Skip to main content
Back to challenges
Challenge

OPC UA Remote Monitoring and Root-Cause Diagnostics with LlamaIndex

Industrial remote telemetry platforms struggle to synthesize multi-sensor OPC UA streams with unstructured maintenance logs during acute equipment faults. You will build an autonomous diagnostic agent using LlamaIndex and Claude 4.1 Opus to correlate time-series vibration anomalies with unstructured technical manuals. The agent must diagnose root causes with at least 90% accuracy.

EngineeringHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build a LlamaIndex-powered RAG and telemetry analysis pipeline using Claude 4.1 Opus to perform automated root-cause analysis on OPC UA stream anomalies.

Delivery guide

How work is evaluated

Evaluation

Evaluates diagnostic accuracy, latency, and correctness of root-cause output generated by the LlamaIndex agent.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

schema_validation

Ensures the generated diagnosis strictly complies with the diagnostic response schema.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

fault_identification_accuracy

Categorical accuracy of target fault code identification • target: 0.9 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Integrate LlamaIndex RAG pipelines with real-time OPC UA time-series data streams

  • Implement multi-document query engines over factory maintenance manuals using Claude 4.1 Opus

  • Detect telemetry anomalies using statistical rolling-window thresholds and trigger automated root-cause queries

  • Evaluate diagnostic accuracy against benchmark ground-truth fault taxonomies

Resources and assets

Reference links and supporting material

Dataset notes

Simulated OPC UA time-series telemetry streams paired with synthetic industrial pump and compressor troubleshooting manuals.

Challenge setup

Evaluates diagnostic accuracy, latency, and correctness of root-cause output generated by the LlamaIndex agent.

Challenge input

JSON containing OPC UA sensor values (temperature, vibration, pressure) and target manual chunk references

LlamaIndex

Required framework assignment for RAG and tool usage.

Claude 4.1 Opus

Required specific model assignment.

Evaluated output

JSON containing diagnosed fault_code, root_cause_description, recommended_action, and confidence_score

Evaluation checks
  • Ensures the generated diagnosis strictly complies with the diagnostic response schema.
  • Categorical accuracy of target fault code identification • target: 0.9 • range: 0-1
Configured evaluation evidence
  • Benchmark: Industrial Fault Diagnosis Benchmark (IFDB)
  • Fault Identification Accuracy target: 0.9
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Llama Index · Required
  • LlamaIndex · Optional
  • Claude Code · Optional
Observation
  • Claude Code · Optional

Evaluation contract

  • schema_validation · Weight 1
  • fault_identification_accuracy · Weight 1

Metrics

  • fault_identification_accuracy · Target 0.9

Benchmarks

  • Industrial Fault Diagnosis Benchmark (IFDB)
  • robotics

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing OPC UA sensor values (temperature, vibration, pressure) and target manual chunk references

    Output: JSON containing diagnosed fault_code, root_cause_description, recommended_action, and confidence_score

    Execution harness: Python

Evaluation tools

  • LlamaIndex · Orchestration Framework
  • Claude 4.1 Opus · Language Model

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about OPC UA Remote Monitoring and Root-Cause Diagnostics with LlamaIndex