Maintenance Assistant

Technicians describe a symptom and get the right manual section and past fixes.

Industry	Level	Difficulty	Recommended mode
Manufacturing & IoT	1 of 5	Beginner	flat

Coming soon

A complete, runnable Maintenance Assistant reference implementation is in progress. The architecture and core code below already work with SrvDB 0.3.

The problem

• Manuals are thick and fault codes cryptic.
• Fixes live in old work orders.
• Connectivity on the floor is poor.

How SrvDB powers Maintenance Assistant

1. Manuals and work orders are embedded in SrvDB.
2. A symptom description is the query.
3. Runs on tablets or edge boxes offline.
4. Resolved work orders are added with upsert.

What changes

Today	With Maintenance Assistant on SrvDB
Searching binders	Answers from a sentence
Fixes forgotten	Every past fix searchable
No signal on the floor	Works offline

How it works

1. Embed manuals and work orders.
2. Copy the database to devices.
3. Query by symptom.
4. Apply the fix.
5. Log and upsert the outcome.

SrvDB features it uses

• Exact search (flat): every query compares against every stored vector, so results are exact and explainable.
• upsert: inserts new items and replaces changed ones, so the knowledge base stays current.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.
• Fully offline: SrvDB runs in-process and never opens a network connection.

Use cases

• Fault-code explanation
• Changeover steps
• Lubrication schedules
• Safety lockout steps
• Spare-part identification
• Shift handover

Core code

embed() is your embedding model (for example sentence-transformers, or a function that turns your records into feature vectors).

import json
import srvdb

db = srvdb.Database("./maintenance-assistant-db", dimension=384)

def ingest(items):
    """items: list of (id, text, metadata dict)"""
    db.upsert(
        ids=[i for i, _, _ in items],
        embeddings=[embed(t) for _, t, _ in items],
        metadatas=[json.dumps(m) for _, _, m in items],
    )
    db.persist()                      # crash-safe checkpoint

def similar_faults(symptom, k=5):
    hits = db.search(embed(symptom), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Safety-critical steps must come from the official manual.

Build roadmap

1. Prototype: load a sample of real data with flat mode and check that searches return what an expert expects.
2. Measure: if you move to an approximate mode, compare its results with flat on the same queries (recall).
3. Pipeline: add continuous upsert and decide when to call persist().
4. Harden: test restarts and crashes, add logging, review every output path with domain experts.
5. Deploy: ship the database directory with the application or service.

All Manufacturing & IoT projects

Level	Project	What it does
1 · Beginner	Maintenance Assistant (this page)	Technicians describe a symptom and get the right manual section and past fixes.
2 · Intermediate	Defect Matcher	Matches new defects to past ones, from text and images.
3 · Advanced	Sensor Anomaly Detector	Flags sensor windows far from normal operation.
4 · Expert	Plant Knowledge Agent	An agent with shift memory across lines, manuals and quality records.
5 · Frontier	Predictive Maintenance at the Edge	Finds machines whose behaviour resembles past pre-failure signatures.

See also: Use cases · Live examples (coming soon)