NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #299 most downloaded on PyPI
Vertex AI API client library
Latest stable
2.10.0
Last release 4 days ago
18 Nov 2026
Ships on a steady schedule
a new release about every 2 weeks
Nearly every release is documented
notes for 60 of the last 60 stable releases
2 versions withdrawn
withdrawn after publishing
6 years old
230 releases · first in 2020
Drag across the ruler to compare, or tap a release to open it.
Add STZ support for Endpoint.deploy and Model.deploy (preview).
create_evaluation_set and create_evaluation_item methods to Vertex AI GenAI SDK evals (83553a9)evaluation_df input support to create_evaluation_run method in Vertex AI GenAI SDK evals (7a1262b)inference_configs to create_evaluation_run method in Vertex AI GenAI SDK evals (5b5e6bd)labels to EvaluationRun in Vertex AI GenAI SDK evals (67cf80b)metrics to create_evaluation_run method in Vertex AI GenAI SDK evals (ce35218)show method for EvaluationRun for Vertex AI GenAI SDK evals (dc16065)Your coding agent can read these notes before it upgrades. Set up the MCP server →
remove deprecated transfer_to_agent parameter
ScaleToZeroSpec is added (62ea30a)class_methods in Agent Engine config. (af8c898)Add ability to use existing sessions for streaming_agent_run_with_events calls.
get_evaluation_set and get_evaluation_item methods to Vertex AI GenAI SDK evals (7757886)show method for EvaluationRun class in Vertex AI GenAI SDK evals (0c932b9)GenAI Client(evals) - Add EvaluationResults to get_evaluation_run method response in Vertex AI GenAI SDK evals
Mitigate breaking change in GenAI SDK for ADK on AgentEngine
create_evaluation_run method to Vertex AI GenAI SDK evals (7db9b4f)get_evaluation_run method to Vertex AI GenAI SDK evals (bbbadbc)dedicated_endpoint_disabled in message .google.cloud.aiplatform.v1beta1.DeployRequest is changed (0722687)Expose user reservation for CustomModel
Add experimental async list_prompts and list_version methods to prompt management
context in Grounding metric (e75d91f)The optimize_prompt method no longer returns the parsed response directly. Code must be updated to access the .raw_text_response or .parsed_response a
optimize_prompt method no longer returns the parsed response directly. Code must be updated to access the .raw_text_response or .parsed_response attribute on the new return object.has_template_config to MultimodalDataset. (97a6e71)GenAI SDK client - Add experimental list_prompts() and list_versions() methods to Prompt Management
GenAI - Added GPT, Qwen, and DeepSeek models support in GenAI batch prediction
GenAI SDK client - Add A2A support in Agent Engine
gpu_partition_size parameter to Model.deploy() method. (966c236)gpu_partition_size type hint to str. (910016d)api_key parameter to vertexai.Client (a9ffc60)GenAI SDK client - remove duplicate types for Content, Part, and evals
disable_container_logging in v1beta1 api (3a75313)encryption_spec support to Agent Engine genai sdk. (3bb8100)gpu_partition_size parameter to Endpoint.deploy() method. (7ebbddb)client.evals module (b915b61)get or update for agent_engines with lightweight creation (d76411a)agent_engine parameter to agent in Agent Engines. (65bf9b6)Add encryption_spec support to Agent Engine create and update.
encryption_spec support to Agent Engine create and update. (1b135ca)run_config parameter to AdkApp query methods (e3b9a76)Add gpu_partition_size to MachineSpec
gpu_partition_size to MachineSpec (b753565)dedicated_endpoint_enabled in message .google.cloud.aiplatform.v1.DeployRequest is changed (b753565)monitored_resource_labels in message .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec is changed (b753565)Add autoscaling_target_pubsub_num_undelivered_messages option in Preview model deployment on Endpoint & Model classes.
A new value NVIDIA_GB200 is added to enum AcceleratorType
NVIDIA_GB200 is added to enum AcceleratorType (d682fac)DeploymentStage for CreateEndpointOperationMetadata and DeployModelOperationMetadata (d682fac)Add service_account parameter to AgentEngine class for creation and update
Add FlexStart option to DeploymentResourcePool.create, Endpoint.deploy, and Model.deploy (preview)
Add Aggregation Output in EvaluateDataset Get Operation Response
boot_disk_type in message .google.cloud.aiplatform.v1beta1.DiskSpec is changed (43eee8d)learning_rate_multiplier in message .google.cloud.aiplatform.v1beta1.SupervisedHyperParameters is changed (43eee8d)machine_spec in message .google.cloud.aiplatform.v1beta1.DedicatedResources is changed (43eee8d)max_replica_count in message .google.cloud.aiplatform.v1beta1.AutomaticResources is changed (43eee8d)max_replica_count in message .google.cloud.aiplatform.v1beta1.DedicatedResources is changed (43eee8d)min_replica_count in message .google.cloud.aiplatform.v1beta1.AutomaticResources is changed (43eee8d)min_replica_count in message .google.cloud.aiplatform.v1beta1.DedicatedResources is changed (43eee8d)model in message .google.cloud.aiplatform.v1beta1.TunedModel is changed (43eee8d)required_replica_count in message .google.cloud.aiplatform.v1beta1.DedicatedResources is changed (43eee8d)training_dataset_uri in message .google.cloud.aiplatform.v1beta1.SupervisedTuningSpec is changed (43eee8d)validation_dataset_uri in message .google.cloud.aiplatform.v1beta1.SupervisedTuningSpec is changed (43eee8d)DedicatedResources is changed (43eee8d)Add ADK version check and set MemoryBankService as default when google-adk>=1.5.0
Add message ColabImage, add field colab_image to NotebookSoftwareConfig
MultimodalDataset.assess(). (0664ea3)Allow installation scripts in AgentEngine.
invoke method. It supports both streaming and non-streaming cases. (e686932)Add import_embeddings method in MatchingEngineIndex resource
Add deprecation notice to readme for Generative AI submodules: vertexai.generative_models, vertexai.language_models, vertexai.vision_models, vertexai.…
OpenModel.list_deploy_options() (9a0eec6)Add DnsPeeringConfig in service_networking.proto
autoscaling_target_request_count_per_minute to model deployment on Endpoint and Model classes (4df909c)show method for EvaluationResult and EvaluationDataset classes in IPython environment (c43de0a)get_rag_engine_config in rag_data.py (726d3a2)update_rag_engine_config in rag_data.py (726d3a2)create_corpus to accept encryption_spec in rag_data.py (865a68c)Add GenAI client (experimental)
train_dataset and validation_dataset in sft.train() docstring to include the Vertex Multimodal Dataset as a dataset source option. (eac1de0)A new field include_thoughts is added to message .google.cloud.aiplatform.v1.GenerationConfig.ThinkingConfig
include_thoughts is added to message .google.cloud.aiplatform.v1.GenerationConfig.ThinkingConfig (f2244aa)include_thoughts is added to message .google.cloud.aiplatform.v1.Part (f2244aa)thought_signature is added to message .google.cloud.aiplatform.v1.Part (f2244aa)thought is added to message .google.cloud.aiplatform.v1.Part (f2244aa)MultimodalDataset.toBigframes(). (ee12f05)thought to be set as input (f2244aa)Add support to process RAG response and generate inline citations in RAG v1.
[vertexai] Fix the result of export function
Add checkpoint ID to endpoint proto
create_corpus to accept encryption_spec in rag_data.py (ad821c5)Fix dedicated endpoint DNS is empty
A new value NVIDIA_B200 & NVIDIA_H200_141GB is added to enum AcceleratorType
NVIDIA_B200 & NVIDIA_H200_141GB is added to enum AcceleratorType (02236be)MultimodalDataset.toBigframes() method to convert dataset to a Bigframes Dataframe object and inspect the dataset in the notebook. (64dfdbc)additional_properties is added to message .google.cloud.aiplatform.v1.Schema (02236be)Deprecate election category HARM_CATEGORY_CIVIC_INTEGRITY
OpenModel.list_deploy_options() (acc301a)OpenModel.deploy() (acc301a)system_labels is added to message google.cloud.aiplatform.v1beta1.DeployRequest (1f98f4e)enable_custom_service_account parameter (must be set to True for successful Persistent Resource). The service_account parameter is retained for backward compatibility. (bf79bdf)ref and defs are added to message .google.cloud.aiplatform.v1.Schema (1f98f4e)Add Model Garden deploy SDK documentation and use cases.
Add pydantic to default required packages for agent engines
Add support for env_vars parameter when creating or updating Agent Engine.
get_rag_engine_config in rag_data.py (cda064e)update_rag_engine_config in rag_data.py (cda064e)Add a module-level function to create a Gemini template config for single-turn Gemini examples without having to explicitly construct the Gemini examp
Add page spans in retrieved contexts from Vertex RAG Engine in aiplatform v1
rag_files_count in message .google.cloud.aiplatform.v1beta1.RagCorpus is changed (30f0fcf)Add AssessData and AssembleData RPCs to DatasetService
deployment_spec and agent_framework field to ReasoningEngineSpec. (4c69301)deployment_spec and agent_framework field to ReasoningEngineSpec. (4c69301)package_spec from required to optional in ReasoningEngineSpec. (4c69301)package_spec from required to optional in ReasoningEngineSpec. (4c69301)Add function_call.id and function_response.id
Add Layout Parser to RAG v1 API
Add EnterpriseWebSearch tool option
Add the initial version of the AG2 agent prebuilt template.
A new field create_time is added to message .google.cloud.aiplatform.v1.GenerateContentResponse
create_time is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (b176d13)create_time is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (b176d13)response_id is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (b176d13)response_id is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (b176d13)unversioned_package_disabled is added to message .google.api.PythonSettings (b176d13)content in message .google.api.Page is changed (b176d13)filter in message .google.cloud.aiplatform.v1.ListNotebookRuntimesRequest is changed (b176d13)filter in message .google.cloud.aiplatform.v1.ListNotebookRuntimeTemplatesRequest is changed (b176d13)filter in message .google.cloud.aiplatform.v1beta1.ListNotebookRuntimesRequest is changed (b176d13)filter in message .google.cloud.aiplatform.v1beta1.ListNotebookRuntimeTemplatesRequest is changed (b176d13)RoutingRule is changed (b176d13)Add notebook helper functions to preview eval SDK to display and visualize evaluation results in an IPython environment
tune_autorater to make it consistent with model parameter in Rapid Eval SDK evaluate function (ef596f5)Deprecate is_default in message .google.cloud.aiplatform.v1.NotebookRuntimeTemplate
.google.cloud.aiplatform.v1beta1.NotebookRuntime (4620e6f).google.cloud.aiplatform.v1.NotebookRuntime (4620e6f)is_default in message .google.cloud.aiplatform.v1.NotebookRuntimeTemplate (4620e6f)is_default in message .google.cloud.aiplatform.v1beta1.NotebookRuntimeTemplate (4620e6f)service_account in message .google.cloud.aiplatform.v1.NotebookRuntime (4620e6f)service_account in message .google.cloud.aiplatform.v1.NotebookRuntimeTemplate (4620e6f)service_account in message .google.cloud.aiplatform.v1beta1.NotebookRuntime (4620e6f)service_account in message .google.cloud.aiplatform.v1beta1.NotebookRuntimeTemplate (4620e6f)Allow users to specify the job_display_name.
Add retrieval_config to ToolConfig v1
Add a new thought field in content proto
TypeAliasType to define aliases for union types in generative models (2224c83)contents arg could be None (ede0266)TypeAliasType from typing_extensions (8497476)A new field list_all_versions to ListPublisherModelsRequest
list_all_versions to ListPublisherModelsRequest (4b7799b)NVIDIA_H100_MEGA_80GB is added to enum AcceleratorType (4b7799b)RequiredReplicaCount field to DedicatedResources in MachineResources (4b7799b)Status field to DeployedModel in Endpoint (4b7799b)Status field to DeployedModel in Endpoint (4b7799b)FeatureMonitorJob (92feb60)GenerationConfig.response_modalities (78898fc)stream_query in LangChain Agent Templates in the Python Reasoning Engine Client (99f613b)Add deprecation warnings for use of similarity_top_k, vector_search_alpha, and vector_distance_threshold in retrieval_query, use RagRetrievalConfig in…
VertexAiSearch and Retrieval to GA (0537fec)FunctionDeclaration.response schema (4288fec)get_default_run method in Experiment class (9388fc9)api_key_config in message .google.cloud.aiplatform.v1beta1.JiraSource is changed (d7dff72)class_method in message .google.cloud.aiplatform.v1beta1.StreamQueryReasoningEngineRequest is changed (from steam_query to stream_query) (b7f9492)Add a nfs_mounts to RaySpec in PersistentResource API
nfs_mounts to RaySpec in PersistentResource API (6a22bef)deploy_index(), find_neighbors(), match(), and read_index_datapoints(). (3ab39a4)register_operations. The class methods spec will be changed according to user's register_operations. (74077b5)to_dict methods. (9d00424)Deprecate asynchronous mode in answer generation
protobuf_pythonic_types_enabled to message ExperimentalFeatures (acf3113)feature_group_id in message .google.cloud.aiplatform.v1.CreateFeatureGroupRequest is changed (acf3113)unit in message .google.api.QuotaLimit is changed (acf3113)BatchCreateFeaturesRequest is modified to call out BatchCreateFeatures (acf3113)index_update_method (7dff586)Audio_timestamp is supported only for some of the models
Add deprecation warning to Ray version 2.9.3
text field for Grounding metadata support chunk output (8a65b1d)audio_timestamp to GenerationConfig. (91c2120)rebase_tuned_model to vertexai.preview.tuning.sft. (2cef97f)Add enable_secure_private_service_connect in service attachment
PscInterfaceConfig field to pipeline_job.proto (44df243)Add rerun method to pipeline job preview client.
A new field response_logprbs is added to message .google.cloud.aiplatform.v1.GenerationConfig
response_logprbs is added to message .google.cloud.aiplatform.v1.GenerationConfig (#4410) (470933f)GenerativeModel.compute_tokens for v1 API (4637b4c)## 1.67.1 (2024-09-18) ### Bug Fixes * Fix rag corpus creation error
Add support for partial failures sink in import rag files.
generative_models classes to use the v1 service APIs instead of v1beta1 (66d84af)GenerativeModel.compute_tokens for v1 API (0de2987)One column per quarter.