v1.118.0

Compare Source

⚠ BREAKING CHANGES

• GenAI SDK client (prompt management) - Split create into two methods, create() and create_version()
• GenAI SDK client (prompt management) - Split get into two methods, get() and get_version()
• GenAI SDK client (prompt management) - Rename list methods to list() and list_versions()
• GenAI SDK client (prompt management) - Rename delete methods to delete() and delete_version()
• GenAI SDK client (prompt management) - Rename prompt_management module to prompts

Features

• Add enable_widget option in Google Maps and additional grounding information (0722687)
• Add filter option for deploy configuration in Model Garden deploy SDK (ac33e87)
• Add Model Garden deploy SDK select verified config guide. (36a5bbc)
• Add private_model_server_enabled to in Endpoint.proto (0722687)
• Add Validation mode in FunctionCallingConfig (0722687)
• Add Validation mode in FunctionCallingConfig (0722687)
• GenAI Client(evals) - Add create_evaluation_run method to Vertex AI GenAI SDK evals (7db9b4f)
• GenAI Client(evals) - Add get_evaluation_run method to Vertex AI GenAI SDK evals (bbbadbc)
• GenAI SDK client (prompt management) - Rename delete methods to delete() and delete_version() (d52ed42)
• GenAI SDK client (prompt management) - Rename list methods to list() and list_versions() (d52ed42)
• GenAI SDK client (prompt management) - Rename prompt_management module to prompts (d52ed42)
• GenAI SDK client (prompt management) - Split create into two methods, create() and create_version() (d52ed42)
• GenAI SDK client (prompt management) - Split get into two methods, get() and get_version() (d52ed42)
• GenAI SDK client(evals) Add data model for agent evaluation (d3ef487)
• PSC support for custom weights deploy (0722687)
• Tuning PreTunedModel API field (0722687)

Bug Fixes

• Mitigate breaking change in GenAI SDK for ADK on AgentEngine (9fa50aa)
• Relax the type annotations to avoid issues with pydantic when deploying (7a6a2f5)
• Remove the upperbound on google-genai for AgentEngine (74726f3)

Documentation

• A comment for field dedicated_endpoint_disabled in message .google.cloud.aiplatform.v1beta1.DeployRequest is changed (0722687)
• Remove legacy internal lint directives (0722687)
• Update the comment for ANY mode in FunctionCallingConfig. (0722687)
• Update the comment for ANY mode in FunctionCallingConfig. (0722687)

Miscellaneous Chores

• Release 1.118.0 (a67a795)

v1.117.0

Compare Source

Features

• Expose user reservation for CustomModel (f796e74)
• Gen AI SDK client - add experimental restore_version method to Prompt Management (820e0b6)

Documentation

• Add generated docs for Gen AI Modules (c3c2f7f)

v1.116.0

Compare Source

Features

• Add experimental async list_prompts and list_version methods to prompt management (13a626b)
• GenAI SDK client - add experimental async delete_prompt and delete_version method to Prompt Management (45e616a)
• Update gapic utils to allows creating RAG clients with api_override (9851905)

Bug Fixes

• GenAI Client(evals) - Add support for context in Grounding metric (e75d91f)
• Pass plugins to the Runner in ADK template. (b43b7b4)

Documentation

• Update AgentEngine with ADK template to the version in GA (0d600fd)

v1.115.0

Compare Source

⚠ BREAKING CHANGES

• The 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.

Features

• Add has_template_config to MultimodalDataset. (97a6e71)
• GenAI SDK client - add experimental async create_version and get methods to prompt management (d8de037)
• GenAI SDK client - Add experimental delete_prompt() and delete_version() methods to Prompt Management (3f7f976)
• GenAI SDK client - Modify optimize_prompt to return raw and parsed responses. (415cf26)
• GenAI SDK client -- add support for user defined labels for ReasoningEngine (002b441)
• Update list_deploy_options api for Vertex AI Model Garden custom model to support filtering by machines that user has quota for. (540e9e0)

Bug Fixes

• GenAI Client(evals) - Improve LiteLLM model completion response parsing (ff55a48)
• Update definition of async_add_session_to_memory to not depend on Session (dc9a5da)

Documentation

• Add Agent Engine with ADK examples to README. (c74305b)
• Streamline installation section in README and add uv package installation command (bf91a55)

Miscellaneous Chores

• Release 1.115.0 (bcf9ce0)

v1.114.0

Compare Source

Features

• GenAI SDK client - Add experimental list_prompts() and list_versions() methods to Prompt Management (18a5559)

Bug Fixes

• GenAI SDK client - Add agent_server_mode arg to AgentEngineConfig and pass it to API request if present. (1f821fd)

v1.113.0

Compare Source

Features

• GenAI - Added GPT, Qwen, and DeepSeek models support in GenAI batch prediction (cdd73d2)
• GenAI Client(evals) - Add support for Vertex Model Garden MaaS models. (751cb18)

Bug Fixes

• GenAI Client(evals) - Update data handling for adaptive rubric multi-turn evaluation metrics (c511490)

v1.112.0

Compare Source

Features

• GenAI SDK client - Add A2A support in Agent Engine (d500945)
• GenAI SDK client - Add Observability GenAI data format converter for evals (0665566)
• GenAI SDK client - Add orderBy to ListMemories (c6872f0)
• GenAI SDK client - Add support for loading evaluation datasets from Observability GCS sources (bfcccc9)
• GenAI SDK client - Add the service account option for the agent engine (219c33f)
• Adding gpu_partition_size parameter to Model.deploy() method. (966c236)
• Change gpu_partition_size type hint to str. (910016d)
• GenAI SDK client - Add api_key parameter to vertexai.Client (a9ffc60)
• GenAI SDK client - Add experimental prompt_management module with create_version and get methods (d5a14ba)
• GenAI SDK client - Add live/bidi agent deployment support for Agent Engine (74e3f25)
• GenAI SDK client - Add sandbox code execution SDK support (74e52d9)
• GenAI SDK client - Remove experimental warning from agent_engines module (42c3c9c)
• GenAI SDK client - Support bidi stream query in agent engines and ADK template. (456249e)

Bug Fixes

• Allow for inheritance of clone behavior in AdkApp (e5ced93)
• GenAI SDK client - Decrease polling interval for GenerateMemories and CreateSession (currently 10s) (77a3933)
• GenAI SDK client - Fix deepcopy for RubricGenerationConfig in RubricBasedMetric. (e39f0bd)
• GenAI SDK client - Handle empty GenerateMemories response (no memories generated) as valid response. (99f0078)

v1.111.0

Compare Source

⚠ BREAKING CHANGES

• GenAI SDK client - remove duplicate types for Content, Part, and evals

Features

• Add disable_container_logging in v1beta1 api (3a75313)
• Add encryption_spec support to Agent Engine genai sdk. (3bb8100)
• Add API response for Gen AI Evaluation in Tuning (3a75313)
• Add Customization Config to Memory Bank (23d7681)
• Add data foundry service synthetic data generation API for v1 (3a75313)
• Add new api for getting deploy options for Vertex AI Model Garden custom model (d0c7803)
• Add support for plugins and credential service in AdkApp (93561a7)
• Add TTL fields for Memory Bank and Sessions (eff6c58)
• Adding gpu_partition_size parameter to Endpoint.deploy() method. (7ebbddb)
• Enabled deploy dedicated endpoint by default (1a3f477)
• GenAI SDK client - Add live/bidi streaming support for Agent Engine (4fec136)
• GenAI SDK client(evals) - Implement Predefined metrics support in Vertex GenAI Eval SDK (248a365)
• GenAI SDK client(evals) - Release GenAI evals module to public preview and remove experimental warning from client.evals module (b915b61)
• GenAI SDK client(evals) - Support Predefined Metrics in generate_rubrics (c0b6f5c)
• Introduce AdkApp in GA (a6600dd)
• RAG - Add support for max_embedding_requests_per_min in upload_file request (a330ecb)
• RAG - Add support for max_embedding_requests_per_min in upload_file request (a885b5d)

Bug Fixes

• GenAI SDK client - Deploy ADK agents using the AdkApp template in GA (4f1e013)
• GenAI SDK client - do not register API methods in get or update for agent_engines with lightweight creation (d76411a)
• GenAI SDK client - Provide the operation error message if it is available (edaedb1)
• GenAI SDK client - switch to nested modules for agent engines (b1d0b7c)
• Rename agent_engine parameter to agent in Agent Engines. (65bf9b6)

Miscellaneous Chores

• GenAI SDK client - remove duplicate types for Content, Part, and evals (b4d37b6)
• Release 1.111.0 (e1ad1c5)

v1.110.0

Compare Source

Features

• Add encryption_spec support to Agent Engine create and update. (1b135ca)
• Add run_config parameter to AdkApp query methods (e3b9a76)
• Add DirectMemoriesSource to SDK (cebad9a)
• Add option EndpointUserId and ModelUserId fields (2aae1f9)
• GenAI SDK client - Agent Engine Session Events SDK (69d87e2)
• RAG - Add support for timeout in upload_file request (bc7e2e9)
• Support for runtime controls and PSC-I in Agent Engine. (ec11bd3)

v1.109.0

Compare Source

Features

• Add gpu_partition_size to MachineSpec (b753565)
• Add API for Gen AI Evaluation in Tuning (b753565)
• Add direct_memories_source (b753565)
• Add expiration for TTL for Memory and Sessions (b753565)
• Add force_delete field to DeleteRagFile 'preview' API request for Vertex RAG (b753565)
• Add Grounding with Google Maps tool (b753565)
• Add memory related methods to AdkApp (1368f6a)
• Add option EndpointUserId and ModelUserId fields (b753565)
• Add support for CMEK, runtime controls, and PSC-I to Reasoning Engine protos (b753565)
• Add update_mask "embedding_metadata" to MatchingEngineIndex upsert_datapoints() to support embedding metadata update. (0870512)
• Added document_name for vertex ai search as part of retrieved context from grounding chunk (b753565)
• Expose RecommendSpecs api to vertex python SDK for Custom Weights Model deployment (b753565)
• Migrate dedicated endpoint to be enabled by default (b753565)
• Support for runtime controls and PSC-I (77f7b8e)

Documentation

• A comment for field dedicated_endpoint_enabled in message .google.cloud.aiplatform.v1.DeployRequest is changed (b753565)
• A comment for field monitored_resource_labels in message .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec is changed (b753565)
• Add encryption_spec to ReasoningEngine (b753565)
• Add psc_interface_config, min/max_instances, resource_limits, container_concurrency to ReasoningEngineSpec (b753565)
• Update comment for allowed values for config models (b753565)

v1.108.0

Compare Source

Features

• Add autoscaling_target_pubsub_num_undelivered_messages option in Preview model deployment on Endpoint & Model classes. (52eacce)

Bug Fixes

• GenAI SDK client - Fix typo in error message for optimize_prompt (63e1caa)
• Set the agent_framework when initializing module-based agent engine (6c15762)

v1.107.0

Compare Source

Features

• A new value NVIDIA_GB200 is added to enum AcceleratorType (d682fac)
• Add DeploymentStage for CreateEndpointOperationMetadata and DeployModelOperationMetadata (d682fac)
• Add a FooBar API (d682fac)
• Add autoscaling metrics parameters for PrivateEndpoint class's model deployment API (58880be)
• Add embedding_metadata to google.cloud.aiplatform.v1.Index (d682fac)
• Add enable_datapoint_upsert_logging to google.cloud.aiplatform.v1.DeployedIndex (d682fac)
• Add exclude_domains for grounding with GoogleSearch and EnterpriseWebSearch (d682fac)
• Add FeatureViewDirectWrite API in v1 (d682fac)
• Add field ReasoningEngineSpec.service_account (d682fac)
• Add ray 2.47 unit tests as required checks (5445648)
• Add the VeoTuningSpec (d682fac)
• Added the ability to use the Model Armor service for content sanitization (d682fac)
• Adds DWS and spot VM feature support to custom batch predictions 2.0 (d682fac)
• GenAI SDK client - add zero-shot prompt optimizer: an option to quickly improve provided system instructions or a prompt, or generate new system instructions based on a prompt. (bc2e8f4)
• GenAI SDK client - Agent Engine Session SDK (8f28c40)
• GenAI SDK client(evals) - add visualization support for rubric-based evaluation workflow (299c44c)
• Online Prediction DeployModel API to support custom metrics based autoscaling (d682fac)
• Remove private preview label from Model Armor protos (d682fac)

Documentation

• Update comments for rpc BatchCreatePullRequestComments, ResolvePullRequestComments and UnresolvePullRequestComments (d682fac)

v1.106.0

Compare Source

Features

• Add service_account parameter to AgentEngine class for creation and update (6359168)
• Add service_account to Reasoning Engine public protos (7b6010b)
• Add service_account to Reasoning Engine public protos (7b6010b)
• Add Vertex AI Model Garden deploy SDK unified Model class in Public Preview (78c8fdd)
• Allow adapter_size=32 for supervised tuning (3a776a7)
• Vertex AI Model Garden deploy SDK Support for self-deploy Partner Model (6c72801)

Bug Fixes

• GenAI SDK client - handle os paths for .whl in requirements when deploying to agent engine (75cd064)
• GenAI SDK client - parsing json body of HTTP response to yield JSON (8cfd9ba)
• Use datasets.MultimodalDataset.from_gemini_request_jsonl() without target_table_id. (e92cca2)

v1.105.0

Compare Source

Features

• Add FlexStart option to DeploymentResourcePool.create, Endpoint.deploy, and Model.deploy (preview) (82dd075)
• Add Ray 2.47 support to RoV Bigquery read/write (8e6df42)
• Add Ray 2.47 support to SDK Client Builder (dde560d)
• Add support for managed oss fine tuning service (2672ec3)
• GenAI SDK client(evals) - Add async evaluate_instances method (a52198a)
• Improve PersistentResource exception logging to include cluster name (4b88698)
• Provide docs for using invoke method. (1315df7)
• RAG - add timeout options for create_corpus, update_corpus and update_rag_engine_config for both v1 and v1beta1 apis. (afa5610)
• Update Ray version support to include Ray v2.47" (e0ee94c)
• Vertex AI Model Garden custom model deploy SDK Public Preview (1ceb2e1)

Bug Fixes

• GenAI SDK client - Fix JS variable name conflict in evals visualization for VS Code iPython environment (079b1f9)

v1.104.0

Compare Source

Features

• Add Aggregation Output in EvaluateDataset Get Operation Response (43eee8d)
• Add API for Managed OSS Fine Tuning (43eee8d)
• Add flexstart option to v1beta1 (43eee8d)
• Expose task_unique_name in pipeline task details for pipeline rerun (43eee8d)
• GenAI SDK client - Add support for context specs when creating agent engine instances (8321826)
• GenAI SDK client(evals) - Add Generate Rubrics API config and internal method (6727fb3)
• GenAI SDK client(evals) - add rubric-based evaluation types (df2390e)
• GenAI SDK client(evals) - Add support for rubric-based metrics, and rubric customization eval workflow (36bfda2)
• Some comments changes in machine_resources.proto to v1beta1 (43eee8d)
• Vertex AI Model Garden custom model deploy Public Preview (43eee8d)

Bug Fixes

• GenAI SDK client(evals) - Handle optional pandas dependency in type hints (cee8d8b)

Documentation

• A comment for field boot_disk_type in message .google.cloud.aiplatform.v1beta1.DiskSpec is changed (43eee8d)
• A comment for field learning_rate_multiplier in message .google.cloud.aiplatform.v1beta1.SupervisedHyperParameters is changed (43eee8d)
• A comment for field machine_spec in message .google.cloud.aiplatform.v1beta1.DedicatedResources is changed (43eee8d)
• A comment for field max_replica_count in message .google.cloud.aiplatform.v1beta1.AutomaticResources is changed (43eee8d)
• A comment for field max_replica_count in message .google.cloud.aiplatform.v1beta1.DedicatedResources is changed (43eee8d)
• A comment for field min_replica_count in message .google.cloud.aiplatform.v1beta1.AutomaticResources is changed (43eee8d)
• A comment for field min_replica_count in message .google.cloud.aiplatform.v1beta1.DedicatedResources is changed (43eee8d)
• A comment for field model in message .google.cloud.aiplatform.v1beta1.TunedModel is changed (43eee8d)
• A comment for field required_replica_count in message .google.cloud.aiplatform.v1beta1.DedicatedResources is changed (43eee8d)
• A comment for field training_dataset_uri in message .google.cloud.aiplatform.v1beta1.SupervisedTuningSpec is changed (43eee8d)
• A comment for field validation_dataset_uri in message .google.cloud.aiplatform.v1beta1.SupervisedTuningSpec is changed (43eee8d)
• A comment for message DedicatedResources is changed (43eee8d)
• Add constraints for AggregationMetric enum and default value for flip_enabled field in AutoraterConfig (43eee8d)

v1.103.0

Compare Source

Features

• Add ADK version check and set MemoryBankService as default when google-adk>=1.5.0 (262fbc3)
• Add logging for agent engine creation (795ee17)
• Populate task_unique_name from initial pipeline run in Pipeline Task Rerun Configs for pipeline job rerun (116a0a6)
• Ummd.MultimodalDataset.from_bigquery() now also accepts a table id (not just a BQ table URI). (6e5c421)

v1.102.0

Compare Source

Features

• Add message ColabImage, add field colab_image to NotebookSoftwareConfig (2c64a76)
• Add message ColabImage, add field colab_image to NotebookSoftwareConfig (2c64a76)
• Configure Bigframes implicitly in MultimodalDataset.assess(). (0664ea3)
• GenAI SDK client - add async version of prompt optimizer (4564c9c)
• GenAI SDK client (evals) - add LLMMetric.load function to load a config file (local or GCS) (56252e8)

Documentation

• Fix the docstring example for unary Endpoint invoke method. (a132e86)

v1.101.0

Compare Source

Features

• Allow installation scripts in AgentEngine. (9296d4d)
• Add invoke method. It supports both streaming and non-streaming cases. (e686932)
• Add computer use support to tools (f56c42e)
• Add computer use support to tools (f56c42e)
• Allow users to pass project_number for custom job service account when service_account is not provided. (5b59030)
• Expose task_unique_name in pipeline task details for pipeline rerun (f56c42e)
• Support creating an invoke enabled model in Python SDK (71a8d7b)

v1.100.0

Compare Source

Features

• Add import_embeddings method in MatchingEngineIndex resource (5a0df36)
• Add invoke_route_prefix to ModelContainerSpec in aiplatform v1 models.proto (4202177)
• Add invoke_route_prefix to ModelContainerSpec in aiplatform v1beta1 models.proto (d4ede02)
• Add Model Garden deploy OSS model API (d4ede02)
• Add PSCAutomationConfig to PrivateServiceConnectConfig in service_networking.proto (d4ede02)
• Add validation assessment for batch prediction. (d570fc9)
• GenAI SDK client - Add batch_evaluate method for asynchronous batch eval. Add transformation support for consistent interface parameters with the evaluate method (4d44f94)
• GenAI SDK client - Add Vertex AI Prompt Optimizer to the Gen AI SDK (experimental) (5daacda)
• GenAI SDK client - Initial release of Agent Engine Memories SDK (e8d18b6)
• GenAI SDK client (evals) - add support for third-party model inference via litellm library (e728d8b)
• matching-engine: Add sync argument to deploy_index (fee1e2d)
• Reasoning Engine v1beta1 subresource updates (d4ede02)
• Updated explicit sync to existing decorator optional_sync (fee1e2d)

Bug Fixes

• Fix auth scope for RAG upload_file (a506b94)
• Fixed return type for deploy_index and added test for sync values (fee1e2d)
• Use PrivateServiceConnectConfig in service_networking in PrivateEndpoint instead of the wrapper class PrivateServiceConnectConfig (87c2c3e)

v1.99.0

Compare Source

Features

• [vertexai] Added concise option name to OpenModel.list_deploy_options() (9a0eec6)
• Add resource usage assessment for batch prediction. (f63e436)
• Add support for ADK memory service to AdkApp template (733fddd)
• GenAI SDK client - Add automatic candidate naming and creation timestamp to evaluation dataset metadata (e8897e7)
• GenAI SDK client - Add support for OpenAI data format for evals (f8f66f1)
• GenAI SDK client - Adding client-based SDKs for Agent Engine (7b51d9e)

Documentation

• Add deprecation notice to readme for Generative AI submodules: vertexai.generative_models, vertexai.language_models, vertexai.vision_models, vertexai.tuning, vertexai.caching (beae2e3)
• Add deprecation notice to readme for Generative AI submodules: vertexai.generative_models, vertexai.language_models, vertexai.vision_models, vertexai.tuning, vertexai.caching (cdee7c2)
• Add deprecation notice to readme for Generative AI submodules: vertexai.generative_models, vertexai.language_models, vertexai.vision_models, vertexai.tuning, vertexai.caching (9b0beae)

v1.98.0

Compare Source

Features

• Add DnsPeeringConfig in service_networking.proto (c5bb99b)
• Add DnsPeeringConfig in service_networking.proto (c5bb99b)
• Add EncryptionSpec field for RagCorpus CMEK feature to v1 (9b48d24)
• Add PSC interface config support for Custom Training Jobs (267b53d)
• Add RagEngineConfig update/get APIs to v1 (c5bb99b)
• Add Scaled tier for RagEngineConfig to v1beta, equivalent to Enterprise (c5bb99b)
• Added autoscaling_target_request_count_per_minute to model deployment on Endpoint and Model classes (4df909c)
• Adding VAPO Prompt Optimizer (PO-data) to the genai SDK. (701b8d4)
• Enable asia-south2 (a1f4205)
• Enable Vertex Multimodal Dataset as input to supervised fine-tuning. (959d798)
• Export global quota configs in preview sdk (7f964d5)
• GenAI SDK client - add show method for EvaluationResult and EvaluationDataset classes in IPython environment (c43de0a)
• Introduce RagFileMetadataConfig for importing metadata to Rag (9b48d24)
• RAG - Add Basic, Scaled and Unprovisioned tier in v1. (726d3a2)
• RAG - Add Scaled and Unprovisioned tier in preview. (726d3a2)
• RAG - Implement v1 get_rag_engine_config in rag_data.py (726d3a2)
• RAG - Implement v1 update_rag_engine_config in rag_data.py (726d3a2)
• Update v1 create_corpus to accept encryption_spec in rag_data.py (865a68c)

Bug Fixes

• Update supported python version for create_reasoning_engine (0059c01)
• Use none check to avoid 30s delay in agent run. (84895b6)

Documentation

• Add GenAI client examples to readme (f1e17a6)

v0.14.1

Compare Source

Bug Fixes

• Add support for a metadata column named id (#​302) (ceffc44)