Generative AI on Vertex AI lets you build production-ready applications that are powered by state-of-the-art generative AI models hosted on Google's advanced, global infrastructure.
|
Enterprise ready Deploy your generative AI applications at scale with enterprise-grade security, data residency, access transparency, and low latency. |
|
State-of-the-art features Expand the capabilities of your applications by using the 2,000,000-token context window supported by Gemini 1.5 Pro. |
|
Open platform Vertex AI gives you access to over 100 models from third-party AI companies, including Anthropic Claude 3.5 Sonnet, Meta Llama 3, and Mistral AI Mixtral 8x7B. |
Core capabilities
-
Multimodal processing
Process multiple types of input media at the same time, such as image, video, audio, and documents.
-
Embeddings generation
Generate embeddings to perform tasks such as search, classification, clustering, and outlier detection.
-
Model tuning
Adapt models to perform specific tasks with greater precision and accuracy.
-
Function calling
Connect models to external APIs to extend the model's capabilities.
-
Grounding
Connect models to external data sources to reduce hallucinations in responses.
-
Vertex AI and Google AI differences
Gemini API in Vertex AI and Google AI both let you incorporate the capabilities of Gemini models into your applications. The platform that's right for you depends on your goals as detailed in the following table.
API | Designed for | Features |
---|---|---|
Vertex AI Gemini API |
|
|
Google AI Gemini API |
|
|
Migrate from Google AI to Vertex AI
Build using Vertex AI SDKs
Vertex AI provides SDKs in the following languages:
Python
from vertexai.generative_models import GenerativeModel
model = GenerativeModel(model_name="gemini-1.5-flash")
response = model.generate_content([Part.from_uri(IMAGE_URI, mime_type="image/jpeg"),"What is this?"])
Node.js
const vertexAI = new VertexAI({project: projectId, location: location});
const generativeVisionModel = vertexAI.getGenerativeModel({ model: "gemini-1.5-flash"});
const result = await model.generateContent([
"What is this?",
{inlineData: {data: imgDataInBase64, mimeType: 'image/png'}}
]);
Java
public static void main(String[] args) throws Exception {
try (VertexAI vertexAi = new VertexAI(PROJECT_ID, LOCATION); ) {
GenerativeModel model = new GenerativeModel("gemini-1.5-flash", vertexAI);
List<Content> contents = new ArrayList<>();
contents.add(ContentMaker
.fromMultiModalData(
"What is this?",
PartMaker.fromMimeTypeAndData("image/jpeg", IMAGE_URI)));
GenerateContentResponse response = model.generateContent(contents);
}
}
Go
model := client.GenerativeModel("gemini-1.5-flash", "us-central1")
img := genai.ImageData("jpeg", image_bytes)
prompt := genai.Text("What is this?")
resp, err := model.GenerateContent(ctx, img, prompt)
C#
var predictionServiceClient = new PredictionServiceClientBuilder {
Endpoint = $"{location}-aiplatform.googleapis.com"
}.Build();
var generateContentRequest = new GenerateContentRequest {
Model = $"projects/{projectId}/locations/{location}/publishers/google/models/gemini-1.5-flash",
Contents = {
new Content {
Role = "USER",
Parts = {
new Part {Text = "What's in this?"},
new Part {FileData = new() {MimeType = "image/jpeg", FileUri = fileUri}}
}
}
}
};
GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);
Get started
-
Try the Gemini API in Vertex AI
New customers get $300 in free credits.
-
Try Vertex AI Studio
Test prompts with no setup required.
-
Call Vertex AI models from OpenAI code
Make Vertex AI model calls by using the OpenAI library.
More ways to get started
- Explore pretrained models in Model Garden.
- Explore the Vertex AI Gemini API SDK reference for Python, Node.js, Java, Go, or C#.
- Learn how to migrate to Vertex AI from Azure OpenAI.
- Learn about responsible AI best practices and Vertex AI safety filters.
- Learn about pricing.