Offline Support Kiosk

A self-service assistant that works without internet.

Industry	Level	Difficulty	Recommended mode
Customer support	5 of 5	Frontier	flat

Coming soon

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

The problem

• Stores, factories and remote sites have poor connectivity.
• Staff need answers anyway.
• Devices lose power.

How SrvDB powers Offline Support Kiosk

1. The knowledge base is shipped as a SrvDB folder.
2. Search runs locally.
3. Crash-safe storage survives power loss.
4. Updates are new folder snapshots.

What changes

Today	With Offline Support Kiosk on SrvDB
No help offline	Full help offline
Paper manuals	Searchable knowledge
Corrupted local data	Crash-safe

How it works

1. Build the knowledge base centrally.
2. Ship snapshots.
3. Search locally.
4. Collect questions offline.
5. Sync later.

SrvDB features it uses

• Fully offline: SrvDB runs in-process and never opens a network connection.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.
• SQ8 compression (sq8): stores each value in one byte, 4× smaller than full precision.
• Exact search (flat): every query compares against every stored vector, so results are exact and explainable.

Use cases

• Retail stores
• Factory floors
• Ships
• Rural service centres
• Appliances
• Events

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("./offline-support-kiosk-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 kiosk_answer(question, k=5):
    hits = db.search(embed(question), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Snapshots must be refreshed regularly.

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 Customer support projects

Level	Project	What it does
1 · Beginner	Knowledge Base Search	Customers and agents find the right article from their own words.
2 · Intermediate	Helpdesk Answer Bot	Drafts replies from similar solved tickets and articles.
3 · Advanced	Ticket Deduplicator	Finds duplicate tickets and emerging issue clusters.
4 · Expert	Customer Memory Agent	Remembers each customer’s history across conversations.
5 · Frontier	Offline Support Kiosk (this page)	A self-service assistant that works without internet.

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