromMimeTypeAndData("image/jpeg", imgUri),
              "Are this video and image correlated?"
          ));

      // Extract the generated text from the model's response.
      String output = ResponseHandler.getText(response);
      return output;
    }
  }
}

Go

import (
	"context"
	"encoding/json"
	"fmt"
	"io"

	"cloud.google.com/go/vertexai/genai"
)

func tryGemini(w io.Writer, projectID string, location string, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"

	ctx := context.Background()
	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("error creating client: %w", err)
	}
	gemini := client.GenerativeModel(modelName)

	img := genai.FileData{
		MIMEType: "image/jpeg",
		FileURI:  "gs://generativeai-downloads/images/scones.jpg",
	}
	prompt := genai.Text("What is in this image?")

	resp, err := gemini.GenerateContent(ctx, img, prompt)
	if err != nil {
		return fmt.Errorf("error generating content: %w", err)
	}
	rb, err := json.MarshalIndent(resp, "", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}
	fmt.Fprintln(w, string(rb))
	return nil
}

C#


using Google.Api.Gax.Grpc;
using Google.Cloud.AIPlatform.V1;
using System.Text;
using System.Threading.Tasks;

public class GeminiQuickstart
{
    public async Task<string> GenerateContent(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-flash-001"
    )
    {
        // Create client
        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        // Initialize content request
        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            GenerationConfig = new GenerationConfig
            {
                Temperature = 0.4f,
                TopP = 1,
                TopK = 32,
                MaxOutputTokens = 2048
            },
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts =
                    {
                        new Part { Text = "What's in this photo?" },
                        new Part { FileData = new() { MimeType = "image/png", FileUri = "gs://generativeai-downloads/images/scones.jpg" } }
                    }
                }
            }
        };

        // Make the request, returning a streaming response
        using PredictionServiceClient.StreamGenerateContentStream response = predictionServiceClient.StreamGenerateContent(generateContentRequest);

        StringBuilder fullText = new();

        // Read streaming responses from server until complete
        AsyncResponseStream<GenerateContentResponse> responseStream = response.GetResponseStream();
        await foreach (GenerateContentResponse responseItem in responseStream)
        {
            fullText.Append(responseItem.Candidates[0].Content.Parts[0].Text);
        }

        return fullText.ToString();
    }
}

REST (OpenAI)

You can call the Inference API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • LOCATION: The region to process the request.
  • MODEL_ID: The name of the model to use.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions

Request JSON body:

{
  "model": "google/MODEL_ID",
  "messages": [{
    "role": "user",
    "content": [
       {
          "type": "text",
          "text": "Describe the following image:"
       },
       {
          "type": "image_url",
          "image_url": {
             "url": "gs://generativeai-downloads/images/character.jpg"
          }
       }
     ]
  }]
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions"

PowerShell

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions" | Select-Object -Expand Content

Python (OpenAI)

You can call the Inference API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

import vertexai
import openai

from google.auth import default, transport

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
location = "us-central1"

vertexai.init(project=PROJECT_ID, location=location)

# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
auth_request = transport.requests.Request()
credentials.refresh(auth_request)

# OpenAI Client
client = openai.OpenAI(
    base_url=f"https://{location}-aiplatform.googleapis.com/v1beta1/projects/{PROJECT_ID}/locations/{location}/endpoints/openapi",
    api_key=credentials.token,
)

response = client.chat.completions.create(
    model="google/gemini-1.5-flash-002",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe the following image:"},
                {
                    "type": "image_url",
                    "image_url": "gs://cloud-samples-data/generative-ai/image/scones.jpg",
                },
            ],
        }
    ],
)

print(response.choices[0].message.content)
# Example response:
# Here's a description of the image:
# High-angle, close-up view of a rustic arrangement featuring several blueberry scones
# on a piece of parchment paper. The scones are golden-brown...

Streaming text response

Generate a streaming model response from a text input.

REST

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • LOCATION: The region to process the request.
  • MODEL_ID: The model ID of the model that you want to use (for example, gemini-1.5-flash-002). See the list of supported models.
  • TEXT: The text instructions to include in the prompt.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:streamGenerateContent

Request JSON body:

{
  "contents": [{
    "role": "user",
    "parts": [{
      "text": "TEXT"
    }]
  }]
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:streamGenerateContent"

PowerShell

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:streamGenerateContent" | Select-Object -Expand Content

Python

import vertexai

from vertexai.generative_models import GenerativeModel

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")
responses = model.generate_content(
    "Write a story about a magic backpack.", stream=True
)

for response in responses:
    print(response.text)
# Example response:
# El
# ara wasn't looking for magic. She was looking for rent money.
# Her tiny apartment, perched precariously on the edge of Whispering Woods,
# ...

NodeJS

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
const PROJECT_ID = process.env.CAIP_PROJECT_ID;
const LOCATION = process.env.LOCATION;
const MODEL = 'gemini-1.5-flash-001';

async function generateContent() {
  // Initialize Vertex with your Cloud project and location
  const vertexAI = new VertexAI({project: PROJECT_ID, location: LOCATION});

  // Instantiate the model
  const generativeModel = vertexAI.getGenerativeModel({
    model: MODEL,
  });

  const request = {
    contents: [
      {
        role: 'user',
        parts: [
          {
            text: 'Write a story about a magic backpack.',
          },
        ],
      },
    ],
  };

  console.log(JSON.stringify(request));

  const result = await generativeModel.generateContentStream(request);
  for await (const item of result.stream) {
    console.log(item.candidates[0].content.parts[0].text);
  }
}

Java

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.generativeai.GenerativeModel;

public class StreamingQuestionAnswer {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    streamingQuestion(projectId, location, modelName);
  }

  // Ask a simple question and get the response via streaming.
  public static void streamingQuestion(String projectId, String location, String modelName)
      throws Exception {
    // Initialize client that will be used to send requests.
    // This client only needs to be created once, and can be reused for multiple requests.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {
      GenerativeModel model = new GenerativeModel(modelName, vertexAI);

      // Stream the result.
      model.generateContentStream("Write a story about a magic backpack.")
          .stream()
          .forEach(System.out::println);

      System.out.println("Streaming complete.");
    }
  }
}

Go

import (
	"context"
	"errors"
	"fmt"
	"io"

	"cloud.google.com/go/vertexai/genai"
	"google.golang.org/api/iterator"
)

// generateContent shows how to	send a basic streaming text prompt, writing
// the response to the provided io.Writer.
func generateContent(w io.Writer, projectID, modelName string) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, projectID, "us-central1")
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	iter := model.GenerateContentStream(
		ctx,
		genai.Text("Write a story about a magic backpack."),
	)
	for {
		resp, err := iter.Next()
		if err == iterator.Done {
			return nil
		}
		if len(resp.Candidates) == 0 || len(resp.Candidates[0].Content.Parts) == 0 {
			return errors.New("empty response from model")
		}
		if err != nil {
			return err
		}
		fmt.Fprint(w, "generated response: ")
		for _, c := range resp.Candidates {
			for _, p := range c.Content.Parts {
				fmt.Fprintf(w, "%s ", p)
			}
		}
	}
}

REST (OpenAI)

You can call the Inference API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • LOCATION: The region to process the request.
  • MODEL_ID: The name of the model to use.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions

Request JSON body:

{
  "model": "google/MODEL_ID",
  "stream": true,
  "messages": [{
    "role": "user",
    "content": "Write a story about a magic backpack."
  }]
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions"

PowerShell

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions" | Select-Object -Expand Content

Python (OpenAI)

You can call the Inference API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

import vertexai
import openai

from google.auth import default, transport

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
location = "us-central1"

vertexai.init(project=PROJECT_ID, location=location)

# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
auth_request = transport.requests.Request()
credentials.refresh(auth_request)

# OpenAI Client
client = openai.OpenAI(
    base_url=f"https://{location}-aiplatform.googleapis.com/v1beta1/projects/{PROJECT_ID}/locations/{location}/endpoints/openapi",
    api_key=credentials.token,
)

response = client.chat.completions.create(
    model="google/gemini-1.5-flash-002",
    messages=[{"role": "user", "content": "Why is the sky blue?"}],
    stream=True,
)
for chunk in response:
    print(chunk.choices[0].delta.content)
# Example response:
# The sky is blue due to a phenomenon called **Rayleigh scattering**. Sunlight is
# made up of all the colors of the rainbow. When sunlight enters the Earth 's atmosphere,
# it collides with tiny air molecules (mostly nitrogen and oxygen). ...

Streaming multi-modal response

Generate a streaming model response from a multi-modal input, such as text and an image.

REST

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • LOCATION: The region to process the request.
  • MODEL_ID: The model ID of the model that you want to use (for example, gemini-1.5-flash-002). See the list of supported models.
  • TEXT: The text instructions to include in the prompt.
  • FILE_URI1: The Cloud Storage URI to the file storing the data.
  • MIME_TYPE1: The IANA MIME type of the data.
  • FILE_URI2: The Cloud Storage URI to the file storing the data.
  • MIME_TYPE2: The IANA MIME type of the data.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:streamGenerateContent

Request JSON body:

{
  "contents": [{
    "role": "user",
    "parts": [
      {
        "text": "TEXT"
      },
      {
        "fileData": {
          "fileUri": "FILE_URI1",
          "mimeType": "MIME_TYPE1"
        }
      },
      {
        "fileData": {
          "fileUri": "FILE_URI2",
          "mimeType": "MIME_TYPE2"
        }
      }
    ]
  }]
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:streamGenerateContent"

PowerShell

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:streamGenerateContent" | Select-Object -Expand Content

Python

import vertexai

from vertexai.generative_models import GenerativeModel, Part

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")
responses = model.generate_content(
    [
        Part.from_uri(
            "gs://cloud-samples-data/generative-ai/video/animals.mp4", "video/mp4"
        ),
        Part.from_uri(
            "gs://cloud-samples-data/generative-ai/image/character.jpg",
            "image/jpeg",
        ),
        "Are these video and image correlated?",
    ],
    stream=True,
)

for response in responses:
    print(response.candidates[0].content.text)
# Example response:
# No, the video and image are not correlated. The video shows a Google Photos
# project where animals at the Los Angeles Zoo take selfies using modified cameras.
# The image is a simple drawing of a wizard.

NodeJS

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
const PROJECT_ID = process.env.CAIP_PROJECT_ID;
const LOCATION = process.env.LOCATION;
const MODEL = 'gemini-1.5-flash-001';

async function generateContent() {
  // Initialize Vertex AI
  const vertexAI = new VertexAI({project: PROJECT_ID, location: LOCATION});
  const generativeModel = vertexAI.getGenerativeModel({model: MODEL});

  const request = {
    contents: [
      {
        role: 'user',
        parts: [
          {
            file_data: {
              file_uri: 'gs://cloud-samples-data/video/animals.mp4',
              mime_type: 'video/mp4',
            },
          },
          {
            file_data: {
              file_uri:
                'gs://cloud-samples-data/generative-ai/image/character.jpg',
              mime_type: 'image/jpeg',
            },
          },
          {text: 'Are this video and image correlated?'},
        ],
      },
    ],
  };

  const result = await generativeModel.generateContentStream(request);

  for await (const item of result.stream) {
    console.log(item.candidates[0].content.parts[0].text);
  }
}

Java

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;

public class StreamingMultimodal {
  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    streamingMultimodal(projectId, location, modelName);
  }

  // Ask a simple question and get the response via streaming.
  public static void streamingMultimodal(String projectId, String location, String modelName)
      throws Exception {
    // Initialize client that will be used to send requests.
    // This client only needs to be created once, and can be reused for multiple requests.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {
      GenerativeModel model = new GenerativeModel(modelName, vertexAI);

      String videoUri = "gs://cloud-samples-data/video/animals.mp4";
      String imgUri = "gs://cloud-samples-data/generative-ai/image/character.jpg";

      // Stream the result.
      model.generateContentStream(
          ContentMaker.fromMultiModalData(
              PartMaker.fromMimeTypeAndData("video/mp4", videoUri),
              PartMaker.fromMimeTypeAndData("image/jpeg", imgUri),
              "Are this video and image correlated?"
          ))
          .stream()
          .forEach(System.out::println);
    }
  }
}

Go

import (
	"context"
	"errors"
	"fmt"
	"io"

	"cloud.google.com/go/vertexai/genai"
	"google.golang.org/api/iterator"
)

func generateContent(w io.Writer, projectID, modelName string) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, projectID, "us-central1")
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)
	iter := model.GenerateContentStream(
		ctx,
		genai.FileData{
			MIMEType: "video/mp4",
			FileURI:  "gs://cloud-samples-data/generative-ai/video/animals.mp4",
		},
		genai.FileData{
			MIMEType: "video/jpeg",
			FileURI:  "gs://cloud-samples-data/generative-ai/image/character.jpg",
		},
		genai.Text("Are these video and image correlated?"),
	)
	for {
		resp, err := iter.Next()
		if err == iterator.Done {
			return nil
		}
		if len(resp.Candidates) == 0 || len(resp.Candidates[0].Content.Parts) == 0 {
			return errors.New("empty response from model")
		}
		if err != nil {
			return err
		}

		fmt.Fprint(w, "generated response: ")
		for _, c := range resp.Candidates {
			for _, p := range c.Content.Parts {
				fmt.Fprintf(w, "%s ", p)
			}
		}
		fmt.Fprint(w, "\n")
	}
}

REST (OpenAI)

You can call the Inference API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • LOCATION: The region to process the request.
  • MODEL_ID: The name of the model to use.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions

Request JSON body:

{
  "model": "google/MODEL_ID",
  "stream": true,
  "messages": [{
    "role": "user",
    "content": [
       {
          "type": "text",
          "text": "Describe the following image:"
       },
       {
          "type": "image_url",
          "image_url": {
             "url": "gs://generativeai-downloads/images/character.jpg"
          }
       }
     ]
  }]
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions"

PowerShell

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions" | Select-Object -Expand Content

Python (OpenAI)

You can call the Inference API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

import vertexai
import openai

from google.auth import default, transport

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
location = "us-central1"

vertexai.init(project=PROJECT_ID, location=location)

# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
auth_request = transport.requests.Request()
credentials.refresh(auth_request)

# OpenAI Client
client = openai.OpenAI(
    base_url=f"https://{location}-aiplatform.googleapis.com/v1beta1/projects/{PROJECT_ID}/locations/{location}/endpoints/openapi",
    api_key=credentials.token,
)

response = client.chat.completions.create(
    model="google/gemini-1.5-flash-002",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe the following image:"},
                {
                    "type": "image_url",
                    "image_url": "gs://cloud-samples-data/generative-ai/image/scones.jpg",
                },
            ],
        }
    ],
    stream=True,
)
for chunk in response:
    print(chunk.choices[0].delta.content)
# Example response:
# Here's a description of the image:
# High-angle, close-up view of a rustic scene featuring several blueberry
# scones arranged on a piece of parchment paper...

Model versions

To use the auto-updated version, specify the model name without the trailing version number, for example gemini-1.5-flash instead of gemini-1.5-flash-001.

For more information, see Gemini model versions and lifecycle.

What's next