v1.75.0

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)

v1.74.0

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)

v1.73.0

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)

v1.72.0

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)

v1.71.1

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)

v1.71.0

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)

v1.70.0

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)

v1.69.0

1.69.0 (2024-10-01)

Features

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

Bug Fixes

• GenAI - Fixed from_dict methods (3090812)

v1.68.0

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)

v1.67.1

1.67.1 (2024-09-18)

Bug Fixes

• Fix rag corpus creation error (6083b93)