v1.90.0

Compare Source

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)

v1.89.0

Compare Source

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)

v1.88.0

Compare Source

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)

v1.87.0

Compare Source

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)

v1.86.0

Compare Source

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)

v1.85.0

Compare Source

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)

v1.84.0

Compare Source

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)

v1.83.0

Compare Source

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)

v1.82.0

Compare Source

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)

v1.81.0

Compare Source

Features

• 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 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 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)
• 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)

v1.80.0

Compare Source

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)

v1.79.0

Compare Source

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)

v1.78.0

Compare Source

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)

v1.77.0

Compare Source

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)

v1.76.0

Compare Source

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)

v1.75.0

Compare Source

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

Compare Source

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

Compare Source

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](https://redirect.github.com/googleapis/python-aiplatform/commit/