Vertex AI release notes

This page documents production updates to Vertex AI. You can periodically check this page for announcements about new or updated features, bug fixes, known issues, and deprecated functionality.

December 10, 2024

Colab Enterprise

Gemini in Colab Enterprise, which is a product in the Gemini for Google Cloud portfolio, now includes error fixing in Preview. Gemini in Colab Enterprise can suggest fixes when your code produces errors. For more information, see Fix errors.

To enable and activate Gemini in Colab Enterprise features, see Set up Gemini in Colab Enterprise.

Generative AI on Vertex AI

Imagen 3 image generation models Generally Available to all users

Imagen 3 image generation models are now available to all users without requiring prior approval. These include the following image generation models:

imagen-3.0-generate-001
imagen-3.0-fast-generate-001 (low latency model)

Prior image generation models (imagegeneration@006, imagegeneration@005, imagegeneration@002) still require approval to use.

For more information, see Imagen on Vertex AI model versions and lifecycle and Generate images using text prompts.

Imagen 3 Customization model Generally Available to approved users

Imagen 3 Customization model is now available to approved users. This includes the following model:

imagen-3.0-capability

Imagen 3 Customization lets you guide image generation by providing reference images (few-shot learning). Imagen 3 Customization lets you customize generated images for the following feature categories:

Subject Customization (product, person, and animal companion)
Style Customization
Controlled Customization (canny edge and scribble)
Instruct Customization (Style transfer)

Imagen 3 editing model Generally Available to approved users

The Imagen 3 Editing model is now available to approved users. This includes the following model:

imagen-3.0-capability

This model offers the following additional features:

Inpainting - Add or remove content from a masked area of an image
Outpainting - Expand a masked area of an image
Product image editing - Identify and maintain a primary product while changing the background or product position

For more information, see Model versions.

December 06, 2024

Generative AI on Vertex AI

A vulnerability was discovered in the Vertex AI API serving Gemini multimodal requests, allowing bypass of VPC Service Controls. For details, see the Security bulletins page.

December 02, 2024

Vertex AI

Preview: You can consume reservations of VMs that have GPUs attached with your custom training jobs or prediction jobs. Reservations of Compute Engine zonal resources help you gain a high level of assurance that your jobs have the necessary resources to run. For more information, see the following:

November 21, 2024

Generative AI on Vertex AI

Mistral Large (24.11) is Generally Available on Vertex AI as a managed model. To learn more, view the Mistral Large (24.11) model card in Model Garden.

The Gen AI evaluation service can now help you evaluate your translation models using MetricX, COMET, and BLEU metrics. To learn more about evaluating your translation models, see Evaluate translation models.

November 20, 2024

Vertex AI Workbench

M126 release

The M126 release of Vertex AI Workbench user-managed notebooks includes the following:

Upgraded JupyterLab to 3.6.8.
One or more supported framework versions have reached their end of patch and support dates. To view end of patch and support dates, see Supported framework versions. To create an instance using an image family that has reached its end of patch and support date, see Create an instance after end of patch and support date.

The M126 release of Vertex AI Workbench managed notebooks includes the following:

Upgraded JupyterLab to 3.6.8.

M126 release

The M126 release of Vertex AI Workbench instances includes the following:

Preview: JupyterLab 4+ is available on new Vertex AI Workbench instances. To try it, select JupyterLab 4 when you create your instance.
Upgraded JupyterLab to 3.6.8.

November 08, 2024

Generative AI on Vertex AI

Batch predictions for Llama models on Vertex AI (MaaS) is available in Preview.

Batch prediction support for Gemini

Batch prediction is available for Gemini in General Availability (GA). Available Gemini models include Gemini 1.0 Pro, Gemini 1.5 Pro, and Gemini 1.5 Flash. To get started with batch prediction, see Get batch predictions for Gemini.

November 05, 2024

Generative AI on Vertex AI

We are extending the availability of Gemini 1.0 Pro 001 and Gemini 1.0 Pro Vision 001 from February 15, 2025 to April 9, 2025. For details, see the Deprecations.

November 04, 2024

Generative AI on Vertex AI

The translation LLM now supports Polish, Turkish, Indonesian, Dutch, Vietnamese, Thai and Czech. For the full list of supported languages, see the Translate text page.

The Anthropic Claude Haiku 3.5 is Generally Available on Vertex AI. To learn more, view the Claude Haiku 3.5 model card in Model Garden.

October 31, 2024

Vertex AI

PSC-I Egress is supported for Ray clusters Vertex AI. PSC-I is recommended for private connectivity since it reduces the chance of IP exhaustion, and allows for transitive peering. Check out Private Service Connect interface for Ray on Vertex AI. This feature is available in Preview.

Private Service Connect interface (PSC-I) is now supported for ML pipeline runs in Vertex AI Pipelines. PSC-I is recommended for private connectivity, since it reduces the chance of IP exhaustion, and allows for transitive peering.

For more information, see Configure Private Service Connect interface for a pipeline. This feature is available in Preview.

October 28, 2024

Generative AI on Vertex AI

You can now fine-tune the following models from the Cloud console:

The Whisper large v3 and Whisper large v3 turbo models have been added to Model Garden.

Updated the fine-tuning notebooks for Gemma 2, Llama 3.1, Mistral, and Mixtral with the following enhancements:

The notebooks use an updated high-performance container for single host multi-GPU LoRA fine-tuning.
- Better throughput and GPU utilization with well-tested max-sequence-lengths.
- Support for input token masking.
- No out of memory (OOM) error during fine-tuning.
Added a custom dataset example that uses a template and format validation.
Support for a default accelerator pool with quota checks.
Improved documentation.

October 25, 2024

Colab Enterprise

Colab Enterprise is now available in the following regions:

Hamina, Finland (europe-north1)
Milan, Italy (europe-west8)
Tel Aviv, Israel (me-west1)
Warsaw, Poland (europe-central2)

See Colab Enterprise locations.

October 22, 2024

Generative AI on Vertex AI

The Anthropic Claude Sonnet 3.5 v2 is Generally Available. To learn more, view the Claude Sonnet 3.5 v2 model card in Model Garden.

October 18, 2024

Generative AI on Vertex AI

The Llama 3.1 405B model that is managed on Vertex AI is now Generally Available.

October 09, 2024

Generative AI on Vertex AI

The Vertex AI Gemini API SDK supports tokenization capabilities for local token counting and computation. This is a streamlined way to compute tokens locally, ensuring compatibility across different Gemini models and their tokenizers. Supported models include gemini-1.5-flash and gemini-1.5-pro . To learn more, see Count tokens.

October 08, 2024

Vertex AI

Vector Search Private Service Connect automation

Deploying an index with Private Service Connect automation is generally available (GA). You can set up a service connection policy so that you don't have to manually create a compute address and forwarding rule after each index deployment.

For more information, see Set up Vector Search with Private Service Connect.

October 04, 2024

Generative AI on Vertex AI

The AI assistant in Vertex AI Studio can help you refine and generate prompts. This feature is in Preview. To learn more, see Use AI-powered prompt writing tools.

Prompt Guard and Flux were added to Model Garden.

You can deploy Hugging Face models on Google Cloud that have text embedding inference enabled or pytorch inference enabled. For more information, see the Hugging Face model deployment in the console.

Added multiple deployment settings (with A100-80G and H100) and sample requests for some popular models, including Llama 3.1, Gemma 2, and Mixtral.

Added dynamic LoRA serving for Llama 3.1 and Stable Diffusion XL.

October 03, 2024

Colab Enterprise

Gemini in Colab Enterprise, which is a product in the Gemini for Google Cloud portfolio, is generally available. Gemini in Colab Enterprise helps you write code by suggesting code as you type. You can also use the Help me code tool to generate code from a description of what you want.

Gemini in Colab Enterprise is available to try at no cost through December 31, 2024.

To learn how to enable and activate Gemini in Colab Enterprise features, see Set up Gemini in Colab Enterprise.

October 01, 2024

Generative AI on Vertex AI

Grounding: Dynamic retrieval for grounded results (GA)

Dynamic retrieval lets you choose when to turn off grounding with Google Search. This is useful when a prompt doesn't require an answer grounded in Google Search, and the supported models can provide an answer based on their knowledge without grounding. Dynamic retrieval helps you manage latency, quality, and cost more effectively.

This feature is Generally Available. For more information, see Dynamic retrieval.

September 30, 2024

Generative AI on Vertex AI

Prompt templates let you to test how different prompt formats perform with different sets of prompt data. This feature is in Preview. To learn more, see Use prompt templates.

September 26, 2024

Vertex AI Workbench

M125 release

The M125 release of Vertex AI Workbench user-managed notebooks includes the following:

Patched a vulnerability with adm and docker permissions when the instance's root access isn't enabled.

The M125 release of Vertex AI Workbench managed notebooks includes the following:

Patched a vulnerability with adm and docker permissions when the instance's root access isn't enabled.

M125 release

The M125 release of Vertex AI Workbench instances includes the following:

bigframes 1.9.0 is now available in all environments except TensorFlow.
Fixed a regression introduced in M124 where Conda was getting downgraded to an older version.
Patched a vulnerability with adm and docker permissions when the instance's root access isn't enabled.

September 25, 2024

Generative AI on Vertex AI

The Llama 3.2 90B model is available in Preview on Vertex AI. Llama 3.2 90B enables developers to build and deploy the latest generative AI models and applications that use Llama's capabilities, such as image reasoning. Llama 3.2 is also designed to be more accessible for on-device applications. For more information, see Llama models.

September 24, 2024

Generative AI on Vertex AI

New stable versions of Gemini 1.5 Pro (gemini-1.5-pro-002) and Gemini 1.5 Flash (gemini-1.5-flash-002) are Generally Available. These models introduce broad quality improvements over the previous 001 versions, with significant gains in the following categories:

Factuality and reduce model hallucinations
Openbook Q&A for RAG use cases
Instruction following
Multilingual understanding in 102 languages, especially in Korean, French, German, Spanish, Japanese, Russian, and Chinese.
SQL generation
Audio understanding
Document understanding
Long context
Math and reasoning

For more information about differences with the previous model versions, see Model versions and lifecycle.

The 2M context window with Gemini 1.5 Pro is now in Generally Available, which opens up long-form multimodal use cases that only Gemini can support.

Use Gemini to directly analyze YouTube videos and publicly available media (such as images, audio, and video) by using a link. This feature is in Public Preview.

The new API parameters audioTimestamp, responseLogprob, and logprobs are in Public Preview. For more information, see API reference.

Gemini 1.5 Pro and Gemini 1.5 Flash now support multimodal input with function calling. This feature is in Preview.

The Vertex AI prompt optimizer adapts your prompts using the optimal instructions and examples to elicit the best performance from your chosen model. This feature is available in Preview. To learn more, see Optimize prompts.

Gemini 1.5 Pro and Gemini 1.5 Flash Tuning is now available in GA. Tune Gemini with text, image, audio, and document data types using the latest models:

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

Gemini 1.0 tuning remains in preview.

For more information on tuning Gemini, see Tune Gemini models by using supervised fine-tuning.

The latest versions of Gemini 1.5 Flash (gemini-1.5-flash-002) and Gemini 1.5 Pro (gemini-1.5-pro-002) use dynamic shared quota, which distributes on-demand capacity among all queries being processed. Dynamic shared quota is Generally Available.

Controlled generation is now Generally Available.

September 23, 2024

Colab Enterprise

You can now use customer-managed encryption keys (CMEK) to protect notebooks in Colab Enterprise.

For more information, see Use customer-managed encryption keys.

September 20, 2024

Generative AI on Vertex AI

Add label metadata to generateContent and streamGenerateContent API calls. For details, see Add labels to API calls.

September 18, 2024

Generative AI on Vertex AI

Model Garden supports an organization policy so that administrators can limit access to certain models and capabilities. For more information, see Control access to Model Garden models

September 17, 2024

Vertex AI

To ensure that VM resources are available when your custom training and prediction jobs need them, you can now use Compute Engine reservations. Reservations provide a high level of assurance in obtaining capacity for Compute Engine resources. This feature is available in Preview for A2 and A3 machine series reservations.

For more information, see Use reservations with training and Use reservations with prediction.

To reduce the cost of running your training and prediction jobs, you can now use Spot VMs. Spot VMs are virtual machine (VM) instances that are excess Compute Engine capacity. Spot VMs have significant discounts, but Compute Engine might preemptively stop or delete Spot VMs to reclaim the capacity at any time. This feature is available in Preview.

For more information, see Use Spot VMs with training and Use Spot VMs with prediction.

September 16, 2024

Vertex AI

Schedule Vertex AI custom training jobs based on resource availability. For details, see the Vertex AI documentation.

September 10, 2024

Vertex AI Workbench

The ability to back up and restore data on a Vertex AI Workbench instance is now available in Preview. For more information, see Back up and restore an instance.

September 09, 2024

Vertex AI

Ray cluster's autoscaling feature is now supported. See Scale Ray clusters on Vertex AI

September 03, 2024

Generative AI on Vertex AI

Gemini 1.5 Flash (gemini-1.5-flash) supports controlled generation.

August 30, 2024

Generative AI on Vertex AI

Gen AI Evaluation Service is Generally Available. To learn more, see the Gen AI Evaluation Service overview.

August 26, 2024

Generative AI on Vertex AI

For controlled generation, you can have the model respond with an enum value in plain text, as defined in your response schema. Set the responseMimeType to text/x.enum. For more information, see Control generated output.

August 22, 2024

Generative AI on Vertex AI

AI21 Labs

Managed models from AI21 Labs are available on Vertex AI. To use a AI21 Labs model on Vertex AI, send a request directly to the Vertex AI API endpoint. For more information, see AI21 models.

August 20, 2024

Vertex AI Workbench

M124 release

The M124 release of Vertex AI Workbench user-managed notebooks includes the following:

Pytorch 2.3.0 with CUDA 12.1 and Python 3.10 user-managed notebooks instances are now available.
Fixed a bug that prevented kernels from appearing when the Cloud Resource Manager API is turned off and Dataproc is enabled.

August 19, 2024

Vertex AI Workbench

The ability to create a Vertex AI Workbench instance based on a custom container is now generally available. Only custom containers derived from the Google-provided base container are supported. For more information, see Create an instance using a custom container.

August 14, 2024

Colab Enterprise

The notebook scheduler is now generally available. See Schedule a notebook run.

August 11, 2024

Vertex AI

Generative AI on Vertex AI supports CMEK, VPC Service Controls, and Data Residency. For more information, see Security controls.

August 09, 2024

Generative AI on Vertex AI

Gemini on Vertex AI supports multiple response candidates. For details, see Generate content with the Gemini API.

August 08, 2024

Vertex AI Workbench

M124 release

The M124 release of Vertex AI Workbench managed notebooks includes the following:

Fixed a bug that prevented kernels from appearing when the Cloud Resource Manager API is turned off and Dataproc is enabled.

M124 release

The M124 release of Vertex AI Workbench instances includes the following:

Fixed a bug that prevented kernels from appearing when the Cloud Resource Manager API is turned off and Dataproc is enabled.
Spark notebooks on Dataproc: The Serverless Spark runtime template creation screen now has an easy-to-use UI for configuring resource allocation, autoscaling, and GPU settings.

August 05, 2024

Colab Enterprise

Fixed an issue in which users weren't able to access the Colab Enterprise UI when Colab Service Status was OFF for everyone in Google Workspace.

Generative AI on Vertex AI

The translation LLM now supports Arabic, Hindi, and Russian. For the full list of supported languages, see the Translate text page.

August 02, 2024

Generative AI on Vertex AI

Vertex AI SDK for Python supports token listing and counting for prompts without the need to make API calls. This feature is available in (Preview). For details, see List and count tokens.

Vertex AI

The Vertex AI Model Registry now offers Preview support for model copy across different projects. For information about how to copy your model projects and regions, see Copy models in Model Registry.

July 31, 2024

Generative AI on Vertex AI

New Imagen on Vertex AI image generation model and features

The Imagen 3 image generation models (imagen-3.0-generate-001 and the low-latency version imagen-3.0-fast-generate-001) are Generally Available to approved users. These models offer the following additional features:

Additional aspect ratios (1:1, 3:4, 4:3, 9:16, 16:9)
Digital watermark (SynthID) enabled by default
Watermark verification
User-configurable safety features (safety setting, person/face setting)

For more information, see Model versions and Generate images using text prompts.

Gemma 2 2B is available in Model Garden. For details, see Use Gemma open models.

The following models have been added to Model Garden:

Gemma 2 2B: A foundation LLM by Google Deepmind.
Qwen2: An LLM series by Alibaba Cloud.
Phi-3: An LLM series by Microsoft.

Resource and deployment settings were made to the following models:

Added GPU inferences for gemma2-27b and gemma2-27b-it with verified performances.
Added verified deployment settings for Mistral AI models that are deployed from Huggingface, including mistralai/mistral-nemo-instruct-2407, mistralai/mistral-nemo-base-2407, mistralai/mistral-large-instruct-2407, and mistralai/codestral-22b-v0.1.
Added multiple deployment settings with A100 (40G), A100 (80G) and H100 (80G) for select models, such as llama3.1, llama3, gemma2, gemma, and mistral-7b.

July 30, 2024

Generative AI on Vertex AI

See the Gemini Online Inference on Vertex AI Service Level Agreement (SLA).

July 24, 2024

Generative AI on Vertex AI

Mistral AI

Managed models from Mistral AI are available on Vertex AI. To use a Mistral AI model on Vertex AI, send a request directly to the Vertex AI API endpoint. For more information, see Mistral AI models.

Vertex AI Workbench

M123 release

The M123 release of Vertex AI Workbench managed notebooks includes the following:

Fixed a bug that caused conflicting permissions with the Jupyter user and google-sudoers.
Updated Nvidia drivers to version 550.90.07 to fix vulnerabilities.

July 23, 2024

Generative AI on Vertex AI

Llama 3.1

The Llama 3.1 405B model is available in Preview on Vertex AI. Llama 3.1 405B provides capabilities from synthetic data generation to model distillation, steerability, math, tool use, multilingual translation, and more. For more information, see Llama models.

July 16, 2024

Colab Enterprise

All Colab Enterprise runtimes are automatically configured with a 100 GiB boot disk in addition to the disk specified in the runtime template. Starting July 16, 2024, the boot disk of a newly created Colab Enterprise runtime automatically defaults to an SSD Persistent Disk. Previously, the boot disk default was a Standard Persistent Disk.

Because of this change, default boot disks of Colab Enterprise runtimes are billed as SSD Persistent Disks instead of Standard Persistent Disks. For more information, see Colab Enterprise pricing.

Vertex AI Workbench

M123 release

The M123 release of Vertex AI Workbench user-managed notebooks includes the following:

Fixed a bug that caused conflicting permissions with the Jupyter user and google-sudoers.
Fixed a bug for custom container instances using a disabled root.

M123 release

The M123 release of Vertex AI Workbench instances includes the following:

Fixed a bug that caused conflicting permissions with the Jupyter user and google-sudoers.

July 02, 2024

Generative AI on Vertex AI

Google's open weight Gemma 2 model is available in Model Garden. For details, see Use Gemma open models.

MaMMUT is now available in Model Garden. MaMMUT is a vision-encoder and text-decoder model for multimodal tasks such as visual question answering, image-text retrieval, text-image retrieval, and generation of multimodal embeddings.

June 28, 2024

Generative AI on Vertex AI

The following models have been added to Model Garden:

36 Hugging Face embedding models with verified deployment settings such as BAAI/bge-m3 and intfloat/multilingual-e5-large-instruct.
35 Hugging Face PyTorch models with verified deployment settings such as stabilityai/stable-diffusion-2-1.

For more information, see the Hugging Face model deployment in the console.

Launched Hex-LLM for high-efficiency large language model serving. This performant TPU serving solution is based on XLA and optimized kernels to achieve high throughput and low latency.

Hex-LLM uses several parallelism strategies for multiple TPU chips, quantizations, dynamic LoRA, and more. Hex-LLM supports the following dense and sparse LLMs:

Gemma 2B and 7B
Gemma 2 9B and 27B
Llama 2 7B, 13B and 70B
Llama 3 8B and 70B
Mistral 7B and Mixtral 8x7B

Updated Docker images in Llama 3 notebooks that are more efficient at tuning.
A notebook-based interactive workshop UI was added in Model Garden for image generative models such as stable-diffusion-xl-base, image inpainting, controlnet. You can find these models from the Open Notebook list.
Colab Notebooks for frequently used models in Model Garden have been revised with no-code or low-code implementations to improve accessibility and user experience.

Vertex AI

Vertex AI custom training on TPU VMs support customer managed encryption keys (CMEK).

June 27, 2024

Generative AI on Vertex AI

Context caching is available for Gemini 1.5 Pro. Use context caching to reduce the cost of requests that contain repeat content with high input token counts. For more information, see Context caching overview.

June 25, 2024

Generative AI on Vertex AI

Controlled generation is available on Gemini 1.5 Pro and supports the JSON schema. For more information, see Control generated output.

June 21, 2024

Vertex AI Workbench

M122 release

The M122 release of Vertex AI Workbench user-managed notebooks includes the following:

Updated Nvidia drivers to version 550.90.07 to fix vulnerabilities.

M122 release

The M122 release of Vertex AI Workbench instances includes the following:

Updated Nvidia drivers to version 550.90.07 to fix vulnerabilities.

June 20, 2024

Generative AI on Vertex AI

The Anthropic Claude Sonnet 3.5 is Generally Available. To learn more, view the Claude Sonnet 3.5 model card in Model Garden.

Vertex AI

Vertex AI custom training supports TPU v5e in us-central1. For details, see Vertex AI locations.

June 18, 2024

Vertex AI

Starting on September 15, 2024, you can only customize classification, entity extraction, and sentiment analysis objectives by moving to Vertex AI Gemini prompts and tuning. Training or updating models for Vertex AI AutoML for Text classification, entity extraction, and sentiment analysis objectives will no longer be available. You can continue using existing Vertex AI AutoML Text models until June 15, 2025. For more information about how Gemini offers enhanced user experience through improved prompting capabilities, see Overview of model tuning for Gemini.

June 17, 2024

Colab Enterprise

You can now use customer-managed encryption keys (CMEK) to protect runtimes in Colab Enterprise. Using CMEK for notebook files isn't currently supported.

For more information, see Use customer-managed encryption keys for runtimes.

Generative AI on Vertex AI

Increased the input token limit for Gemini 1.5 Pro from 1M to 2M. For more information, see Google models.

June 11, 2024

Generative AI on Vertex AI

Upload media from Google Drive

You can upload media, such as PDF, MP4, WAV, and JPG files from Google Drive, when you send image, video, audio, and document prompt requests.

June 10, 2024

Colab Enterprise

Gemini in Colab Enterprise, which is a product in the Gemini for Google Cloud portfolio, is available in Preview. Gemini in Colab Enterprise helps you write code by suggesting code as you type. You can also use the Help me code tool to generate code from a description of what you want.

To learn how to enable and activate Gemini in Colab Enterprise features, see Set up Gemini in Colab Enterprise.

The notebook scheduler is now available in Preview. You can schedule a notebook to run immediately one time, or on a recurring schedule.

For more information, see Schedule a notebook run.

Generative AI on Vertex AI

Experiment in the Vertex AI Studio login-free

The Vertex AI Studio multi-model prompt designer can be accessed login-free. With this feature, prospective customers can use the Vertex AI Studio to test queries before deciding to sign up and create an account. To learn more about this experience, see Vertex AI Studio console experiences or to access the console directly go to Vertex AI Studio.

June 07, 2024

Vertex AI Workbench

You can now create a Vertex AI Workbench instance based on a custom container. This feature is available in Preview. Only custom containers derived from the Google-provided base container are supported. For more information, see Create an instance using a custom container.

June 03, 2024

Vertex AI Workbench

You can now use Workforce Identity Federation with Vertex AI Workbench instances in Preview. Workforce Identity Federation lets you create and manage Vertex AI Workbench instances with credentials provided by an external identity provider (IdP). For more information, see Create an instance with third party credentials.

May 31, 2024

Generative AI on Vertex AI

Anthropic Claude 3.0 Opus model

The Anthropic Claude 3.0 Opus model is Generally Available. To learn more, see its model card in Model Garden.

Generative AI on Vertex AI Regional APIs

Generative AI on Vertex AI regional APIs are available in the following three regions:

us-east5
me-central1
me-central2

Vertex AI

Model Monitoring v2 is in Preview, which centralizes model monitoring configuration and visualization on a model version and enables monitoring models being served outside of Vertex AI. For more information, see Vertex AI Model Monitoring overview.

Vertex AI Regional APIs

Vertex AI regional APIs are available in the following seven regions:

us-east5
us-south1
africa-south1
europe-southwest1
europe-west12
me-central1
me-central2

May 28, 2024

Generative AI on Vertex AI

Gemini models support the frequencyPenalty and presencePenalty parameters. Use frequencyPenalty to control the probability of repeated text in a response. Use presencePenalty to control the probability of generating more diverse content. For more information, see Gemini model parameters.

Vertex AI

Vector Search sparse embeddings and hybrid search in Public preview

Vector Search supports sparse embeddings and hybrid search in Public preview. Hybrid search uses both dense and sparse embeddings, which lets you search based on a combination of keyword search and semantic search. For how to format dense, sparse, and hybrid embeddings, see Input data and structure.

May 24, 2024

Generative AI on Vertex AI

The Gemini 1.5 Pro (gemini-1.5-pro-001) and Gemini 1.5 Flash (gemini-1.5-flash-001) models are Generally Available. For more information, see Google models, Overview of the Gemini API, and Send multimodal prompt requests.

May 20, 2024

Generative AI on Vertex AI

The following models have been added to Model Garden:

E5: A text embedding model series that can be served with a GPU or CPU.
Instant ID: An identity preserving text-to-image generation model.
Stable Diffusion XL lightning: A text-to-image generation model that is based on SDXL but requires fewer inference iterations.

To see a list of all available models, see Explore models in Model Garden.

May 17, 2024

Vertex AI Workbench

M121 release

The M121 release of Vertex AI Workbench user-managed notebooks includes the following:

Updated Nvidia drivers to 550.54.15 to fix an issue where Nvidia drivers failed to install on startup after Debian 11 images upgraded kernel to linux-image-5.10.0-29-cloud-amd64.
The linux-headers-cloud-amd64 metapackage is now installed for faster driver recompiling on kernel upgrades.
TensorFlow 2.6 CPU and GPU images are deprecated. There will be no further updates to these images in future releases.

The M121 release of Vertex AI Workbench managed notebooks includes the following:

Updated the R CPU kernel from R 4.3 to R 4.4.

M121 release

The M121 release of Vertex AI Workbench instances includes the following:

Updated Nvidia drivers to 550.54.15 to fix an issue where Nvidia drivers failed to install on startup after Debian 11 images upgraded kernel to linux-image-5.10.0-29-cloud-amd64.
The linux-headers-cloud-amd64 metapackage is now installed for faster driver recompiling on kernel upgrades.

May 14, 2024

Generative AI on Vertex AI

Gemini 1.5 Flash (Preview)

Gemini 1.5 Flash (gemini-1.5-flash-preview-0514) is available in Preview. Gemini 1.5 Flash is a multimodal model designed for fast, high volume, cost-effective text generation and chat applications. It can analyze text, code, audio, PDF, video, and video with audio.

Grounding Gemini with Google Search is GA

The Gemini API Grounding with Google Search feature is available in GA. This is available for Gemini 1.0 Pro models. To learn more about model grounding, see Grounding with Google Search.

Batch prediction support for Gemini

Batch prediction is available for Gemini in preview. Available Gemini models include Gemini 1.0 Pro, Gemini 1.5 Pro, and Gemini 1.5 Flash. To get started with batch prediction, see Get batch predictions for Gemini.

PaliGemma model

The PaliGemma model is available. PaliGemma is a lightweight open model that's part of the Google Gemma model family. It's the Gemma model family's best model option for image captioning tasks and visual question and answering tasks. Gemma models are based on Gemini models and intended to be extended by customers.

New stable text embedding models

The following text embedding models are available GA:

text-embedding-004
text-multilingual-embedding-002

For details on how to use these models, see Get text embeddings.

Vertex AI

Ray on Vertex AI is now generally available (GA) and includes the following updates:

Ray version 2.9.3 and Python 3.10 are supported. For information about Ray image support policies, see Supported versions.
VPC peering connection is no longer required if you use public endpoints.
Custom images are supported with Ray on Vertex AI.
You can use custom service accounts with Ray on Vertex AI.
A Colab template is not automatically created when you create a Ray Cluster. Instead, you can connect directly to Ray on Vertex AI clusters from Colab Enterprise's side panel.

For Ray on Vertex AI, Ray version 2.4 is no longer supported. Migrate your code to support Ray 2.9.3 or later and then delete Ray clusters that are running 2.4.

April 30, 2024

Vertex AI

Vertex AI custom training supports TPU v5e. For details, see Training with TPU accelerators.

April 29, 2024

Vertex AI Workbench

M120 release

The M120 release of Vertex AI Workbench managed notebooks includes the following:

Minor bug fixes for the libcurl package.

April 25, 2024

Vertex AI Workbench

M120 release

The M120 release of Vertex AI Workbench user-managed notebooks includes the following:

Upgraded TensorFlow 2.15 user-managed notebooks to TensorFlow 2.15.1.
Minor bug fixes for the libcurl package.

M120 release

The M120 release of Vertex AI Workbench instances includes the following:

Minor bug fixes for the libcurl package.

April 18, 2024

Generative AI on Vertex AI

Meta's open weight Llama 3 model is available in the Vertex AI Model Garden.

April 15, 2024

Vertex AI

Persistent resource for Vertex AI custom training is generally available (GA).

Vertex AI Feature Store

The following features of Vertex AI Feature Store are now generally available (GA):

Optimized online serving: Serve features at ultra-low latencies. For more information, see Optimized online serving.
Search using embeddings: Perform vector similarity searches to retrieve semantically similar or related features for real-time serving. You can search using embeddings if your online store is configured to support embeddings. For more information, see Search using embeddings.
Feature view sync: Refresh or synchronize the feature data in a feature view within an online store from the feature data source in BigQuery. For more information, see Sync feature data to online store.

April 11, 2024

Generative AI on Vertex AI

Anthropic Claude 3.0 Opus model

The Anthropic Claude 3.0 Opus model is available in Preview. The Claude 3.0 Opus model is an Anthropic partner model that you can use with Vertex AI. It's the most capable of the Anthropic models at performing complex tasks quickly. To learn more, see its model card in Model Garden.

April 09, 2024

Generative AI on Vertex AI

New Imagen on Vertex AI image generation model and features

The 006 version of the Imagen 2 image generation model (imagegeneration@006) is now available. This model offers the following additional features:

Additional aspect ratios (1:1, 3:4, 4:3, 9:16, 16:9)
Digital watermark (SynthID) enabled by default
Watermark verification*
New user-configurable safety features (safety setting, person/face setting)

For more information, see Model versions and Generate images using text prompts.

* The seed field can't be used while digital watermark is enabled.

New Imagen on Vertex AI image editing model and features

The 006 version of the Imagen 2 image editing model (imagegeneration@006) is now available. This model offers the following additional features:

Inpainting - Add or remove content from a masked area of an image
Outpainting - Expand a masked area of an image
Product image editing - Identify and maintain a primary product while changing the background or product position

For more information, see Model versions.

Change in Imagen image generation version 006 (imagegeneration@006) seed field behavior

For the new Imagen image generation model version 006 (imagegeneration@006) the seed field behavior has changed. For the v.006 model a digital watermark is enabled by default for image generation. To be able to use a seed value to get deterministic output you must disable digital watermark generation by setting the following parameter: "addWatermark": false.

For more information, see the Imagen for image generation and editing API reference.

CodeGemma model

The CodeGemma model is available. CodeGemma is a lightweight open model that's part of the Google Gemma model family. CodeGemma is the Gemma model family's code generation and code completion offering. Gemma models are based on Gemini models and intended to be extended by customers.

Grounding Gemini and Grounding with Google Search

The Gemini API now supports Grounding with Google Search in Preview. Currently available for Gemini 1.0 Pro models.

Regional APIs

Regional APIs are available in 11 new countries for Gemini, Imagen, and embeddings.
US and EU have machine-learning processing boundaries for the gemini-1.0-pro-001, gemini-1.0-pro-002, gemini-1.0-pro-vision-001, and imagegeneration@005 models.

Generative AI on Vertex AI security control update

Security controls are available for the online prediction feature for Gemini 1.0 Pro and Gemini 1.0 Pro Vision.

Gemini 1.5 Pro (Preview)

Gemini 1.5 Pro (gemini-1.5-pro-preview-0409) is available in Preview. Gemini 1.5 Pro is a multimodal model that analyzes text, code, audio, PDF, video, and video with audio.

New text embedding models

The following text embedding models are now in Preview.

text-embedding-preview-0409
text-multilingual-embedding-preview-0409

When evaluated using the MTEB benchmarks, these models produce better embeddings compared to previous versions. The new models also offer dynamic embedding sizes, which you can use to output smaller embedding dimensions, with minor performance loss, to save on computing and storage costs.

For details on how to use these models, refer to the public documentation and try out our Colab.

System instructions

System instructions are supported in Preview by the Gemini 1.0 Pro (stable version gemini-1.0-pro-002 only) and Gemini 1.5 Pro (Preview) multimodal models. Use system instructions to guide model behavior based on your specific needs and use cases. For more information, see System instructions examples.

Supervised Tuning for Gemini

Supervised tuning is available for the gemini-1.0-pro-002 model.

Online Evaluation Service

Generative AI evaluation supports online evaluation in addition to pipeline evaluation. The list of supported evaluation metrics has also expanded. See API reference and SDK reference.

Generative AI Knowledge Base

The Jump Start Solution: Generative AI Knowledge Base demonstrates how to build a simple chatbot with business- and domain-specific knowledge.

Text translation

Translate text in Vertex AI Studio is available in Preview.

Gemini 1.0 Pro stable version 002

The 002 version of the Gemini 1.0 Pro multimodal model (gemini-1.0-pro-002) is available. For more information about stable versions of Gemini models, see Gemini model versions and lifecycle.

Vertex AI Studio features and updates

The Vertex AI Studio supports side-by-side comparison to allow users to compare up to 3 prompts in a side-by-side view.
The Vertex AI Studio supports rapid evaluation in console and the ability to upload a ground truth response (or a model response to try to emulate).

To learn more, see Try your prompts in Vertex AI Studio

April 02, 2024

Generative AI on Vertex AI

Model Garden supports all Text Generation Inference supported models in HuggingFace:

Verified deployment settings for about 400 Hugging Face text generation models (including google/gemma-7b-it, meta-llama/Llama-2-7b-chat-hf, and mistralai/Mistral-7B-v0.1).
Other Hugging Face text generation models have unverified deployment settings that are auto generated.

March 29, 2024

Generative AI on Vertex AI

The MedLM-large model infrastructure has been upgraded to improve latency and stability. Responses from the model might be slightly different.

Vertex AI Workbench

M119 release

The M119 release of Vertex AI Workbench user-managed notebooks includes the following:

Fixed an issue wherein Dataproc extensions caused JupyterLab to crash when remote kernels weren't available.

March 18, 2024

Vertex AI

Vector Search heuristics-based compaction

Vector Search uses heuristics-based metrics assess whether to trigger compaction. This prevents unnecessary compaction, and thus reduces cost. For general information about compaction, see Compaction.

Vertex AI Workbench

M118 release

The M118 release of Vertex AI Workbench user-managed notebooks includes the following:

PyTorch 2.1.0 with CUDA 12.1 and Python 3.10 user-managed notebooks instances are now available.
PyTorch 2.2.0 with CUDA 12.1 and Python 3.10 user-managed notebooks instances are now available.
Updated Nvidia drivers of older user-managed notebooks images to R535.

The M118 release of Vertex AI Workbench managed notebooks includes the following:

Updated Nvidia drivers to R535, which fixed a bug where the latest PyTorch 2.0 kernel didn't work due to outdated drivers.

M118 release

The M118 release of Vertex AI Workbench instances includes the following:

Updated Nvidia drivers to R535.

March 08, 2024

Vertex AI

Vertex AI Feature Store

The following features of Vertex AI Feature Store are now available in Preview:

Integration of Vertex AI Feature Store with Dataplex: Online store instances, feature views, and feature groups are now automatically registered as data assets in Data Catalog, a Dataplex feature that catalogs metadata from these resources. You can use the metadata search capability of Dataplex to search for and view the metadata of these resources. For more information, see Search for resource metadata in Data Catalog.
Service account configuration for feature views: You can configure a feature view to use a dedicated service account. By default, every feature view uses the service account configured for your project. For more information, see Configure the service account for a feature view.
Multiple entity IDs for a feature view: While creating or updating a feature view, you can specify multiple entity ID columns. For more information, see Create a feature view.

March 05, 2024

Vertex AI

Create an empty index with Vector Search

You can create an empty index in Vector Search for batch and for streaming. No embedding data is required at index creation time, which enables faster startup time. To learn more, see Manage indexes.

March 04, 2024

Vertex AI

Vertex AI Prediction

You can now use A3 machine types to serve predictions.

February 29, 2024

Vertex AI

Vector Search feature launch

Update streaming index metadata: With this launch, you can directly update restricts and numeric restricts of data points inside StreamUpdate indexes without the compaction cost of a full update. To learn more, see Update dynamic metadata.

February 28, 2024

Vertex AI Workbench

M117 release

The M117 release of Vertex AI Workbench instances includes the following:

Removed the Cloud Storage browser in the left side pane in favor of the existing Mount shared storage button.

February 27, 2024

Colab Enterprise

VPC Service Controls has general availability support in Colab Enterprise.

For more information, see Use VPC Service Controls.

February 26, 2024

Vertex AI

Structured logging support for Vertex AI custom training. For details, see Write code to return container logs.

Ground Multimodal Models

Model grounding for gemini-pro is available in Preview. Use grounding to connect the gemini-pro model to unstructured text data stores in Vertex AI Search. Grounding lets models access and use the information in the data repositories to generate more enhanced and nuanced responses. For more information, see Ground multimodal models.

February 21, 2024

Vertex AI

Gemma open models are available

Gemma models, a family of lightweight, open models built from the same research and technology used to create the Gemini models, are available to run on your hardware, mobile devices, or hosted services. To learn more, see Use Gemma open models and the Gemma Model Garden card.

February 15, 2024

Vertex AI

The Vertex AI Gemini 1.0 Pro and Gemini 1.0 Pro Vision multimodal language models are generally available (GA). They have also been made available in the following regions: europe-west1, europe-west2, europe-west3, europe-west4, and europe-west9.

For more information, see the following topics:

February 09, 2024

Vertex AI

Multimodal embeddings video support is generally available

Embeddings for video data is now generally available (GA) using the multimodal embedding model (multimodalembedding). For more information, see the product documentation.

This features incurs pricing based on the mode you use. For more information, see pricing.

February 08, 2024

Vertex AI Workbench

M116 release

The M116 release of Vertex AI Workbench user-managed notebooks includes the following:

Updated custom container user-managed notebooks to use NVIDIA driver version 535.104.05.
Fixed bugs in custom container user-managed notebooks where GPUs either wouldn't attach to the container properly, or detached after some time.

The M116 release of Vertex AI Workbench managed notebooks includes the following:

Fixed a bug (present in versions M113 through M115) that prevented new local kernels from being usable.

February 07, 2024

Vertex AI

The following models have been added to Model Garden:

Stable Diffusion XL LCM: The Latent Consistency Model (LCM) enhances text-to-image generation in Latent Diffusion Models by enabling faster and high-quality image creation with fewer steps.
LLaVA 1.5: Deploy LLaVA 1.5 models.
PyTorch-ZipNeRF: The Pytorch-ZipNeRF model is a state-of-the-art implementation of the ZipNeRF algorithm in the Pytorch framework, designed for efficient and accurate 3D reconstruction from 2D images.
LLaMA 2 (Quantized): A quantized version of Meta's Llama 2 models.
WizardLM: WizardLM is a large language model (LLM) developed by Microsoft, fine-tuned on complex instructions by adapting the Evol-Instruct method.
WizardCoder: WizardCoder is a large language model (LLM) developed by Microsoft, fine-tuned on complex instructions by adapting the Evol-Instruct method to the domain of code.
AutoGluon: With AutoGluon you can train and deploy high-accuracy machine learning and deep learning models for tabular data.
Lama (Large mask inpainting): Use Large Mask Inpainting with fast Fourier convolutions (FFCs), a high receptive field perceptual loss, and large training masks for resolution-robust image inpainting.

The following changes have been made to Model Garden:

Added one-click tuning button, and dedicated deployment, tuning, quantization, and evaluation notebooks for Llama 2.
Added one-click deployment button for more than 20 models with pre-trained OSS artifacts, including Salesforce/blip-image-captioning-base and timbrooks/instruct-pix2pix.
Supported CodeLlaMA70b with notebooks and the one-click deployment button.
Added tuning notebooks for Mistral models.
Added serving notebooks for Stable Video Diffusion Img2Vid XT. These notebooks are used for research purposes.

February 05, 2024

Vertex AI

Query an index from the Vector Search console

Vector Search has launched an improved console experience for querying both private and public deployed indexes, now available in Preview. From the console, you can create an index and endpoint, deploy the index to the endpoint, and query the index for nearest neighbors. For more information, see Manage indexes.

January 29, 2024

Vertex AI

Vertex Prediction

You can now customize more deployment parameters when uploading your models, such as shared memory allocation and custom startup and readiness probes. These parameters may be useful when deploying LLMs.

For more information, see Deploy generative AI models, Custom container requirements for prediction, and ModelContainerSpec.

January 19, 2024

Vertex AI Workbench

M115 release

The M115 release of Vertex AI Workbench user-managed notebooks includes the following:

Added support for TensorFlow 2.15 with Python 3.10 on Debian 11.
Added support for TensorFlow 2.14 with Python 3.10 on Debian 11.

The M115 release of Vertex AI Workbench managed notebooks includes the following:

Fixed the BigQuery connector within PySpark containers.

M115 release

The M115 release of Vertex AI Workbench instances includes the following:

Added support for venv kernels.

January 16, 2024

Vertex AI Workbench

Vertex AI Workbench managed notebooks is deprecated. On January 30, 2025, support for managed notebooks will end and the ability to create managed notebooks instances will be removed. Existing instances will continue to function but patches, updates, and upgrades won't be available. To continue using Vertex AI Workbench, you can migrate your managed notebooks instances to Vertex AI Workbench instances.

Vertex AI Workbench user-managed notebooks is deprecated. On January 30, 2025, support for user-managed notebooks will end and the ability to create user-managed notebooks instances will be removed. Existing instances will continue to function but patches, updates, and upgrades won't be available. To continue using Vertex AI Workbench, you can migrate your user-managed notebooks instances to Vertex AI Workbench instances.

January 12, 2024

Vertex AI

Model tuning for the textembedding-gecko and textembedding-gecko-multilingual models is available in GA. You can use supervised fine-tuning to tune the textembedding-gecko model. For more information, see Tune text embeddings.

January 08, 2024

Vertex AI

AutoSxS evaluates LLMs side by side

The automatic side-by-side (AutoSxS) evaluation tool is available in Preview to A/B test the performance of your LLMs or pre-generated predictions. It's comparable to human evaluators, yet faster, available on-demand, and more cost-efficient.

January 05, 2024

Vertex AI

Generative AI on Vertex AI regional expansion

Generative AI on Vertex AI features for Batch Prediction and Model Evaluation are available in 12 additional Google Cloud regions.

December 29, 2023

Vertex AI

Vertex AI regional expansion

Vertex AI features for AutoML Forecasting, AutoML Tabular, Batch Prediction, Online Prediction, Pipelines, Training, Vector Search, and Vizier are available in 10 additional Google Cloud regions.

December 27, 2023

Vertex AI

Vertex Prediction

Quota for Custom model serving is now calculated based on your deployed model's real-time usage of compute resources.

Previously, compute resources, such as the number of Nvidia A100 GPUs being used, were deducted from your project's quota based on the deployed model's maxReplicaCount.

This change lets you deploy models based on actual compute usage rather than max usage, but it can prevent your deployed models from autoscaling if your quota is exhausted.

December 18, 2023

Vertex AI

Model Garden updates:

Support for hyperparameter tuning and customized datasets for OpenLLaMA models using the dataset format used by supervised tuning in Vertex AI.
Support for GPTQ conversions for falcon-instruct models.
Add Latent Consistent Models, and research purpose only SDXL-Turbo models to stable diffusion XL notebooks.
Add Mixtral 8x7B models in the Mistral notebook.

December 14, 2023

Vertex AI

Vertex AI Prediction

You can now use Cloud TPU v5e to serve online predictions. For more information, see Use Cloud TPUs for online prediction.

Vertex AI Workbench

M114 release

The M114 release of Vertex AI Workbench user-managed notebooks includes the following:

Starting with this release, Python 3.7 is no longer available.
Upgraded R to 4.3 on Debian 11 Python 3.10 instances.
Upgraded JupyterLab to 3.6.6.

The M114 release of Vertex AI Workbench managed notebooks includes the following:

Starting with this release, Python 3.7 is no longer available.
Added new Dataproc extension for remote kernels.
Upgraded JupyterLab to 3.6.6.
Fixed an issue that sometimes prevented users from running or scheduling notebooks using a default kernel.

December 13, 2023

Vertex AI

Vertex AI Gemini models

Vertex AI Gemini Pro and Gemini Pro Vision multimodal language models are available in Preview. For more information, see the following topics:

Imagen 2 General Availability

The 005 version of Imagen's image generation model (imagegeneration@005) is now generally available (GA) for image generation tasks. This model version is now the default for image generation tasks. For more information, see the product documentation.

For general information about Imagen models and versions, see Imagen model versions and lifecycle.

December 12, 2023

Vertex AI

Text embedding model 003 (textembedding-gecko@003) available

The updated stable version of the text embedding foundation model, textembedding-gecko@003, is available. textembedding-gecko@003 features improved quality compared to the previous stable versions, textembedding-gecko@001 and textembedding-gecko@002. For more information on model versions, see Model versions and lifecycle.

December 08, 2023

Vertex AI

Generative AI on Vertex AI security control update

The Access Transparency (AXT) security control is available for the following features:

Embeddings for Multimodal online prediction
Imagen on Vertex AI online prediction
Imagen on Vertex AI tuning

December 06, 2023

Vertex AI

Version @002 of the models for text, chat, code, and code chat are available. The @002 model versions include improved prompt responses. The @002 models are:

text-bison@002
chat-bison@002
code-bison@002
codechat-bison@002

To ensure that you always use the stable model version, specify the model identifier with the version number. For example, text-bison@002. For more information, see Model versions and lifecycle.

Version 2 of the stable version of the Codey code completion foundation model, named code-gecko@002, is available. code-gecko@002 features improved quality and reduced latency compared to the previous stable version, code-gecko@001. These improvements can lead to a higher rate of acceptance.

December 05, 2023

Vertex AI

Grounding with Vertex AI Search

Model grounding is available in (Preview). Use grounding to connect the text-bison and chat-bison models to unstructured data stores in Vertex AI Search. Grounding lets models access and use the information in the data repositories to generate more enhanced and nuanced responses. For more information, see the Grounding Overview.

December 01, 2023

Vertex AI

The following Vertex AI Model Garden updates are available:

Updated default model deployment settings with L4 GPUs, such as LLaMA2, falcon-instruct, openllama, Stable Diffusion 1.5, 2.1, and XL models.
Support for hyperparameter tuning and customized datasets for LLaMA2 models using the dataset format used by supervised tuning in Vertex AI.
Recommended LoRA and QLoRA settings for large language model tuning in Vertex AI. For details, see LoRA and QLoRA recommendations for LLMs.
Support for AWQ and GPTQ conversions for LLaMA2 and OpenLLaMA models.
Benchmark reports for ViT pytorch and JAX training, OpenLLaMA 3b/7b/13b hyperparameter tuning, and Stable Diffusion 1.5 tuning and serving.

November 30, 2023

Vertex AI

The Unicorn model size for PaLM 2 for Text is generally available (GA). The text-unicorn model provides improved response quality and reasoning capability compared to the text-bison model. For details, see Model information.

Vertex AI's integration of model and dataset metadata into Dataplex's Data Catalog service is now generally available (GA). Search and discover these assets across projects and regions in Dataplex. Learn more at Use Data Catalog to search for model and dataset resources.

Note: For datasets of type TEXT_PROMPT, navigating in the UI from Data Catalog back to Vertex AI (via the Open in Vertex AI button, or using the Resource URL link) results in a blank page. This is a known issue and expected to be fixed in the near future. To directly view TEXT_PROMPT datasets in Vertex AI, navigate to the Generative AI My Prompts tab.

November 24, 2023

Vertex AI

ComputeToken API now available in Preview

The ComputeToken API is now available in (Preview). You can use this API to get a list of tokens for a given prompt. A token is a way to represent a common sequence of characters found in a text input. To learn more, see Get a list of tokens.

November 17, 2023

Vertex AI

Vertex AI Feature Store

The following features of the new and improved Vertex AI Feature Store are now generally available (GA):

Feature Registry: Register your feature data sources in BigQuery by creating feature groups and features. For more information, see Create a feature group and Create a feature.
Cloud Bigtable online serving: Serve features from one or more BigQuery data sources. You can set up Cloud Bigtable online serving by defining online serving clusters called online store instances and creating feature views within the online store instances.

Note that the following features of Vertex AI Feature Store are still in Preview:

Serve features at ultra-low latencies with Optimized online serving.
Sync data in a feature view within an online store.
Retrieve vector embeddings for real-time serving.

For more information, see About Vertex AI Feature Store.

November 16, 2023

Vertex AI Workbench

M113 release

The M113 release of Vertex AI Workbench instances includes the following:

Added the Dataproc JupyterLab plugin to Vertex AI Workbench instances. To get started, see Create a Dataproc-enabled instance.
When using an instance's Google Cloud CLI, gcloud config is preset with the following defaults:
- project is set to your instance's project.
- Your compute region is set to your instance's region.
- Your Dataproc region is set to your instance's region.
Fixed an issue that prevented Dataproc kernels from working.
Fixed a CORS (cross-origin resource sharing) error.

M113 release

The M113 release of Vertex AI Workbench user-managed notebooks includes the following:

Miscellaneous bug fixes and improvements in Python 3.10 notebooks.

November 13, 2023

Vertex AI

Numerical filtering available in Vertex AI Vector Search

With Vector Search you can restrict results by "filtering" your index results. In addition to filtering by using categorical restrictions, you can now use numeric filtering. To learn more, see Filter vector matches.

November 10, 2023

Vertex AI

Generative AI on Vertex AI

Security controls are available for additional Generative AI on Vertex AI features.

November 07, 2023

Vertex AI

Training on TPU VMs is generally available (GA).

November 03, 2023

Vertex AI

The following models have been added to Model Garden:

ImageBind: Multimodal embedding model.
Vicuna v1.5: LLM finetuned based on llama2.
OWL-ViT v2: SoTA Open Vocabulary Object Detection model.
DITO: SoTA Open Vocabulary Object Detection model.
NLLB: Multi-language translation model.
Mistral-7B: SoTA LLM at small size.
BioGPT: LLM finetuned for biomedical domain.
BiomedCILP: Multimodal foundational model finetuned for biomedical domain.

To see a list of all available models, see Explore models in Model Garden.

New textembedding-gecko and textembedding-gecko-multilingual stable model versions

The following stable model versions are available in Generative AI on Vertex AI:

textembedding-gecko@002
textembedding-gecko-multilingual@001

For more information on model versions, see Model versions and lifecycle.

Model Garden

Improved language model serving throughput. For details, see Serving open source large language models efficiently on Model Garden. Notebooks in the relevant model cards have been updated accordingly.
Inference speed up to 2 times faster compared with original implementation for Stable Diffusion 1.5, 2.1, and XL models.
Improved the workflow of the Deploy button in all supported model cards.
Updated notebooks for Llama2, OpenLlama, and Falcon Instruct with suggested machine specs for model serving, and EleutherAI's evaluation harness dockers for model evaluation.

November 02, 2023

Vertex AI

Generative AI support on Vertex AI

Generative AI on Vertex AI can be accessed through 12 regional APIs in North America, Europe, and Asia. Regional APIs let customers control where data is stored at-rest.

October 30, 2023

Vertex AI

Deep Learning VM Images is a set of prepackaged virtual machine images with a deep learning framework that are ready to be run out of the box. Recently, an out-of-bounds write vulnerability was discovered in the ReadHuffmanCodes() function in the libwebp library. This might impact images that use this library.

Google Cloud continuously scans its publicly published images and updates the packages to assure patched distros are included in the latest releases available for customer adoption. Deep Learning VM Images have been updated to ensure that the latest VM images include the patched distros. Customers adopting the latest VM images are not exposed to this vulnerability.

For more information, see the Vertex AI security bulletin.

October 17, 2023

Vertex AI

New Vertex AI Vector Search Console

Vector Search has launched a console experience in Google Cloud for creating and deploying indexes, now available in Preview. From the console, you can create indexes, and create public or VPC endpoints for your indexes, and deploy. For more information, see Manage indexes.

Vertex AI Vector Search Improvements

Vector Search has improved the initial index creation process for smaller indexes (<100MB), reducing time to build from about 1 hour to about 5 mins. To get started, see Vector Search quickstart to create an index.

October 11, 2023

Colab Enterprise

Colab Enterprise is now generally available (GA). Colab Enterprise combines the popular collaborative features of Colaboratory with the security and compliance capabilities of Google Cloud. Colab Enterprise includes:

Sharing and collaborating functionality, with IAM access control.
Google-managed compute and runtime provisioning, with configurable runtime templates.
Integrations with Vertex AI and BigQuery.
Inline code completion with Duet AI (Preview) assistance.
End-user credential authentication for running your notebook code.
Idle shutdown for runtimes (Experimental).

To get started, see Introduction to Colab Enterprise or create a notebook and start coding.

October 10, 2023

Vertex AI Workbench

M112 release

The M112 release of Vertex AI Workbench user-managed notebooks includes the following:

Miscellaneous bug fixes and improvements.

October 05, 2023

Vertex AI

Ray on Vertex AI is now available in Preview

Ray is an open-source framework for scaling AI and Python applications. Ray provides the infrastructure to perform distributed computing and parallel processing for your machine learning workflow.

You can now create Ray clusters and develop your Ray applications on Vertex AI. This feature is in Preview. For more information, see Ray on Vertex AI overview.

October 04, 2023

Vertex AI

Model tuning for the textembedding-gecko model is now available in Preview

You can now use supervised fine-tuning to tune the textembedding-gecko model. This feature is in (Preview). For more information, see Tune text embeddings.

Vertex AI Prediction

You can now use C3 machine types to serve predictions.

Vertex AI Feature Store

The new and improved Vertex AI Feature Store is now available in Preview. With the new Vertex AI Feature Store you can streamline your feature management in the following ways:

Store and maintain your offline feature data in BigQuery, taking advantage of the data management capabilities of BigQuery. In the new Vertex AI Feature Store, BigQuery serves as the offline store. You don't need to copy or import feature data to an offline store in Vertex AI.
Register your feature data sources in BigQuery by creating feature groups and features.
Define online serving clusters called online store instances; and then serve features from one or more BigQuery data sources, by aggregating them in a feature view within an online store instance. Use Optimized online serving for ultra-low latency needs and Cloud Bigtable online serving for high data volumes.
Retrieve vector embeddings stored in BigQuery for real-time serving.

For more information, see About Vertex AI Feature Store.

October 03, 2023

Vertex AI

TorchServe is used to host PyTorch machine learning models for online prediction. Vertex AI provides pre-built PyTorch model serving containers which depend on TorchServe. Vulnerabilities were recently discovered in TorchServe which would allow an attacker to take control of a TorchServe deployment if its model management API is exposed. Customers with PyTorch models deployed to Vertex AI online prediction are not affected by these vulnerabilities, since Vertex AI does not expose TorchServe's model management API. Customers using TorchServe outside of Vertex AI should take precautions to ensure their deployments are set up securely.

For more information, see the Vertex AI security bulletin.

September 25, 2023

Vertex AI Workbench

Vertex AI Workbench instances are now generally available (GA). Vertex AI Workbench instances combine features from managed notebooks and user-managed notebooks to provide a robust data science solution. Supported features include:

Idle timeout
BigQuery and Cloud Storage integrations
End-user and service account authentication
VPC Service Controls
Customer managed encryption keys (CMEK) and Cloud External Key Manager (Cloud EKM)
Health status monitoring
Scheduled notebook runs
Dataproc integration

To get started, see Introduction to Vertex AI Workbench instances.

September 18, 2023

Vertex AI Workbench

Debian 10 and Python 3.7 images have reached their end of patch and support life for Vertex AI Workbench managed notebooks and user-managed notebooks. Debian 11 and Python 3.10 images are available.

September 14, 2023

Vertex AI Workbench

v1 & v2

M111 release

The M111 release of Vertex AI Workbench instances includes the following:

Miscellaneous software updates.

The M111 release of Vertex AI Workbench user-managed notebooks includes the following:

PyTorch 2.0 user-managed notebooks instances now include PyTorch XLA 2.0.
Miscellaneous software updates.

The M111 release of Vertex AI Workbench managed notebooks includes the following:

Miscellaneous software updates.

September 08, 2023

Vertex AI

Vertex AI Prediction

You can now use A2 Ultra machines to serve predictions in us-central1, us-east4, europe-west4, and asia-southeast1. Each A2 Ultra machine has a fixed number of NVIDIA A100 80GB GPUs attached.

September 06, 2023

Vertex AI

Vertex AI Prediction

The following prebuilt containers for prediction have been updated:

tf2-cpu.2-12
tf2-gpu.2-12
tf2-cpu.2-11
tf2-gpu.2-11
tf2-cpu.2-10
tf2-gpu.2-10
tf2-cpu.2-9
tf2-gpu.2-9
tf2-cpu.2-8
tf2-gpu.2-8
sklearn-cpu.1-2
xgboost-cpu.1-7
pytorch-cpu.2-0
pytorch-gpu.2-0
pytorch-cpu.1-13
pytorch-gpu.1-13

To update your containers, redeploy your models. To learn more, see Vertex AI framework support policy and Prebuilt containers for prediction.

September 01, 2023

Vertex AI

Pricing update

The pricing for text-bison has been reduced to $0.0005 per 1,000 input and output characters. For details, see Vertex AI Pricing.

August 31, 2023

Vertex AI

Experiment management: Google Cloud console now supports visualization of your model's performance changes over steps during training, and shows advanced run comparisons. To learn more, see Compare and analyze runs: Google Cloud console.

August 29, 2023

Colab Enterprise

Colab Enterprise is now available in Preview. Colab Enterprise combines the popular collaborative features of Colaboratory with the security and compliance capabilities of Google Cloud. Colab Enterprise includes:

Sharing and collaborating functionality, with IAM access control.
Google-managed compute and runtime provisioning, with configurable runtime templates.
Integrations with Vertex AI and BigQuery.
Inline code completion with Duet AI assistance.
End-user credential authentication for running your notebook code.

To get started, see Introduction to Colab Enterprise or create a notebook and start coding.

Vertex AI

Imagen on Vertex AI now offers the following Generally Available (GA) features:

* Restricted access feature.

For more information about Imagen or how to get access to restricted GA features, see the Imagen on Vertex AI overview.

Stream responses from Generative AI models

Generative AI model streaming support is now Generally Available (GA). After you send a prompt, the model returns response tokens as they're generated instead of waiting for the entire output to be available.

Supported models are:

text-bison
chat-bison
code-bison
codechat-bison

To learn more, see Stream responses from Generative AI models.

New Generative AI support on Vertex AI models and expanded language support

Generative AI support on Vertex AI has been updated to include new language model candidates (latest models), language models that support input and output tokens up to 32k, and more supported languages.

For details, see Available models and Model versions and lifecycle.

Model tuning for the text-bison model is now Generally Available (GA)

Tuning the text-bison model with supervised fine-tuning (SFT) is now Generally Available (GA) . For more information, see Tune text models.

Model tuning for the chat-bison model is now available in Preview

You can now use supervised fine-tuning to tune the chat-bison model. This feature is in (Preview). For more information, see Tune text models.

New embedding model now available in Preview

Generative AI support on Vertex AI users can now create embeddings using a new model trained on a wide range of non-English languages in (Preview).

textembedding-gecko-multilingual

To learn more, see Get text embeddings.

Reinforcement learning from human feedback (RLHF) tuning for text-bison The Generative AI text generation foundation model (text-bison) now supports RLHF tuning. The RLHF tuning feature is in (Preview). For more information, see Use RLHF model tuning.

Vertex AI Codey APIs language support

Vertex AI Codey APIs now support additional programming languages. For more information, see Supported coding languages

Vertex AI Codey APIs now support supervised fine-tuning (SFT)

The code chat (codechat-bison) and code generation (code-bison) Vertex AI Codey APIs models now support supervised fine-tuning (SFT). The supervised-fine tuning for Vertex AI Codey APIs models feature is in (Preview). For more information, see Tune code models.

Metrics-based model evaluation

You can evaluate the performance of foundation models and tuned models against an evaluation dataset for classification, summarization, question answering, and general text generation. This feature is available in (Preview).

To learn more, see Evaluate model performance.

Vertex AI Vector Search is the new product name for Vertex AI Matching Engine.

Vertex AI Model Registry Models and managed datasets are now synced to Dataplex's Data Catalog service. Data Catalog enables organization-wide search and discovery of data artifacts, while still maintaining IAM boundaries. The sync and search of these assets is available in Preview. For more information, see Data Catalog documentation.

CountToken API now available in Preview

The CountToken API is now available in (Preview). You can use this API to get the token count and the number of billable characters for a prompt. To learn more, see Get token count.

The Vertex AI Pipelines Template Gallery is now generally available (GA). The Template Gallery contains Google-authored pipeline and component templates to bootstrap your MLOps practice. Customize and run the templates as-is or embed them into your own pipelines. For more information, see Use a prebuilt template from the Template Gallery.

August 28, 2023

Vertex AI

Tabular Workflow for Forecasting is available in Preview. For documentation, refer to Tabular Workflow for Forecasting.

August 22, 2023

Vertex AI

Vertex AI custom training has launched persistent resources in Preview. A persistent resource is a long-running cluster of machines that you can use to run custom training jobs. Once created, the persistent resource remains available for future training jobs, so you don't have to wait for compute resources to be provisioned each time you want to train a model.

August 18, 2023

Vertex AI

The Vertex AI Matching Engine public endpoint is now generally available (GA). For information about how to get started, see Matching Engine Setup.

August 11, 2023

Vertex AI

Generative AI on Vertex AI supports CMEK, VPC Service Controls, Data Residency, and Access Transparency. For more information, see Security controls.

August 10, 2023

Vertex AI Workbench

v1 & v2

M110 release

The M110 release of Vertex AI Workbench user-managed notebooks includes the following:

Added support for TensorFlow 2.13 with Python 3.10 on Debian 11.
Added support for TensorFlow 2.8 with Python 3.10 on Debian 11.
Miscellaneous software updates.

TensorFlow 2.9 user-managed instances are deprecated.

The M110 release of Vertex AI Workbench managed notebooks includes the following:

Increased shared memory size to available memory capacity.
Added support for Python 3.10 on Debian 11.
- Added support for PyTorch 2.0 with Python 3.10.

August 09, 2023

Vertex AI

Imagen Multimodal embeddings available in GA

Imagen on Vertex AI now offers the following GA feature:

Multimodal embeddings

This feature incurs different pricing based on if you use image input or text input. For more information, see the multimodal embeddings feature page.

August 02, 2023

Vertex AI

Prebuilt containers to perform custom training with TensorFlow 2.12 are now generally available (GA).

Updated prebuilt images for Tensorflow 2.11 are now available.

August 01, 2023

Vertex AI

Vertex AI Tensorboard pricing has changed from a per-user monthly license of $300 per month to $10 GiB per month for storage of your logs. This means no more subscription fees. You only pay for the storage you've used. See the Vertex AI Tensorboard: Delete Outdated Tensorboard Experiments tutorial for how to manage storage.

The schedules API for Vertex AI Pipelines is now generally available (GA). You can schedule recurring pipeline runs in Vertex AI by specifying a frequency in cron syntax, and optionally the start time and/or end time. Additionally, you can pause, resume, update, and delete schedules.For more information, see Schedule a pipeline run with scheduler API.

July 28, 2023

Vertex AI

The learning_rate parameter in generative AI model tuning is now learning_rate_multiplier. To use the model's or tuning method's default learning rate, use the default learning_rate_multiplier value of 1.0.

If you haven't configured learning_rate before, no action is needed. If using tuning_method=tune_v2 with the v2.0.0 pipeline template (Python SDK v1.28.1+), the recommended learning rate is 0.0002. To convert your custom learning_rate to learning_rate_multiplier, calculate as follows:

learning_rate_multiplier = custom_learning_rate_value / 0.0002

July 19, 2023

Vertex AI Workbench

Vertex AI Workbench instances are now available in Preview. Vertex AI Workbench instances combine features from managed notebooks and user-managed notebooks to provide a robust data science solution. Supported features include:

Idle timeout
BigQuery and Cloud Storage integrations
End-user and service account authentication
VPC Service Controls
Customer managed encryption keys (CMEK)
Health status monitoring
Run notebooks on a schedule
Dataproc integration

To get started, see Introduction to Vertex AI Workbench instances.

July 18, 2023

Vertex AI

Model tuning updates for text-bison:

Upgraded tuning pipeline now offers more efficient tuning and better performance on text-bison.
New learning_rate parameter lets you adjust the step size at each iteration.

For details, see Tune language foundation models.

July 17, 2023

Vertex AI

Imagen on Vertex AI now offers the following Generally Available (GA) features:

* Restricted access feature.

For more information about Imagen or how to get access to restricted GA or Preview features, see the Imagen on Vertex AI overview.

Imagen now supports human face generation for the following features:

* Restricted access feature.

Human face generation is enabled by default, except for images with children and/or celebrities. For more information, see the usage guidelines.

The Vertex AI PaLM API has added support for the following languages:

Spanish (es)
Korean (ko)
Hindi (hi)
Chinese (zh)

For the complete list of supported languages, see Supported languages.

July 13, 2023

Vertex AI

Support for batch text (text-bison) requests is now available in (GA). You can review pricing for the chat-bison model at Vertex AI pricing page.

July 10, 2023

Vertex AI

Support for PaLM 2 for Chat (chat-bison) is now available in (GA). You can review pricing for the chat-bison model at Vertex AI pricing page.

July 07, 2023

Vertex AI

GCSFuse support for custom training is generally available (GA).

July 06, 2023

Vertex AI

Vertex AI model evaluation is now generally available (GA) with the following new Preview features:

Model evaluation with sliced metrics.
Model evaluation with fairness and bias metrics.
Vision error analysis for AutoML image classification models.

June 30, 2023

Vertex AI

Vertex Explainable AI

Support for example-based explanations is now generally available (GA).

Vertex AI data labeling is deprecated and will no longer be available on Google Cloud after July 1, 2024. For new labeling tasks, you can use add labels using the Google Cloud console or access data labeling solutions from our partners in the Google Cloud Console Marketplace, such as Labelbox and Snorkel.

June 29, 2023

Vertex AI

Vertex AI Codey APIs

The Vertex AI Codey APIs are now generally available (GA). Use the Codey APIs to create solutions with code generation, code completion, and code chat. Because the Vertex AI Codey APIs are GA, you incur usage costs if you use them. To learn about pricing, see the Generative AI support on Vertex AI pricing page.

The models in this release include:

code-bison (code generation)
codechat-bison (multi-turn code chat)
code-gecko (code completion)

The maximum tokens for input was increased from 4,096 to 6,144 tokens for code-bison and codechat-bison to allow longer prompts and chat history. The maximum tokens for output was increased from 1,024 to 2,048 for code-bison and codechat-bison to allow for longer responses.

Additional programming languages are supported. For more information, see Supported coding languages.

Several fine-tuning datasets were removed from the code-bison and codechat-bison models to implement the following improvements:

Excessive chattiness.
Artifacting, such as NBSP (non-breaking space) characters.
Low quality code responses.

To learn about cloud horizontals, please see Vertex AI certifications.

Vertex AI Pipeline task-level logs are now generally available (GA) in Cloud Logging. Additionally, from Cloud Logging you can route pipeline logs to a Pub/Sub sink to power your event-driven architecture. For more information, see View pipeline job logs.

June 26, 2023

Vertex AI Workbench

M109 release

The M109 release of Vertex AI Workbench user-managed notebooks includes the following:

PyTorch 2.0 with Python 3.10 and CUDA 11.8 user-managed notebooks instances are now available.
Miscellaneous software updates.

The M109 release of Vertex AI Workbench managed notebooks includes the following:

Fixed a bug that caused high cpu utilization due to excessive internal diagnostic tool processes.
Fixed a bug that was showing incorrect kernel image icons in the Jupyterlab launcher.

June 20, 2023

Vertex AI

A100 80GB accelerators are now generally available (GA) for custom training jobs in the following regions:

asia-southeast1
europe-west4
us-central1
us-east4

For more information, see Locations.

The Google Cloud Pipeline Components (GCPC) SDK v2 is now generally available (GA). GCPC v2 introduces support for the KFP v2 SDK and is fully supported by Vertex AI Pipelines.

To learn more about the updates in the latest version of the GCPC SDK, see the Google Cloud Pipelines Components Release Notes.

The Kubeflow Pipelines (KFP) SDK v2 is now generally available (GA). KFP SDK v2 introduces several improvements for authoring pipelines and is fully supported by Vertex AI Pipelines.

To learn more about the changes in KFP v2, see the KFP v2 Release Notes and KFP v2 migration guide.

June 15, 2023

Vertex AI

The chat-bison@001 model has been updated to better follow instructions in the context field. For details, on how to create chat prompts for chat-bison@001, see Design chat prompts.

June 09, 2023

Vertex AI

HIPAA compliance for Generative AI on Vertex AI

Generative AI support on Vertex AI now supports HIPAA compliance. The coverage includes components of the Model Garden and Generative AI Studio.

To learn more about Vertex certifications, see Vertex AI features and Vertex AI certifications.

June 07, 2023

Vertex AI

PaLM Text and Embeddings APIs, and Generative AI Studio

The Generative AI support on Vertex AI is now generally available (GA). With this feature launch, you can leverage the PaLM API to generate AI models that you can test, tune, and deploy in your AI-powered applications. With the GA of these features, you will incur usage costs if you use the text-bison and textembedding-gecko PaLM APIs. To learn about pricing, see the Vertex AI pricing page.

Features and models in this release include:

PaLM 2 for Text: text-bison
Embedding for Text: textembedding-gecko
Generative AI Studio for Language

Vertex AI Model Garden

The Vertex AI Model Garden is now generally available (GA). The Model Garden is a platform that helps you discover, test, customize, and deploy Vertex AI and select OSS models. These models range from tunable to task-specific - all available on the Model Garden page in the Google Cloud console.

To get started, see Explore AI models and APIs in Model Garden.

Vertex AI Codey APIs

The Vertex AI Codey APIs are now in Preview. With the Codey API, code generation, code completion, and code chat APIs can be used from any Google Cloud project without allowlisting. The APIs can be accessed from the us-central1 region. The Codey APIs can be used in the Generative AI studio or programmatically in REST commands.

To get started, see the Code models overview.

June 01, 2023

Vertex AI

Vertex Prediction

You can now specify a multi-region BigQuery table as the input or output to a batch prediction request.

May 18, 2023

Vertex AI

Vertex Prediction

You can now co-host models on the same VM from the Google Cloud Console. Previously, this capability was available only from the REST API. For more information, see Share resources across deployments.

May 16, 2023

Vertex AI

Vertex AI custom training now supports deep integration with Vertex AI Experiments. You can submit training jobs with autologging enabled to automatically log parameters and model performance metrics. For more information, see Run training job with experiment tracking

The scheduler API for Vertex AI Pipelines is now available in Preview. You can schedule recurring pipeline runs in Vertex AI by specifying a frequency, start time (optional), and end time (optional). For more information, see Schedule a pipeline run with scheduler API.

May 10, 2023

Vertex AI

Generative AI Support for Vertex AI

Generative AI Support for Vertex AI is now available in Preview. With this feature launch, you can leverage the Vertex AI PaLM API to generate AI models that you can test, tune, and deploy in your AI-powered applications.

Features and models in this release include:

PaLM 2 for Text: text-bison@001
PaLM 2 for Chat: chat-bison@001
Embedding for Text: textembedding-gecko@001
Generative AI Studio for Language
Tuning for PaLM 2
Vertex AI SDK v1.25, which includes new features such as TextGenerationModel(text-bison@001), ChatModel(chat-bison@001), TextEmbeddingModel(textembedding-gecko@001)

You can interact with the generative AI features on Vertex AI by using Generative AI Studio in the Google Cloud console, the Vertex AI API, and the Vertex AI SDK for Python.

Learn more about Generative AI Support for Vertex AI
See an Introduction to Generative AI Studio
Get started with a Generative AI Studio quickstart

Vertex AI Model Garden

The Vertex AI Model Garden is now available in Preview. The Model Garden is a platform that helps you discover, test, customize, and deploy Vertex AI and select OSS models. These models range from tunable to task-specific - all available on the Model Garden page in the Google Cloud console.

To get started, see Explore AI models and APIs in Model Garden.

May 09, 2023

Vertex AI

Vertex AI Prediction

You can now use G2 accelerator-optimized machine types to serve predictions. Each G2 machine has a fixed number of NVIDIA L4 GPUs attached.

May 04, 2023

Vertex AI Workbench

M108 release

The M108 release of Vertex AI Workbench user-managed notebooks includes the following:

Miscellaneous software updates.

April 14, 2023

Vertex AI

Vertex AI Prediction

You can now update some scaling and container logging configuration settings on a DeployedModel without undeploying and redeploying it to an endpoint.

For more information, see update the scaling configuration and container logging.

April 13, 2023

Vertex AI

The Timeseries Insights API is now generally available (GA). With the Timeseries Insights API, you can forecast and detect anomalies over billions of events in real time. For more information, see Timeseries Insights.

Vertex AI Workbench

M107 release

The M107 release of Vertex AI Workbench user-managed notebooks includes the following:

Fixed a bug that displayed the wrong version of the JupyterLab user interface.
Fixed a bug where a cron job for the diagnostic tool was added at every restart.
Miscellaneous software updates.

April 06, 2023

Vertex AI Workbench

M106 release

The M106 release of Vertex AI Workbench user-managed notebooks includes the following:

Rolled back a previous change in which Jupyter dependencies were located in a separate Conda environment.
Fixed a bug in which kernels used by notebooks did not contain the specified machine learning frameworks.
Miscellaneous software updates.

April 04, 2023

Vertex AI

The Vertex AI Matching Engine service now offers Preview support for deploying an index to a public endpoint. For information about how to get started, see Matching Engine Setup.

Vertex AI Prediction

You can now view logs for Vertex AI Batch Prediction jobs in Cloud Logging.

Vertex AI Pipelines is now integrated with Cloud Asset Inventory service. You can use Cloud Asset Inventory to search, export, monitor, and analyze pipeline resources and metadata, and also view the resource history.

April 03, 2023

Vertex AI

The Vertex AI Model Registry now offers Preview support for model copy between regions. For information about how to copy your model between regions, see Copy models in Model Registry.

March 31, 2023

Vertex AI Workbench

M105 release

The M105 release of Vertex AI Workbench user-managed notebooks includes the following:

The following user-managed notebooks images are now available with Python 3.10 on Debian 11:
- TensorFlow 2.11 CPU (tf-2-11-cpu-debian-11-py310)
- TensorFlow 2.11 GPU with Cuda 11.3 (tf-2-11-cu113-notebooks-debian-11-py310)
- PyTorch 1.13 with Cuda 11.3 (pytorch-1-13-cu113-notebooks-debian-11-py310)
- Base CPU (common-cpu-notebooks-debian-11-py310)
- Base GPU with Cuda 11.3 (common-cu113-notebooks-debian11-py310)
The following user-managed notebooks images are now available with Python 3.9 on Debian 11:
- TensorFlow 2.6 CPU (tf-2-6-cpu-notebooks-debian-11-py39)
- TensorFlow 2.6 GPU with Cuda 11.3 (tf-2-6-cu113-notebooks-debian-11-py39)
Jupyter-related libraries have been moved to a different Conda environment, separate from the one containing machine learning frameworks and base software libraries.

March 28, 2023

Vertex AI

Vertex AI Pipelines cost showback with billing labels is now generally available (GA). You can now use billing labels to review the cost of a pipeline run, along with the cost of individual resources generated from Google Cloud Pipeline Components in the pipeline run. For more information, see Understand pipeline run costs.

March 27, 2023

Vertex AI Workbench

M105 release

The M105 release of Vertex AI Workbench managed notebooks includes the following:

Fixed an issue wherein a runtime with idle shutdown enabled doesn't detect activity and shuts down.
Fixed an issue wherein the runtime data disk runs out of space and prevents access.
Fixed an issue wherein end user credentials are not preserved after shutdown.
Changed Health Agent logging levels from DEBUG to INFO.

March 21, 2023

Vertex AI

Vertex AI supports running Explainable AI on certain types of BQML models when they are added to the Vertex AI Model Registry (GA). To learn more, see Explainable AI for BigQuery ML models.

Vertex AI Feature Store

The ability to delete feature values from an entity type is now generally available (GA). The following features are available:

Links to additional resources:

March 20, 2023

Vertex AI

Vertex AI Prediction

You can now use N2, N2D, C2, and C2D machine types to serve predictions.

March 16, 2023

Vertex AI Workbench

M104 release

The M104 release of Vertex AI Workbench user-managed notebooks includes the following:

Fixed a regression in which jupyter-user metadata was ignored.
Enabled access to the Jupyter Gateway Client configuration by using the notebook-enable-gateway-client and gateway-client-url metadata tags.
Added the following packages:
- google-cloud-artifact-registry
- google-cloud-bigquery-storage
- google-cloud-language
- keyring
- keyrings.google-artifactregistry-auth
Fixed a bug in which curl could not find the right SSL certificate path by default.

TensorFlow Enterprise 2.1 has reached the end of its support period. See Version details.

March 03, 2023

Vertex AI

Pre-built containers to perform custom training with TensorFlow 2.11, PyTorch 1.12, or PyTorch 1.13 are now generally available (GA).

February 28, 2023

Vertex AI

A new custom training overview page is available. The new overview page covers the following topics:

What is custom training?
Benefits of custom training on Vertex AI.
How custom training works.
Custom training workflow.

February 21, 2023

Vertex AI Workbench

M104 update

This update of the M104 release of Vertex AI Workbench managed notebooks includes the following:

Fixed a bug where local and remote kernels are not displayed. This happens when remote kernels are not accessible.
Minor bug fixes and improvements.

February 14, 2023

Vertex AI

Vertex AI Prediction

Pre-built PyTorch containers for serving predictions from PyTorch models is generally available (GA).

Vertex AI Matching Engine now supports Private Service Connect in Preview. To learn how to set up a a Private Service Connect instance, see Using Private Service Connect.

February 13, 2023

Vertex AI

Support for resource-level IAM policies for Vertex AI featurestore and entityType resources is generally available (GA). For more information, see Control access to resources.

February 10, 2023

Vertex AI

When performing distributed training, Vertex AI properly sets the primary replica in CLUSTER_SPEC as workerpool0 instead of chief. For details, see Format CLUSTER_SPEC.

February 09, 2023

Vertex AI Workbench

M104 release

The M104 release of Vertex AI Workbench managed notebooks includes the following:

Added a fix for a security vulnerability in single-user managed notebooks instances.
Made enhancements to the network selection user experience in the managed notebooks executor.
Minor bug fixes and improvements.

February 06, 2023

Vertex AI

The Vertex AI Pipelines Template Gallery is now available in Preview. You can bootstrap your MLOps workflows with Google-authored pipeline and component templates. For more information, see Use a prebuilt template from the Template Gallery.

January 30, 2023

Vertex AI Workbench

M103 release

The M103 release of Vertex AI Workbench user-managed notebooks includes the following:

Fixed a bug in which a warning tells the user to run jupyter lab build when creating a new instance.
Upgraded PyTorch to 1.13.1.
Minor bug fixes and improvements.

January 26, 2023

Vertex AI

Tabular Workflow for End-to-End AutoML is generally available (GA). For documentation, refer to Tabular Workflow for End-to-End AutoML.

January 18, 2023

Vertex AI

Vertex AI Explainability

When uploading TensorFlow 2 models, the ExplanationMetadata field is now optional, making it easier to configure your model for explainability. For more information, see Import a model with an explanationSpec field.

January 11, 2023

Vertex AI

Vertex AI Matching Engine is available in the following regions:

us-west2 – (Los Angeles)
us-west3 – (Salt Lake City)
northamerica-northeast1 – (Montréal)
northamerica-northeast2 – (Toronto)
europe-central2 – (Warsaw)
europe-west2 – (London)
europe-west3 – (Frankfurt)
europe-west6 – (Zurich)
asia-east1 – (Taiwan)
Asia-east2 – (Hong Kong)
me-west1 – (Tel aviv)

To see all of the available locations for Matching Engine, see the Vertex AI Locations page.

December 20, 2022

Vertex AI

Vertex AI TensorFlow Profiler

Vertex AI TensorFlow Profiler is generally available GA. You can use TensorFlow Profiler to debug model training performance for your custom training jobs.

For details, see Profile model training performance using Profiler.

Vertex AI Matching Engine

Vertex AI Matching Engine now offers General Availability support for updating your indices using Streaming Update, which is real-time indexing for the Approximate Nearest Neighbor (ANN) service.

Vertex AI Feature Store streaming ingestion is now generally available (GA).

You can now override the default data retention limit of 4000 days for the online store and the offline store in Vertex AI Feature Store.

You can set the data retention limit for the online store at the featurestore level.
You can set the data retention limit for the offline store at the entity type level.

December 15, 2022

Vertex AI Workbench

M102 release

The M102 release of Vertex AI Workbench user-managed notebooks includes the following:

TensorFlow 2.11 is now available.
PyTorch 1.13 is now available.
Regular security patches and package upgrades.

December 09, 2022

Vertex AI Workbench

M101 release

The M101 release of Vertex AI Workbench includes the following:

TensorFlow patch version upgrades:
- From 2.8.3 to 2.8.4.
- From 2.9.2 to 2.9.3.
- From 2.10.0 to 2.10.1.
TensorFlow 1.15 on Vertex AI Workbench is now deprecated.
Added *.notebooks.cloud.google.com as part of the domains required for users to access Notebooks API. Removed *.datalab.cloud.google.com.
Regular security patches and package upgrades.

December 05, 2022

Vertex AI

The Pipeline Templates feature is now generally available (GA). The Your Templates tab is supported by Artifact Registry and allows you to publish and curate pipeline and component templatess. For documentation, refer to Create, upload, and use a pipeline template.

November 30, 2022

Vertex AI

AutoML image model updates

AutoML image classification and object detection now support a higher-accuracy model type. This model is available in Preview.

For information about how to train a model using the higher accuracy model type, see Begin AutoML model training.

Batch prediction is currently not supported for this model type.

Cloud Logging for Vertex AI Pipelines is now generally available (GA). For more information, see View pipeline job logs.

November 18, 2022

Vertex AI

Vertex AI Prediction

You can now perform some simple filtering and transformation on the batch input in your BatchPredictionJob requests without having to write any code in the prediction container. This feature is in Preview. For more information, see Filter and transform input data.

November 17, 2022

Vertex AI

The Vertex AI Pipelines email notification component is now generally available (GA). This component enables you to configure your pipeline to send up to three emails upon success or failure of a pipeline run. For more information, see Configure email notifications and the Email notification component.

November 16, 2022

Vertex AI

Vertex AI has added support for the following regions:

us-west3 (Salt Lake City)
europe-central2 (Warsaw)
asia-southeast2 (Jakarta)
me-west1 (Tel aviv)

Some features of Vertex AI are not supported in these regions. Check feature availability for all regions on the Vertex AI Locations page.

November 10, 2022

Vertex AI

AutoML Image Classification Error Analysis

Error analysis allows you to examine error cases after training a model from within the model evaluation page. This feature is available in Preview.

For each image you can inspect similar images from the training set to help identify the following:

Label inconsistencies between visually similar images
Outliers if a test sample has no visually similar images in the training set

After fixing any data issues, you can retrain the model to improve model performance.

November 09, 2022

Vertex AI

Feature Transform Engine is available in Preview. For documentation, refer to Feature engineering.

November 08, 2022

Vertex AI Workbench

M100 release

The M100 release of Vertex AI Workbench includes the following:

Fixed a bug that prevented an instance with a GPU from starting.
Regular package updates.
Miscellaneous bug and display fixes.

Fixed a server-side request forgery (SSRF) vulnerability. Previous versions of managed notebooks and user-managed notebooks instances still contain the vulnerability. It is recommended that you migrate your data to a new instance.

November 04, 2022

Vertex AI

Vertex AI Prediction

You can now use A2 machine types to serve predictions.

Vertex ML Metadata

You can now filter contexts, executions, and artifacts by association and attribution.

Custom training on Vertex AI now supports NVIDIA A100 80GB GPUs on a2-ultragpu-1g/2g/4g/8g machines. For details, see Configure compute resources for custom training.

November 03, 2022

Vertex AI

Vertex AI Prediction

Custom prediction routines (CPR) are now Generally Available. CPR lets you easily build custom containers for prediction with pre/post processing support.

October 27, 2022

Vertex AI

Vertex AI Prediction

You can now use E2 machine types to serve predictions.

October 25, 2022

Vertex AI Workbench

v1beta1

The v1beta1 version of the Notebooks API is scheduled for removal no earlier than January 16, 2023. After this date, you must use Notebooks API v1 to manage Vertex AI Workbench resources.

October 18, 2022

Vertex AI Workbench

M98 release

The M98 release of Vertex AI Workbench managed notebooks includes the following:

Upgraded Go from 1.16.5 to 1.19.2.
Upgraded R from 4.1 to 4.2.
Upgraded JupyterLab from 3.2 to 3.4.
Miscellaneous bug and display fixes.
Added a fix for the BigQuery SQL editor to run queries correctly in non-US locations.
Regular package updates.

Learn more about managed notebooks versions.

October 12, 2022

Vertex AI

Tabular Workflow for TabNet Training is available in Preview. For documentation, refer to Tabular Workflows for TabNet Training.

Tabular Workflow for Wide & Deep Training is available in Preview. For documentation, refer to Tabular Workflow for Wide & Deep Training.

October 11, 2022

Vertex AI

Vertex AI Feature Store streaming ingestion is available in Preview.

October 10, 2022

Vertex AI

The Vertex AI Model Registry is generally available (GA). Vertex AI Model Registry is a searchable repository where you can manage the lifecycle of your ML models. From the Vertex AI Model Registry, you can better organize your models, train new versions, and deploy directly to endpoints.

The Vertex AI Model Registry and BigQuery ML integration is generally available (GA). With this integration, BigQuery ML models can be managed alongside other ML models in Vertex AI to easily version, evaluate, and deploy for prediction.

October 06, 2022

Vertex AI

Incrementally train an AutoML model

You can now incrementally train an AutoML image classification or object detection model by selecting a previously trained model. This feature is in Preview. For more information, see Train an AutoML image classification model.

October 05, 2022

Vertex AI

Vertex AI Feature Store

The ability to delete feature values from an entity type is now available in Preview. The following features are available:

Links to additional resources:

October 04, 2022

Vertex AI

Vertex AI model evaluation is now available in Preview. Model evaluation provides model evaluation metrics, such as precision and recall, to help you determine the performance of your models.

September 26, 2022

Vertex AI

Vertex AI Model Monitoring

Vertex AI Model Monitoring now offers Preview support for batch prediction jobs. For more details, see Vertex AI Model Monitoring for batch predictions.

Vertex AI Feature Store

Feature value monitoring is now generally available (GA).

September 22, 2022

Vertex AI

Vertex AI Matching Engine

Vertex AI Matching Engine now offers Preview support for updating your indices using Streaming Update, which is real-time indexing for the Approximate Nearest Neighbor (ANN) service.

September 20, 2022

Vertex AI

The option to configure pipeline run caching (enable_caching) is now available in the Cloud console.

Vertex AI Workbench

M96 release

The M96 release of Vertex AI Workbench managed notebooks includes the following:

Fixed a problem where users were not able to save large Notebooks.
Fixed a display issue when using JupyterLab's simple interface.
Improved timeout behavior switch hardware operations.
Improved error messaging when a service account cannot access the Runtime.
Security fixes.
Regular package refreshment and bug fixes.

Learn more about managed notebooks versions.

September 14, 2022

Vertex AI

You can now limit the number of concurrent or parallel task runs in a pipeline run using dsl.ParallelFor. For more information, see the Kubeflow Pipelines SDK Documentation.

The performance of the ListPipelineJobs API has been improved via a new readMask that lets you filter out large fields. To leverage this in the Python SDK, use the new enable_simple_view.

August 17, 2022

Vertex AI Workbench

v1beta1 & v1

M95 release

The M95 release of Vertex AI Workbench managed notebooks includes the following:

Fixed a bug where users were regularly getting a 502 error when trying to access JupyterLab.
Fixed a bug where opening an instance in Single User mode slowed the start of an instance.
Fixed a bug where a managed notebooks instance was not starting after adding a GPU.
Fixed bugs on the Serverless Spark form input.
Improved the ActivityLog refresh after Serverless Spark creation.
Fixed a bug related to the display of materialized views in BigQuery.
Refreshed the JupyterLab interface with an improved Google-specific theme.
Fixed a bug related to viewing Cloud Storage buckets and folders with large numbers of objects.
Regular package refreshment and bug fixes.

Learn more about managed notebooks versions.

August 12, 2022

Vertex AI

Vertex Explainable AI

Vertex Explainable AI now offers Preview support for example-based explanations. For more information, see Configure example-based explanations for custom training.

August 01, 2022

Vertex AI

TensorFlow Profiler integration: Debug model training performance for your custom training jobs. For details, see Profile model training performance using Profiler.

July 29, 2022

Vertex AI

Vertex AI now offers Preview support for Custom prediction routines (CPR). CPR lets you easily build custom containers for prediction with pre/post processing support.

July 18, 2022

Vertex AI

NFS support for custom training is GA. For details, see Mount an NFS share for custom training.

July 14, 2022

Vertex AI

The Pipeline Templates feature is available in Preview. For documentation, refer to Create, upload, and use a pipeline template.

The features supported by pipeline templates include the following:

Create a template registry using Artifact Registry (AR).
Compile and publish a pipeline template.
Create a pipeline run using the template and filter the runs.
Manage (create, update, or delete) the pipeline template resources.

July 12, 2022

Vertex AI

You can now use a pre-built container to perform custom training with TensorFlow 2.9

July 11, 2022

Vertex AI

Vertex AI Pipelines now lets you configure task-level retries. You can set the number of times a task is retried before it fails. For more information about this option, see the Kubeflow Pipelines SDK Documentation.

July 06, 2022

Vertex AI

Tabular Workflows is available in Preview. For documentation, refer to Tabular Workflows on Vertex AI.

End-to-End AutoML workflow is available in Public Preview. For documentation, refer to End-to-End AutoML.

June 30, 2022

Vertex AI

Feature: Vertex AI Experiments is generally available (GA). Vertex AI Experiments helps users track and compare multiple experiment runs and analyze key model metrics.

Features supported by Experiments include:

Vary and track parameters and metrics.
Compare parameters, metrics, and artifacts between pipeline runs.
Track steps and artifacts to capture the lineage of experiments.
Compare vertex pipelines against Notebook experiments.

June 28, 2022

Vertex AI

Vertex AI Forecasting is available in GA. The following features are available:

June 17, 2022

Vertex AI

Support for IAM resource-level policies for Vertex AI featurestore and entityType resources is available in Preview.

May 27, 2022

Vertex AI Workbench

v1beta1 & v1

M93 release

The M93 release of Vertex AI Workbench managed notebooks includes the following:

Fixed a bug that prevented kernels from shutting down properly in Vertex AI Workbench managed notebooks.

Learn more about managed notebooks versions.

May 24, 2022

Vertex AI

You can now configure the failure policy for a pipeline run.

May 18, 2022

Vertex AI

The ability to configure Vertex AI private endpoints is now general available (GA). Vertex AI private endpoints provide a low-latency, secure connection to the Vertex AI online prediction service. You can configure Vertex AI private endpoints by using VPC Network Peering. For more information, see Use private endpoints for online prediction.

May 12, 2022

Vertex AI Workbench

v1beta1 & v1

M91 release

The M91 release of Vertex AI Workbench managed notebooks includes the following:

Log streaming to the consumer project via Logs Viewer is now supported.
Added the net-tools package.
Regular package refreshments and bug fixes.

Fixed an issue that caused Spark server networking errors when using Dataproc Serverless Spark and VPC Peering.

Learn more about managed notebooks versions.

April 26, 2022

Vertex AI

You can now train your custom models using Cloud TPU Architecture (TPU VMs).

April 21, 2022

Vertex AI

You can now use a pre-built container to perform custom training with PyTorch 1.11.

April 06, 2022

Vertex AI

Vertex AI Model Registry is available in Preview. Vertex AI Model Registry is a searchable repository where you can manage the lifecycle of your ML models. From the Vertex AI Model Registry, you can better organize your models, train new versions, and deploy directly to endpoints.

Vertex AI Workbench

v1beta1 & v1

Vertex AI Workbench is generally available (GA). Vertex AI Workbench is a single notebook surface for all your data science needs that lets you access BigQuery data and Cloud Storage from within JupyterLab, execute notebook code in Vertex AI custom training and Spark, use custom containers, manage costs with idle timeout, and secure your instances with VPC Service Controls and customer managed encryption keys (CMEK).

Features supported include:

Google-managed instances and the latest GPU support
Idle shutdown for managed notebooks instances
Custom containers
End-user and service account authentication
Native plug-ins for BigQuery and Cloud Storage
In-notebook Spark connect to Dataproc clusters
Jobs support via the managed notebooks executor on Vertex AI custom training and Spark
One-click deploy for NGC containers
VPC Service Controls
Customer managed encryption keys (CMEK)

The Vertex AI Workbench managed notebooks executor is generally available (GA). Use the executor to run notebook files on a schedule or as a one-time execution. You can use parameters in your execution to make specific changes to each run. For example, you might specify a different dataset to use, change the learning rate on your model, or change the version of the model. For more information, see Run notebook files with the executor.

March 07, 2022

Vertex AI

Vertex AI Feature Store online store autoscaling is available in Preview. The online store nodes automatically scale to balance performance and cost with different traffic patterns. The offline store already scales automatically.

You can now mount Network File System (NFS) shares to access remote files when you run a custom training job. For more information, see Mount an NFS share for custom training.

This feature is in Preview.

Google Cloud Pipeline Components SDK v1.0 is now generally available.

February 16, 2022

Vertex AI

You can now use a pre-built container to perform custom training with TensorFlow 2.8.

February 10, 2022

Vertex AI

For Vertex AI featurestore resources, the online store is optional. You can set the number of online nodes to 0. For more information, see Manage featurestores.

January 04, 2022

Vertex AI

You can now use a pre-built container to perform custom training with PyTorch 1.10.

December 23, 2021

Vertex AI

There are now three Vertex AI release note feeds. Add any of the following to your feed reader:

For both Vertex AI and Vertex AI Workbench: https://cloud.google.com/feeds/vertex-ai-product-group-release-notes.xml
For Vertex AI only: https://cloud.google.com/feeds/vertex-ai-release-notes.xml
For Vertex AI Workbench only: https://cloud.google.com/feeds/aiplatformnotebooks-release-notes.xml

December 02, 2021

Vertex AI

You can now use a pre-built container to perform custom training with TensorFlow 2.7.

December 01, 2021

Vertex AI

Vertex AI TensorBoard is generally available (GA).

November 19, 2021

Vertex AI

The autopackaging feature of the gcloud ai custom-jobs create command is generally available (GA). Autopackaging lets you use a single command to run code on your local computer as a custom training job in Vertex AI.

The gcloud ai customs-jobs local-run command is generally available (GA). You can use this command to containerize and run training code locally.

November 09, 2021

Vertex AI

Vertex AI Pipelines is generally available (GA).

November 02, 2021

Vertex AI

Using interactive shells to inspect custom training jobs is generally available (GA).

You can use these interactive shells with VPC Service Controls.

October 25, 2021

Vertex AI

Vertex ML Metadata is generally available (GA).

October 11, 2021

Vertex AI Workbench

v1beta1 & v1

Vertex AI Workbench is now available in Preview. Vertex AI Workbench is a notebook-based development environment for the entire data science workflow.

The Notebooks product and all existing Notebooks instances are now part of Vertex AI Workbench as user-managed notebooks.

October 05, 2021

Vertex AI

Vertex Feature Store is generally available (GA).

September 24, 2021

Vertex AI

Vertex Matching Engine is generally available (GA).

September 21, 2021

Vertex AI

Vertex AI Vizier is generally available (GA).

September 15, 2021

Vertex AI

Vertex Explainable AI is generally available (GA).

September 13, 2021

Vertex AI

You can use a pre-built container to serve predictions from TensorFlow 2.6 models.

September 10, 2021

Vertex AI

Vertex Model Monitoring is generally available (GA).

When you perform custom training, you can access Cloud Storage buckets by reading and writing to the local filesystem. This feature, based on Cloud Storage Fuse, is available in Preview.

Vertex AI Workbench

v1beta1 & v1

Due to a recent change, the iam.serviceAccounts.actAs permission on the specified service account for the notebook instance is required for users to continue to have access to their notebook instances. The Google internal Inverting Proxy server that provides access to notebook instances now verifies that this permission is present before allowing users access to the JupyterLab URL. The JupyterLab URL this update covers is: *.notebooks.googleusercontent.com This update only applies to notebook instances in Single User mode and verifies that the assigned single user is authorized to execute code inside the notebook instance. Notebook instances running in Service Account or Project Editor mode already perform this verification via the Inverting Proxy server.

August 30, 2021

Vertex AI

You can now use a pre-built container to perform custom training with TensorFlow 2.6 and PyTorch 1.9.

August 24, 2021

Vertex AI

The following tools for creating embeddings to use with Vertex Matching Engine are available in Preview:

the Two Tower built-in algorithm
the Swivel pipeline template

August 02, 2021

Vertex AI

Vertex Pipelines is available in the following regions:

us-east1 (South Carolina)
europe-west2 (London)
asia-southeast1 (Singapore)

See all the locations where Vertex Pipelines is available.

July 28, 2021

Vertex AI

You can use the Reduction Server algorithm (Preview) to increase throughput and reduce latency during distributed custom training.

July 27, 2021

Vertex AI

The following features are generally available (GA):

July 26, 2021

Vertex AI Workbench

v1beta1 & v1

If using proxy single-user mode, Notebooks API now verifies if the specified user (proxy-user-mail) has Service Account permissions on the Service Account. This check is performed during instance creation and registration.

July 20, 2021

Vertex AI

Private endpoints for online prediction are now available in preview. After you set up VPC Network Peering with Vertex AI, you can create private endpoints for low-latency online prediction within your private network.

Additionally, the documentation for VPC Network Peering with custom training has moved. The general instructions for setting up VPC Network Peering with Vertex AI are available at the original link, https://cloud.google.com/vertex-ai/docs/general/vpc-peering. The documentation for custom training is now available here: Using private IP with custom training.

July 19, 2021

Vertex AI

You can now use an interactive shell to inspect your custom training container while it runs. The interactive shell can be helpful for monitoring and debugging training.

This feature is available in preview.

July 14, 2021

Vertex AI

You can now use the gcloud beta ai custom-jobs create command to build a Docker image based on local training code, push the image to Container Registry, and create a CustomJob resource.

July 08, 2021

Vertex AI

You can now containerize and run your training code locally by using the new gcloud beta ai custom-jobs local-run command. This feature is available in preview.

June 25, 2021

Vertex AI

You can now use NVIDIA A100 GPUs and several accelerator-optimized (A2) machine types for training. You must use A100 GPUs and A2 machine types together. Learn about their pricing.

June 18, 2021

Vertex AI Workbench

Support for Compute Reservations. Notebooks API allows the use of Compute Reservations during instance creation.

June 11, 2021

Vertex AI

You can now use a pre-built container to serve predictions from TensorFlow 2.5 models.

You can now use a pre-built container to serve predictions from XGBoost 1.4 models.

May 18, 2021

Vertex AI

AI Platform (Unified) is now Vertex AI.

Vertex AI has added support for custom model training, custom model batch prediction, custom model online prediction, and a limited number of other services in the following regions:

us-west1
us-east1
us-east4
northamerica-northeast1
europe-west2
europe-west1
asia-southeast1
asia-northeast1
australia-southeast1
asia-northeast3

Vertex AI now supports forecasting with time series data for AutoML tabular models, in Preview. You can use forecasting to predict a series of numeric values that extend into the future.

Vertex Pipelines is now available in Preview. Vertex Pipelines helps you to automate, monitor, and govern your ML systems by orchestrating your ML workflow.

Vertex Model Monitoring is now available in Preview. Vertex Model Monitoring enables you to monitor model quality over time.

Vertex Feature Store is now available in Preview. Vertex Feature Store provides a centralized repository for organizing, storing, and serving ML features.

Vertex ML Metadata is now available in Preview. Vertex ML Metadata lets you record the metadata and artifacts produced by your ML system so you can analyze the performance of your ML system.

Vertex Matching Engine is now available in Preview. Vertex Matching Engine enables vector similarity search.

Vertex TensorBoard is now available in Preview. Vertex TensorBoard enables you to track, visualize, and compare ML experiments.

May 03, 2021

Vertex AI

You can now use a pre-built container to serve predictions from TensorFlow 2.4 models.

You can now use a pre-built container to serve predictions from scikit-learn 0.24 models.

You can now use a pre-built container to serve predictions from XGBoost 1.3 models.

April 27, 2021

Vertex AI

AI Platform Vizier is now available in preview. Vizier is a feature of AI Platform (Unified) that you can use to perform black-box optimization. You can use Vizier to tune hyperparameters or optimize any evaluable system.

April 15, 2021

Vertex AI

The Python client library for AI Platform (Unified) is now called the AI Platform (Unified) SDK. With the release of version 0.7 (Preview), the AI Platform (Unified) SDK provides two levels of support. The high-level aiplatform library is designed to simplify common data science workflows by using wrapper classes and opinionated defaults. The lower-level aiplatform.gapic library remains available for those times when you need more flexibility or control. Learn more.

March 31, 2021

Vertex AI

AI Platform (Unified) is now available in General Availability (GA).

AI Platform (Unified) has added support for the following regions for custom model training, as well as batch and online prediction for custom-trained models:

us-west1 (Oregon)
us-east1 (South Carolina)
us-east4 (N. Virginia)
northamerica-northeast1 (Montreal)
europe-west2 (London)
europe-west1 (Belgium)
asia-southeast1 (Singapore)
asia-northeast1 (Tokyo)
australia-southeast1 (Sydney)
asia-northeast3 (Seoul)

March 26, 2021

Vertex AI Workbench

Cross Project Service Account is supported for user-managed notebooks.

March 15, 2021

Vertex AI

You can now use a pre-built container to perform custom training with PyTorch 1.7.

March 04, 2021

Vertex AI Workbench

New Notebooks instances add labels for VM image (goog-caip-notebook) and volume (goog-caip-notebook-volume).

March 02, 2021

Vertex AI

CMEK compliance using the client libraries

You can now use the client libraries to create resources with a customer-managed encryption key (CMEK).

For more information on creating a resource with an encryption key using the client libraries, see Using customer-managed encryption keys (CMEK).

March 01, 2021

Vertex AI

The client library for Java now includes enhancements to improve usage of training and prediction features. The client library includes additional types and utility functions for sending training requests, sending prediction requests, and reading prediction results.

To use these enhancements, you must install the latest version of the client library.

February 25, 2021

Vertex AI

AI Platform (Unified) now supports Access Transparency in beta. Google Cloud organizations with certain support packages can use this feature. Learn more about using Access Transparency with AI Platform (Unified).

The client libraries for Node.js and Python now include enhancements to improve usage of training and prediction features. These client libraries include additional types and utility functions for sending training requests, sending prediction requests, and reading prediction results.

To use these enhancements, you must install the latest version of the client libraries.

The predict and explain method calls no longer require the use of a different service endpoint (for example, https://us-central1-prediction-aiplatform.googleapis.com). These methods are now available on the same endpoint as all other methods.

In addition to Docker images hosted on Container Registry, you can now use Docker images hosted on Artifact Registry and Docker Hub for custom container training on AI Platform.

The Docker images for pre-built training containers and pre-built prediction containers are now available on Artifact Registry.

You can now use a pre-built container to perform custom training with TensorFlow 2.4.

You can now use a pre-built container to serve predictions from TensorFlow 2.3 models.

You can now use a pre-built container to serve predictions from XGBoost 1.2 models.

February 01, 2021

Vertex AI

You can now use a pre-built container to perform custom training with PyTorch 1.6.

Vertex AI Workbench

Notebooks Terraform Module supports Notebooks API v1

January 23, 2021

Vertex AI Workbench

VPC-SC for Notebooks (now known as user-managed notebooks) is now Generally Available.

Notebooks API supports Shielded VM configuration.

January 19, 2021

Vertex AI

Preview: Select AI Platform (Unified) resources can now be configured to use Customer-managed encryption keys (CMEK).

Currently you can only create resources with a CMEK key in the UI; this functionality is not currently available using the client libraries.

January 11, 2021

Vertex AI

The default boot disk type for virtual machine instances used for custom training has changed from pd-standard to pd-ssd. Learn more about disk types for custom training and read about pricing for different disk types.

If you previously used the default disk type for custom training and want to continue training with the same disk type, make sure to explicitly specify the pd-standard boot disk type when you perform custom training.

January 06, 2021

Vertex AI

You can now use a pre-built container to perform custom training with TensorFlow 2.3.

December 17, 2020

Vertex AI

AI Platform (Unified) now stores and processes your data only in the region you specify for most features. Learn more.

November 16, 2020

Vertex AI

Preview release

AI Platform (Unified) is now available in Preview.

For more information, see the product documentation.

September 21, 2020

Vertex AI Workbench

AI Platform Notebooks (now known as user-managed notebooks) API is now Generally Available. The API now includes an isUpgradable endpoint and adds manual and auto-upgrade functionality to notebooks instances created using the API.

Cloud Audit Logging for AI Platform Notebooks (now known as user-managed notebooks) is now Generally Available.

Granular IAM permissions for AI Platform Notebooks (now known as user-managed notebooks) is now Generally Available.

AI Platform Notebooks now supports E2 machine types.

The following new regions have been added:

europe-west2 (London, UK)
europe-west3 (Frankfurt, Germany)
europe-west6 (Zürich, Switzerland)

March 31, 2020

Vertex AI Workbench

v1beta1

AI Platform Notebooks (now known as user-managed notebooks) is now Generally Available. Some integrations with and specific features of AI Platform Notebooks are still in beta, such as Virtual Private Cloud Service Controls, Identity and Access Management (IAM) roles, and AI Platform Notebooks API.

February 04, 2020

Vertex AI Workbench

v1beta1

VPC Service Controls now supports AI Platform Notebooks. Learn how to use a notebook instance within a service perimeter. This functionality is in beta.

February 03, 2020

Vertex AI Workbench

v1beta1

AI Platform Notebooks now supports Access Transparency. Access Transparency provides you with logs of actions that Google staff have taken when accessing your data. To learn more about Access Transparency, see the Overview of Access Transparency.

September 12, 2019

Vertex AI Workbench

You can now use customer-managed encryption keys (CMEK) to protect data on the boot disks of your AI Platform Notebooks (now known as user-managed notebooks) VM instances. CMEK in AI Platform Notebooks is generally available. For more information, see Using customer-managed encryption keys (CMEK).

September 09, 2019

Vertex AI Workbench

v1beta1

AI Platform Notebooks now provides more ways for you to customize your network settings, encrypt your notebook content, and grant access to your notebook instance. These options are available when you create a notebook.

Now you can implement AI Platform Notebooks using custom containers. Use a Deep Learning Containers image or create a derivative container of your own, then create a new notebook instance using your custom container.

July 12, 2019

Vertex AI Workbench

v1beta1

R upgraded to version 3.6.

R Notebooks are no longer dependent on a Conda environment.

June 03, 2019

Vertex AI Workbench

v1beta1

You can now create AI Platform Notebooks instances with R and core R packages installed. Learn how to install R dependencies, and read guides for using R with BigQuery in AI Platform Notebooks and using R and Python in the same notebook.

March 01, 2019

Vertex AI Workbench

v1beta1

AI Platform Notebooks is now available in beta. AI Platform Notebooks enables you to create and manage virtual machine (VM) instances that are pre-packaged with JupyterLab and a suite of deep learning software.

Visit the AI Platform Notebooks overview and the guide to creating a new notebook instance to learn more.