v1.32.0

1.32.0 (2023-09-05)

Features

• LLM - Added stop_sequences parameter to streaming methods and CodeChatModel (d62bb1b)
• LLM - Improved the handling of temperature and top_p in streaming (6566529)
• Support bigframes sharded parquet ingestion at remote deserialization (Tensorflow) (a8f85ec)
• Release Vertex SDK Preview (c60b9ca)
• Allow setting default service account (d11b8e6)

Bug Fixes

• Fix feature update since no LRO is created (468e6e7)
• LLM - CodeGenerationModel now supports safety attributes (c2c8a5e)
• LLM - Fixed batch prediction on tuned models (2a08535)
• LLM - Fixed the handling of the TextEmbeddingInput.task_type parameter. (2e3090b)
• Make statistics Optional for TextEmbedding. (7eaa1d4)

v1.31.1

1.31.1 (2023-08-24)

• fix: LLM - De-hardcoded the max_output_tokens default value for the CodeGenerationModel (f5a20eb)

v1.31.0

1.31.0 (2023-08-21)

Features

• Add disable_retries option to custom jobs. (db518b0)
• LLM - Added support for stop_sequences in inference (6f7ea84)
• LLM - Exposed the TextGenerationResponse.raw_prediction_response (f8f2b9c)
• LLM - Made tuning asynchronous when tuning becomes GA (226ab8b)
• LLM - release model evaluation for TextGenerationModel to public preview (8df5185)
• LLM - Released TextGenerationModel tuning to GA (62ff30d)
• LLM - Support streaming prediction for chat models (ce60cf7)
• LLM - Support streaming prediction for code chat models (0359f1d)
• LLM - Support streaming prediction for code generation models (3a8348b)
• LLM - Support streaming prediction for text generation models (fb527f3)
• LLM - TextEmbeddingModel - Added support for structural inputs (TextEmbeddingInput), auto_truncate parameter and result statistics (cbf9b6e)
• LVM - Added support for Image Generation models (b3729c1)
• LVM - Released ImageCaptioningModel to GA (7575046)
• LVM - Released ImageQnAModel to GA (fd5cb02)
• LVM - Released MultiModalEmbeddingModel to GA (e99f366)
• LVM - Removed the width and height parameters from ImageGenerationModel.generate_images since the service has dropped support for image sizes and aspect ratios (52897e6)
• Scheduled pipelines client GA. (62b8b23)

Documentation

• Generate documentation for tune_model and related class (705e1ea)
• LVM - Added autogenerated documentation for visual models (18e8bb2)

v1.30.1

1.30.1 (2023-08-11)

Features

• LLM - Added tuning support for chat-bison models (3a97c52)
• LLM - Added tuning support for codechat-bison models (af6e455)

Bug Fixes

• LLM - Fixed the TextGenerationModel.predict parameters (f3b25ab)

Miscellaneous Chores

• Release 1.30.1 (d1c79c4)

v1.30.0

1.30.0 (2023-08-10)

Features

• Add model.evaluate() method to Model class (51df86e)
• Add support for providing only text to MultiModalEmbeddingModel.get_embeddings() (38ec40a)

Bug Fixes

• LLM - Fixed filter in list_tuned_model_names (57806fb)

v1.29.0

1.29.0 (2023-08-02)

Features

• Add preview CustomJob which can be run on persistent resource (56906b0)
• LLM - Support for Batch Prediction for the textembedding models (preview) (a368538)
• LLM - Support tuning for the code-bison model (preview) (e4b23a2)
• LVM - Large Vision Models SDK (preview release). Support for image captioning and image QnA (imagetext model) and multi modal embedding (multimodelembedding model) (preview) (9bbf1ea)

Bug Fixes

• LLM - Fixed get_tuned_model for the future models that are not text-bison (1adf72b)

Documentation

• Fix auto-generated pydoc for language_models (7d72bd1)
• LLM - Made it possible to provide message history to CodeChatModel when starting chat. (cf46145)

v1.28.1

1.28.1 (2023-07-18)

Features

• LLM - Released the BatchPrediction to GA for TextGenerationModel (701c3a2)
• LLM - Support tuning in the "us-central1" location (4aa7745)

Bug Fixes

• Fix artifact registry link not showing in ui when creating schedules with SDK. (203cb47)
• Fixed the installation error caused by a PyYAML issue (4b86ce1)
• Require model name in ModelEvaluation.list() (aed8c76)

Documentation

• Fixed a docstring for train_steps (1f55b05)

Miscellaneous Chores

• Release 1.28.1 (8ebf22e)

v1.28.0

1.28.0 (2023-07-08)

Features

• LLM - Released the Chat models to GA (22aa26d)

v1.27.1

1.27.1 (2023-07-06)

Features

• Add sdk support for xai example-based explanations (f9ca1d5)

Miscellaneous Chores

• Release 1.27.1 (2159f29)

v1.27.0

1.27.0 (2023-06-30)

Features

• Add submit for CustomTrainingJob and CustomContainerTrainingJob which won't block until complete. (d6476d0)
• LLM - Added support for learning_rate in tuning (c6cdd10)
• LLM - Released the Codey models to GA (89609c9)

Bug Fixes

• Fix aiplatform.init bug by replacing experiment_name with experiment (c60773a)
• Fix error when calling update_state() after ExperimentRun.list() (cb255ec)
• LLM - Exported the ChatMessage class (7bf7634)
• LLM - Fixed the chat models failing due to safetyAttributes format (459ba86)
• Vizier - Fixed pyvizier client study creation errors (16299d1)

Documentation

• Fixed a docstring for _Dataset (b68a941)
• Fixed a docstring for TimeSeriesDataset (a7dfce2)
• Populate GA LLM SDK Pydocs (e248285)
• Update scheduled pipelines client max_run_count docstring with allowed values. (750e161)