Skip to main content

AI Management Console

The AI stack comes with one management console. You monitor GPU load, LLM latency, and document indexing status in your browser without logging into the server.

This document is for first-time users. Work through the 10-minute walkthrough in order, then find screen-by-screen details as needed.

Who uses this

Field operators and system administrators. The console is mostly read-only, so accidental clicks rarely break anything. Only three places let you change data: document upload, document deletion, and feature backfill — all marked separately in this document.


Access and login

The address depends on your deployment. Confirm with your administrator which one applies.

DeploymentAddress
Domain-based installationhttps://admin.<COMPANY_DOMAIN>
IP access on company networkhttp://<AI_SERVER_IP>:9080

Enter your user ID and password on the login screen. The default ID is admin; your administrator sets the password during installation.

Only one account

The console has no per-user accounts. The entire operations team shares one account. Since there is no per-user audit trail, keep the password within your team.

One login, 8 hours

You must log in again after 8 hours. Your screen URL is remembered, so you return to where you left off. Service restart may log everyone out — see Sessions keep dropping.

Console labels are in English

Menu and button text appears in English (only the home screen service cards have Korean descriptions). In the explanation below, actual English screen names are bold with Korean meaning alongside.


10-minute walkthrough

New users: follow this sequence. View only — make no changes.

Step 1 — Log in and view home

Logging in takes you straight to Home. A single-line status summary appears at the top.

정상 12 주의 0 중단 0 합계 12

This number is your entire AI stack health snapshot. If 중단 is 0, you can rest easy. Numbers update every 20 seconds automatically — no refresh needed.

Click the expand arrow on the right side of the summary line to see a list of individual service states. If you expand it, it stays expanded on your next visit.

Yellow light appeared

Hover your mouse over that service in the list. Why it is yellow appears in a tooltip. For example, the service may be alive but its database connection down.

Step 2 — Scan the service cards

Below the summary line are service cards. One card = one service.

  • Border color and status dot show whether it is healthy
  • Click to enter that service's screen
  • Some cards are not clickable — they are internal services you cannot reach directly from the browser. Think of them as status-only cards

Step 3 — Check GPU

Click GPU on the left sidebar. A table of GPU devices appears.

ColumnMeaning
UtilizationHow busy the GPU is right now
MemoryHow much the model is using
TemperatureHigh sustained temperature degrades performance
XIDCount of NVIDIA hardware or driver errors
If XID is not 0, do not ignore it

XID means GPU hardware or driver error. Left unattended, the typical next symptom is server down. If you see a non-zero number, note it exactly and report it to your system administrator.

Step 4 — Check LLM response speed

Click LLM on the sidebar. One row per model shows response speed and throughput.

When you hear "answers are slow lately," check the P95 column here (the 5th slowest among the last 100 requests). If it is much higher than usual, the complaint is valid. The small line chart at the end shows recent trend.

Step 5 — Enter one service

Click RAG API on the sidebar. Its menu unfolds on the left. Click Documents. A list of indexed documents appears.

Do not click anything here — just note how many documents are indexed. When the chatbot says "I could not find related documents," this is the first place to check.

Step 6 — View logs

In the same service menu, click Logs. Recent logs appear in newest-first order (latest at the top). You do not need to SSH into the server and run docker logs.

Step 7 — Done

You have now seen 90% of what the console does. In summary:

Check overall status on home → navigate to the suspicious service → read the logs.

Find other screens in the reference below as needed.


Screen map

MenuFunction
HomeOverall status summary + service cards
GPUGPU device utilization, memory, temperature, XID
LLMModel response speed and throughput
RAG APIDocument search engine — indexing, sync, query testing
Timeseries InsightEquipment anomaly detection and forecasting
Document ParsingService to extract tables and fields from documents
VisionImage reading service (defect classification, gauge reading)
Operations Manual ↗This manual you are reading (new window)

GPU and LLM appear above the services intentionally. Most issues trace down from infrastructure, so scanning top-to-bottom finds problems faster.

Manual link will not open on air-gapped networks

Operations Manual points to an external site (docs.plantpulse.io). It won't open where internet is unavailable. A local copy of the manual is bundled with the server installation — contact your administrator.

Four services share identical menus

RAG API · Timeseries Insight · Document Parsing · Vision all have the same four menus. Learn once, apply everywhere.

MenuFunction
MCP Server InfoList of tools this service offers to the AI copilot
API EndpointsList of APIs this service provides (for integration developers)
LogsRecent logs (newest first)
SettingsCurrent configuration values — read-only
Settings is not for editing

It only displays values; it cannot change them. Passwords and API keys appear masked. To actually change settings, see Credentials and Operations.


This service lets the chatbot answer based on company documents. When you hear "the chatbot can't find documents," start here.

MenuFunction
DocumentsList of indexed documents. Upload and delete are available here
Sync HistoryWhen sync ran and whether it succeeded
Query TestEnter search terms to test directly what matches
Common 4 menusSee table above

When chatbot cannot find a document

  1. Check Documents to see if the document is in the list — if not, indexing failed
  2. If it is there, use Query Test with language similar to what the user asked
  3. If still no match, try different search modes — you can choose among hybrid, local, global, naive, mix. Default is hybrid
  4. Check Sync History to verify the last sync did not fail
Document deletion in Documents cannot be undone

The chatbot stops using a deleted document as evidence. To use it again, you must re-upload the original file. Do not delete if you do not have the original file.


Timeseries Insight — Anomaly detection and forecasting

This engine finds anomaly signals in equipment data and predicts the future. It has the most menus.

Analysis screens

Each category pairs Anomaly Detection with Forecast.

CategoryScreens
Asset (equipment)Anomaly Detection · Forecast · Health Index
ProductionAnomaly Detection · Quality Forecast
AlarmFrequency Anomaly · Failure Forecast · Duration Analysis · Sensor Correlation · Statistics
SystemAnomaly Detection · Forecast
ProfilingAsset Profiling — deep dive into one equipment

Feature Store — the fuel for analysis

Analyses above run on processed data stacked in the feature store. Empty or stale results usually mean the problem is here.

MenuFunction
Pipeline StatusIs data processing running normally now
Run HistoryPast execution history and pass/fail
Feature DataQuery the actual stored values
BackfillRecalculate a missing period
Backfill makes the server busy

It recalculates historical periods, so wide ranges take time and raise server load. Run it during low-production hours, with the narrowest range needed. For first-time use, consult your administrator.


Document Parsing · Vision

Both services have only the four common menus. In the console, you check they are alive and review logs when issues arise.

  • Document Parsing — extracts layout, tables, and fields from documents
  • Vision — classifies defects from images or reads gauges

Both are internal services unreachable directly from the browser, so their home screen cards are not clickable. The console polls their status on your behalf.


Troubleshooting

SymptomLook firstThen
Chatbot can't find documentsRAG API → DocumentsQuery Test for direct search → Sync History
Chatbot answers are slowLLM P95 columnGPU utilization and temperature
Analysis results are emptyInsight → Pipeline StatusRun History failed rows
Yellow light on homeExpand status list, check tooltipThat service → Logs
Red light on homeThat service → LogsOperations restart procedure
Screen is blank with error bannerService may not be up yetCheck status on home
「Empty」 and 「unreachable」 are different

The console shows an error banner, not a blank table, when data cannot be fetched. An error banner means connection failed, not missing data.


Accounts and sessions

Console accounts are managed via environment variables, not a database.

VariableMeaningDefault
ADMIN_AUTH_USERNAMELogin user IDadmin
ADMIN_AUTH_PASSWORDLogin passwordNone — must be set
ADMIN_SESSION_SECRETSession signing keyIf empty, generated fresh on each restart
ADMIN_SESSION_MAX_AGELogin session duration (minutes)480 (8 hours)
Missing password blocks startup

If ADMIN_AUTH_PASSWORD is empty, the console refuses to start. This prevents an unauthenticated admin portal from quietly running — normal behavior.

Sessions keep dropping

If ADMIN_SESSION_SECRET is empty, each service restart generates a new signing key, logging everyone out. Set a value and logins survive restarts.

Console password cannot be changed via bin/passwd.sh

Console credentials are not in the key management list that bin/passwd.sh handles — see the table in Credentials. To change it, edit the environment file directly and restart the service. Contact your administrator.