In-car Manual Assistant

Answers drivers’ questions from the owner’s manual, offline.

Industry	Level	Difficulty	Recommended mode
Robotics & automotive	1 of 5	Beginner	flat

Coming soon

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

The problem

• Manuals are long and rarely read.
• Cars are often offline.
• Answers must be accurate.

How SrvDB powers In-car Manual Assistant

1. The manual is embedded and stored in the vehicle.
2. Spoken questions become searches.
3. Answers cite manual sections.
4. Runs without connectivity.

What changes

Today	With In-car Manual Assistant on SrvDB
Glovebox manuals	Spoken answers
Cloud dependence	Offline
Guesswork	Cited sections

How it works

1. Embed manual.
2. Ship with firmware.
3. Answer questions.
4. Log unanswered ones.
5. Update with releases.

SrvDB features it uses

• Fully offline: SrvDB runs in-process and never opens a network connection.
• Exact search (flat): every query compares against every stored vector, so results are exact and explainable.
• Rust API: embed SrvDB directly in Rust services and devices.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.

Use cases

• Warning-light explanations
• Feature how-tos
• Maintenance intervals
• Tyre pressure
• Charging (EVs)
• Infotainment help

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("./in-car-manual-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 manual_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

• Safety-critical instructions follow official procedures.

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 Robotics & automotive projects

Level	Project	What it does
1 · Beginner	In-car Manual Assistant (this page)	Answers drivers’ questions from the owner’s manual, offline.
2 · Intermediate	Diagnostic Assistant	Technicians match symptoms and trouble codes to past repairs.
3 · Advanced	Scenario Miner	Finds driving or robot episodes similar to a scenario of interest.
4 · Expert	Robot Episodic Memory	Robots remember places, objects and outcomes.
5 · Frontier	Autonomous Fleet Memory	Share learned experience across a fleet with database snapshots.

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