Release Notes

v2.0.0 (2026-07) — Major Architecture Overhaul

info

The v1.x entries below are a historical record based on the pre-overhaul architecture. For the current architecture, refer to this v2.0.0 entry.

Chat Orchestration Brought In-House (Langflow Removed)

• Chat/agent execution has been consolidated into the AI Chat Web built-in agent (AgentOrchestrator + ToolRegistry).
• The Langflow engine and its 15 custom components, Arize Phoenix, and Jupyter have been removed from the stack.
• LLM inference now goes through the LiteLLM (:4000, gpt-4o) gateway. Agent execution flow can be reviewed under "View Tasks" on the chat screen.

MCP / Ontology Integration

• The former standalone services plantpulse-mcp-server (:50000) and plantpulse-ontology (:8888) have been archived and replaced by the platform's server-web integrated MCP (/api/v5/mcp, api_key authentication). Ontology tools have been absorbed into the integrated MCP.
• The built-in agent's ToolRegistry dynamically discovers tools via tools/list.

RAG → LightRAG Migration

• The in-house RAG server (formerly plantpulse-rag) has been replaced by the official LightRAG 1.5.4 server. Document management is performed in the LightRAG WebUI (/webui).

Shared Infrastructure

• PostgreSQL, Cassandra, Redis, and MinIO now use the PlantPulse Platform installation as shared infrastructure (the AI stack no longer runs its own embedded instances).

---

v1.4.0 (2026-03-29)

Documentation

• Expanded question examples to 178 (finer-grained feature store coverage, more complex questions, added business scenarios)
• Added troubleshooting guide
• Added API integration guide
• Added release notes page
• Added GitBook online manual URL to README

---

v1.3.0 (2026-03-29)

Documentation

• Expanded question examples to 170 (broken down by domain)
• Added 3 appendix algorithm guides:
  • Understanding RAG algorithms (chunking, embedding, hybrid search, reranking)
  • Understanding AI model algorithms (TSPulse anomaly detection, TTM forecasting, feature store)
  • Understanding the ontology (knowledge graph) (graph DB, subgraph traversal)
• Added troubleshooting guide
• Added API integration guide
• Added release notes page

---

v1.2.0 (2026-03-29)

Documentation

• Added 3 appendix algorithm guides

---

v1.1.0 (2026-03-29)

Documentation

• Added question examples page (130 items)

---

v1.0.0 (2026-03-29)

Initial Release

Initial build of the PlantPulse AI product manual GitBook.

Platform Composition

• 151 MCP tools integrated
  • PlantPulse MCP Server: 116 read-only APIs
  • TimeSeries-Insight: 27 AI analysis tools
  • Ontology: 5 graph tools
  • RAG: 3 search tools
• 15 custom Langflow components
• AURA LLM — in-house industry-specific model (LLM + Embedding + Reranker)

AI Models

Model	Purpose
AURA LLM	Conversation/analysis/report generation
AURA Embedding	Vector embedding (2560 dimensions)
AURA Reranker	Reranking of search results
IBM Granite TSPulse	Time series anomaly detection
TinyTimeMixer (TTM)	Time series forecasting

Infrastructure

Component	Technology
Backend	Java 21 / Spring Boot 3.4, Python / FastAPI
Graph DB	Neo4j
Vector DB	Qdrant
Relational DB	PostgreSQL 18
Time series DB	Apache Cassandra
Cache	Valkey (Redis compatible)
Object storage	MinIO (S3 compatible)
LLM proxy	LiteLLM
AI workflow	Langflow
AI observability	Arize Phoenix
Experimentation environment	Jupyter Notebook

Key Features by Module

AI Chat Web

• Natural language queries against factory data
• SSE real-time streaming responses
• Rich visualization with ECharts/Mermaid
• Multi AI Flow management

MCP Server

• 116 read-only APIs based on OPC-UA/ISA-95
• 10 data domains: equipment, OPC, work orders, sites, tags, OEE, calendar, system, RAM, EMS, alarms, points, and more
• Native KST time handling

TimeSeries-Insight

• Anomaly detection across 7 domains (IBM Granite TSPulse)
• Forecasting across 7 domains (TinyTimeMixer TTM)
• In-depth alarm analysis (statistics, duration, correlation)
• Feature store (automatic hourly/daily computation, vector embedding, LLM context)
• Equipment health score (0–100)

Ontology

• Factory knowledge graph with 14 node types
• Subgraph traversal (configurable depth)
• Automatic 60-second synchronization between the PlantPulse DB and Neo4j

RAG

• 4 search modes (hybrid, naive, local, global)
• Hybrid search (Dense + Sparse)
• Multimodal support (text + images + tables)
• Docling document parser, reranker

AI Studio

• Langflow visual flow programming
• 15 PlantPulse-specific components
• LiteLLM LLM proxy
• Arize Phoenix AI evaluation/monitoring
• Jupyter Notebook experimentation environment