v1.58.0

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)

v1.57.0

1.57.0 (2024-06-26)

Features

• Add _ModelBasedMetric base class to vertexai.preview.evaluation.metrics and allow metric spec customization (536f1d5)
• Add _AutomaticMetric type and support customizing metric spec for automatic pointwise metrics. Add Rouge metric to vertexai.preview.evaluation.metrics (f6b6dee)
• Add 12 model-based pointwise metric classes to vertexai.preview.evaluation.metrics (4742a87)
• Add display tuning job button for Ipython environments when starting a new job (b1e9a6c)
• Add encryption_spec to TuningJob (5a6ce78)
• Add enum value MALFORMED_FUNCTION_CALL to .google.cloud.aiplatform.v1beta1.content.Candidate.FinishReason (5a6ce78)
• Add fields grounding_chunks and grounding_supports to GroundingMetadata (5a6ce78)
• Add MALFORMED_FUNCTION_CALL to FinishReason (5a6ce78)
• Add preflight_validations to PipelineJob (5a6ce78)
• Add streamRawPredict rpc to prediction service (5a6ce78)
• Add support for hybrid queries for private endpoint in Matching Engine Index Endpoint. (ce65eab)
• Add text field in Segment (5a6ce78)
• Change the icon for the model evaluation link to a lightbulb for ipython environments (7dad7f0)
• Endpoint.direct_predict (9351e1a)
• Endpoint.direct_predict_async (9351e1a)
• Endpoint.direct_raw_predict (9351e1a)
• Endpoint.direct_raw_predict_async (9351e1a)
• Endpoint.stream_direct_predict (9351e1a)
• Endpoint.stream_direct_raw_predict (9351e1a)
• Endpoint.stream_raw_predict (9351e1a)
• Expose new text embedding tuning parameters in GA namespace. (249a5fa)
• GenAI - Batch Prediction - Added support for tuned GenAI models (a90ee8d)
• Mark default profile run as complete when calling end_upload_tb_log (6397f30)
• Sample code for Vertex AI Feature Store (2c28b4e)
• Sample code for Vertex AI Feature Store (2fbf5a5)
• Tokenization - Added count_tokens support for local tokenization (a8a4c30)
• Update rich html Ray on Vertex Client Context widget (380c9d9)

Bug Fixes

• FeatureGroup.create() - remove unused entity id column param (c46f3e9)
• Fix bug where retry_timeout does not work with evaluation with experiments (a31ac4d)
• Use default run_name in Tensorboard uploader for direct directory upload. (78a92a1)

Documentation

• A comment for field distibution in message .google.cloud.aiplatform.v1beta1.model_monitoring_stats.ModelMonitoringStatsDataPoint is changed. (5a6ce78)
• A comment for field name in message .google.cloud.aiplatform.v1beta1.cached_content.CachedContent is changed (5a6ce78)
• A comment for field source in message .google.cloud.aiplatform.v1beta1.tool.Retrieval is added. (5a6ce78)
• Update the documentation for the time_series_dataset and video_dataset classes (2cf4cb9)

v1.56.0

1.56.0 (2024-06-18)

Features

• Add retry_timeout to EvalTask in vertexai.preview.evaluation (4d9ee9d)
• Add hybrid query example to vector search sample. (510da5e)
• Add metric classes for 2 pairwise metrics for rapid evaluation SDK. (831c8e4)
• Add pipeline_job_name to allow PipelineJob.get(pipeline_job_name) (32e3b22)
• Add sample code show how to create an optimized private online store in Vertex AI Feature Store. (e352175)
• GenAI - Context Caching - add get() classmethod and refresh() instance method (6be874a)
• GenAI - Context Caching - also print model_name and expire_time. (d548c11)
• GenAI - Tuning - Added support for CMEK (eb651bc)

Bug Fixes

• Do not reset aiplatform.Experiment or aiplatform.ExperimentRun unnecessarily when running tensorboard uploader. (28a091a)

Documentation

• Update the documentation for the time_series_dataset and video_dataset classes (d5dc7b5)

v1.55.0

1.55.0 (2024-06-12)

Features

• view model evaluations when AustoSxS pipeline completes (17c59c4c2)
• Add support for user-configurable 1P embedding models and quota for RAG (8b3beb666)
• Add Webpage Browser Extension to Vertex AI Extension SDK (c222f4bdb)
• Add enable_tracing to LangchainAgent. (cad035cb3)
• Implement multithreaded batch inference in Rapid Evaluation SDK for performance improvement (3c6d1732b)

Bug Fixes

• support VPC and BYOSA case in Ray on Vertex JobSubmissionClient using cluster resource name (662d039c9)
• Include tensorboard profiler requirements when installing google-cloud-aiplatform[tensorboard] (4f1b5593b)
• fix numerical NaN experiment run logging error in EvalTask. (641faec0b)
• Generate uuid run_name when run_name_prefix is not specified. (4e2d87f9a)

Documentation

• Update the documentation for the image_dataset class (583cb9313)
• Include imports in experiment_tracking samples directly in cloud.google.com snippets. (3ffb6cba7)

v1.54.1

1.54.1 (2024-06-07)

Bug Fixes

• _append_tool_name list index out of range (#3914) (323c2f5)

v1.54.0

1.54.0 (2024-06-06)

BREAKING CHANGES

• Remove Vertex SDK data science package (ec4ec8f)

Features

• Add display experiment run button for Ipython environments (ba65828)
• Add hybrid search for public find_neighbors() call. (9d35617)
• Enable Ray Job submission without VPC peering (37875b5)
• GenAI - Allowed callable functions to return values directly in Automatic Function Calling (768af67)
• GenAI - Release ToolConfig to GA (bc8b14a)
• Sample code for Vertex AI Feature Store (6c14e8b)
• Support VertexTool in langchain template. (28a3c56)

Bug Fixes

• Allow non-lro delete method (c23c0ad)
• Deep copy dataset before passing it to evaluation (019b610)
• Ensure model starts with publishers/ when users provide resource path from models/ (d689331)
• Fix failed unit tests due to google-cloud-storage upgrade. (945b9e4)
• Generalize RAG files import from Google Drive (88c6a6a)
• Set upper bound of setuptools to unbreak public Colab for using vertex_ray namespace (6cc45bb)

v1.53.0

1.53.0 (2024-05-30)

Features

• Add a cloneable protocol for Reasoning Engine. (8960a80)
• Add labels parameter to the supervised tuning train method (f7c5567)
• Added reboot command for PersistentResource (7785f8c)
• Added the new GenerationConfig.response_schema field (#3772) (5436d88)
• Enable Tensorboard profile plugin in all regions by default. (8a4a41a)
• GenAI - Added the response_schema parameter to the GenerationConfig class (b5e2c02)
• LLM - Added the seed parameter to the TextGenerationModel's predict methods (cb2f4aa)

Bug Fixes

• Create run_name when run_name_prefix is not specified for Tensorboard uploader. (ac17d87)
• GenAI - Tuning - Supervised - Fix adapter_size parameter handling to match enum values. (1cc22c3)
• Model Monitor console uri. (71fbc81)

v1.52.0

1.52.0 (2024-05-21)

Features

• Add FeatureGroup delete (f9011e0)
• Add support for ToolConfig in the LangChain template (9bda328)
• Create Vertex Experiment when uploading Tensorboard logs (339f8b6)
• GenAI - Add BatchPredictionJob for GenAI models (df4a4f2)
• GenAI - Add cancel, delete, list methods in BatchPredictionJob (7ff8071)
• GenAI - Added the BatchPredictionJob.submit method (4d091c6)
• Private Endpoints - Added private service connect support to prediction endpoint. (6bdcfb3)

Bug Fixes

• Add validation for evaluation dataset fields, update logging info for eval api request count (d6ef500)
• Fix feature attribution drift visualization for model monitoring SDK (710f33d)
• Fix the default value of response_column_name in EvalTask.evaluate() (98f9b35)
• Update get_experiment_df to pass Experiment and allow empty metrics. (de5d0f3)

Documentation

• Add Vertex Model Monitoring V2 SDK documentation (b47e6ff)
• Update docstrings for rapid evaluation library. (d6d371d)

v1.51.0

1.51.0 (2024-05-10)

Features

• Add FeatureGroup create function (3938107)
• Add FeatureGroup init/get (e47d436)
• Add support for BaseModels in LangChain templates (5eb885e)
• Added the vision_models.Image._mime_type property to make vision_models.Image compatible with generative_models.Image (6557d88)
• AutoSxS Pairwise Metric in Rapid Evaluation SDK (b0c5eda)
• GenAI - Grounding - Released Google Web Search retriever to GA (32b030a)
• GenAI - Tuning - Supervised - Added support for the adapter_size parameter (88188d2)
• LLM - Made the tuning location parameters truly optional (bae8429)
• LLM - Support tuning of new text embedding models by migrating to the new v1.1.3 pipeline. (7fea754)
• LLM - Text embedding - Added the output_dimensionality and learning_rate_multiplier parameters to text embedding tuning (Preview only) (cc8bc96)
• LLM - Text Embedding - Added validation for text embedding tuning parameters. (5a300c1)
• Release Ray on Vertex SDK to GA (f7c5132)
• Support custom service account for Ray cluster creation and Ray Client connection (e0c6227)
• Support vector_distance_threshold filtering and file-based retrieval for RAG (cd85d8f)

Bug Fixes

• A bug in the evaluation library where the job crashes if only custom metrics are specified. (c528b6f)
• Add DeprecationWarning to vertexai.preview predictive models SDK (3c3727b)
• Add MAX_TOKENS to the list of successful finish reasons for Rapid Evaluation SDK (195c77e)
• AttributeError for TorchModelSerializer.deserialize in torch >=2.3.0 (20b1866)
• GenAI - Fixed handling of multiple tools in AutomaticFunctionCallingResponder (58e6ac9)
• Remove InternalServerError and Unknown evaluation service error from retriable exceptions (12c147b)
• Upload the reference model in model registry (510c833)

v1.50.0

1.50.0 (2024-05-02)

Features

• Add Candidate.grounding_metadata property (b22a8b8)
• Add option to not include time_series_metrics in get_experiment_df call. This will improve execution time for Experiments with large number of runs. (78a95c5)
• Add tune_model and deploy_tuned_model for TextEmbeddingModel. (42f5d6f)
• Automatically populate parents for full resource name in Vertex RAG SDK (26657ff)
• Deploy a tuned text embedding model -- it doesn't matter, if it's tuned using Node.js, or curl. (8ca9cdf)
• Make get_embeddings work both for foundational & tuned models. (b8b589c)
• Python SDK for Vertex Model Monitoring V2. (021d59f)
• Support public endpoint for Ray Client (57a5f78)

Bug Fixes

• Add deprecation warnings when using Ray v2.4 (3a36784)
• Append allowed_plugins in tb-gcp-uploader to default allowed plugins (aab9c3e)
• LLM - Added missing parameters to the no-op _TunableTextEmbeddingModelMixin.get_tuned_model method (eb05ac4)
• LVM - Fixed the typo in the VisionModel aspect ratio type annotation (2d19137)
• Move torch import (e6d34df)
• Ray - Fixed exception when using Ray 2.4 (2661f52)