Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:SeldonIO Seldon core Seldon Pipeline Load And Status

From Leeroopedia
Revision as of 13:51, 16 February 2026 by Admin (talk | contribs) (Auto-imported from implementations/SeldonIO_Seldon_core_Seldon_Pipeline_Load_And_Status.md)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Property Value
Implementation Name Seldon Pipeline Load And Status
Type External Tool Doc
Overview Concrete CLI tools for deploying and validating monitoring pipelines in Seldon Core 2
Domains MLOps, Kubernetes
Implements Principle SeldonIO_Seldon_core_Monitoring_Pipeline_Validation
Source docs-gb/cli/seldon_pipeline_load.md:L1-25, docs-gb/cli/seldon_pipeline_status.md:L1-25
External Dependencies seldon CLI, kubectl, Seldon scheduler, Kafka
Knowledge Sources Repo (https://github.com/SeldonIO/seldon-core)
Last Updated 2026-02-13 00:00 GMT

Code Reference

Pipeline Load Command

seldon pipeline load -f samples/pipelines/income.yaml

Pipeline Status Command

seldon pipeline status income-production -w PipelineReady

Expected Status Response

pipelineName: income-production
versions:
- pipeline:
    name: income-production
    steps:
      income:
        - name: income
      income-preprocess:
        - name: income-preprocess
      income-outlier:
        - name: income-outlier
          inputs:
          - income-preprocess
      income-drift:
        - name: income-drift
          batch:
            size: 20
    output:
      steps:
      - income
      - income-outlier.outputs.is_outlier
  state:
    pipelineVersion: 1
    status: PipelineReady
    reason: "created pipeline"
    lastChangeTimestamp: "2023-..."

Key Parameters

Command Parameter Description Example
seldon pipeline load -f / --file-path Path to pipeline CRD YAML manifest -f samples/pipelines/income.yaml
seldon pipeline status pipelineName Name of the pipeline to check income-production
seldon pipeline status -w / --wait Wait condition to block until state is reached PipelineReady

Pipeline States

State Description
PipelineCreating Pipeline is being set up, Kafka topics being created
PipelineReady All steps are loaded and the pipeline is serving requests
PipelineFailed One or more steps failed to load
PipelineTerminating Pipeline is being unloaded
PipelineTerminated Pipeline has been fully removed

I/O Contract

Inputs

Input Type Description
Pipeline CRD YAML File path Monitoring pipeline definition (income-production)
All component models Pre-deployed income, income-preprocess, income-drift, income-outlier must be loaded

Outputs

Output Type Description
Pipeline active State change Pipeline transitions to PipelineReady
Pipeline version Integer pipelineVersion increments with each load (e.g., 1)
Step listing Status response All 4 steps listed with their configurations
Kafka topics Auto-created Inter-step communication channels established

Usage Examples

Full Deployment and Validation Sequence

# Step 1: Load the monitoring pipeline
seldon pipeline load -f samples/pipelines/income.yaml

# Step 2: Wait for pipeline readiness (blocks until ready or timeout)
seldon pipeline status income-production -w PipelineReady

# Step 3: Verify the pipeline version and step count
seldon pipeline status income-production | jq '.versions[0].state'

Checking Individual Step Readiness

# Verify each model component is available before loading the pipeline
seldon model status income -w ModelAvailable
seldon model status income-preprocess -w ModelAvailable
seldon model status income-drift -w ModelAvailable
seldon model status income-outlier -w ModelAvailable

# Then load the pipeline
seldon pipeline load -f samples/pipelines/income.yaml
seldon pipeline status income-production -w PipelineReady

Unloading the Pipeline

# Unload the pipeline (stops serving but keeps models loaded)
seldon pipeline unload income-production

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment