RT Command Line Tool ¶

rtcmd is CVEDIA-RT's command-line interface for system administration, model management, inference operations, and hardware diagnostics. It provides programmatic access to core CVEDIA-RT functionality without requiring the GUI.

Overview ¶

rtcmd is organized into subcommands, each focused on specific functionality:

config - View and modify server configuration
modelforge - Download and manage AI models
licensing - License activation and management
inference - Run, benchmark, and evaluate AI models
onvif - Discover and configure ONVIF cameras
vpu - List and inspect AI accelerator capabilities
videodec - List available video decoders
systeminfo - Generate comprehensive system reports
streamgauge - Stream testing and performance analysis

Global Options ¶

rtcmd [GLOBAL_OPTIONS] SUBCOMMAND [OPTIONS]

Global Options:
  -h, --help          Show help message
  -v, --version       Show CVEDIA-RT version
  --verbose           Enable verbose output
  --config FILE       Use custom configuration file
  --profile FILE      Record performance profile (Tracy format)

Available Commands ¶

Server Configuration ¶

config - Configuration Management ¶

View and modify CVEDIA-RT server configuration settings.

rtcmd config [OPTIONS]

Options:
  -h, --help                  Print this help message and exit
  --help-all                  Print help for all subcommands
  -c, --config-file PATH      Path to rtconfig.json (default: $RT_HOME/rtconfig.json)
  -l, --list                  List all configurable settings and their current values
  -g, --get KEY               Get the value of a config key (e.g., webserver.host)
  -s, --set KEY=VALUE         Set a config value (e.g., webserver.port=8080)

Available Config Keys:

Key	Description
`webserver.host`	Web server bind address
`webserver.port`	Web server port
`webserver.enabled`	Enable web server (true/false)
`webserver.name`	Web server name

Exit Codes:

Code	Description
0	Success
1	Generic error
2	Unknown config key
3	Invalid value
4	Config file not found
5	Failed to save config

Usage Examples:

# List all configurable settings
rtcmd config --list

# Get current web server host
rtcmd config --get webserver.host

# Set web server port
rtcmd config --set webserver.port=8080

# Set web server bind address
rtcmd config --set webserver.host=0.0.0.0

Server Binding IP Configuration ¶

Changing the server binding IP can significantly impact how your server is accessed. Here are the available options:

127.0.0.1 (Default)

Restricts access to local connections only. This is ideal for all-in-one deployments where external access is not required.

rtcmd config --set webserver.host=127.0.0.1

0.0.0.0 (All Interfaces)

Allows the server to be accessible from any network interface. This is suitable for distributed deployments where the server needs to be accessed by other machines on the network.

rtcmd config --set webserver.host=0.0.0.0

Specific Network IP

Limits the server visibility to a selected network interface. Use this when you want to restrict access to a specific network.

rtcmd config --set webserver.host=192.168.1.100

Important

An incorrect IP can prevent access to the server. Always verify network connectivity after changing the binding address.

Model Management ¶

modelforge - AI Model Downloads ¶

Download and manage AI models from the CVEDIA Model Repository.

# Search for available models
rtcmd modelforge --search "detection"

# Download a specific model
rtcmd modelforge --download "model-uri"

# Download with overwrite
rtcmd modelforge --download "model-uri" --overwrite

# List downloaded models
rtcmd modelforge --list

Licensing ¶

licensing - License Management ¶

Activate and manage CVEDIA-RT licenses.

# Activate a license
rtcmd licensing --activate "LICENSE-KEY"

# Check license status  
rtcmd licensing --status

# List active licenses
rtcmd licensing --list

# Deactivate a license
rtcmd licensing --deactivate "LICENSE-KEY"

AI Inference Operations ¶

inference - Model Testing ¶

Run, benchmark, and evaluate AI models.

# Run inference on an image
rtcmd inference run --model "model-path" --input "image.jpg"

# Benchmark model performance
rtcmd inference benchmark --model "model-path" --iterations 100

# Evaluate model accuracy
rtcmd inference evaluate --model "model-path" --dataset "test-data/"

Subcommands:

run - Execute inference on input data
benchmark - Measure model performance metrics
evaluate - Test model accuracy against datasets

Camera Management ¶

onvif - ONVIF Camera Discovery ¶

Discover and configure ONVIF-compatible IP cameras on the network.

# Discover cameras on network
rtcmd onvif --discover

# List previously discovered cameras
rtcmd onvif --list

# Get camera details by UUID
rtcmd onvif --id "camera-uuid"

# Set camera credentials
rtcmd onvif --id "camera-uuid" --username "admin" --password "pass"

Hardware Diagnostics ¶

vpu - AI Accelerator Information ¶

List and inspect AI accelerator capabilities (VPUs, GPUs, NPUs).

# List all available AI accelerators
rtcmd vpu --list

# Get capabilities for specific device
rtcmd vpu --deviceid "device-id"

# Output in bare format (scripting)
rtcmd vpu --list --bare

videodec - Video Decoder Information ¶

List available hardware and software video decoders.

# List all video decoders
rtcmd videodec --list

# Show decoder capabilities
rtcmd videodec --capabilities

System Information ¶

systeminfo - System Reports ¶

Generate comprehensive system information reports.

# Generate system report
rtcmd systeminfo

# Output to JSON file
rtcmd systeminfo --output system-report.json

# Include detailed hardware info
rtcmd systeminfo --detailed

# Export specific information
rtcmd systeminfo --hardware --inference-engines

Includes:

Hardware specifications (CPU, GPU, memory)
Available inference engines and capabilities
System libraries and versions
Network configuration
Storage information

streamgauge - Stream Testing ¶

Test and analyze video stream performance.

# Test stream performance
rtcmd streamgauge --input "rtsp://camera/stream"

# Benchmark multiple streams
rtcmd streamgauge --input "stream1.mp4" --input "stream2.mp4"

# Generate performance report
rtcmd streamgauge --input "source" --report output.json

Usage Examples ¶

Development Workflow ¶

# 1. Check system capabilities
rtcmd systeminfo --inference-engines

# 2. Download required models
rtcmd modelforge --download "securt/person-detection-v1"

# 3. Test model performance
rtcmd inference benchmark --model "securt/person-detection-v1"

# 4. Discover available cameras
rtcmd onvif --discover

# 5. Test camera stream
rtcmd streamgauge --input "rtsp://192.168.1.100/stream"

Hardware Diagnostics ¶

# Complete hardware assessment
rtcmd systeminfo --detailed --output system-full.json
rtcmd vpu --list > accelerators.txt
rtcmd videodec --list > decoders.txt

# Test inference capabilities
for device in $(rtcmd vpu --list --bare | jq -r '.devices[].id'); do
    echo "Testing device: $device"
    rtcmd inference benchmark --device "$device" --model "test-model"
done

Configuration ¶

rtcmd uses the same configuration system as other CVEDIA-RT components:

Global Config: rtconfig.json
Custom Config: Use --config flag
Environment Variables: Standard RT environment variables

Custom Configuration ¶

# Use custom configuration
rtcmd --config /path/to/custom.json modelforge --list

# Override specific settings
export RT_LOG_LEVEL=debug
rtcmd --verbose inference benchmark --model "test"

Output Formats ¶

Most commands support multiple output formats:

Human-readable (default): Formatted for terminal display
JSON: Machine-readable structured data (--json)
Bare/Raw: Minimal output for scripting (--bare)

# Human-readable output
rtcmd vpu --list

# JSON output for parsing  
rtcmd vpu --list --json

# Bare output for scripting
rtcmd vpu --list --bare

Error Handling ¶

rtcmd provides detailed error messages and exit codes:

Exit Code 0: Success
Exit Code 1: General error
Exit Code 2: Invalid arguments
Exit Code 3: Runtime error

rtcmd modelforge --download "invalid-uri"
if [ $? -ne 0 ]; then
    echo "Download failed"
fi

Performance Profiling ¶

Use the --profile option to record detailed performance metrics:

# Record performance profile
rtcmd --profile trace.tracy inference benchmark --model "test"

# View with Tracy profiler
# https://github.com/wolfpld/tracy

Integration with RT Ecosystem ¶

rtcmd integrates seamlessly with other CVEDIA-RT components:

RT Server: Manage models and check system status
RT Studio: Validate models before GUI use
VMS Plugins: System diagnostics and model verification

Next Steps ¶

Modelforge - Detailed model management
Global Config - Configuration reference
RT Server - Production deployment
RT Studio - Development interface