Releases: googleapis/python-aiplatform
Releases · googleapis/python-aiplatform
v1.156.0
v1.155.0
1.155.0 (2026-06-02)
Features
- Add Skill Registry GetSkillRevision and ListSkillRevisions to SDK (94cd20c)
- Add Skill Registry ListSkills and DeleteSkill to SDK (57097a3)
- Forward per-call
http_optionsfromAgentEngine.queryfamily of methods. (e6818d3) - GenAI client - Add retrieve_contexts and ask_contexts methods to RAG module (b90e084)
- GenAI SDK client - Add RAG module with list_corpora, get_corpus, get_file, list_files, and get_config methods (3bc2f58)
Bug Fixes
- Job state name print (be945df)
- Route Endpoint.predict_async via dedicated DNS when the endpoint is dedicated (b6a9652)
- Update authorization for streaming_agent_run_with_events (ae54eb5)
- Using location and project parsed from resource name if not provided (caa416a)
Documentation
v1.154.0
1.154.0 (2026-05-27)
Features
- Add new fields (027acc8)
- Add Skill Registry module to Vertex AI client - Get Skill method (df50ac0)
- Make skill_id a required parameter in
skills.create(bc4be37)
Bug Fixes
- Fix flaky evaluation test failures caused by thread execution order (9f97738)
- Fix SkillRevision state enum in Python SDK (1585602)
- GenAI Client(evals) - Map legacy RubricMetric.GROUNDEDNESS to grounding_v1 (9770c31)
Documentation
v1.153.1
v1.153.0
1.153.0 (2026-05-14)
Features
- GenAI Client(evals) - Add red_teaming_config support for create_evaluation_run (657f379)
- Migrate Agent Engines, Evaluation, Prompt Management, and Skill features to agentplatform (74ec5e1)
Bug Fixes
- Inject agents map from agent_info into agent_data for create_evaluation_run (a4ffb67)
Documentation
- Add Skill Registry Python SDK section in README (9f8e24c)
v1.152.0
1.152.0 (2026-05-11)
Features
- Add GetSkillRevision and ListSkillRevisions methods in Vertex AI Skill Registry SDK (e4fdb7a)
- Add ListSkills and DeleteSkill methods in Vertex AI Skill Registry SDK (8578bfd)
- Add mTLS support for telemetry endpoint in adk.py. (7b0c995)
- Add Update Skill method for Vertex AI Skill Registry SDK (48f792b)
- GenAI Client(evals) - Add allow_cross_region_model support for create_evaluation_run (3ce4b02)
Bug Fixes
v1.151.0
1.151.0 (2026-05-07)
Features
- Add client for Vertex AI Skill Registry - Get Skill method (6f89fd3)
- Add Create Skill method for Vertex AI Skill Registry SDK (67097eb)
- Add RetrieveSkills semantic search method in Vertex AI Skill Registry SDK (f5909b2)
- Migrate rag to agentplatform (d947295)
Bug Fixes
- Disable bound token sharing check for this Vertex AI SDK code path: google3/third_party/py/google/cloud/aiplatform/vertexai/agent_engines/ (b234d9d)
- GenAI Client(evals) - fix
referencecolumn visualization for eval_result (42de11b)
Documentation
- Update Prompts sample in readme to use create_version (e50f375)
v1.150.0
1.150.0 (2026-05-05)
Features
- Add Agent Engine Runtime Versioning support to SDK. (b8eaefb)
- Add Agent Engine Sandbox Snapshots Module (f48e54b)
- Add support for templates sub-module for Sandboxes in Vertex AI GenAI SDK. (68f053e)
- Add support for wait for operation complete for sandbox sub-modules (737ad1c)
- Disable streaming check that should have already been disabled (762d20c)
- Faster sandbox creation with templates and snapshots and improve dataplane routing and security. (9dccee2)
- GenAI Client(evals) - Support eval_cases with multi-turn agent_data in run_inference() (a1680d3)
- GenAI Client(evals) - Support N+1 Agent Engine inference via agent_data in run_inference() (9ea4aa6)
- GenAI SDK client(multimodal) - Accept an explicit bigquery_uri parameter in create_from_bigquery (0bb2ecd)
- Migrate model garden to agentplatform (d5e71ff)
- Migrate resources to agentplatform (5788c50)
- Update sdk to support python-a2a sdk 1.0 via a new GA A2a framework template (762d20c)
Bug Fixes
v1.149.0
1.149.0 (2026-04-27)
Features
- Add asyncQueryReasoningEngine to aiplatform v1 API (6332d33)
- Add asyncQueryReasoningEngine to aiplatform v1beta1 API (6332d33)
- Add delete_evaluation_metric to GenAI SDK (6b63480)
- Add evaluation configuration and dataset runs to TuningJob (6332d33)
- Add evaluation metrics and autorater configuration to the AI Platform v1 API (6332d33)
- Add filter and order_by support to list_evaluation_metrics (a7acc97)
- Add multimodal input support and custom output formats to evaluation metrics (6332d33)
- Add OnlineEvaluator API and update Evaluation API (6332d33)
- Add origin to AttributeContext.Request (6332d33)
- GenAI Client(evals): Add allow_cross_region_model to generate_conversation_scenarios to enable cross region support for gemini 3 based model (dc3b639)
- GenAI SDK client(multimodal) - Allow passing dataset ID in addition to full resource name in dataset methods. (2fd8ca0)
- Migrate batch_predictions to agentplatform (53e16ba)
- Model Registry CopyModel BYOSA (6332d33)
- New field CopyModelRequest.custome_service_account for Model Registry CopyModel BYOSA (6332d33)
- Support VeoLoraTuningSpec in the tuning jobs (6332d33)
- Synchronize google/api/expr/v1alpha1 (6332d33)
Bug Fixes
- Add serializer to async_create_session to address 500 error in Agent Engine (AgentServerMode.EXPERIMENTAL). (ffe7fc7)
- deps: Bump litellm cap to >=1.83.7 for additional CVE remediation (3bd0b25)
- GenAI SDK client(multimodal) - Fix Pydantic validation errors when using
create_*in some cases (ca6b45e) - PrivateEndpoint.raw_predict parameter name (3d380ba)
- Removing Python 3.9 support due to EOL (dbdd7b1)
- Unpin litellm upper bound to allow CVE-2026-35030 remediation (e5e6346)
- Update litellm to >=1.83.0 to resolve security vulnerability (ac5a5e4)
Documentation
- Update comments and formatting (6332d33)
- Update doc string to replace
Vertex AIwithGemini Enterprise Agent Platform, update method error message to replaceVertex AIwithGemini Enterprise Agent Platform (previously known as Vertex AI), update converter error message to replaceVertex AIwithGemini Enterprise Agent Platform(18d97b6) - Update SelectiveGapicGeneration usage doc (6332d33)
- Update various comments (6332d33)
v1.148.1
1.148.1 (2026-04-17)
Bug Fixes
- Disable bound token sharing check for agent_engines (04d5092)
- Fix column name inconsistency (history vs conversation_history) across evaluation flows (37f72e5)
- Fix create_session AttributeError for agents without AdkApp (3e85f64)
- Fix NameError when evaluating ADK agents with AgentTool via GenAI Evals SDK (04c5e02)
- GenAI Client(evals): Lazy-load ADK imports in _evals_common.py to avoid top-level ImportError (c378551)
- GenAI SDK client(multimodal) - Remove
UpdateMultimodalDatasetConfigand replace withVertexBaseConfig. (f5dc932) - Strip None fields from agent_data in GenerateLossClusters to prevent INVALID_ARGUMENT errors (f2d73fd)