google-cloud-aiplatform

1.111.0 (2025-08-27)

⚠ 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)

1.110.0 (2025-08-18)

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)

1.109.0 (2025-08-13)

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)

1.108.0 (2025-08-07)

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)

1.107.0 (2025-08-06)

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)

1.106.0 (2025-07-30)

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)

1.105.0 (2025-07-22)

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)

1.104.0 (2025-07-15)

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)

1.103.0 (2025-07-10)

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)

1.102.0 (2025-07-08)

Features

• 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)

1.101.0 (2025-07-01)

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)

1.100.0 (2025-06-26)

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)

1.99.0 (2025-06-24)

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)

1.98.0 (2025-06-19)

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)
• 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)

1.97.0 (2025-06-11)

Features

• Add GenAI client (experimental) (166b747)
• Expose UrlContextMetadata API to v1 (b57cbd3)
• Expose UrlContextMetadata API to v1beta1 (b57cbd3)
• Integration with Vertex AI Multimodal Datasets: Update train_dataset and validation_dataset in sft.train() docstring to include the Vertex Multimodal Dataset as a dataset source option. (eac1de0)
• RAG - Introduce configuration to corpus types, with DocumentCorpus and MemoryCorpus options. (ede4b5b)

Bug Fixes

• Add default auth scope (3d747e7)
• Add support for ADK Agents as a supported type for agent engine (6b177ca)
• Set memory corpus configuration into RagCorpus object. (39d3c70)

1.96.0 (2025-06-03)

Features

• A new field include_thoughts is added to message .google.cloud.aiplatform.v1.GenerationConfig.ThinkingConfig (f2244aa)
• A new field include_thoughts is added to message .google.cloud.aiplatform.v1.Part (f2244aa)
• A new field thought_signature is added to message .google.cloud.aiplatform.v1.Part (f2244aa)
• A new field thought is added to message .google.cloud.aiplatform.v1.Part (f2244aa)
• Add json schema support to structured output and function declaration (f2244aa)
• Add json schema support to structured output and function declaration (f2244aa)
• Add network_attachment to PscInterfaceConfig (f2244aa)
• Add psc_interface_config to CustomJobSpec (f2244aa)
• Add psc_interface_config to PersistentResource (f2244aa)
• Add psc_interface_config to PipelineJob (f2244aa)
• Expose URL Context API to v1 (f2244aa)
• Expose URL Context API to v1beta1 (f2244aa)

Bug Fixes

• Small fix in MultimodalDataset.toBigframes(). (ee12f05)

Documentation

• Allow field thought to be set as input (f2244aa)

Miscellaneous Chores

• Release 1.96.0 (97be629)

1.95.1 (2025-05-30)

Features

• Add support to process RAG response and generate inline citations in RAG v1. (2b2dc4f)
• Register async methods to AdkApp. (cb2754d)

Bug Fixes

• Fix CachedContent.create if the kms_key_name is not given (05986c0)

Miscellaneous Chores

• Release 1.95.1 (1d2387f)

1.95.0 (2025-05-28)

Features

• [vertexai] Fix the result of export function (9427b15)
• Add async support for reasoning engine. (1b7d29c)
• Introduce RAG as context/memory store for Gemini Live API (787c60f)
• Update AdkApp template to match ADK async interface. After this change, AdkApp will only work with ADK >= 1.0.0. (e1745d7)

1.94.0 (2025-05-22)

Features

• Add checkpoint ID to endpoint proto (f0812e3)
• Add checkpoint ID to endpoint proto (f0812e3)
• Add encryption_spec to Model Monitoring public preview API (f0812e3)
• Add VertexAISearch.max_results, filter, data_store_specs options (f0812e3)
• Add VertexAISearch.max_results, filter, data_store_specs options (f0812e3)
• Adding thoughts_token_count to prediction service (f0812e3)
• Adding thoughts_token_count to v1beta1 client library (f0812e3)
• Update preview create_corpus to accept encryption_spec in rag_data.py (ad821c5)

Bug Fixes

• Throw error when user is using google-adk>=1.0.0 as it is not well supported for now. (634bb78)

1.93.1 (2025-05-20)

Bug Fixes

• Fix dedicated endpoint DNS is empty (fc6d893)
• Fix resolving between passed and attached read configs in multimodal datasets (4429e36)

1.93.0 (2025-05-15)

Features

• A new value NVIDIA_B200 & NVIDIA_H200_141GB is added to enum AcceleratorType (02236be)
• Add MultimodalDataset.toBigframes() method to convert dataset to a Bigframes Dataframe object and inspect the dataset in the notebook. (64dfdbc)
• Add ANN feature for RagManagedDb (02236be)
• Add EncryptionSpec for RagCorpus CMEK feature (02236be)
• Add support for system paths in ModuleAgent (8c95d3f)
• Allow customers to set kms_key_name for context caching create method (c551cc6)
• GenAI - Release the Model Garden SDK to GA (49c3418)
• New field additional_properties is added to message .google.cloud.aiplatform.v1.Schema (02236be)
• Populate agent_framework field in the RE spec. (0a127fd)
• RAG - Add ANN and KNN retrieval strategies for RagManagedDb in preview (8c0bf19)
• Support async stream query in agent engines and adk template. (0c4f4a6)
• Support Python 3.13 for reasoning engine. (51b13e5)
• Update v1 sdk to support llmparser in import file functions (03a7861)

Bug Fixes

• Fix the type annotation for content dictionaries in AdkApp (674beaa)

Documentation

• Fix links and typos (02236be)
• Remove comments for a non public feature (#5301) (02236be)
• Update doc publisher for Gemini docs (6700e3d)

1.92.0 (2025-05-08)

⚠ BREAKING CHANGES

• Removed support for session resource paths that do not include reasoning engine

Features

• [vertexai] Added a concise option to OpenModel.list_deploy_options() (acc301a)
• [vertexai] Added system labels to OpenModel.deploy() (acc301a)
• A new field system_labels is added to message google.cloud.aiplatform.v1beta1.DeployRequest (1f98f4e)
• Add enable_custom_service_account parameter (must be set to True for successful Persistent Resource). The service_account parameter is retained for backward compatibility. (bf79bdf)
• Add dedicated_endpoint_enabled and dedicated_endpoint_dns property. (32ee6d9)
• Add gemini_request_read_config field to AssembleDataRequest and AssessDataRequest in aiplatform v1beta (1f98f4e)
• Add google.genai.types.Content as an allowed message type to ADK's stream_query method (6b131d1)
• Adding ThinkingConfig to v1 client library (1f98f4e)
• Adding ThinkingConfig to v1beta1 client library (1f98f4e)
• Allow customers to set encryption_spec for context caching (1f98f4e)
• Deprecate election category HARM_CATEGORY_CIVIC_INTEGRITY (1f98f4e)
• Deprecated EventActions.transfer_to_agent and replaced with EventActions.transfer_agent (1f98f4e)
• Implement check_license_agreement_status and accept_model_license_agreement for Model Garden OpenModel. (3289d92)
• In predict/rawPredict/streamRawPredict, send requests to the correct DNS based on endpoint type. (32ee6d9)
• Model Registry Model Checkpoint API (1f98f4e)
• New fields ref and defs are added to message .google.cloud.aiplatform.v1.Schema (1f98f4e)
• Remove the requirement for a staging bucket to be set if an agent engine is created without extra packages or requirements files. (6de9de1)

Bug Fixes

• Only set parameters when it is not None for predict requests. (32ee6d9)
• Raise exception with details for dedicated endpoint if predict failed. (32ee6d9)
• Removed support for session resource paths that do not include reasoning engine (1f98f4e)
• Set the app_name in AdkApp template to GOOGLE_CLOUD_AGENT_ENGINE_ID if it exists. (1cbe028)

Documentation

• Deprecate election category HARM_CATEGORY_CIVIC_INTEGRITY (1f98f4e)
• Fix comment for field_mapping field in GeminiTemplateConfig (1f98f4e)
• Update an outdated URL (1f98f4e)

Miscellaneous Chores

• Release 1.92.0 (5d60f6b)

1.91.0 (2025-04-30)

Features

• Add Model Garden deploy SDK documentation and use cases. (6eea5f4)
• Allow setting Vertex Model Garden source model version id during model upload (b1bbba6)
• GenAI - Add support for self-hosted OSS models in Batch Prediction. (c76ac62)
• GenAI - Support batch prediction in Model Garden OpenModel. (8bf30b7)
• Update upperbound for langgraph (547bf01)

Bug Fixes

• Removing Python 3.8 support due to EOL (4330b2f)

1.90.0 (2025-04-22)

Features

• Add pydantic to default required packages for agent engines (6960ae4)
• Introduce a ModuleAgent template to Agent Engine (5efcd6b)

Bug Fixes

• Broken import of VertexAiSessionService in AdkApp (b84657a)
• deps: Allow werkzeug 3.x (0cb2b93)
• Pin pydantic version lower-bound limit to 2.11.1 to fix a pydantic dependency issue. (a5c1130)
• Pin pydantic version lower-bound limit to 2.11.1 to fix a pydantic dependency issue. (180cbba)

1.89.0 (2025-04-16)

Features

• Add support for env_vars parameter when creating or updating Agent Engine. (691c1f6)
• Add UpdateRagEngineConfig rpc (64386e9)
• Implement preview get_rag_engine_config in rag_data.py (cda064e)
• Implement preview update_rag_engine_config in rag_data.py (cda064e)
• Update win rate calculation in GenAI Evaluation for rubric based evaluation (d442c42)

Bug Fixes

• Include the env variables of the AdkApp when cloning (9814768)

1.88.0 (2025-04-09)

Features

• Add a module-level function to create a Gemini template config for single-turn Gemini examples without having to explicitly construct the Gemini example. (126d10c)
• Add autoscaling_target_request_count_per_minute option in Preview model deployment on Endpoint & Model classes. (0f1f10a)
• Add Gen AI logging public preview API (1589f66)
• Add new template for AgentEngine (0478f10)
• Add the possibility to create multimodal datasets without explicitly specifying a bigquery dataset/table. (f5043a6)
• Allow EvalTask to take dataset as a Google sheet - simplifying rubric revision CUJ (15df1f6)
• Allow table targets in multi-region datasets when creating multimodal datasets (2d7bc32)
• Check if rubrics column is present before converting list of rubrics to string (6c1569b)
• Convert list of rubrics to a string before sending the API request. This allows users to use default parse_rubrics function that returns a list of rubrics with customized prompts, and bring their own rubrics as a list. (9f21b73)
• GenAI Evaluation: Release GenAI Evaluation SDK autorater metric configuration utils to vertexai.preview module. (f816d5a)
• GenAI Evaluation: Release GenAI Evaluation SDK parsing rubric generation response with additional fields to vertexai.preview module. (79ca86a)
• GenAI Evaluation: Release GenAI Evaluation SDK rubric based evaluation to vertexai.preview module. (bb07581)
• Model optimizer SDK support (f257298)
• Track the output path for metrics_table in experiments metadata, if output bucket is specified but no file name is specified, we will generate a unique file name (be2c99f)

Bug Fixes

• Preprend question tag to rubric critiquing response after editing the predefined prompts to end with <question> to avoid parsing errors (0abd6ad)

1.87.0 (2025-04-01)

Features

• Add page spans in retrieved contexts from Vertex RAG Engine in aiplatform v1 (30f0fcf)
• Add page spans in retrieved contexts from Vertex RAG Engine in aiplatform v1beta1 (30f0fcf)
• Add support for Vertex AI Search engine (30f0fcf)
• Add validation of the BigQuery location when creating a MultimodalDataset (98459aa)
• Adding Vertex AI Search Config for RAG corpuses to SDK (a7453da)
• Allow using multimodal datasets in the SDK. (d951b74)
• ExampleStore SDK in public preview (50fbdee)
• GenAI Evaluation: Release GenAI Evaluation SDK multimodal evaluation to vertexai.preview module. (f090ca1)
• Make it optional to pass in an instance of an agent when creating a new ReasoningEngine instance (f3addc9)
• Support creating multimodal datasets from a JSONL file containing Gemini requests (a323679)
• Vertex AI Model Garden open model export SDK Public Preview (898109d)

Bug Fixes

• Propagating import result sink correctly in the vertexai sdk. (184cca5)
• Remove the xprof dependency from Vertex Tensorboard uploader. (1336b85)

Documentation

• A comment for field rag_files_count in message .google.cloud.aiplatform.v1beta1.RagCorpus is changed (30f0fcf)

1.86.0 (2025-03-26)

Features

• Add a ExportPublisherModel API (#5055) (4c69301)
• Add AssessData and AssembleData RPCs to DatasetService (4c69301)
• Add batch prediction assessments to multimodal dataset RPCs (a6d975e)
• Add env variables and agent framework to ReasoningEngineSpec (4c69301)
• Add env variables and agent framework to ReasoningEngineSpec in v1beta1 (4c69301)
• Add example, example_store, and example_store_service protos (a6d975e)
• Add import result bq sink to the import files API (4c69301)
• Add import result bq sink to the import files API (4c69301)
• Add import result gcs sink to the import files API (4c69301)
• Add import result gcs sink to the import files API (4c69301)
• Add model_config field for model selection preference (a6d975e)
• Add multihost_gpu_node_count to Vertex SDK. (03d9bf7)
• Add ray 2.33 and 2.42 unit tests as required checks (51dbe94)
• Add session.proto and session_service.proto (a6d975e)
• Add support for version 2.42 for RoV Bigquery read/write (6090205)
• Add the initial version of the LlamaIndex agent prebuilt template. (f1f2ea5)
• Add the initial version of the LlamaIndex agent prebuilt template. (8cbea81)
• Add VertexAISearch.engine option (4c69301)
• Change format string assembly logic for prompt templates. (43ebe97)
• Copy output uploading features from GA Eval SDK to preview. (d6f99cb)
• Enable force deletion in ReasoningEngine (a6d975e)
• Enable force deletion in ReasoningEngine v1beta1 (a6d975e)
• Modify v1 sdk to support rerankers (ececfb3)
• Update GenAI Evaluation QPS to 10. (0995ce2)
• Update GenAI Evaluation QPS to 10. (a59b0a6)
• Update multimodal evaluation (content_map_instance), rubric generation (rubric_based_instance, etc) and raw_output(raw_output, custom_output, etc) proto change in online eval API (a6d975e)
• Update Ray system tests to be compatible with new RoV 2.42 changes (fbb9560)
• Update setup.py for including Ray v2.42 (827b484)

Bug Fixes

• Format of the input to GetPublisherModelRequest for Hugging Face models. (8f7e8b9)
• Format of the input to GetPublisherModelRequest for Hugging Face models. (96d2ecb)
• GenAI Eval: fix a prompt template variable parsing issue when multiline json structures are present (5da362f)
• GenAI Eval: fix a prompt template variable parsing issue when multiline json structures are present (fd12cb8)
• GenAI Evaluation: Fix system instruction not being added to PairwiseMetric. (5c60d95)
• GenAI Evaluation: Fix system instruction not being added to PairwiseMetric. (c65879d)
• Update ipython import according to the latest ipython docs (533012a)

Documentation

• Add deployment_spec and agent_framework field to ReasoningEngineSpec. (4c69301)
• Add deployment_spec and agent_framework field to ReasoningEngineSpec. (4c69301)
• Update comment for package_spec from required to optional in ReasoningEngineSpec. (4c69301)
• Update comment for package_spec from required to optional in ReasoningEngineSpec. (4c69301)

1.85.0 (2025-03-18)

Features

• Add function_call.id and function_response.id (3f6c824)
• Add Python version 3.12 to Agent Engine (1232132)
• Add Ray 2.42 support to SDK Client Builder (2a67076)
• Add reranker config to RAG v1 API (3f6c824)
• Add support for version 2.42 for RoV Bigquery read/write (f4ce684)
• Implement GA versions of agent engine prebuilt templates (37b72c2)
• Modify v1 sdk to support rerankers (a6b7de5)

Bug Fixes

• Allow Protobuf 6.x (3f6c824)
• Preserve system_instruction in LangchainAgent clone() (63fc33e)
• Resolve issue where pre-release versions of dependencies are installed (de83fe3)

Documentation

• Update SDK Job Submission with Ray v2.42 updated comments (f281113)

1.84.0 (2025-03-11)

Features

• Add Layout Parser to RAG v1 API (ba9a314)
• Add multihost_gpu_node_count to Vertex SDK for multihost GPU support (ba9a314)
• Add request/response logging to PSC endpoints (b36a43a)
• Add support for Document AI Layout Parser in RAG v1 (1837390)
• Add the system tests for AG2 prebuilt template (80cfc2f)
• Add the system tests for Langgraph prebuilt template (833c1d2)
• Allowing users to choose whether to use the hf model cache (ba9a314)
• Allowing users to choose whether to use the hf model cache (ba9a314)
• Allowing users to specify the version id of the Model Garden model (ba9a314)
• Allowing users to specify the version id of the Model Garden model (ba9a314)
• GA Context Cache Python SDK (3aa0c6d)
• Support custom predictor Docker image builds on non-x86 architectures (#2115) (87dd5c0)
• Vertex AI Model Garden deploy SDK Support for container specifications and equivalent Model Garden models for Hugging Face (e425ded)

1.83.0 (2025-03-05)

Features

• Add EnterpriseWebSearch tool option (816a607)
• Add notebook helper functions to eval SDK to display and visualize evaluation results in an IPython environment (acf8a80)
• Add VertexAISearch.engine option (816a607)
• Eval SDK: Modify Gemini scraping to log errors during response generation and return a consistent error message (cc2d36e)
• Vertex AI Model Garden open model deploy SDK Public Preview (4c8c277)

Bug Fixes

• Add request metadata to rag methods. (b2cc069)
• Migration to python 3.12. called_once was deleted in favor of assert_called_once, since it was largely misused (b4ec000)
• Resolve issue where pre-release versions of dependencies are installed (35cf246)

1.82.0 (2025-02-26)

Features

• Add Model Garden deploy API (e356f5a)
• Add the initial version of the AG2 agent prebuilt template. (abf08da)
• Implement preview deployment with RolloutOptions. (8cefabb)
• Vertex AI Agent Engine GA SDK (632730c)

Bug Fixes

• Avoid hard-coding the LinearRegression class name in tests (7121770)
• Clean up unused EmbeddingModelConfig. (4998c1a)
• Fix rag_embedding_model_config logic indentation (63736ef)
• PrivateEndpoint predict method should set parameters in request payload. (c7526a1)

1.81.0 (2025-02-18)

Features

• A new field create_time is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (b176d13)
• A new field create_time is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (b176d13)
• A new field response_id is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (b176d13)
• A new field response_id is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (b176d13)
• A new field unversioned_package_disabled is added to message .google.api.PythonSettings (b176d13)
• Add additional Probe options to v1 model.proto (b176d13)
• Add Notebooks Runtime Software Configuration (b176d13)
• Add Notebooks Runtime Software Configuration (b176d13)
• Add REST Interceptors which support reading metadata (b176d13)
• Add REST Interceptors which support reading metadata (b176d13)
• Add RolloutOptions to DeployedModel in v1beta1 endpoint.proto, add additional Probe options in v1beta1 model.proto (b176d13)
• Add support for reading selective GAPIC generation methods from service YAML (b176d13)
• Add support for reading selective GAPIC generation methods from service YAML (b176d13)
• EvaluateDataset API v1beta1 initial release (b176d13)
• EvaluateDataset API v1beta1 initial release (b176d13)
• Use default file name if one isn't provided when uploading evaluation results to GCS. (d86d87a)

Bug Fixes

• deps: Require grpc-google-iam-v1>=0.14.0 (b176d13)
• Prediction stream raw predict url for non dedicated endpoint (b91a8aa)

Documentation

• A comment for field content in message .google.api.Page is changed (b176d13)
• A comment for field filter in message .google.cloud.aiplatform.v1.ListNotebookRuntimesRequest is changed (b176d13)
• A comment for field filter in message .google.cloud.aiplatform.v1.ListNotebookRuntimeTemplatesRequest is changed (b176d13)
• A comment for field filter in message .google.cloud.aiplatform.v1beta1.ListNotebookRuntimesRequest is changed (b176d13)
• A comment for field filter in message .google.cloud.aiplatform.v1beta1.ListNotebookRuntimeTemplatesRequest is changed (b176d13)
• A comment for message RoutingRule is changed (b176d13)

1.80.0 (2025-02-11)

Features

• Add notebook helper functions to preview eval SDK to display and visualize evaluation results in an IPython environment (1ab4344)
• Add vertex_registry_source to create_feature_view method (0abe0b7)
• Support global endpoint natively (d4cae46)
• Support Python 3.12 for reasoning engine. (1624a23)
• Upload dataset URI, metric criteria, and rating rubrics used in an evaluation to GCS. (aabb579)

Bug Fixes

• Handle the streaming of JSON delimited by newlines (acc82c5)
• Use GA generative_models path in tune_autorater to make it consistent with model parameter in Rapid Eval SDK evaluate function (ef596f5)

Documentation

• Fix minor typos in generative model readme. (d0ef994)

1.79.0 (2025-01-28)

Features

• Add machine_spec, data_persistent_disk_spec, network_spec, euc_config, shielded_vm_config to .google.cloud.aiplatform.v1beta1.NotebookRuntime (4620e6f)
• Add machine_spec, data_persistent_disk_spec, network_spec, euc_config, shielded_vm_config to message .google.cloud.aiplatform.v1.NotebookRuntime (4620e6f)
• Add per-modality token count break downs for GenAI APIs (4620e6f)
• Add per-modality token count break downs for GenAI APIs (4620e6f)
• Add speculative decoding spec to DeployedModel proto (4620e6f)
• Enable FeatureGroup IAM Methods in v1beta1 API version (4620e6f)
• Enable FeatureView Service Account in v1 API version (4620e6f)
• Enable UpdateFeatureMonitor in v1beta1 API version (4620e6f)
• Expose code execution tool API to v1 (4620e6f)
• GenAI Evaluation: Release GenAI Evaluation SDK Autorater Config/Tuning/Evaluation to vertexai.preview module. (4531d08)
• Reasoning Engine v1 GAPIC release (4620e6f)
• Remove autorater config related visibility v1beta1 (4620e6f)
• Update supported locations (50a66b7)
• Upload aggregate metrics and generative models used in an evaluation to GCS. (713ffac)

Documentation

• Deprecate is_default in message .google.cloud.aiplatform.v1.NotebookRuntimeTemplate (4620e6f)
• Deprecate is_default in message .google.cloud.aiplatform.v1beta1.NotebookRuntimeTemplate (4620e6f)
• Deprecate service_account in message .google.cloud.aiplatform.v1.NotebookRuntime (4620e6f)
• Deprecate service_account in message .google.cloud.aiplatform.v1.NotebookRuntimeTemplate (4620e6f)
• Deprecate service_account in message .google.cloud.aiplatform.v1beta1.NotebookRuntime (4620e6f)
• Deprecate service_account in message .google.cloud.aiplatform.v1beta1.NotebookRuntimeTemplate (4620e6f)

1.78.0 (2025-01-21)

Features

• Allow users to specify the job_display_name. (1d1b3f0)
• Implement method to get number of pending jobs. (ec57cf4)
• Reasoning Engine v1 GAPIC release (4eab30e)
• Update comment for LlmParser default gemini requests per minute (97be726)

Documentation

• Update the code snippet for LangGraph Agent template (9e6cc62)

1.77.0 (2025-01-15)

Features

• Add Context Cache to v1 (2148b18)
• Add retrieval_config to ToolConfig v1 (2148b18)
• Add retrieval_config to ToolConfig v1beta1 (2148b18)
• Display button to view evaluation results in an Ipython environment. (30a9403)
• Enable LangGraph Agent Templates in the Python Reasoning Engine Client (26a08c7)
• Promote network_configs field to v2 API (2148b18)

Bug Fixes

• Use typing.TYPE_CHECKING to differentiate pytype checks and runtime imports for pydantic. (0823323)

Documentation

• Fix comment typo in eval_task.py (cabe522)
• Improve description of enable_simple_view parameter (f019e18)

1.76.0 (2025-01-06)

Features

• Add a new thought field in content proto (67358fa)
• Add Model Garden deploy API (67358fa)
• Add required_replica to Vertex SDK (f5ddbb8)
• Update v1beta1 sdk to support llmparser in import file functions (1eb493b)
• Use TypeAliasType to define aliases for union types in generative models (2224c83)

Bug Fixes

• Caching - Fixed an edge case where the contents arg could be None (ede0266)
• Catch runtime errors in the import of TypeAliasType from typing_extensions (8497476)
• EvalTask evaluation should only display experiment button once for ipython environments (88d2656)

Documentation

• A comment for field labels in message .google.cloud.aiplatform.v1beta1.PublisherModel is changed (67358fa)
• Add latest_stats_count to get_feature in FeatureGroup. (15bfb54)

1.75.0 (2024-12-17)

Features

• A new field list_all_versions to ListPublisherModelsRequest (4b7799b)
• A new value NVIDIA_H100_MEGA_80GB is added to enum AcceleratorType (4b7799b)
• Add new RequiredReplicaCount field to DedicatedResources in MachineResources (4b7799b)
• Add new Status field to DeployedModel in Endpoint (4b7799b)
• Add new Status field to DeployedModel in Endpoint (4b7799b)
• Add properties feature_stats_and_anomalies to FeatureMonitorJob (92feb60)
• Add service renaming to GoSettings (4b7799b)
• Add support for opt-in debug logging (#4734) (4b7799b)
• Add workbench_runtime and kernel_name to NotebookExecutionJob (4b7799b)
• Add workbench_runtime and kernel_name to NotebookExecutionJob (4b7799b)
• Feature Store - Support returning stats in get feature (9a12097)
• GenAI - Added support for GenerationConfig.response_modalities (78898fc)
• Support stream_query in LangChain Agent Templates in the Python Reasoning Engine Client (99f613b)
• Support streaming in the Reasoning Engine Python client. (a604a2e)

Bug Fixes

• RAG - Fix the uri used for upload_file (05f27b6)
• Rag - fix upload file environment mismatch (b9fecea)

Documentation

• A comment for field encryption_spec in message .google.cloud.aiplatform.v1.NotebookExecutionJob is changed (4b7799b)
• A comment for field encryption_spec in message .google.cloud.aiplatform.v1beta1.NotebookExecutionJob is changed (4b7799b)

1.74.0 (2024-12-04)

Features

• Add browse pre-built metrics button for Ipython environments when listing example metrics for Gen AI Evaluation (58ba55e)
• Add compatibility for RagRetrievalConfig in rag_store and rag_retrieval (c52e3e4)
• Add deprecation warnings for use of similarity_top_k, vector_search_alpha, and vector_distance_threshold in retrieval_query, use RagRetrievalConfig instead. (c52e3e4)
• Add FeatureMonitorJob Create,Get,List in Vertex AI SDK (03eb735)
• Add List FeatureMonitor function to FeatureGroup in Vertex AI SDK (21bc83b)
• Add sdk support to inference timeout on cloud-based endpoints (dedicated or PSC). (f917269)
• Add support for Document AI Layout Parser as a RAG import option (565c800)
• Add support for ranking field in rag_retrieval_config for rag_store creation. (6faa1d0)
• Add vector_similarity_threshold support within RagRetrievalConfig in rag_store and rag_retrieval GA and preview versions (9402b3d)
• Add Vertex RAG service proto to v1 (a56e4dd)
• Adding Vertex AI Search Config for RAG corpuses to SDK (d3d69d6)
• Fix file type mismatch in uploading eval results to GCS, supported types: CSV, JSON. (905c766)
• GenAI - Grounding - Released VertexAiSearch and Retrieval to GA (0537fec)
• GenAI - Release the Prompt Management feature to Public Preview (7432c2c)
• GenAI - Support FunctionDeclaration.response schema (4288fec)
• GenAI - Tuning - Added support for BYOSA (7cbda03)
• Refactor rag_store and rag_retrieval to use v1 protos (dfe6d6c)
• Support multi-methods in SDK. (f02692d)
• Support NFS for Ray cluster creation (1ca9a05)
• Support RagFileTransformationConfig in upload_file function in V1 sdk (88ac48c)
• Update v1 sdk to use new RagCorpus, RagVectorDbConfig, & RagEmbeddingModelConfig proto (47a5a6d)
• Update v1 sdk to use new RagFileTransformationConfig proto (c23c62d)
• Update v1beta1 sdk for RagFileTransformationConfig and Ranking protos (ffe3230)
• Update v1beta1 sdk for RagVectorDbConfig & RagCorpus protos. Backward compatible with older fields. (216a30f)

Bug Fixes

• get_default_run method in Experiment class (9388fc9)
• Add MatchingEngineIndexConfig enums to proto value converters (e6d3df8)
• RAG Fix v1 rag_store compatibility with generative_models Tool by changing back to v1beta1 (e220312)
• Remove redundant progress bar update commands within runnable inference (598c931)
• Update upperbounds on pydantic version to < 2.10 to mitigate version comparison checks (c13b6a8)

Documentation

• A comment for field api_key_config in message .google.cloud.aiplatform.v1beta1.JiraSource is changed (d7dff72)
• A comment for field class_method in message .google.cloud.aiplatform.v1beta1.StreamQueryReasoningEngineRequest is changed (from steam_query to stream_query) (b7f9492)
• Updated example usage in docstring for rag_retrieval preview and GA (a1f8bc2)
• Updated example usage in docstring for rag_store preview and GA (a1f8bc2)

1.73.0 (2024-11-19)

Features

• Add a nfs_mounts to RaySpec in PersistentResource API (6a22bef)
• Add a v1 UpdateEndpointLongRunning API (6a22bef)
• Add BatchCreateFeatures rpc to feature_registry_service.proto (68fc5f2)
• Add BYOSA field to tuning_job (68fc5f2)
• Add BYOSA field to tuning_job (68fc5f2)
• Add COMET and MetricX to the evaluation SDK (4135810)
• Add Create FeatureMonitor function to FeatureGroup in Vertex AI SDK (285ec2c)
• Add CustomEnvironmentSpec to NotebookExecutionJob (6a22bef)
• Add CustomEnvironmentSpec to NotebookExecutionJob (6a22bef)
• Add default_runtime in Vertex Pipeline SDK preview. (44587ec)
• Add fast_tryout_enabled to FasterDeploymentConfig v1 proto (68fc5f2)
• Add FeatureMonitor to FeatureGroup in Vertex AI SDK (f2233ce)
• Add PSC automation support to matching engine index endpoint deploy_index(), find_neighbors(), match(), and read_index_datapoints(). (3ab39a4)
• Add vertex_rag_source to create_feature_view method (ca61c5a)
• Adding fast_tryout_enabled option to Vertex SDK (fde1b96)
• Allow setting Vertex Model Garden source model name during model upload (3af9cc8)
• Allow user control which class methods to export via register_operations. The class methods spec will be changed according to user's register_operations. (74077b5)
• COMET added to evaluation service proto (68fc5f2)
• Expose system_labels field to model deployment APIs in Vertex public preview SDK (13cede4)
• Expose system_labels field to model deployment APIs in Vertex Python SDK (75655af)
• GenAI - Grounding - Added grounding dynamic_retrieval config to Vertex SDK (c39334a)
• GenAI Evaluation: Release GenAI Evaluation SDK Agent Evaluation features to vertexai.preview module. (41cd5a8)
• MetricX added to evaluation service proto (68fc5f2)
• Trajectory eval metrics added to evaluation service proto (6a22bef)
• Vision Models - Add support for Imagen 3 Capabilities to Vertex SDK (9a30c31)

Bug Fixes

• GenAI - Fixed GAPIC-renamed keys (keys with trailing underscore) in structures returned by the to_dict methods. (9d00424)
• Implementation of proto conversion in reasoning engine utils when message is not specified (99fafe9)
• Remove check on serving_container_image_uri when artifact_uri and local_model is given (ccd89b4)

Documentation

• Automatic Function calling comment update (91f85ac)
• Clarity and typo fixes for documentation (6a22bef)
• Fix example rpc naming (6a22bef)
• GenAI - Grounding - Added sample for grounding with Google Search to the Vertex GenAI SDK README. (4bf9816)

1.72.0 (2024-11-12)

Features

• Add AdvancedCompleteQuery API (169dd44)
• Add BatchCreateFeatures rpc to feature_registry_service.proto (acf3113)
• Add BillingEstimation in data store (169dd44)
• Add code execution tool API (169dd44)
• Add fast_tryout_enabled to FasterDeploymentConfig message in aiplatform v1beta1 endpoint.proto (169dd44)
• Add Feature Monitoring API to Feature Store (acf3113)
• Add field protobuf_pythonic_types_enabled to message ExperimentalFeatures (acf3113)
• Add GroundedGenerationService API (169dd44)
• Add lite search API to allow public website search with API key (169dd44)
• Add new PscInterfaceConfig field to custom_job.proto (169dd44)
• Add one_box_page_size on search (169dd44)
• Add Sitemap APIs to preview channel (169dd44)
• Add StopNotebookRuntime method (169dd44)
• Add StopNotebookRuntime method (169dd44)
• Add system labels field to model garden deployments (acf3113)
• Add UpdateEndpointLongRunning API in v1beta1 version (169dd44)
• Adding fast_tryout_enabled option to Vertex public preview SDK (98288b8)
• Increase the upperbounds on langchain dependencies to support v0.3+ (1fca9c0)
• Support advanced boost search (169dd44)
• Support Google Workspace search (169dd44)
• Support natural language understanding search (169dd44)
• Support query regex in control match rules (169dd44)
• Support search personalization to preview channel (169dd44)

Bug Fixes

• Add timeout to prediction rawPredict/streamRawPredict (b7de16a)
• Convert float values with no decimals to integers in FunctionCall. (a1857ed)
• Deepcopy error from baseline_model in pairwiseMetric (ccc5c85)

Documentation

• A comment for field feature_group_id in message .google.cloud.aiplatform.v1.CreateFeatureGroupRequest is changed (acf3113)
• A comment for field unit in message .google.api.QuotaLimit is changed (acf3113)
• A comment for message BatchCreateFeaturesRequest is modified to call out BatchCreateFeatures (acf3113)
• Deprecate asynchronous mode in answer generation (169dd44)
• Deprecate extractive_answers in answer generation (169dd44)
• Keep the API doc up-to-date with recent changes (169dd44)
• samples: Fixed Vertex AI Vector Search Create Index index_update_method (7dff586)
• Update documentation (169dd44)
• Update feature creation message commentary (acf3113)

1.71.1 (2024-10-31)

Bug Fixes

• Audio_timestamp is supported only for some of the models (df7269e)
• Ignore AttributeError exception when importing google.auth.aio (832fe60)
• System test case media input file non existent (c0718e1)

1.71.0 (2024-10-29)

Features

• Add text field for Grounding metadata support chunk output (8a65b1d)
• Add audio_timestamp to GenerationConfig (8a65b1d)
• Add private async REST support for transport override (c0b31e2)
• Add support for self-signed JWT for queries on private endpoints (5025d03)
• Add support for task type (CODE_RETRIEVAL_QUERY) through get_embeddings. (7246497)
• From vertexai.batch_prediction import BatchPredictionJob (fe53922)
• GenAI - add labels (92c13dd)
• GenAI - Added audio_timestamp to GenerationConfig. (91c2120)
• GenAI - Added Anthropic models support in GenAI batch prediction (0866009)
• GenAI - Tuning - Added support for tuned model rebasing. Added rebase_tuned_model to vertexai.preview.tuning.sft. (2cef97f)
• Introduce DefaultRuntime to PipelineJob (8a65b1d)
• Release API key support for GenerateContent to Public Preview (a4d4e46)
• Support customizing bring-your-own-response eval use case to use any columns (3e7bf81)
• Support PSC-I ingress in Ray Client (da76253)
• Support tuning new text & code embedding model in LLM SDK. (4268f28)
• Update Experiment run names to be compatible with One Platform API (c4b9ec2)
• Vision Models - onboard Image Segmentation. (ae63a43)

Bug Fixes

• Add deprecation warning to Ray version 2.9.3 (0ce106b)

Documentation

• A comment for field partner_model_tuning_spec in message .google.cloud.aiplatform.v1beta1.TuningJob is changed (#4538) (914c63c)
• Comment update (b04196b)
• Update the documentation for the tabular_dataset class (82bb938)

1.70.0 (2024-10-08)

Features

• Add a dynamic retrieval API (44df243)
• Add enable_secure_private_service_connect in service attachment (44df243)
• Add new PscInterfaceConfig field to pipeline_job.proto (44df243)
• Add psc_automation_configs to DeployIndex v1 (44df243)
• Add TunedModelRef and RebaseTunedModel Api for Vertex GenAiTuningService (44df243)
• Add TunedModelRef and RebaseTunedModel Api for Vertex GenAiTuningService (44df243)
• Add update_corpus method for vertex rag (09353cf)
• Automatically end Experiment runs when Tensorboard CustomJob is complete (30cf221)
• Vision Models - Add new safety filter levels to Vertex AI Image Generation API. (b1d5007)

Bug Fixes

• Annotate PipelineJob and PipelineTaskRerunConfig fields as optional (44df243)
• Update the docstring for LangchainAgent (f7fe2b0)

Documentation

• Add sample to retrieve experiment backing tensorboard resource name (138dc1a)
• GenAI - update comments in GenerationConfig property (c670eeb)
• Limit comment SupervisedTuningSpec for 1p tuning (44df243)

1.69.0 (2024-10-01)

Features

• Add rerun method to pipeline job preview client. (29dec74)

Bug Fixes

• GenAI - Fixed from_dict methods (3090812)

1.68.0 (2024-09-24)

Features

• A new field response_logprbs is added to message .google.cloud.aiplatform.v1.GenerationConfig (#4410) (470933f)
• Add support for partial failures sink in import rag files. (8070411)
• Add support for SharePoint as a ImportRagFiles source. (f89df1f)
• Adding Vertex Vector Search Vector DB option for RAG corpuses to SDK (d4193f2)
• Batch_predict method generally-available at TextEmbeddingModel. (73c0dae)
• GenAI - Add model routing config to sdk (c0626fe)
• GenAI - Add support for logprobs and response_logprobs. (7acf0f7)

Bug Fixes

• Fix rag corpus creation error (d25edce)
• Fix typo in eval_task docstring (86fc215)
• Fix typos in evaluation example metric prompt templates. (5f4d586)
• GenAI - Fixed GenerativeModel.compute_tokens for v1 API (4637b4c)
• Tensorboard - Fix error in tensorboard batch upload of nested dirs (86be328)

Documentation

• Update Gemini docs (c561aa6)
• Update Gemini docs (2b84142)

1.67.1 (2024-09-18)

Bug Fixes

• Fix rag corpus creation error (6083b93)

1.67.0 (2024-09-17)

Features

• Add support for partial failures sink in import rag files. (07e471e)
• Adding Feature Store Vector DB option for RAG corpuses to SDK (cfc3421)
• Adding Pinecone Vector DB option for RAG corpuses to SDK (f78b953)
• Adding Vertex Vector Search Vector DB option for RAG corpuses to SDK (f882657)
• Allow customizing pipeline caching options for model evaluation jobs. (73490b2)
• GenAI - Switched the GA version of the generative_models classes to use the v1 service APIs instead of v1beta1 (66d84af)

Bug Fixes

• GenAI - Fixed GenerativeModel.compute_tokens for v1 API (0de2987)
• Tensorboard - Fix error in tensorboard batch upload of nested dirs (ab157c8)

Documentation

• Manually add summary overview page. (0bc608a)

1.66.0 (2024-09-11)

Features

• Add max_wait_duration option to custom jobs. (ee65917)
• Add Ray 2.33 support to SDK Client Builder, remove deprecated protocol_version from ray client context. (708a67b)
• Add support for version 2.33 for RoV Bigquery read/write, remove dead code from version 2.4 (a4b6c60)
• Update Ray system tests to be compatible with new RoV 2.33 changes (8c7bf27)
• Update setup.py for including Ray v2.33, restrict RoV prediction to 2.9.3 for now (71c6f3c)

Bug Fixes

• Identify nested Vertex Tensorboard profile runs for uploading when standard event data is not present (0a08027)
• Move region tag to include imports (6d1f7fd)
• Move region tag to include imports (#4357) (6d1f7fd)
• Rollback change to tensorboard uploader causing increased latency (879dbcd)

Documentation

• Update SDK Job Submission with Ray v2.33 updated comments (7fda11f)

1.65.0 (2024-09-04)

⚠ BREAKING CHANGES

• Tokenization - Deprecated ComputeTokenResult.token_info_list in favor of ComputeTokenResult.tokens_info

Features

• Add support for system instruction and tools in tokenization. (72fcc06)
• Add vector search alpha to rag retrieval for hybrid search ranking (6624ebe)
• Adding Weaviate Vector DB option for RAG corpuses to SDK (9b28202)
• GenAI - Added system_instruction and tools support to GenerativeModel.count_tokens (50fca69)
• GenAI - Added Llama3 support in GenAI batch prediction (6166152)
• PrivateEndpoint.stream_raw_predict (197f333)
• Support reserved_ip_ranges for VPC network in Ray on Vertex cluster (36a56b9)
• Tokenization - Deprecated ComputeTokenResult.token_info_list in favor of ComputeTokenResult.tokens_info (efbcb54)

Bug Fixes

• Tensorboard - Fixed bug in tensorboard uploader where profile logs are not uploaded from nested run directories. (37627de)
• Tokenizers - Fixed Tokenizer.compute_tokens (c29fa5d)

1.64.0 (2024-08-27)

Features

• Add support for Prediction dedicated endpoint. predict/rawPredict/streamRawPredict can use dedicated DNS to access the dedicated endpoint. (3d68777)
• Add unit tests for Gen AI evaluation module (94289b5)
• GenAI - Added the model Distillation feature (private preview) (a0d4ff2)
• Grounding - Allow initialization of grounding.VertexAISearch with full resource name or data store ID, project ID, and location. (f334321)
• Make Rouge class available in base level init (aed82a1)
• Read for online store w/private service connect (7af80c6)
• Support autoscaling in Ray on Vertex (961da42)

Bug Fixes

• Fix error in tensorboard uploader thrown when time_series_id is None (d59a052)
• Fix typo in prompt templates: (c8fa7a8)
• Update generative models tests to be parameterized on environment variable name (be4cbea)

Documentation

• samples: Adding code sample for vector search create streaming index (71464e7)

1.63.0 (2024-08-20)

Features

• A new field satisfies_pzs is added to message .google.cloud.aiplatform.v1.BatchPredictionJob (#4192) (6919037)
• Add advanced PDF parsing option for RAG file import (6e1dc06)
• Add multithreading for custom metric computation. (2c93fc1)
• Add progress bar for generating inference. (b78714f)
• Add progress bar to custom metrics. (3974aec)
• Add Prompt class support for configs and Prompt.generate_content wrapper (7f1e031)
• GenAI - Added seed parameter to the GenerationConfig class (9f1e073)
• GenAI - Added the Candidate.avg_logprobs property (de80695)
• GenAI - Released the Prompt feature to Public Preview (64eeab8)
• GenAI Evaluation: Add generic model-based PointwiseMetric and PairwiseMetric classes that allow customizing metric prompt templates. Add PointwiseMetricPromptTemplate, PairwiseMetricPromptTemplate classes to help formulate and customize metric prompt templates. Add metric_column_mapping parameter to EvalTask for metric prompt template input variable name mapping. (fd38b49)
• GenAI Evaluation: Open source model-based metric prompt template examples for Gemini 1.5 Pro autorater. Add MetricPromptTemplateExamples class to help retrieve model-based metric prompt templates. (fd38b49)
• GenAI Evaluation: Release GenAI Evaluation SDK GA features to vertexai.preview module. (fd38b49)
• Publish GenAI Evaluation SDK GA features to vertexai.evaluation module. Switch GenAI Evaluation Service client to v1 version. (45e4251)

Bug Fixes

• Add support of display_name to create_cached_content in python SDK (ecc2d54)
• Always upload the pickled object and dependencies tarball when creating ReasoningEngine (34ef5a3)
• Remove grouding attribution (f6ece65)

Documentation

• Update Prompt docstring for batch prompting (e96b6e6)

1.62.0 (2024-08-13)

Features

• Add metadata to evaluation result. (375095e)
• Add Prompt class for multimodal prompt templating (1bdc235)
• Add support for query method in Vertex AI Extension SDK (0008735)
• Add support for reservation affinity in custom training jobs. (802609b)
• Add support for strategy in custom training jobs. (a076191)
• Adding spot, reservation_affinity to Vertex SDK (3e785bd)
• Support api keys in initializer and create_client (7404f67)
• Support creating optimized online store with private service connect (659ba3f)
• Support disable Cloud logging in Ray on Vertex (accaa97)
• Support PSC-Interface in Ray on Vertex (accaa97)

Bug Fixes

• Added credentials, project, and location on PipelineJobSchedule init (281c171)
• Avoid breakage of langchain from orjson 3.10.7 (c990f73)
• Deprecate disable_attribution in GoogleSearchRetrieval. (c68d559)

Documentation

• Update the docstring for compute_tokens method. (849e8d4)

1.61.0 (2024-08-05)

Features

• Add a warning message for scheduled deprecation of Coherence metric class (7f238fb)
• Add deprecation messages for all model-based metric classes (71c0fd3)
• Add support for task type (CODE_RETRIEVAL_QUERY) through get_embeddings. (f2ce1e4)
• Add system_instruction to LangchainAgent template. (c71c3dd)
• Adding Slack and Jira data connector for RAG to SDK (d92e7c9)
• Allow protobuf 5.x (ce9cd5d)
• LVM - Release ImageGenerationModel to GA (718c199)
• Support "update" for reasoning engine. (b73ef3e)
• Update Rapid Evaluation Service QPS. Add a customizable evaluation service QPS parameter. (9ee9289)

Documentation

• Change init sample to use vertexai (829e0f6)
• Make small fixes to file import documentation (f7d65c3)

1.60.0 (2024-07-24)

Features

• Add preflight validations to PipelineJob submit and run methods. (c5a3535)
• Add support for langchain v0.2+ package versions in default installation (259b638)
• GenAI - Added tokenization support via GenerativeModel.compute_tokens (cfe0cc6)
• GenAI - ContextCaching - allow from_cached_content to take the cached_content resource name (8f53902)
• Make count_tokens generally-available at TextEmbeddingModel. (efb8413)

Bug Fixes

• Avoid throw error when Part.text is empty in modality content checks (bbd4a49)
• Correct logit_bias type annotation to accept keys as strings (2676d25)
• Create FV embedding dimensions sample - dimensions should be an int (2aa221e)
• Fix the sync option for Model Monitor job creation (22151e2)
• Include DeploymentResourcePool class in aiplatform top-level sdk module (ecc4f09)
• Overriding the current TracerProvider when enabling tracing (1476c10)
• Pass the project ID from vertexai.init to CloudTraceSpanExporter when enable_tracing=True for LangchainAgent (3ec043e)

Documentation

• GenAI - Update README.md for Vertex Generative AI SDK for Python to add subsections to the right nav. (42af742)

1.59.0 (2024-07-09)

Features

• Add model and contents fields to ComputeTokensRequest v1 (f6e7b9c)
• Add model and contents fields to ComputeTokensRequest v1beta1 (f6e7b9c)
• Add role field to TokensInfo v1 (f6e7b9c)
• Add role field to TokensInfo v1beta1 (f6e7b9c)
• GenAI - Tuning - Released the Supervised Fine Tuning feature o GA (ae47639)

Bug Fixes

• deps: Require proto-plus 1.22.3 (4131e65)
• Offline store - set application name + remove session param (7395665)

1.58.0 (2024-07-03)

Features

• Add deploy_metadata to PublisherModel.Deploy v1 (71e41c8)
• Add deploy_metadata to PublisherModel.Deploy v1beta1 (b5c3cdd)
• Add display tuning job button for Ipython environments when getting an existing job (872b455)
• Add private_service_connect_config and service_attachment fields to DedicatedServingEndpoint v1 (71e41c8)
• Add satisfies_pzs and satisfies_pzi fields to Model v1 (71e41c8)
• Add satisfies_pzs and satisfies_pzi fields to Model v1beta1 (b5c3cdd)
• Add satisfies_pzs and satisfies_pzi fields to Tensorboard v1 (71e41c8)
• Add satisfies_pzs and satisfies_pzi fields to Tensorboard v1beta1 (b5c3cdd)
• Add UpdateDeploymentResourcePool method to DeploymentResourcePoolService v1 (71e41c8)
• Add UpdateDeploymentResourcePool method to DeploymentResourcePoolService v1beta1 (b5c3cdd)
• Add use_effective_order field to BleuSpec v1beta1 (b5c3cdd)
• GenAI - Evaluation - Add a progress bar for evaluation service requests (bbffb0d)
• GenAI - Evaluation - Implement rate limiter and refactor parallelization for online evaluation service requests (bbffb0d)
• GenAI - Evaluation - Return partial evaluation results with error logging (bbffb0d)
• Migrate DeploymentResourcePool and associated functionality to V1 namespace for GA launch of model co-hosting. (1474d98)

Bug Fixes

• IndexConfig - use TreeAhConfig as default algorithm_config. (341d287)
• LVM - Update Video.load_from_file() to support storage.googleapis.com links (b63f960)

Documentation

• Update comments of AutoscalingSpec v1 (71e41c8)
• Update comments of AutoscalingSpec v1beta1 (b5c3cdd)
• Update import paths for Gemini README (46b3042)