NVIDIA Clara Deploy SDK User Guide
- 1. Introduction
- 2. Installation
- 2.1. System Requirements
- 2.2. Ansible Installation
- 2.3. Verify Installation
- 2.4. Installation on a Cloud Service Provider (CSP)
- 2.5. Installing Clara in a system protected by a firewall
- 2.5.1. Login to staging system
- 2.5.2. Log in to the DGX Container Registry.
- 2.5.3. Download container images on staging system
- 2.5.4. Generate a tar.gz for container images on staging system
- 2.5.5. Login to production system
- 2.5.6. Transfer Images to production system
- 2.5.7. Load Images on production system
- 3. Uninstallation
- 4. Clara Administration
- 5. Core Concepts
- 6. How to Run a Reference Pipeline
- 6.1. Select a Reference Pipeline
- 6.2. Run Reference Pipelines by Sending DICOM Instances Over Network
- 6.2.1. External DICOM Sender and DICOM Receiver
- 6.2.2. Customize the Pipeline
- 6.2.3. Create the Pipeline
- 6.2.4. Configure the Clara DICOM Adapter
- 6.2.5. Trigger Pipeline
- 6.2.6. Check Job Status and Download/View Payloads in Clara Console/Dashboard
- 6.2.7. Verify That the External DICOM Receiver Received Your Images
- 6.2.1. External DICOM Sender and DICOM Receiver
- 6.3. Run Reference Pipelines using Local Input Files
- 7. How to Run a Reference Pipeline using Model Repository
- 7.1. Select a Reference Pipeline
- 7.2. Run Reference Pipelines by Sending DICOM Instances Over Network
- 7.2.1. External DICOM Sender and DICOM Receiver
- 7.2.2. Customize the Pipeline
- 7.2.3. Create the Pipeline
- 7.2.4. Configure the Clara DICOM Adapter
- 7.2.5. Trigger Pipeline
- 7.2.6. Check Job Status and Download/View Payloads in Clara Console/Dashboard
- 7.2.7. Verify That the External DICOM Receiver Received Your Images
- 7.2.1. External DICOM Sender and DICOM Receiver
- 8. Clara Pipeline Driver API
- 8.1. Clara Pipeline Driver Overview
- 8.2. Clara Pipeline Callbacks
- 8.3. Clara Pipeline Driver
- 8.4. NVIDIA Clara Pipeline Driver Guidance
- 8.5. Clara Pipeline Fast I/O Allocations
- 8.6. Clara Pipeline Fast I/O Context
- 8.7. Clara Pipeline Fast I/O Entries
- 8.7.1. Output Entries
- 8.7.2. Input Entries
- 8.7.3. FastIO Entry Automatic and Manual Allocation
- 8.7.4. FastIO Entry I/O Access
- 8.7.5. Name
- 8.7.6. Shape
- 8.7.7. Element Type
- 8.7.8. Size in Bytes
- 8.7.9. Dynamic Indices
- 8.7.10. Is Dynamic
- 8.7.11. Update Shape
- 8.7.12. Access
- 8.7.13. Allocate
- 8.7.14. Is Allocated
- 8.7.15. Map Allocation
- 8.7.16. Unmap Allocation
- 8.8. Clara Pipeline Payload
- 8.9. Clara Pipeline Payload Entry
- 8.10. Clara Pipeline Driver Callbacks
- 8.11. Clara Pipeline Fast I/O Allocations
- 8.12. Clara Pipeline Fast I/O Context
- 8.13. Clara Pipeline FastIO Entry
- 8.13.1. Pre-allocated FastIO Entries
- 8.13.2. Dynamic-size FastIO Entries
- 8.13.3. Input- and Output-Type FastIO Entries
- 8.13.3.1. FastIO Entry Accessors and Mutators
- 8.13.3.1.1. Name
- 8.13.3.1.2. Is Pre-Allocated
- 8.13.3.1.3. Access
- 8.13.3.1.4. Access
- 8.13.3.1.5. Shape
- 8.13.3.1.6. Element Type
- 8.13.3.1.7. Dynamic Indices of the Shape
- 8.13.3.1.8. Is Dynamic
- 8.13.3.1.9. Update Shape
- 8.13.3.1.10. Get Values of Allocation as Read-Only Bytes
- 8.13.3.1.11. Get Values of Allocation as Numpy Array
- 8.13.3.1.12. Set the Values in the Allocation
- 8.13.3.1. FastIO Entry Accessors and Mutators
- 8.14. Pipeline Stage Payload
- 8.15. Pipeline Payload Entry
- 8.16. Clara Pipeline Callbacks
- 8.17. Clara Pipeline Driver
- 8.18. Clara Pipeline Payload
- 8.19. Clara Pipeline Payload Entry
- 8.1. Clara Pipeline Driver Overview
- 9. Pipeline Definition Language
- 9.1. Clara Pipeline Definition Language Overview
- 9.2. Clara Deploy SDK Pipeline Glossary
- 9.3. Operators
api-version
0.7.0
api-version
0.5.0
- 9.6. The Anatomy of an Operator
- 9.7. Argo vs. Clara Orchestration
- 9.8. Pipelines
- 9.9. Services
- 9.10. Connections
- 9.11. Container
- 9.12. Document
- 9.13. Import
- 9.14. Input
- 9.15. Operator
- 9.16. Output
- 9.17. Pipeline
- 9.18. Requests
- 9.19. Service
- 9.20. Syntax & Grammar
- 9.21. Template
- 9.22. Clara Structures and Primitives
- 9.23. Variables
- 9.1. Clara Pipeline Definition Language Overview
- 10. Bundled Operators
- 10.1. Clara DICOM Reader
- 10.2. Clara DICOM Writer
- 10.3. Clara Deploy DICOM Parser Operator
- 10.4. Clara Deploy Base Inference Operator V2
- 10.4.1. Overview
- 10.4.2. Inputs
- 10.4.3. Outputs
- 10.4.4. Environment Variables
- 10.4.5. AI Model
- 10.4.6. Directory Structure
- 10.4.7. Executing Operator as Docker Container
- 10.4.8. Executing Operator Docker Container Interactively
- 10.4.9. Creating Model Specific Application
- 10.4.10. License
- 10.4.11. Suggested Reading
- 10.4.1. Overview
- 10.5. Clara AI Liver Tumor Segmentation Operator
- 10.6. Clara Deploy SDK VNet Segmentation Operator
- 10.7. Clara AI Brain Tumor Segmentation Operator
- 10.8. Clara AI Hippocampus Segmentation Operator
- 10.9. Clara AI Spleen Segmentation
- 10.10. Malaria Microscopy Classification Operator
- 10.11. Clara AI Lung Tumor Segmentation Operator
- 10.12. Colon Tumor Segmentation Operator
- 10.13. Clara AI Pancreas Tumor Segmentation
- 10.14. Chest X-ray Classification Operator
- 10.15. Breast Microscopy Classification Operator
- 10.16. Clara AI Prostate Segmentation
- 10.17. CT Recon Operator
- 10.18. Clara Register Results
- 10.19. Clara Genomics Analysis
- 10.20. FastIO-ITK Operator
- 10.21. DICOM RTSTRUCT Writer Operator
- 10.22. Clara FastIO Variable Passthrough - Nifti to FastIO Variable Conveter Operator
- 10.23. Clara FastIO Variable Passthrough - Fastio to Npz Converter Operator
- 10.24. Clara FastIO Variable Passthrough - Compare Operator
- 10.25. DeepStream App Operator
- 10.26. Digital Pathology Image Processing Operator
- 10.26.1. Overview
- 10.26.2. Commands
- 10.27. Clara Deploy AI Lung Segmentation Operator
- 10.28. Clara Deploy AI COVID-19 Classification Operator
- 10.29. Clara Deploy AI COVID-19 Lesion Segmentation Operator
- 10.30. Clara Deploy Series Selector
- 10.31. Copy customized rules file overwriting the default one.
- 10.32. Digital Pathology Nuclei Segmentation Operator
- 10.33. Clara Deploy DICOM Segmentation Writer Operator
- 10.34. Clara Deploy DICOM Report Object Writer
- 10.35. Registration Operator
- 10.1. Clara DICOM Reader
- 11. User Defined Operators
- 11.1. Developing Clara Pipeline Operators Using the Operator Development Kit
- 11.2. Developing Clara Operators Using the Operator Development Kit
- 11.2.1. Overview of the Operator Development Kit
- 11.2.2. Package Contents
- 11.2.3. Run the Example Liver Segmentation Model Locally
- 11.2.4. Customizing the Operator Development Kit Example Code
- 11.2.5. Deploy an Existing Container as a Clara Operator
- 11.2.6. Deploying a Single-Operator Pipeline to Existing Clara Cluster
- 11.1. Developing Clara Pipeline Operators Using the Operator Development Kit
- 12. Bundled Pipelines
- 12.1. Liver Segmentation Pipeline
- 12.2. CT Reconstruction Pipeline
- 12.3. Multi AI Pipeline
- 12.4. Vnet Segmentation pipeline
- 12.5. Clara AI Brain Tumor Segmentation Pipeline
- 12.6. Hippocampus Segmentation Pipeline
- 12.7. Spleen Segmentation Pipeline
- 12.8. Malaria Microscopy Classification Pipeline
- 12.9. Lung Tumor Segmentation Pipeline
- 12.10. Colon Tumor Segmentation Pipeline
- 12.11. Pancreas Tumor Segmentation Pipeline
- 12.12. Chest X-ray Classification Pipeline
- 12.13. Breast Pathology Image Classification Pipeline
- 12.14. Clara AI Prostate Segmentation Pipeline
- 12.15. De Novo Sequence Assembly - Clara Genomics Analysis
- 12.16. 3D Image Processing Pipeline using FastIO
- 12.17. FastIO Passthrough Pipeline Using FastIO Variable API
- 12.18. Suggested Reading
- 12.19. DeepStream Batch Pipeline
- 12.20. Digital Pathology Image Processing Pipeline
- 12.21. Clara Deploy AI COVID-19 Classification Pipeline
- 12.22. Clara Advanced DICOM Integration Pipeline
- 12.23. Clara Deploy DICOM Series Selection Pipeline
- 12.24. Digital Pathology Nuclei Segmentation Pipeline
- 12.25. Registration Pipeline
- 12.1. Liver Segmentation Pipeline
- 13. User Defined Pipelines
- 13.1. Build Custom Operators
- 13.2. Place AI Model Files in the Right Directory
- 13.3. Start With a Reference Pipeline
- 13.4. Modify the Pipeline
- 13.5. External DICOM Sender and DICOM Receiver
- 13.6. Create the Pipeline
- 13.7. Configure the Clara DICOM Destination
- 13.8. Trigger Pipeline
- 13.9. Verify the Pipeline Execution in the Dashboard
- 13.10. Verify the External DICOM Receiver Received the Images
- 14. Bundled Services
- 14.1. Clara Results Service
- 14.1.1. Task States
- 14.1.2. Definitions
- 14.1.3. Requirements
- 14.1.4. Running the Results Service
- 14.1.5. API Usage
- 14.1.6. Database
- 14.1.7. License
- 14.2. Clara Dashboard Render Service
- 14.3. Clara Management Console
- 14.1. Clara Results Service
- 15. Connectivity With a PACS/DICOM Server
- 16. Clara Deploy GPU Profiler
- 17. Clara CLI
- 18. Load Generator
- 19. Platform API
- 19.1. Clara Deploy SDK Platform API Overview
- 19.1.1. Concepts
- 19.1.2. Clara Service
- 19.1.3. Jobs Service
- 19.1.4. Models Service
- 19.1.5. Payloads Service
- 19.1.6. Pipelines Service
- 19.1.7. Create a New Pipeline
- 19.1.8. Get a List of Existing Pipelines
- 19.1.9. Create and Start a Job
- 19.1.10. Get Status of a Job
- 19.1.11. Get a File Listing from a Payload
- 19.1.12. Download a File from a Payload
- 19.1.13. Introduction to GRPC and Protobuf
- 19.1.14. GRPC Examples
- 19.1.1. Concepts
- 19.2. GpuUtilization
- 19.3. ProcessDetails
- 19.4. Clara Stop RPC
- 19.5. ClaraStopRequest
- 19.6. ClaraStopResponse
- 19.7. Clara Stop RPC
- 19.8. ClaraUtilizationRequest
- 19.9. ClaraUtilizationResponse
- 19.10. Clara Version RPC
- 19.11. ClaraVersionRequest
- 19.12. ClaraVersionResponse
- 19.13. Pipelines Create RPC
- 19.14. PipelinesCreateRequest
- 19.15. PipelinesCreateResponse
- 19.16. Pipelines Details RPC
- 19.17. PipelinesDetailsRequest
- 19.18. PipelinesDetailsResponse
- 19.19. Pipelines List RPC
- 19.20. PipelinesListRequest
- 19.21. PipelinesListResponse
- 19.22. PipelineDetails
- 19.23. Pipelines Remove RPC
- 19.24. PipelinesRemoveRequest
- 19.25. PipelinesRemoveResponse
- 19.26. Pipelines Update RPC
- 19.27. PipelinesUpdateRequest
- 19.28. PipelinesUpdateResponse
- 19.29. PipelineDefinitionFile
- 19.30. Jobs Cancel RPC
- 19.31. JobsCancelRequest
- 19.32. JobsCancelResponse
- 19.33. Jobs Create RPC
- 19.34. JobsCreateRequest
- 19.35. JobsCreateResponse
- 19.36. Jobs List RPC
- 19.37. JobsListRequest
- 19.38. JobsListResponse
- 19.39. Jobs ReadLogs RPC
- 19.40. JobsReadLogsRequest
- 19.41. JobsReadLogsResponse
- 19.42. Jobs Start RPC
- 19.43. JobsStartRequest
- 19.44. JobsStartResponse
- 19.45. NamedValue
- 19.46. Jobs Status RPC
- 19.47. JobsStatusRequest
- 19.48. JobsStatusResponse
- 19.49. JobsDetails
- 19.50. JobFilter
- 19.51. JobOperatorDetails
- 19.52. JobOperatorStatus
- 19.53. JobPriority
- 19.54. JobState
- 19.55. JobStatus
- 19.56. Payloads Create RPC
- 19.57. PayloadsCreateRequest
- 19.58. Payloads Details RPC
- 19.59. PayloadsDetailsRequest
- 19.60. PayloadsDetailsResponse
- 19.61. Payloads Download RPC
- 19.62. PayloadsDownloadRequest
- 19.63. PayloadsDownloadResponse
- 19.64. Payloads Create RPC
- 19.65. PayloadsCreateRequest
- 19.66. Payloads Upload RPC
- 19.67. PayloadsUploadRequest
- 19.68. PayloadsUploadResponse
- 19.69. PayloadFileDetails Message
- 19.70. PayloadType
- 19.71. RPC Error Codes
- 19.72. Identifier
- 19.73. RequestHeader
- 19.74. ResponseHeader
- 19.75. Timestamp
- 19.76. Version
- 19.1. Clara Deploy SDK Platform API Overview
- 20. Third Party Tools
- 21. Release Notes
- 21.1. Version 0.8.1-1 (Secutity Patched R8 Release)
- 21.2. Version 0.8.1 (R8)
- 21.2.1. What’s New
- 21.2.2. DICOM Parser Supporting Series Selection Rules
- 21.2.3. Series Selector Supporting Series Selection Rules via Environment Variable
- 21.2.4. Operators Supporting Selected Images Metadata
- 21.2.5. Reference Pipeline Definition Specifying System Memory Request
- 21.2.6. Fixed: COVID Lung Lesion DICOM Segmentation Image Orientation Issue
- 21.2.7. Platform Server Now Performs Clean-up as Part of its Start-up Routine
- 21.2.8. Long Running Pipeline-jobs Will be Timed Out and Terminated
- 21.2.9. Memory and CPU Utilization Limits are Now Applied to Pipelines
- 21.2.10. Creation of New Pipeline-jobs Will be Rejected When Storage Space is Low
- 21.2.11. Clara Platform Server Removes Stopped Pods More Quickly
- 21.2.12. Pyloads Download feature in Clara Management Console can now be disabled
- 21.2.13. Ansible Uninstall Support
- 21.2.14. Removal of Bootstrap.sh
- 21.2.15. Memory and CPU Utilization Limits are Now Applied to Pipelines
- 21.2.16. Creation of New Pipeline-jobs Will be Rejected When Storage Space is Low
- 21.2.17. Platform Pod Eviction Due To Low Ephemeral Storage
- 21.2.18. Clara GPU Profiler
- 21.2.19. Clara Pipeline Driver
- 21.2.20. CLI - State Filter in List jobs command
- 21.2.21. Data Corruption when Using Pipeline-Services
- 21.2.1. What’s New
- 21.3. Version 0.7.4 (R7)
- 21.3.1. What’s New
- 21.3.1.1. Clara GPU Profiler
- 21.3.1.2. Render Server - displaying orientation labels to slice view
- 21.3.1.3. Jupyter notebook based interactive rendering
- 21.3.1.4. Clara Management Console: Ability to view datasets which were not pre-registered
- 21.3.1.5. DICOM Adapter Open Source
- 21.3.1.6. Surface Mesh in STL Format in DICOM RTSTRUCT Instance
- 21.3.2. Clara Management Console: Enhanced Jobs filtering
- 21.3.3. Clara Management Console: Auto Log Off
- 21.3.4. Using different environment variables for the same pipeline service can make Clara Platform API Server confusing
- 21.3.5. Clara Management Console - Log Viewer may have problems visualizing very large logs
- 21.3.6. Clara Management Console - Jobs View filters don’t get reset on navigating to the other view
- 21.3.7. Digital Pathology Nuclei Segmentation Pipeline doesn’t work on A100
- 21.3.1. What’s New
- 21.4. Version 0.7.3 (R7)
- 21.4.1. What’s New
- 21.4.1.1. Support for A100 platform
- 21.4.1.2. DICOM Adapter: Enable plug-in development for grouping data and triggering
- 21.4.1.3. AI Base Operator V2 Updated
- 21.4.1.4. COVID-19 Pipeline Updated with new AI operators
- 21.4.1.5. Render Server - Video Stream Encoding using Software Mode
- 21.4.1.6. GPU Profiling Tool
- 21.4.1.7. Clara Management Console - Job DAG View
- 21.4.1.8. Clara Management Console - Basic Authentication
- 21.4.1.9. Ansible Scripts
- 21.4.1.10. Platform Server: Enable metadata for jobs, models, pipelines and reusable payloads.
- 21.4.1.11. Platform Server - Clara::Utilization API
- 21.4.2. Error in submitting Clara jobs due to valid job names which can not be inserted as labels due to sizing constraints:
- 21.4.3. Multi-AI with shmem
- 21.4.4. DeepStream Batch Pipeline doesn’t support A100
- 21.4.1. What’s New
- 21.5. Version 0.7.2 (R7)
- 21.5.1. What’s New
- 21.5.1.1. DICOM Adapter Now Supports Concurrent Associations
- 21.5.1.2. Exporting DICOM SR Object
- 21.5.1.3. COVID-19 Pipeline Support for DICOM Segmentation and Encapsulated PDF Output
- 21.5.1.4. Viewing payloads from Clara Console
- 21.5.1.5. Viewing Logs for Operators
- 21.5.1.6. GPU Profiling Tool
- 21.5.1.7. Model Analyzer
- 21.5.2. Fixed Platform Server Crash Issue Caused by Argo
- 21.5.3. DICOM Adapter Configuration File Changes
- 21.5.4. DICOM Adapter Kubernetes Custom Resource Changes
- 21.5.5. AE Title Job Processor for DICOM Adapter CLI
- 21.5.6. Platform API JobsService::ClaraStop RPC Has Been Removed
- 21.5.7. Clara Console
- 21.5.8. Render Server fails to start on A100 GPU
- 21.5.9. Multi-AI with shmem
- 21.5.10. Containers started by pipeline services are not correctly managed by Platform Server
- 21.5.1. What’s New
- 21.6. Version 0.7.1 (R7)
- 21.6.1. What’s New
- 21.6.1.1. Segmentation Algorithm: Automatic Bone Segmentation for Multi-AI Pipeline
- 21.6.1.2. Reference Operator: Automatic detection of Lung ROI for Multi-AI Pipeline
- 21.6.1.3. Reference Pipeline: Nuclei Segmentation Pipeline for Digital Pathology
- 21.6.1.4. Reference Operator: DICOM Segmentation Object Writer
- 21.6.1.5. Clara Management Console: Downloading Payloads
- 21.6.1.6. Render Server: Shared Memory for Loading Datasets
- 21.6.1.7. Python Client
- 21.6.1.8. Platform Server Resource Management
- 21.6.1.9. Platform Server Job Operator Logs API
- 21.6.2. DICOM Parser generated image slices may be out of order
- 21.6.3. DICOM RT STRUCT Writer output misaligned
- 21.6.4. Pipeline job operators and services no longer have access to unassigned GPU resources
availableGpus
- 21.6.6. Pipeline operators and services that need GPU resources must specify GPU resource requirements
- 21.6.7. Render Server fails to start on A100 GPU
nvidia-smi
- 21.6.9. Register results with multi AI + shared memory
- 21.6.10. Pipeline jobs which require more GPU resources than are available in the cluster are unable to be executed
- 21.6.11. Clara Orchestrator pipeline operator run times are incorrectly reported
- 21.6.12. Job status for jobs using Argo orchestrator is incorrectly reported
- 21.6.13. Job status for jobs using Clara Orchestrator without CPDriver is incorrectly reported
- 21.6.14. Failure to cancel downloading the operators/jobs payload
- 21.6.1. What’s New
- 21.7. Version 0.6.1 (R6)
- 21.7.1. Reference Pipeline: Implementation Update for the Digital Pathology Pipeline
- 21.7.2. Reference Pipeline: Implementation Update for the Multi-AI Pipeline
- 21.7.3. Clara Deploy GPU Profiling Tool
- 21.7.4. Reference Operator: New Base AI Inference Operator
- 21.7.5. Render Server: Area Measurement
- 21.7.6. Clara Console: Details for a Job
- 21.7.7. DICOM Adapter CLI
- 21.7.8. Clara Platform Server: Pod Cleaners and Job Controllers
- 21.7.9. Reference Operator DICOM Parser does not support DICOM files .DCM extension
- 21.7.10. Reference Operator DICOM Parser does not extract Series Description tag
- 21.7.11. Helm 2.15.2 upgrade
- 21.7.12. DICOM Adapter
- 21.8. Version 0.6.0 (R6)
- 21.8.1. Reference Pipeline: Detection of COVID-19 in CT datasets
- 21.8.2. Reference Pipeline: Usage of Shared Memory in Multi-AI CT Pipeline
- 21.8.3. Reference Operator: DICOM Parser Operator
- 21.8.4. Reference Pipeline: Digital Pathology
- 21.8.5. Reference Pipeline: DICOM Series Selection Pipeline
- 21.8.6. Render Server: Visualization of Multi-Resolution Data
- 21.8.7. Render Server: Supporting Color Data Type
- 21.8.8. Render Server: Static Scale
- 21.8.9. Render Server: Distance Measurement
- 21.8.10. Render Server: Picture-in-Picture
- 21.8.11. Configuring DICOM Adapter via REST APIs
- 21.8.12. Helm Upgrade
- 21.8.13. Results Service
- 21.8.14. Jobs API Reports Incorrect Job State
- 21.8.15. Pipeline Services Conflict with Resource Manager
- 21.8.16. Deploying Triton via Pipeline Services Consumes All GPUs
- 21.8.17. Triton Inference Server Consumes Memory of Unassigned GPU(s)
- 21.8.18. Deleted Jobs Listed and/or Deleting Jobs with CLI Can Error
- 21.8.19. Corrupted Tiles in the Output of the Digital Pathology Image Processing Pipeline
- 21.9. Version 0.5.0 (R5)
- 21.9.1. Platform
- 21.9.2. Application
- 21.9.2.1. Fast I/O Integrated with Clara Platform Driver
- 21.9.2.2. Histopathology Pipeline
- 21.9.2.3. Prostate Segmentation Pipeline
- 21.9.2.4. Multi-AI Pipeline
- 21.9.2.5. De Novo Assembly Pipeline
- 21.9.2.6. 3D Cropping Pipeline using Shared Memory
- 21.9.2.7. Deep Stream Batch Pipeline
- 21.9.2.8. DICOM Parser Operator
- 21.9.3. Render Server
- 21.9.4. Management Console
- 21.9.5. Jobs API Reports Incorrect Job Information for Argo Based Pipelines
- 21.9.6. Clara Deploy SDK from NGC Only Uses a Single GPU
- 21.9.7. Pipeline Services Conflict with Resource Manager
- 21.9.8. Deploying Triton via Pipeline Services Consumes All GPUs
- 21.9.9. Argo Workflow Support is Deprecated
- 21.9.10. Support for Pipeline Definitions < 0.4.0 is Deprecated
- 21.9.11. Pipeline Services are Deprecated
- 21.9.1. Platform
- 21.10. Version 0.4.1 (hotfix)
- 21.11. Version 0.4.0 (R4)
- 21.11.1. Clara Pipeline Driver
- 21.11.2. Orchestration in two modes
- 21.11.3. File Adapter
- 21.11.4. CLI Improvements
- 21.11.5. Centralized Logging
- 21.11.6. Monitoring Performance
- 21.11.7. Shared Memory Context
- 21.11.8. Optimized CT Recon Pipeline
- 21.11.9. Optimized Liver Tumor Segmentation Pipelines
- 21.11.10. Render Server Improvements
- 21.11.11. Automatic Payload Cleanup
- 21.11.12. New Pipelines
- 21.12. Version 0.2.0 (R2)
- 21.13. Version 0.1.7 (Deprecated)
- 21.14. Version 0.1.6 (Deprecated)
- 21.15. Pre-alpha (Deprecated)
- 21.16. Known Issues
[ERROR Port-XXXXX]: Port XXXXX is in use
/var/lib/etcd is not empty
- 21.16.3. Installation error with coreDNS pod failures
- 21.16.4. Installation error with space in the path
- 21.16.5. Recon operator does not exit with the right error code
- 21.16.6. Minimum opacity value of the transfer function editor cannot be changed (since 0.4.0)
- 21.16.7. Intensity Range Selectors in Transfer Function Editor are not displayed properly (since 0.4.0)
- 21.16.8. White empty viewport
- 21.16.9. Session management
- 21.16.10. Changing datasets results in “Unable to reach RenderServer”
- 21.17. Support
- 21.1. Version 0.8.1-1 (Secutity Patched R8 Release)
- 22. License