Clara Deploy SDK Logo
0.7.1-e3a26d1
  • Documentation Home
  • 1. Introduction
    • 1.1. Architecture
      • 1.1.1. Clara Platform
        • 1.1.1.1. Clara Platform API
      • 1.1.2. DICOM Adapter
      • 1.1.3. Results Service
      • 1.1.4. Clara Pipeline
      • 1.1.5. Tensor RT Inference Server
      • 1.1.6. Render Server
      • 1.1.7. Clara I/O Model
  • 2. Installation
    • 2.1. System Requirements
    • 2.2. Steps to Install
    • 2.3. Verify Installation
    • 2.4. Installation on a Cloud Service Provider (CSP)
      • 2.4.1. AWS Virtual Machine Configuration
      • 2.4.2. Azure Virtual Machine Configuration
      • 2.4.3. GCP Virtual Machine Configuration
  • 3. Uninstallation
    • 3.1. Steps to uninstall Clara
  • 4. Clara Administration
    • 4.1. Configuration
      • 4.1.1. Clara Deploy SDK Platform
      • 4.1.2. Render Server
      • 4.1.3. Management Console
    • 4.2. Start/Stop/Restart the platform
      • 4.2.1. Restarting the Operating System
    • 4.3. Network Configuration
    • 4.4. AI models for TensorRT Inference Server
    • 4.5. Key Commands
  • 5. Core Concepts
    • 5.1. Directed Acyclic Graph (DAG)
    • 5.2. Data Source
    • 5.3. Operator
    • 5.4. Pipeline
    • 5.5. Service
    • 5.6. Job
    • 5.7. Triggering a Pipeline
    • 5.8. Data Sink
  • 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
        • 6.2.1.1. Install DCMTK
        • 6.2.1.2. Setup an External DICOM Receiver
        • 6.2.1.3. Setup an External DICOM Sender
      • 6.2.2. Customize the Pipeline
        • 6.2.2.1. Customize GPU request
        • 6.2.2.2. Customize the Orchestration Mode
      • 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
    • 6.3. Run Reference Pipelines using Local Input Files
      • 6.3.1. Publish the Pipeline
      • 6.3.2. Trigger Pipeline
      • 6.3.3. Check Job Status and Download/View Payloads in Clara Console/Dashboard
      • 6.3.4. Download and Verify the Outputs
  • 7. Clara Pipeline Driver API
    • 7.1. Clara Pipeline Driver Overview
      • 7.1.1. Fast I/O: Shared Memory Data Exchange Between Operators
        • 7.1.1.1. Fast I/O Contexts and Allocations
        • 7.1.1.2. Fast I/O Variables
      • 7.1.2. Python Client
      • 7.1.3. Native Client
    • 7.2. Clara Pipeline Callbacks
      • 7.2.1. Operator Life-cycle
      • 7.2.2. Prepare Callback
      • 7.2.3. Execute Callback
      • 7.2.4. Cleanup Callback
      • 7.2.5. Notification Callback
    • 7.3. Clara Pipeline Driver
      • 7.3.1. Create
      • 7.3.2. Query
        • 7.3.2.1. Clara Query Enumeration
      • 7.3.3. Release
      • 7.3.4. Start
      • 7.3.5. Wait for Completion
    • 7.4. NVIDIA Clara Pipeline Driver Guidance
      • 7.4.1. Using the Library Shared Object
      • 7.4.2. Pipeline OPerator Life-Cycle
      • 7.4.3. Querying Clara Info
    • 7.5. Clara Pipeline Fast I/O Allocations
      • 7.5.1. Allocation Ownership and Lifespan
      • 7.5.2. Core Allocation and Memory Management Functions
        • 7.5.2.1. Release
        • 7.5.2.2. Free
        • 7.5.2.3. Are Same
        • 7.5.2.4. Size
        • 7.5.2.5. Map
        • 7.5.2.6. Unmap
      • 7.5.3. Metadata Functions
        • 7.5.3.1. Set Type And Dimensions
        • 7.5.3.2. Element Type
        • 7.5.3.3. Dimensions
        • 7.5.3.4. Dimension
        • 7.5.3.5. Num Elements
    • 7.6. Clara Pipeline Fast I/O Context
      • 7.6.1. Create
      • 7.6.2. Publish
      • 7.6.3. Get
    • 7.7. Clara Pipeline Fast I/O Entries
      • 7.7.1. Output Entries
      • 7.7.2. Input Entries
      • 7.7.3. FastIO Entry Automatic and Manual Allocation
        • 7.7.3.1. Well-defined FastIO Entries are Automatically Allocated
        • 7.7.3.2. Dynamic FastIO Entries Should Be Manually Allocated
        • 7.7.3.3. Freeing Allocations
      • 7.7.4. FastIO Entry I/O Access
      • 7.7.5. Name
      • 7.7.6. Shape
      • 7.7.7. Element Type
      • 7.7.8. Size in Bytes
      • 7.7.9. Dynamic Indices
      • 7.7.10. Is Dynamic
      • 7.7.11. Update Shape
      • 7.7.12. Access
      • 7.7.13. Allocate
      • 7.7.14. Is Allocated
      • 7.7.15. Map Allocation
      • 7.7.16. Unmap Allocation
    • 7.8. Clara Pipeline Payload
      • 7.8.1. Input Entries
      • 7.8.2. Output Entries
      • 7.8.3. Fast I/O Context
      • 7.8.4. Fast I/O Input Entries
      • 7.8.5. Fast I/O Output Entries
    • 7.9. Clara Pipeline Payload Entry
      • 7.9.1. Name
      • 7.9.2. Path
    • 7.10. Clara Pipeline Driver Callbacks
      • 7.10.1. Prepare
      • 7.10.2. Execute
      • 7.10.3. Cleanup
      • 7.10.4. Notification
    • 7.11. Clara Pipeline Fast I/O Allocations
      • 7.11.1. Allocation Ownership and Lifespan
      • 7.11.2. Core Allocation and Memory Management Functions
        • 7.11.2.1. Size
        • 7.11.2.2. Publish
        • 7.11.2.3. Release
        • 7.11.2.4. Free
        • 7.11.2.5. Map
        • 7.11.2.6. Unmap
        • 7.11.2.7. Map As Numpy Array
      • 7.11.3. Metadata Functions
        • 7.11.3.1. Set Type And Dimensions
        • 7.11.3.2. Element Type
        • 7.11.3.3. Dimensions
    • 7.12. Clara Pipeline Fast I/O Context
      • 7.12.1. Create
      • 7.12.2. Get
      • 7.12.3. Publish Array
    • 7.13. Clara Pipeline FastIO Entry
      • 7.13.1. Pre-allocated FastIO Entries
      • 7.13.2. Dynamic-size FastIO Entries
      • 7.13.3. Input- and Output-Type FastIO Entries
        • 7.13.3.1. FastIO Entry Accessors and Mutators
    • 7.14. Pipeline Stage Payload
      • 7.14.1. Input Entries
      • 7.14.2. Output Entries
      • 7.14.3. Fast I/O Context
      • 7.14.4. FastIO Input Entries
      • 7.14.5. FastIO Output Entries
    • 7.15. Pipeline Payload Entry
      • 7.15.1. Name
      • 7.15.2. Path
    • 7.16. Clara Pipeline Callbacks
      • 7.16.1. Operator Life-cycle
      • 7.16.2. Prepare
      • 7.16.3. Execute
      • 7.16.4. Cleanup
      • 7.16.5. Notification Callback
    • 7.17. Clara Pipeline Driver
      • 7.17.1. Clara Operator Life-Cycle
        • 7.17.1.1. Application Data
        • 7.17.1.2. Job Identity
        • 7.17.1.3. Job Name
        • 7.17.1.4. Stage Name
        • 7.17.1.5. Stage Timeout
        • 7.17.1.6. Start
        • 7.17.1.7. Wait for Completion
    • 7.18. Clara Pipeline Payload
      • 7.18.1. Input Entries
      • 7.18.2. Output Entries
    • 7.19. Clara Pipeline Payload Entry
      • 7.19.1. Name
      • 7.19.2. Path
  • 8. Pipeline Definition Language
    • 8.1. Clara Pipeline Definition Language Overview
      • 8.1.1. Features
        • 8.1.1.1. Pipelines
        • 8.1.1.2. Services
        • 8.1.1.3. Operators
    • 8.2. Clara Deploy SDK Pipeline Glossary
      • 8.2.1. Clara Deploy SDK PLatform
      • 8.2.2. Container
      • 8.2.3. Containerized Application
      • 8.2.4. Directed Acyclic Graph (DAG)
      • 8.2.5. Payload
      • 8.2.6. Pipeline
      • 8.2.7. Pipeline Application
      • 8.2.8. Pipeline Job
      • 8.2.9. Operator
      • 8.2.10. Service
    • 8.3. Operators
    • 8.4. Clara Types (pipeline api-version 0.5.0 and above)
    • 8.5. The Anatomy of an Operator
      • 8.5.1. Disk-based I/O
      • 8.5.2. Shared Memory I/O
    • 8.6. Argo vs. Clara Orchestration
    • 8.7. Pipelines
      • 8.7.1. A simple pipeline example
      • 8.7.2. Pipelines with Untyped Operators
      • 8.7.3. Pipelines with Typed Operators for Performance and Explicit Data Typing
        • 8.7.3.1. Implicit Semantics, Explicit Types
        • 8.7.3.2. Operator Reuse Across Pipelines
    • 8.8. Services
    • 8.9. Connections
      • 8.9.1. Properties
        • 8.9.1.1. http
    • 8.10. Container
      • 8.10.1. Properties
        • 8.10.1.1. image
        • 8.10.1.2. tag
        • 8.10.1.3. command
    • 8.11. Document
      • 8.11.1. Properties
        • 8.11.1.1. api-version
        • 8.11.1.2. description
        • 8.11.1.3. name
    • 8.12. Import
      • 8.12.1. Properties
        • 8.12.1.1. path
        • 8.12.1.2. args
      • 8.12.2. Overriding Values on Import
        • 8.12.2.1. Example
    • 8.13. Input
      • 8.13.1. Properties
        • 8.13.1.1. from
        • 8.13.1.2. name
        • 8.13.1.3. path
        • 8.13.1.4. type
        • 8.13.1.5. element-type
        • 8.13.1.6. shape
        • 8.13.1.7. Examples:
    • 8.14. Operator
      • 8.14.1. Properties
        • 8.14.1.1. api-version
        • 8.14.1.2. container
        • 8.14.1.3. description
        • 8.14.1.4. input
        • 8.14.1.5. output
        • 8.14.1.6. parameters
        • 8.14.1.7. name
        • 8.14.1.8. models
        • 8.14.1.9. requests
        • 8.14.1.10. services
        • 8.14.1.11. variables
    • 8.15. Output
      • 8.15.1. Properties
        • 8.15.1.1. name
        • 8.15.1.2. path
        • 8.15.1.3. type
        • 8.15.1.4. element-type
        • 8.15.1.5. shape
        • 8.15.1.6. Examples:
    • 8.16. Pipeline
      • 8.16.1. Properties
        • 8.16.1.1. api-version
        • 8.16.1.2. orchestrator
        • 8.16.1.3. description
        • 8.16.1.4. operators
        • 8.16.1.5. parameters
        • 8.16.1.6. name
        • 8.16.1.7. variables
    • 8.17. Requests
      • 8.17.1. Properties
        • 8.17.1.1. cpu
        • 8.17.1.2. gpu
        • 8.17.1.3. memory
    • 8.18. Service
      • 8.18.1. Properties
        • 8.18.1.1. api-version
        • 8.18.1.2. connections
        • 8.18.1.3. container
        • 8.18.1.4. description
        • 8.18.1.5. name
        • 8.18.1.6. requests
        • 8.18.1.7. variables
    • 8.19. Syntax & Grammar
      • 8.19.1. YAML Basics
        • 8.19.1.1. Scalar Value:
        • 8.19.1.2. List Value
        • 8.19.1.3. Object Value
        • 8.19.1.4. Array Value
        • 8.19.1.5. Scalar Value with New Line Character
        • 8.19.1.6. Comments
        • 8.19.1.7. Indentation and White Space Matters
      • 8.19.2. Operator Definitions
      • 8.19.3. Service Definitions
    • 8.20. Template
      • 8.20.1. Properties
        • 8.20.1.1. parameters
        • 8.20.1.2. Example:
      • 8.20.2. Placeholders
    • 8.21. Clara Structures and Primitives
      • 8.21.1. Clara Structures
      • 8.21.2. Clara Primitive Types
      • 8.21.3. Examples of Valid Declarations
    • 8.22. Variables
  • 9. Bundled Operators
    • 9.1. Clara DICOM Reader
      • 9.1.1. Requirements
      • 9.1.2. Running the DICOM Reader
    • 9.2. Clara DICOM Writer
      • 9.2.1. Requirements
      • 9.2.2. Running the DICOM Writer
    • 9.3. Clara Deploy DICOM Parser Operator
      • 9.3.1. Overview
      • 9.3.2. Inputs
      • 9.3.3. Outputs
      • 9.3.4. Directory Structure
      • 9.3.5. Parameters
      • 9.3.6. Executing Operator Locally
      • 9.3.7. Executing Operator in Docker
        • 9.3.7.1. Prerequisites
        • 9.3.7.2. Step 1
        • 9.3.7.3. Step 2
        • 9.3.7.4. Step 3
        • 9.3.7.5. Step 4
        • 9.3.7.6. Step 5
      • 9.3.8. License
      • 9.3.9. Suggested Reading
    • 9.4. Clara Deploy Base Inference Application
      • 9.4.1. Overview
        • 9.4.1.1. Version information
      • 9.4.2. Inputs
      • 9.4.3. Outputs
      • 9.4.4. AI Model
        • 9.4.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.4.5. Directory Structure
      • 9.4.6. Executing Locally
      • 9.4.7. Executing in Docker
        • 9.4.7.1. Prerequisites
        • 9.4.7.2. Step 1
        • 9.4.7.3. Step 2
        • 9.4.7.4. Step 3
        • 9.4.7.5. Step 4
        • 9.4.7.6. Step 5
      • 9.4.8. Creating Model Specific Application
        • 9.4.8.1. Prerequisites
    • 9.5. Clara AI Liver Tumor Segmentation Operator
      • 9.5.1. Overview
      • 9.5.2. Inputs
      • 9.5.3. Outputs
      • 9.5.4. AI Model
        • 9.5.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.5.5. Directory Structure
      • 9.5.6. Executing Operator Locally
      • 9.5.7. Executing Operator in Docker
        • 9.5.7.1. Prerequisites
        • 9.5.7.2. Step 1
        • 9.5.7.3. Step 2
        • 9.5.7.4. Step 3
        • 9.5.7.5. Step 4
        • 9.5.7.6. Step 5
    • 9.6. Clara Deploy SDK VNet Segmentation Operator
      • 9.6.1. Overview
      • 9.6.2. Data Input
      • 9.6.3. Data Output
      • 9.6.4. Parameters
      • 9.6.5. Dependencies
      • 9.6.6. Execution of VNet Segmentation Operator
        • 9.6.6.1. Prerequisites
        • 9.6.6.2. Step 1
        • 9.6.6.3. Step 2
        • 9.6.6.4. Step 3
        • 9.6.6.5. Step 4
        • 9.6.6.6. Step 5
    • 9.7. Clara AI Brain Tumor Segmentation Operator
      • 9.7.1. Overview
      • 9.7.2. Inputs
      • 9.7.3. Outputs
      • 9.7.4. AI Model
        • 9.7.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.7.5. Directory Structure
      • 9.7.6. Executing Operator Locally
      • 9.7.7. Executing Operator in Docker
        • 9.7.7.1. Prerequisites
        • 9.7.7.2. Step 1
        • 9.7.7.3. Step 2
        • 9.7.7.4. Step 3
        • 9.7.7.5. Step 4
        • 9.7.7.6. Step 5
    • 9.8. Clara AI Hippocampus Segmentation Operator
      • 9.8.1. Overview
      • 9.8.2. Inputs
      • 9.8.3. Outputs
      • 9.8.4. AI Model
        • 9.8.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.8.5. Directory Structure
      • 9.8.6. Executing Operator Locally
      • 9.8.7. Executing Operator in Docker
        • 9.8.7.1. Prerequisites
        • 9.8.7.2. Step 1
        • 9.8.7.3. Step 2
        • 9.8.7.4. Step 3
        • 9.8.7.5. Step 4
        • 9.8.7.6. Step 5
    • 9.9. Clara AI Spleen Segmentation
      • 9.9.1. Overview
      • 9.9.2. Inputs
      • 9.9.3. Outputs
      • 9.9.4. AI Model
        • 9.9.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.9.5. Directory Structure
      • 9.9.6. Executing Operator Locally
      • 9.9.7. Executing Operator in Docker
        • 9.9.7.1. Prerequisites
        • 9.9.7.2. Step 1
        • 9.9.7.3. Step 2
        • 9.9.7.4. Step 3
        • 9.9.7.5. Step 4
        • 9.9.7.6. Step 5
        • 9.9.7.7. Step 6
    • 9.10. Malaria Microscopy Classification Operator
      • 9.10.1. Overview
      • 9.10.2. Inputs
      • 9.10.3. Outputs
      • 9.10.4. AI Model
        • 9.10.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.10.5. Directory Structure
      • 9.10.6. Executing the Operator Locally
      • 9.10.7. Executing the Operator in Docker
        • 9.10.7.1. Prerequisites
        • 9.10.7.2. Step 1
        • 9.10.7.3. Step 2
        • 9.10.7.4. Step 3
        • 9.10.7.5. Step 4
        • 9.10.7.6. Step 5
        • 9.10.7.7. Step 6
    • 9.11. Clara AI Lung Tumor Segmentation Operator
      • 9.11.1. Overview
      • 9.11.2. Inputs
      • 9.11.3. Outputs
      • 9.11.4. AI Model
        • 9.11.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.11.5. Directory Structure
      • 9.11.6. Executing Operator Locally
      • 9.11.7. Executing Operator in Docker
        • 9.11.7.1. Prerequisites
        • 9.11.7.2. Step 1
        • 9.11.7.3. Step 2
        • 9.11.7.4. Step 3
        • 9.11.7.5. Step 4
        • 9.11.7.6. Step 5
    • 9.12. Clara AI Colon Tumor Segmentation Operator
      • 9.12.1. Overview
      • 9.12.2. Inputs
      • 9.12.3. Outputs
      • 9.12.4. AI Model
        • 9.12.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.12.5. Directory Structure
      • 9.12.6. Executing Operator Locally
      • 9.12.7. Executing Operator in Docker
        • 9.12.7.1. Prerequisites
        • 9.12.7.2. Step 1
        • 9.12.7.3. Step 2
        • 9.12.7.4. Step 3
        • 9.12.7.5. Step 4
        • 9.12.7.6. Step 5
    • 9.13. Clara AI Pancreas Tumor Segmentation
      • 9.13.1. Overview
      • 9.13.2. Inputs
      • 9.13.3. Outputs
      • 9.13.4. AI Model
        • 9.13.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.13.5. Directory Structure
      • 9.13.6. Executing Operator Locally
      • 9.13.7. Executing Operator in Docker
        • 9.13.7.1. Prerequisites
        • 9.13.7.2. Step 1
        • 9.13.7.3. Step 2
        • 9.13.7.4. Step 3
        • 9.13.7.5. Step 4
        • 9.13.7.6. Step 5
    • 9.14. Chest X-ray Classification Operator
      • 9.14.1. Overview
      • 9.14.2. Inputs
      • 9.14.3. Outputs
      • 9.14.4. AI Model
        • 9.14.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.14.5. Directory Structure
      • 9.14.6. Executing Operator Locally
      • 9.14.7. Executing Operator in Docker
        • 9.14.7.1. Prerequisites
        • 9.14.7.2. Step 1
        • 9.14.7.3. Step 2
        • 9.14.7.4. Step 3
        • 9.14.7.5. Step 4
        • 9.14.7.6. Step 5
        • 9.14.7.7. Step 6
    • 9.15. Breast Microscopy Classification Operator
      • 9.15.1. Overview
      • 9.15.2. Inputs
      • 9.15.3. Outputs
      • 9.15.4. AI Model
        • 9.15.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.15.5. Directory Structure
      • 9.15.6. Executing the Operator Locally
      • 9.15.7. Executing the Operator in Docker
        • 9.15.7.1. Prerequisites
        • 9.15.7.2. Step 1
        • 9.15.7.3. Step 2
        • 9.15.7.4. Step 3
        • 9.15.7.5. Step 4
        • 9.15.7.6. Step 5
        • 9.15.7.7. Step 6
    • 9.16. Clara AI Prostate Segmentation
      • 9.16.1. Overview
      • 9.16.2. Inputs
      • 9.16.3. Outputs
      • 9.16.4. AI Model
        • 9.16.4.1. NVIDIA TensorRT Inference Server (TRTIS)
      • 9.16.5. Directory Structure
      • 9.16.6. Executing Operator Locally
      • 9.16.7. Executing Operator in Docker
        • 9.16.7.1. Prerequisites
        • 9.16.7.2. Step 1
        • 9.16.7.3. Step 2
        • 9.16.7.4. Step 3
        • 9.16.7.5. Step 4
        • 9.16.7.6. Step 5
        • 9.16.7.7. Step 6
    • 9.17. CT Recon Operator
      • 9.17.1. Overview
      • 9.17.2. Data Input
      • 9.17.3. Data Output
      • 9.17.4. Parameters
      • 9.17.5. Dependencies
      • 9.17.6. Directory Structure
      • 9.17.7. Optimization
    • 9.18. Clara Register Results
      • 9.18.1. Requirements/Dependencies
      • 9.18.2. Source Code & Pipeline Example
      • 9.18.3. Inputs
      • 9.18.4. Outputs
      • 9.18.5. Directory Structure
      • 9.18.6. Executing the Operator Within a Container
        • 9.18.6.1. Steps
        • 9.18.6.2. Example
    • 9.19. Clara Genomics Analysis
      • 9.19.1. Overview
        • 9.19.1.1. Components in the toolset:
        • 9.19.1.2. 3rd party tools:
      • 9.19.2. Directory Structure
    • 9.20. FastIO-ITK Operator
      • 9.20.1. Overview
      • 9.20.2. Commands
        • 9.20.2.1. read_volume
        • 9.20.2.2. filter_volume
        • 9.20.2.3. write_volume
    • 9.21. DICOM RTSTRUCT Writer Operator
      • 9.21.1. Overview
      • 9.21.2. Inputs
      • 9.21.3. Outputs
      • 9.21.4. Directory Structure
      • 9.21.5. Executing the Operator Locally
      • 9.21.6. Executing Operator in Docker
        • 9.21.6.1. Prerequisites
        • 9.21.6.2. Step 1
        • 9.21.6.3. Step 2
        • 9.21.6.4. Step 3
        • 9.21.6.5. Step 4
        • 9.21.6.6. Step 5
        • 9.21.6.7. Step 6
    • 9.22. Clara FastIO Variable Passthrough - Nifti to FastIO Variable Conveter Operator
      • 9.22.1. Overview
      • 9.22.2. Inputs
      • 9.22.3. Outputs
      • 9.22.4. Directory Structure
      • 9.22.5. License
      • 9.22.6. Suggested Reading
    • 9.23. Clara FastIO Variable Passthrough - Fastio to Npz Converter Operator
      • 9.23.1. Overview
      • 9.23.2. Inputs
      • 9.23.3. Outputs
      • 9.23.4. Directory Structure
      • 9.23.5. License
      • 9.23.6. Suggested Reading
    • 9.24. Clara FastIO Variable Passthrough - Compare Operator
      • 9.24.1. Overview
      • 9.24.2. Inputs
      • 9.24.3. Outputs
      • 9.24.4. Directory Structure
      • 9.24.5. License
      • 9.24.6. Suggested Reading
    • 9.25. DeepStream App Operator
      • 9.25.1. Quick Start
      • 9.25.2. Inputs & Outputs
      • 9.25.3. Sample AI model (Organ Object Detector)
    • 9.26. Digital Pathology Image Processing Operator
      • 9.26.1. Overview
      • 9.26.2. Commands
        • 9.26.2.1. process_image_no
        • 9.26.2.2. tile_image_jpg
        • 9.26.2.3. tile_image_jpg_chunk
        • 9.26.2.4. tile_image_zarr
        • 9.26.2.5. filter_image_jpg_serial
        • 9.26.2.6. filter_image_jpg_multithreading
        • 9.26.2.7. filter_image_jpg_multiprocessing
        • 9.26.2.8. filter_image_jpg_dali
        • 9.26.2.9. filter_image_jpg_dali_chunk
        • 9.26.2.10. filter_image_zarr
        • 9.26.2.11. stitch_image_jpg
        • 9.26.2.12. stitch_image_jpg_chunk
        • 9.26.2.13. stitch_image_zarr
    • 9.27. Clara Deploy AI Lung Segmentation Operator
      • 9.27.1. Overview
      • 9.27.2. Inputs
      • 9.27.3. Outputs
      • 9.27.4. AI Model
        • 9.27.4.1. NVIDIA Triton Inference Server (formerly known as TRTIS)
      • 9.27.5. Directory Structure
      • 9.27.6. Executing Operator Locally
      • 9.27.7. Executing Operator in Docker
        • 9.27.7.1. Prerequisites
        • 9.27.7.2. Step 1
        • 9.27.7.3. Step 2
        • 9.27.7.4. Step 3
        • 9.27.7.5. Step 4
        • 9.27.7.6. Step 5
        • 9.27.7.7. Step 6
      • 9.27.8. License
      • 9.27.9. Suggested Reading
    • 9.28. Clara Deploy AI COVID-19 Classification Operator
      • 9.28.1. Overview
      • 9.28.2. Inputs
      • 9.28.3. Outputs
      • 9.28.4. AI Model
        • 9.28.4.1. NVIDIA Triton Inference Server (formerly known as TRTIS)
      • 9.28.5. Directory Structure
      • 9.28.6. Executing Operator Locally
      • 9.28.7. Executing Operator in Docker
        • 9.28.7.1. Prerequisites
        • 9.28.7.2. Step 1
        • 9.28.7.3. Step 2
        • 9.28.7.4. Step 3
        • 9.28.7.5. Step 4
        • 9.28.7.6. Step 5
      • 9.28.8. License
      • 9.28.9. Suggested Reading
    • 9.29. Clara Deploy Series Selector
      • 9.29.1. Overview
      • 9.29.2. Inputs
      • 9.29.3. Outputs
      • 9.29.4. Directory Structure
      • 9.29.5. Executing Operator in Docker
        • 9.29.5.1. Prerequisites
        • 9.29.5.2. Step 1
        • 9.29.5.3. Step 2
        • 9.29.5.4. Step 3
        • 9.29.5.5. Step 4
        • 9.29.5.6. Step 5
      • 9.29.6. Executing Operator Locally
      • 9.29.7. Customizing Series Matching Rules
    • 9.30. Copy customized rules file overwriting the default one.
      • 9.30.1. License
      • 9.30.2. Suggested Reading
    • 9.31. Clara Deploy Base Inference Operator V2
      • 9.31.1. Overview
        • 9.31.1.1. Version information
      • 9.31.2. Inputs
      • 9.31.3. Outputs
      • 9.31.4. AI Model
        • 9.31.4.1. NVIDIA Triton Inference Server
      • 9.31.5. Directory Structure
      • 9.31.6. Executing Locally
      • 9.31.7. Executing in Docker
        • 9.31.7.1. Prerequisites
        • 9.31.7.2. Step 1
        • 9.31.7.3. Step 2
        • 9.31.7.4. Step 3
        • 9.31.7.5. Step 4
        • 9.31.7.6. Step 5
      • 9.31.8. Creating Model Specific Application
        • 9.31.8.1. Prerequisites
        • 9.31.8.2. Steps
      • 9.31.9. License
      • 9.31.10. Suggested Reading
    • 9.32. Digital Pathology Nuclei Segmentation Operator
      • 9.32.1. Overview
      • 9.32.2. Commands
        • 9.32.2.1. segmentation
    • 9.33. Clara Deploy DICOM Segmentation Writer Operator
      • 9.33.1. Overview
      • 9.33.2. Inputs
      • 9.33.3. Outputs
      • 9.33.4. Directory Structure
      • 9.33.5. Executing the Operator Docker Image
        • 9.33.5.1. Prerequisites
        • 9.33.5.2. Step 1
        • 9.33.5.3. Step 2
        • 9.33.5.4. Step 3
        • 9.33.5.5. Step 4
        • 9.33.5.6. Step 5
        • 9.33.5.7. Step 6
      • 9.33.6. Executing the Operator Docker Image Interactively
      • 9.33.7. License
      • 9.33.8. Suggested Reading
  • 10. User Defined Operators
    • 10.1. Clara Deploy Operator Development Guide
      • 10.1.1. Role of an Operator in Clara Deploy
      • 10.1.2. Building and Testing Application Container Image
      • 10.1.3. Publishing an Application Docker Image
      • 10.1.4. Uploading AI Models
      • 10.1.5. Creating and Testing Pipelines
    • 7.1. Clara Pipeline Driver Overview
      • 7.1.1. Fast I/O: Shared Memory Data Exchange Between Operators
        • 7.1.1.1. Fast I/O Contexts and Allocations
        • 7.1.1.2. Fast I/O Variables
      • 7.1.2. Python Client
      • 7.1.3. Native Client
    • 10.2. Debugging Operator
      • 10.2.1. Remote Debugging Python Application with VSCode
  • 11. Bundled Pipelines
    • 11.1. Liver Segmentation Pipeline
      • 11.1.1. Pipeline Definition
      • 11.1.2. Executing the Pipeline
    • 11.2. CT Reconstruction Pipeline
      • 11.2.1. Overview
      • 11.2.2. Data
      • 11.2.3. Operators
      • 11.2.4. Execution of Reconstruction docker
        • 11.2.4.1. Reconstruction Operator Docker Image
      • 11.2.5. Execute of Reconstruction Pipeline within Clara
        • 11.2.5.1. Execution Steps on Clara Platform
        • 11.2.5.2. Check Job Status and Download/View Payloads in Clara Console/Dashboard
        • 11.2.5.3. Download and Verify the Outputs
      • 11.2.6. CT Recon Perf pipeline
      • 11.2.7. CT Recon Liver segmentation pipeline
    • 11.3. Multi AI Pipeline
      • 11.3.1. Overview
      • 11.3.2. Data
      • 11.3.3. Execution Steps on Clara Platform
    • 11.4. Vnet Segmentation pipeline
      • 11.4.1. Overview
      • 11.4.2. Data
      • 11.4.3. Operators
    • 11.5. Clara AI Brain Tumor Segmentation Pipeline
      • 11.5.1. Pipeline Definition
      • 11.5.2. Executing the Pipeline
    • 11.6. Hippocampus Segmentation Pipeline
      • 11.6.1. Pipeline Definition
      • 11.6.2. Executing the Pipeline
    • 11.7. Spleen Segmentation Pipeline
      • 11.7.1. Pipeline Definition
      • 11.7.2. Executing the Pipeline
    • 11.8. Malaria Microscopy Classification Pipeline
      • 11.8.1. Pipeline Definition
      • 11.8.2. Executing the Pipeline
    • 11.9. Lung Tumor Segmentation Pipeline
      • 11.9.1. Pipeline Definition
      • 11.9.2. Executing the Pipeline
    • 11.10. Colon Tumor Segmentation Pipeline
      • 11.10.1. Pipeline Definition
      • 11.10.2. Executing the Pipeline
    • 11.11. Pancreas Tumor Segmentation Pipeline
      • 11.11.1. Pipeline Definition
      • 11.11.2. Executing the Pipeline
    • 11.12. Chest X-ray Classification Pipeline
      • 11.12.1. Pipeline Definition
      • 11.12.2. Executing the Pipeline
    • 11.13. Breast Pathology Image Classification Pipeline
      • 11.13.1. Pipeline Definition
      • 11.13.2. Executing the Pipeline
    • 11.14. Clara AI Prostate Segmentation Pipeline
      • 11.14.1. Pipeline Definition
      • 11.14.2. Executing the Pipeline
    • 11.15. De Novo Sequence Assembly - Clara Genomics Analysis
      • 11.15.1. Pipeline Definition
      • 11.15.2. Executing the Pipeline
      • 11.15.3. Data Input
      • 11.15.4. Data Output
    • 11.16. 3D Image Processing Pipeline using FastIO
      • 11.16.1. Pipeline Definition
      • 11.16.2. Executing the Pipeline
      • 11.16.3. Data Input
      • 11.16.4. Data Output
      • 11.16.5. Viewing the Output Volume Image
    • 11.17. FastIO Passthrough Pipeline Using FastIO Variable API
      • 11.17.1. Pipeline Definition
      • 11.17.2. Data Input
      • 11.17.3. Data Output
      • 11.17.4. Executing the Pipeline
      • 11.17.5. Check Job Status and Download/View Payloads in Clara Console/Dashboard
      • 11.17.6. Download and Verify the Outputs
    • 11.18. Suggested Reading
    • 11.19. DeepStream Batch Pipeline
      • 11.19.1. Pipeline Definition
      • 11.19.2. Executing the Pipeline
      • 11.19.3. Data Input
      • 11.19.4. Data Output
      • 11.19.5. Viewing the Output Video
      • 11.19.6. Performance Implications
    • 11.20. Digital Pathology Image Processing Pipeline
      • 11.20.1. Pipeline Definition
        • 11.20.1.1. dp-sample-pipeline-no-optimization.yaml
        • 11.20.1.2. dp-sample-pipeline.yaml
      • 11.20.2. Executing the Pipeline
      • 11.20.3. Data Input
      • 11.20.4. Data Output
      • 11.20.5. Viewing the Output Volume Image
    • 11.21. Clara Deploy AI COVID-19 Classification Pipeline
      • 11.21.1. Pipeline Definition
      • 11.21.2. Executing the Pipeline
      • 11.21.3. License
      • 11.21.4. Suggested Reading
    • 11.22. Clara Deploy DICOM Series Selection Pipeline
      • 11.22.1. Overview
      • 11.22.2. Pipeline Definition
      • 11.22.3. Executing the Pipeline
      • 11.22.4. License
      • 11.22.5. Suggested Reading
    • 11.23. Digital Pathology Nuclei Segmentation Pipeline
      • 11.23.1. Pipeline Definition
        • 11.23.1.1. dp-nuclei-segmentation-pipeline.yaml
      • 11.23.2. Executing the Pipeline
      • 11.23.3. Data Input
      • 11.23.4. Data Output
      • 11.23.5. Viewing the Output Volume Image
  • 12. User Defined Pipelines
    • 12.1. Build Custom Operators
    • 12.2. Place AI Model Files in the Right Directory
    • 12.3. Start With a Reference Pipeline
    • 12.4. Modify the Pipeline
    • 12.5. External DICOM Sender and DICOM Receiver
      • 12.5.1. Install dcmtk
      • 12.5.2. Setup an External DICOM Receiver
      • 12.5.3. Setup an External DICOM Sender
    • 12.6. Create the Pipeline
    • 12.7. Configure the Clara DICOM Destination
    • 12.8. Trigger Pipeline
    • 12.9. Verify the Pipeline Execution in the Dashboard
    • 12.10. Verify the External DICOM Receiver Received the Images
  • 13. Bundled Services
    • 13.1. DICOM Adapter
      • 13.1.1. Introduction
        • 13.1.1.1. Requirements
        • 13.1.1.2. Usages
        • 13.1.1.3. DICOM Interface
        • 13.1.1.4. Changelog
        • 13.1.1.5. Third Party Tools
      • 13.1.2. Setup
        • 13.1.2.1. Install Clara DICOM Adapter Helm Chart
        • 13.1.2.2. Running the Clara DICOM Adapter
        • 13.1.2.3. Configuration
      • 13.1.3. APIs
        • 13.1.3.1. RESTful APIs
      • 13.1.4. References
        • 13.1.4.1. Configuration Schema
    • 13.2. Clara Results Service
      • 13.2.1. Cleanup Service
      • 13.2.2. Task States
      • 13.2.3. Definitions
      • 13.2.4. Requirements
      • 13.2.5. Running the Results Service
        • 13.2.5.1. Run the Results Service
      • 13.2.6. API Usage
        • 13.2.6.1. POST /api/tasks/register/[agent-name]
        • 13.2.6.2. GET /api/tasks/[agent-name]/[state]
        • 13.2.6.3. PUT /api/tasks/success/[taskId]
        • 13.2.6.4. PUT /api/tasks/failure/[taskId]
      • 13.2.7. Database
      • 13.2.8. License
        • 13.2.8.1. Third Party Licenses
    • 13.3. Clara Dashboard Render Service
      • 13.3.1. Getting Started
        • 13.3.1.1. Minimum Requirement
        • 13.3.1.2. Starting the Service
      • 13.3.2. Basic Interface
        • 13.3.2.1. Notifications
        • 13.3.2.2. Navigation Menu
        • 13.3.2.3. Application Menu
      • 13.3.3. Render Service Interface
        • 13.3.3.1. Live Stream Interactions
      • 13.3.4. Dataset Service File Format
        • 13.3.4.1. Meta File
        • 13.3.4.2. JSON File
      • 13.3.5. Camera Tab
      • 13.3.6. Transfer Function Tab
        • 13.3.6.1. Histogram
        • 13.3.6.2. Regions
        • 13.3.6.3. Components
        • 13.3.6.4. Globals
      • 13.3.7. Volume Crop Tab
      • 13.3.8. Info Tab
      • 13.3.9. Help Tab
    • 13.4. Clara Management Console
      • 13.4.1. Getting Started
        • 13.4.1.1. Minimum Requirement
        • 13.4.1.2. Starting the Service
      • 13.4.2. Basic Interface
        • 13.4.2.1. Navigation Menu
        • 13.4.2.2. Pipelines View
      • 13.4.3. Jobs View
      • 13.4.4. Job Details View
  • 14. Connectivity With a PACS/DICOM Server
    • 14.1. Configuring the DICOM Adapter to Receive Images
    • 14.2. Configuring the DICOM Adapter to Send Images
    • 14.3. Troubleshooting Connectivity
      • 14.3.1. Q: Clara is not receiving data from PACS or other DICOM-enabled devices
      • 14.3.2. Q: Clara is receiving DICOM data but not launching a new job
      • 14.3.3. Q: Results are not delivered to PACS or other DICOM-enabled devices
  • 15. Clara CLI
    • 15.1. Overview of clara
      • 15.1.1. Syntax
      • 15.1.2. Actions
      • 15.1.3. Commands
      • 15.1.4. Resource Types
      • 15.1.5. Examples: Common Operations
      • 15.1.6. Plugins
        • 15.1.6.1. Examples: Creating and Using Plugins
        • 15.1.6.2. Examples: Using the clara-platform plugin
        • 15.1.6.3. Examples: Using the clara-dicom plugin
        • 15.1.6.4. Examples: Using the clara-render plugin
        • 15.1.6.5. Examples: Using the clara-pull plugin
    • 15.2. Clara Deploy SDK Configuration
      • 15.2.1. Structure
      • 15.2.2. config.yaml
      • 15.2.3. Pointing to a remote host
    • 15.3. Getting Started
      • 15.3.1. create model
        • 15.3.1.1. Usage
        • 15.3.1.2. Flags
      • 15.3.2. list model
        • 15.3.2.1. Usage
        • 15.3.2.2. Flags
      • 15.3.3. delete models
        • 15.3.3.1. Usage
        • 15.3.3.2. Arguments
      • 15.3.4. create job
        • 15.3.4.1. Usage
        • 15.3.4.2. Flags
      • 15.3.5. start job
        • 15.3.5.1. Usage
        • 15.3.5.2. Flags
      • 15.3.6. create pipelines
        • 15.3.6.1. Usage
        • 15.3.6.2. Flags
      • 15.3.7. list pipelines
        • 15.3.7.1. Usage
        • 15.3.7.2. Flags
      • 15.3.8. describe pipeline
        • 15.3.8.1. Usage
        • 15.3.8.2. Flags
      • 15.3.9. list jobs
        • 15.3.9.1. Usage
        • 15.3.9.2. Flags
      • 15.3.10. cancel jobs
        • 15.3.10.1. Usage
        • 15.3.10.2. Flags
        • 15.3.10.3. Arguments
      • 15.3.11. delete payloads
        • 15.3.11.1. Usage
        • 15.3.11.2. Arguments
      • 15.3.12. download
        • 15.3.12.1. Usage
        • 15.3.12.2. Arguments
      • 15.3.13. describe job
        • 15.3.13.1. Usage
        • 15.3.13.2. Flags
      • 15.3.14. config
        • 15.3.14.1. Usage
        • 15.3.14.2. Flags
      • 15.3.15. logs (deprecated)
        • 15.3.15.1. Usage
        • 15.3.15.2. Available Containers
        • 15.3.15.3. Flags
      • 15.3.16. version
        • 15.3.16.1. Usage
    • 15.4. Extending clara with Plugins
      • 15.4.1. Before you begin
      • 15.4.2. Installing clara plugins
        • 15.4.2.1. Limitations
      • 15.4.3. Writing clara plugins
      • 15.4.4. Example plugin
      • 15.4.5. Using a plugin
      • 15.4.6. Naming a plugin
      • 15.4.7. Flags and argument handling
      • 15.4.8. Names with dashes and underscores
      • 15.4.9. Uninstalling a plugin
    • 15.5. clara-render Plugin
      • 15.5.1. start
        • 15.5.1.1. Usage
      • 15.5.2. restart
        • 15.5.2.1. Usage
      • 15.5.3. stop
        • 15.5.3.1. Usage
    • 15.6. clara-dicom Plugin
      • 15.6.1. start
        • 15.6.1.1. Usage
      • 15.6.2. Flags
      • 15.6.3. restart
        • 15.6.3.1. Usage
      • 15.6.4. stop
        • 15.6.4.1. Usage
      • 15.6.5. logs (deprecated)
        • 15.6.5.1. Usage
  • 16. Load Generator
    • 16.1. Pipeline Load Generator CLI (cpload)
      • 16.1.1. Requirement:
      • 16.1.2. Syntax:
        • 16.1.2.1. generate subcommand
        • 16.1.2.2. target subcommand
  • 17. Platform API
    • 17.1. Clara Deploy SDK API Overview
      • 17.1.1. Concepts
        • 17.1.1.1. Services
      • 17.1.2. Clara Service
      • 17.1.3. Jobs Service
      • 17.1.4. Models Service
      • 17.1.5. Payloads Service
      • 17.1.6. Pipelines Service
        • 17.1.6.1. Examples
      • 17.1.7. Create a New Pipeline
      • 17.1.8. Get a List of Existing Pipelines
      • 17.1.9. Create and Start a Job
      • 17.1.10. Get Status of a Job
      • 17.1.11. Get a File Listing from a Payload
      • 17.1.12. Download a File from a Payload
        • 17.1.12.1. Useful Links
      • 17.1.13. Introduction to GRPC and Protobuf
      • 17.1.14. GRPC Examples
    • 17.2. Clara Stop RPC
    • 17.3. ClaraStopRequest
      • 17.3.1. Properties
        • 17.3.1.1. header
    • 17.4. ClaraStopResponse
      • 17.4.1. Properties
        • 17.4.1.1. header
    • 17.5. Clara Version RPC
    • 17.6. ClaraVersionRequest
      • 17.6.1. Properties
        • 17.6.1.1. header
    • 17.7. ClaraVersionResponse
      • 17.7.1. Properties
        • 17.7.1.1. header
        • 17.7.1.2. version
    • 17.8. Pipelines Create RPC
      • 17.8.1. Types
    • 17.9. PipelinesCreateRequest
      • 17.9.1. Properties
        • 17.9.1.1. header
        • 17.9.1.2. definition
    • 17.10. PipelinesCreateResponse
      • 17.10.1. Properties
        • 17.10.1.1. header
        • 17.10.1.2. pipeline_id
    • 17.11. Pipelines Details RPC
      • 17.11.1. Messages
    • 17.12. PipelinesDetailsRequest
      • 17.12.1. Properties
        • 17.12.1.1. header
        • 17.12.1.2. pipeline_id
    • 17.13. PipelinesDetailsResponse
      • 17.13.1. Properties
        • 17.13.1.1. header
        • 17.13.1.2. pipeline_id
        • 17.13.1.3. name
        • 17.13.1.4. definition
    • 17.14. Pipelines List RPC
      • 17.14.1. Messages
    • 17.15. PipelinesListRequest
      • 17.15.1. Properties
        • 17.15.1.1. header
    • 17.16. PipelinesListResponse
      • 17.16.1. Properties
        • 17.16.1.1. header
        • 17.16.1.2. details
    • 17.17. PipelineDetails
      • 17.17.1. Properties
        • 17.17.1.1. pipeline_id
        • 17.17.1.2. name
    • 17.18. Pipelines Remove RPC
    • 17.19. PipelinesRemoveRequest
      • 17.19.1. Properties
        • 17.19.1.1. header
        • 17.19.1.2. pipeline_id
    • 17.20. PipelinesRemoveResponse
      • 17.20.1. Properties
        • 17.20.1.1. header
    • 17.21. Pipelines Update RPC
      • 17.21.1. Messages
    • 17.22. PipelinesUpdateRequest
      • 17.22.1. Properties
        • 17.22.1.1. header
        • 17.22.1.2. pipeline_id
        • 17.22.1.3. definition
    • 17.23. PipelinesUpdateResponse
      • 17.23.1. Properties
        • 17.23.1.1. header
    • 17.24. PipelineDefinitionFile
      • 17.24.1. Properties
        • 17.24.1.1. content
    • 17.25. Jobs Cancel RPC
      • 17.25.1. Messages
    • 17.26. JobsCancelRequest
      • 17.26.1. Properties
        • 17.26.1.1. header
        • 17.26.1.2. job_id
        • 17.26.1.3. reason
    • 17.27. JobsCancelResponse
      • 17.27.1. Properties
        • 17.27.1.1. header
        • 17.27.1.2. job_id
        • 17.27.1.3. job_state
        • 17.27.1.4. job_status
    • 17.28. Jobs Create RPC
      • 17.28.1. Messages
    • 17.29. JobsCreateRequest
      • 17.29.1. Properties
        • 17.29.1.1. header
        • 17.29.1.2. pipeline_id
        • 17.29.1.3. name
        • 17.29.1.4. priority
        • 17.29.1.5. input_payloads
    • 17.30. JobsCreateResponse
      • 17.30.1. Properties
        • 17.30.1.1. header
        • 17.30.1.2. job_id
        • 17.30.1.3. payload_id
    • 17.31. Jobs List RPC
      • 17.31.1. Messages
    • 17.32. JobsListRequest
      • 17.32.1. Properties
        • 17.32.1.1. header
        • 17.32.1.2. filter
    • 17.33. JobsListResponse
      • 17.33.1. Properties
        • 17.33.1.1. header
        • 17.33.1.2. job_details
    • 17.34. Jobs ReadLogs RPC
      • 17.34.1. Messages
    • 17.35. JobsReadLogsRequest
      • 17.35.1. Properties
        • 17.35.1.1. header
        • 17.35.1.2. job_id
        • 17.35.1.3. operator_name
    • 17.36. JobsReadLogsResponse
      • 17.36.1. Properties
        • 17.36.1.1. header
        • 17.36.1.2. job_id
        • 17.36.1.3. operator_name
        • 17.36.1.4. logs
    • 17.37. Jobs Start RPC
      • 17.37.1. Messages
    • 17.38. JobsStartRequest
      • 17.38.1. Properties
        • 17.38.1.1. header
        • 17.38.1.2. job_id
    • 17.39. JobsStartResponse
      • 17.39.1. Properties
        • 17.39.1.1. header
        • 17.39.1.2. state
        • 17.39.1.3. status
    • 17.40. NamedValue
      • 17.40.1. Properties
        • 17.40.1.1. name
        • 17.40.1.2. value
    • 17.41. Jobs Status RPC
      • 17.41.1. Messages
    • 17.42. JobsStatusRequest
      • 17.42.1. Properties
        • 17.42.1.1. header
        • 17.42.1.2. job_id
    • 17.43. JobsStatusResponse
      • 17.43.1. Properties
        • 17.43.1.1. header
        • 17.43.1.2. pipeline_id
        • 17.43.1.3. payload_id
        • 17.43.1.4. state
        • 17.43.1.5. status
        • 17.43.1.6. name
        • 17.43.1.7. priority
        • 17.43.1.8. created
        • 17.43.1.9. started
        • 17.43.1.10. stopped
        • 17.43.1.11. operator_details
        • 17.43.1.12. messages
    • 17.44. JobsDetails
      • 17.44.1. Properties
        • 17.44.1.1. job_id
        • 17.44.1.2. payload_id
        • 17.44.1.3. pipeline_id
        • 17.44.1.4. job_name
        • 17.44.1.5. state
        • 17.44.1.6. status
        • 17.44.1.7. priority
        • 17.44.1.8. created
        • 17.44.1.9. started
        • 17.44.1.10. stopped
    • 17.45. JobFilter
      • 17.45.1. Properties
        • 17.45.1.1. completed_before
        • 17.45.1.2. created_after
        • 17.45.1.3. has_state
        • 17.45.1.4. has_status
        • 17.45.1.5. pipeline_id
    • 17.46. JobOperatorDetails
      • 17.46.1. Properties
        • 17.46.1.1. name
        • 17.46.1.2. status
        • 17.46.1.3. created
        • 17.46.1.4. started
        • 17.46.1.5. stopper
    • 17.47. JobOperatorStatus
    • 17.48. JobPriority
    • 17.49. JobState
    • 17.50. JobStatus
    • 17.51. Payloads Create RPC
      • 17.51.1. Messages
    • 17.52. PayloadsCreateRequest
      • 17.52.1. Properties
        • 17.52.1.1. header
        • 17.52.1.2. PayloadsCreateResponse
      • 17.52.2. Properties
        • 17.52.2.1. header
        • 17.52.2.2. payload_id
        • 17.52.2.3. type
    • 17.53. Payloads Details RPC
      • 17.53.1. Messages
    • 17.54. PayloadsDetailsRequest
      • 17.54.1. Properties
        • 17.54.1.1. header
        • 17.54.1.2. payload_id
    • 17.55. PayloadsDetailsResponse
      • 17.55.1. Properties
        • 17.55.1.1. header
        • 17.55.1.2. payload_id
        • 17.55.1.3. file
    • 17.56. Payloads Download RPC
      • 17.56.1. Messages
    • 17.57. PayloadsDownloadRequest
    • 17.58. PayloadsDownloadResponse
      • 17.58.1. Properties
        • 17.58.1.1. header
        • 17.58.1.2. details
        • 17.58.1.3. data
    • 17.59. Payloads Create RPC
      • 17.59.1. Messages
    • 17.60. PayloadsCreateRequest
      • 17.60.1. Properties
        • 17.60.1.1. header
        • 17.60.1.2. PayloadsCreateResponse
      • 17.60.2. Properties
        • 17.60.2.1. header
        • 17.60.2.2. payload_id
        • 17.60.2.3. type
    • 17.61. Payloads Upload RPC
      • 17.61.1. Messages
    • 17.62. PayloadsUploadRequest
      • 17.62.1. Properties
        • 17.62.1.1. header
        • 17.62.1.2. payload_id
        • 17.62.1.3. details
        • 17.62.1.4. data
    • 17.63. PayloadsUploadResponse
      • 17.63.1. Properties
        • 17.63.1.1. details
    • 17.64. PayloadFileDetails Message
      • 17.64.1. Properties
        • 17.64.1.1. mode
        • 17.64.1.2. size
    • 17.65. PayloadType
    • 17.66. RPC Error Codes
      • 17.66.1. Pipeline Service Errors
        • 17.66.1.1. Invalid Pipeline ID
        • 17.66.1.2. Missing/Invalid Pipeline
        • 17.66.1.3. Pipeline Store Error
        • 17.66.1.4. Pipeline List Error
        • 17.66.1.5. Pipeline Update Error
        • 17.66.1.6. Pipeline Definition Error
        • 17.66.1.7. Pipeline Load Error
      • 17.66.2. Jobs Service Errors
        • 17.66.2.1. Invalid Job ID
        • 17.66.2.2. Missing/Invalid Job
        • 17.66.2.3. Job Store Error
        • 17.66.2.4. Jobs List Error
        • 17.66.2.5. Invalid Job Name
        • 17.66.2.6. Invalid Job Variable
        • 17.66.2.7. Create Payload Failed
        • 17.66.2.8. Job Start Error
        • 17.66.2.9. Job Cancel Error
      • 17.66.3. Payloads Service Errors
        • 17.66.3.1. Invalid Payload ID
        • 17.66.3.2. Missing/Invalid Payload
        • 17.66.3.3. Missing File
        • 17.66.3.4. Delete Contents Failure
        • 17.66.3.5. Payload Details Failure
        • 17.66.3.6. Download File Failure
        • 17.66.3.7. Upload File Failure
        • 17.66.3.8. Payload Delete Failure
    • 17.67. Identifier
      • 17.67.1. Properties
        • 17.67.1.1. value
    • 17.68. RequestHeader
      • 17.68.1. Properties
        • 17.68.1.1. api_version
        • 17.68.1.2. user_agent
    • 17.69. ResponseHeader
      • 17.69.1. Properties
        • 17.69.1.1. code
        • 17.69.1.2. messages
    • 17.70. Timestamp
      • 17.70.1. Properties
        • 17.70.1.1. value
    • 17.71. Version
      • 17.71.1. Properties
        • 17.71.1.1. major
        • 17.71.1.2. minor
        • 17.71.1.3. patch
        • 17.71.1.4. label
  • 18. Metrics Platform
    • 18.1. Overview of the Clara Monitoring Platform
    • 18.2. Getting Started
    • 18.3. Viewing Results in Grafana
    • 18.4. Creating New Pipelines
  • 19. Third Party Tools
    • 19.1. Orthanc
      • 19.1.1. Overview
      • 19.1.2. How to Install
    • 19.2. DCM4CHE
      • 19.2.1. Overview
      • 19.2.2. How to Install
    • 19.3. 3D Slicer
      • 19.3.1. Overview
      • 19.3.2. How to Install
    • 19.4. OHIF Viewer
      • 19.4.1. Overview
      • 19.4.2. How to Install
    • 19.5. Oviyam
      • 19.5.1. Overview
      • 19.5.2. How to Install
    • 19.6. Horos
      • 19.6.1. Overview
      • 19.6.2. How to Install
  • 20. Open Source Software
  • 21. Release Notes
    • 21.1. Version 0.7.1 (R7)
      • 21.1.1. Introduction
        • 21.1.1.1. What’s New
      • 21.1.2. Issues Fixed and Enhancements
        • 21.1.2.1. DICOM Parser generated image slices may be out of order
        • 21.1.2.2. DICOM RT STRUCT Writer output misaligned
        • 21.1.2.3. Pipeline job operators and services no longer have access to unassigned GPU resources
      • 21.1.3. Breaking Changes
        • 21.1.3.1. Configuration availableGpus no longer affects Platform Server
        • 21.1.3.2. Pipeline operators and services that need GPU resources must specify GPU resource requirements
      • 21.1.4. Known Issues
        • 21.1.4.1. Render Server fails to start on A100 GPU
        • 21.1.4.2. nvidia-smi command inside the container may not work in KVM
        • 21.1.4.3. Register results with multi AI + shared memory
        • 21.1.4.4. Pipeline jobs which require more GPU resources than are available in the cluster are unable to be executed
        • 21.1.4.5. Clara Orchestrator pipeline operator run times are incorrectly reported
        • 21.1.4.6. Job status for jobs using Argo orchestrator is incorrectly reported
        • 21.1.4.7. Job status for jobs using Clara Orchestrator without CPDriver is incorrectly reported
        • 21.1.4.8. Failure to cancel downloading the operators/jobs payload
    • 21.2. Version 0.6.1 (R6)
      • 21.2.1. Introduction
      • 21.2.2. What’s New
        • 21.2.2.1. Reference Pipeline: Implementation Update for the Digital Pathology Pipeline
        • 21.2.2.2. Reference Pipeline: Implementation Update for the Multi-AI Pipeline
        • 21.2.2.3. Clara Deploy GPU Profiling Tool
        • 21.2.2.4. Reference Operator: New Base AI Inference Operator
        • 21.2.2.5. Render Server: Area Measurement
        • 21.2.2.6. Clara Console: Details for a Job
        • 21.2.2.7. DICOM Adapter CLI
        • 21.2.2.8. Clara Platform Server: Pod Cleaners and Job Controllers
      • 21.2.3. Issues Fixed and Enhancements
        • 21.2.3.1. Reference Operator DICOM Parser does not support DICOM files .DCM extension
        • 21.2.3.2. Reference Operator DICOM Parser does not extract Series Description tag
        • 21.2.3.3. Helm 2.15.2 upgrade
      • 21.2.4. Breaking Changes
        • 21.2.4.1. DICOM Adapter
    • 21.3. Version 0.6.0 (R6)
      • 21.3.1. Introduction
      • 21.3.2. What’s New
        • 21.3.2.1. Reference Pipeline: Detection of COVID-19 in CT datasets
        • 21.3.2.2. Reference Pipeline: Usage of Shared Memory in Multi-AI CT Pipeline
        • 21.3.2.3. Reference Operator: DICOM Parser Operator
        • 21.3.2.4. Reference Pipeline: Digital Pathology
        • 21.3.2.5. Reference Pipeline: DICOM Series Selection Pipeline
        • 21.3.2.6. Render Server: Visualization of Multi-Resolution Data
        • 21.3.2.7. Render Server: Supporting Color Data Type
        • 21.3.2.8. Render Server: Static Scale
        • 21.3.2.9. Render Server: Distance Measurement
        • 21.3.2.10. Render Server: Picture-in-Picture
        • 21.3.2.11. Configuring DICOM Adapter via REST APIs
        • 21.3.2.12. Helm Upgrade
      • 21.3.3. Breaking Changes
        • 21.3.3.1. Results Service
      • 21.3.4. Known Issues
        • 21.3.4.1. Jobs API Reports Incorrect Job State
        • 21.3.4.2. Pipeline Services Conflict with Resource Manager
        • 21.3.4.3. Deploying Triton via Pipeline Services Consumes All GPUs
        • 21.3.4.4. Triton Inference Server Consumes Memory of Unassigned GPU(s)
        • 21.3.4.5. Deleted Jobs Listed and/or Deleting Jobs with CLI Can Error
        • 21.3.4.6. Corrupted Tiles in the Output of the Digital Pathology Image Processing Pipeline
    • 21.4. Version 0.5.0 (R5)
      • 21.4.1. Introduction
      • 21.4.2. What’s New
        • 21.4.2.1. Platform
        • 21.4.2.2. Application
        • 21.4.2.3. Render Server
        • 21.4.2.4. Management Console
      • 21.4.3. Known Issues & Workaround
        • 21.4.3.1. Jobs API Reports Incorrect Job Information for Argo Based Pipelines
        • 21.4.3.2. Clara Deploy SDK from NGC Only Uses a Single GPU
        • 21.4.3.3. Pipeline Services Conflict with Resource Manager
        • 21.4.3.4. Deploying Triton via Pipeline Services Consumes All GPUs
      • 21.4.4. Deprecation Notice
        • 21.4.4.1. Argo Workflow Support is Deprecated
        • 21.4.4.2. Support for Pipeline Definitions < 0.4.0 is Deprecated
        • 21.4.4.3. Pipeline Services are Deprecated
    • 21.5. Version 0.4.1 (hotfix)
    • 21.6. Version 0.4.0 (R4)
      • 21.6.1. Introduction
      • 21.6.2. What’s New
        • 21.6.2.1. Clara Pipeline Driver
        • 21.6.2.2. Orchestration in two modes
        • 21.6.2.3. File Adapter
        • 21.6.2.4. CLI Improvements
        • 21.6.2.5. Centralized Logging
        • 21.6.2.6. Monitoring Performance
        • 21.6.2.7. Shared Memory Context
        • 21.6.2.8. Optimized CT Recon Pipeline
        • 21.6.2.9. Optimized Liver Tumor Segmentation Pipelines
        • 21.6.2.10. Render Server Improvements
        • 21.6.2.11. Automatic Payload Cleanup
        • 21.6.2.12. New Pipelines
    • 21.7. Version 0.2.0 (R2)
    • 21.8. Version 0.1.7 (Deprecated)
    • 21.9. Version 0.1.6 (Deprecated)
    • 21.10. Pre-alpha (Deprecated)
    • 21.11. Known Issues
      • 21.11.1. Installation
        • 21.11.1.1. Installation error with message [ERROR Port-XXXXX]: Port XXXXX is in use
        • 21.11.1.2. Installation error with message /var/lib/etcd is not empty
        • 21.11.1.3. Installation error with coreDNS pod failures
        • 21.11.1.4. Installation error with space in the path
      • 21.11.2. Installation error due insufficient Disk Space to Deploy Clara Container Images
      • 21.11.3. Operators cannot access the internet or Clara Service IPs due to the institution-wide proxy server settings
      • 21.11.4. Recon
        • 21.11.4.1. Recon operator does not exit with the right error code
      • 21.11.5. Render Service
        • 21.11.5.1. Minimum opacity value of the transfer function editor cannot be changed (since 0.4.0)
        • 21.11.5.2. Intensity Range Selectors in Transfer Function Editor are not displayed properly (since 0.4.0)
        • 21.11.5.3. White empty viewport
        • 21.11.5.4. Session management
        • 21.11.5.5. Changing datasets results in “Unable to reach RenderServer”
    • 21.12. Support
  • 22. License
Clara Deploy SDK
  • Docs »
  • 8. Pipeline Definition Language

8. Pipeline Definition Language¶

  • 8.1. Clara Pipeline Definition Language Overview
  • 8.2. Clara Deploy SDK Pipeline Glossary
  • 8.3. Operators
  • 8.4. Clara Types (pipeline api-version 0.5.0 and above)
  • 8.5. The Anatomy of an Operator
  • 8.6. Argo vs. Clara Orchestration
  • 8.7. Pipelines
  • 8.8. Services
  • 8.9. Connections
  • 8.10. Container
  • 8.11. Document
  • 8.12. Import
  • 8.13. Input
  • 8.14. Operator
  • 8.15. Output
  • 8.16. Pipeline
  • 8.17. Requests
  • 8.18. Service
  • 8.19. Syntax & Grammar
  • 8.20. Template
  • 8.21. Clara Structures and Primitives
  • 8.22. Variables
Next Previous

© Copyright 2018-2020, NVIDIA Corporation. All rights reserved.

Built with Sphinx using a theme provided by Read the Docs.