Glossary
Platform Terms
| Term | Description |
|---|---|
| PlantPulse AI | The industrial AI copilot platform as a whole |
| PlantPulse IIoT | The PlantPulse industrial IoT foundation platform (data collection/management) |
| AURA | PlantPulse's in-house industry-specific LLM |
| MCP | Model Context Protocol — an AI-to-data standard integration protocol proposed by Anthropic |
| Unified MCP | The MCP endpoint (/api/v5/mcp) provided by the PlantPulse Platform server-web — integrates plant data with ontology tools |
| Built-in agent | The agent loop embedded in AI Chat Web (AgentOrchestrator + ToolRegistry) — invokes tools automatically |
| Feature store | A system that stores and serves precomputed equipment features and LLM context |
ISA-95 / Asset Hierarchy
| Term | Description |
|---|---|
| Site | Plant/site — a physical location |
| Area | Zone — manufacturing building, utility building, etc. |
| Line | Production line |
| Equipment | Equipment — fillers, packagers, compressors, etc. |
| Tag | Sensor tag — a measurement point such as temperature, pressure, or vibration |
| Point | Time series data point — an individual value collected from a sensor |
| OPC | OLE for Process Control — the industrial automation communication standard |
Production Metrics
| Term | Description |
|---|---|
| OEE | Overall Equipment Effectiveness — availability x performance x quality |
| Availability | Actual runtime relative to planned production time |
| Performance | Actual output relative to theoretical output |
| Quality | Ratio of good units to total output |
| MTBF | Mean Time Between Failures |
| MTTR | Mean Time To Repair |
| MTTA | Mean Time To Acknowledge — time from alarm occurrence to acknowledgement |
| RAM | Reliability, Availability, Maintainability |
| EMS | Energy Management System |
AI / ML Terms
| Term | Description |
|---|---|
| RAG | Retrieval-Augmented Generation |
| LLM | Large Language Model |
| Embedding | The process of converting text/data into a vector (array of numbers) |
| Reranker | A model that re-evaluates the relevance of search results and reorders them |
| Ontology | A knowledge structure that defines relationships between entities |
| Knowledge Graph | A structure that represents entities and their relationships as a graph |
| Anomaly Detection | Detection of data that deviates from normal patterns |
| IBM Granite TSPulse | IBM's foundation model for time series anomaly detection |
| TinyTimeMixer (TTM) | IBM's lightweight time series forecasting model |
| SSE | Server-Sent Events — real-time data push from server to client |
| Fine-tuning | Additional training of a pre-trained model on domain-specific data |
Documentation
| Term | Description |
|---|---|
| SOP | Standard Operating Procedure |
| MSDS | Material Safety Data Sheet |
| Docling | IBM's document parsing library |
| Chunk | A unit produced by splitting a document into fixed-size segments |
Infrastructure
| Term | Description |
|---|---|
| LiteLLM | A proxy server that unifies multiple LLMs behind a single OpenAI-compatible API (chat LLM gateway) |
| LightRAG | The official open-source server (1.5.4) used as the RAG engine — hybrid search + knowledge graph |
| Qdrant | High-performance vector database |
| Valkey | Redis-compatible open-source in-memory cache |
| MinIO | S3-compatible object storage |
| DGX Spark | NVIDIA's compact AI computing system |
info
As of the 2026-07 revamp, Langflow, Arize Phoenix, and Jupyter have been removed from the stack.