Skip to main content

RAG — Technical Document Search

Overview

PlantPulse RAG is a RAG (Retrieval-Augmented Generation) search server that lets AI instantly search and reference technical documents, manuals, SOPs, and regulations from the manufacturing field.

It provides accurate, context-aware document search through four search modes, and also supports multimodal (image, table, etc.) search.

Architecture — RAG API for the UI, LightRAG for the engine

Document search is split into two layers.

  • RAG API (plantpulse-rag-api) — the layer that users and AI actually interact with. It provides the document management screens and the search API.
  • LightRAG — the internal engine that performs the actual indexing and search. It is not exposed externally and is reached only through the RAG API.

In other words, there is no way to open LightRAG's address or WebUI (/webui) directly. All document work is done from the RAG API screens. (The legacy in-house server plantpulse-rag has been archived, and the direct-upload path through the LightRAG WebUI was replaced by the Documents screen below as of 2026-07-30.)


Search Modes

ModeDescriptionBest suited for
hybrid (default)Dense + Sparse combinedGeneral document search (recommended)
naiveSemantic (meaning-based) searchConceptual questions, finding similar documents
localDetailed search within a documentChecking specific details of a particular document
globalSearch across document relationshipsConsolidated information spanning multiple documents

Access Paths

TaskWhere
Ask via chatAI Chat Web — the built-in agent calls the rag_search tool automatically
Run a search directlyQuery screen of the RAG API dashboard
Upload, delete, or list documentsDocuments screen of the RAG API dashboard
Check auto-sync resultsSync History screen of the RAG API dashboard
Investigate indexing failuresLogs screen of the RAG API dashboard

Two Paths for Incoming Documents

Documents are indexed in one of two ways. How you manage them depends on which path they came in through.

PathSourceDescription
Auto syncDocuments attached to equipment in PlatformWhen you attach a document to equipment in Platform, it is indexed automatically on a schedule. There is no need to upload it separately on the RAG side
Manual uploadDocuments screenUpload documents that do not belong to any equipment (common regulations, training materials, etc.) directly. The originals are stored separately and survive re-indexing
Manage equipment documents in Platform

Manually uploading a document that belongs to equipment into RAG will put it out of sync with Platform's document ledger. Management stays simpler if you attach equipment documents to the equipment in Platform and leave RAG to auto sync.


Multimodal Support

Search over multimodal content — text plus images, tables, and more — is supported:

  • Attach an equipment photo and ask "What is this part?"
  • Photo of an instrument panel → search the related configuration manual
  • Image URL or Base64 data supported

From Registration to Searchable

문서 등록 (플랫폼 설비 첨부 / Documents 화면 업로드)


파싱 — PDF·DOCX·이미지에서 텍스트와 표를 추출


청킹 — 검색 단위로 잘게 나눔


임베딩 — 각 조각을 벡터로 변환

├──▶ 벡터 저장소 (유사도 검색)
└──▶ 지식 그래프 (엔티티·관계 추출)

A document is not searchable immediately after registration. It appears in results only after parsing and embedding are complete, so if a document you just uploaded is not being found, check its processing status on the Sync History screen first.


Manageable Document Types

Document typeExamplesAI use
Maintenance manualsPeriodic inspection procedures per equipment, lubricant replacement intervalsProvides appropriate countermeasures immediately when an anomaly is detected
SOPsWork procedures per process, safety procedures, quality inspection criteriaAccurate step-by-step guidance
Safety regulationsChemical MSDS, occupational health and safety rules, emergency response manualsImmediate reference to regulations in hazardous situations
Technical specificationsEquipment specs, sensor specifications, allowable rangesReference for anomaly judgment thresholds
Incident/failure reportsPast failure cases, root cause analyses, recurrence prevention measuresCause estimation based on similar cases
Training materialsNew-hire training texts, process descriptions, quality trainingSupport for field training

Configuration

Search parameters such as the embedding model, chunk size, and Top-K are LightRAG engine settings and cannot be changed from the UI. The values currently in effect can be viewed on the Config screen of the RAG API dashboard (tokens and passwords are shown masked).

What you typically need to adjust during operation is on the sync side.

ItemDescription
Sync enabledTurns automatic indexing of Platform equipment documents on and off
Sync intervalHow often Platform is checked for document changes
Documents indexed per runUpper limit processed per cycle — used to control load during a large initial influx
Maximum file sizeDocuments larger than this are skipped

Usage Scenarios

ScenarioSearch example
Check a maintenance procedure"How to replace the injector bearing" → maintenance manual
Reference a safety regulation"Response procedure for a nitrogen gas leak" → emergency response manual
Anomaly response guidance"Inspection items for a temperature sensor fault" → inspection SOP
Search past cases"Cause of last year's Line 3 injector failure" → failure report
Verify a specification"Allowable temperature range for the injector" → technical specification