googleapis/google-cloud-node aiplatform-v3.35.0

aiplatform: v3.35.0

on GitHub

3.35.0 (2025-02-28)

Features

• A new field create_time is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (fdef07b)
• A new field create_time is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (fdef07b)
• A new field list_all_versions to ListPublisherModelsRequest (fdef07b)
• A new field response_id is added to message .google.cloud.aiplatform.v1.GenerateContentResponse (fdef07b)
• A new value NVIDIA_H100_MEGA_80GB is added to enum AcceleratorType (fdef07b)
• A new value NVIDIA_H100_MEGA_80GB is added to enum AcceleratorType (fdef07b)
• Add a new thought field in content proto (fdef07b)
• Add additional Probe options to v1 model.proto (fdef07b)
• Add Context Cache to v1 (fdef07b)
• Add GenerationConfig.MediaResolution (fdef07b)
• Add GenerationConfig.Modality (fdef07b)
• Add GenerationConfig.SpeechConfig (fdef07b)
• Add LLM parser proto to API (fdef07b)
• Add machine_spec, data_persistent_disk_spec, network_spec, euc_config, shielded_vm_config to .google.cloud.aiplatform.v1beta1.NotebookRuntime (fdef07b)
• Add machine_spec, data_persistent_disk_spec, network_spec, euc_config, shielded_vm_config to message .google.cloud.aiplatform.v1.NotebookRuntime (fdef07b)
• Add Model Garden deploy API (fdef07b)
• Add Model Garden deploy API (#5836) (fdef07b)
• Add new RequiredReplicaCount field to DedicatedResources in MachineResources (fdef07b)
• Add new RequiredReplicaCount field to DedicatedResources in MachineResources (fdef07b)
• Add new Status field to DeployedModel in Endpoint (fdef07b)
• Add new Status field to DeployedModel in Endpoint (fdef07b)
• Add Notebooks Runtime Software Configuration (fdef07b)
• Add Notebooks Runtime Software Configuration (fdef07b)
• Add optimized config in v1 API (fdef07b)
• Add per-modality token count break downs for GenAI APIs (fdef07b)
• Add per-modality token count break downs for GenAI APIs (fdef07b)
• Add rag_files_count to RagCorpus to count number of associated files (fdef07b)
• Add retrieval_config to ToolConfig v1 (fdef07b)
• Add retrieval_config to ToolConfig v1beta1 (fdef07b)
• Add RolloutOptions to DeployedModel in v1beta1 endpoint.proto, add additional Probe options in v1beta1 model.proto (fdef07b)
• Add speculative decoding spec to DeployedModel proto (fdef07b)
• Add Tool.GoogleSearch (fdef07b)
• Add Vertex RAG service proto to v1 (fdef07b)
• Add workbench_runtime and kernel_name to NotebookExecutionJob (fdef07b)
• Add workbench_runtime and kernel_name to NotebookExecutionJob (fdef07b)
• Enable FeatureGroup IAM Methods in v1beta1 API version (fdef07b)
• Enable FeatureGroup Service Account and IAM methods (fdef07b)
• Enable FeatureView Service Account in v1 API version (fdef07b)
• Enable UpdateFeatureMonitor in v1beta1 API version (fdef07b)
• EvaluateDataset API v1beta1 initial release (fdef07b)
• Expose code execution tool API to v1 (fdef07b)
• Introduce HybridSearch and Ranking configuration for RAG (fdef07b)
• Introduce VertexAiSearch integration for RAG (fdef07b)
• Model Registry Checkpoint API (fdef07b)
• Model Registry Checkpoint API (fdef07b)
• Paging changes for bigquery (fdef07b)
• Reasoning Engine v1 GAPIC release (fdef07b)
• Remove autorater config related visibility v1beta1 (fdef07b)
• Support streaming and multi class methods in Reasoning Engine v1beta1 API (fdef07b)

Bug Fixes

• Add x-goog-request params to headers for LRO-polling methods (fdef07b)
• Finalize fixing typings for headers in generator (fdef07b)
• Fix typings for headers in generator (fdef07b)
• Remove extra protos in ESM & capture ESM in headers (fdef07b)