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)

v1.67.0

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)

v1.66.0

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)

v1.65.0

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)