Diagnostic Assistant

Technicians match symptoms and trouble codes to past repairs.

Industry	Level	Difficulty	Recommended mode
Robotics & automotive	2 of 5	Intermediate	flat

Coming soon

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

The problem

• Trouble codes have many causes.
• Repair history is unsearchable.
• Diagnostics take hours.

How SrvDB powers Diagnostic Assistant

1. Repair records are embedded with codes and fixes.
2. Symptoms query similar past repairs.
3. Ranked fixes shown.
4. New repairs added with upsert.

What changes

Today	With Diagnostic Assistant on SrvDB
Trial-and-error	Ranked likely fixes
Lost history	Searchable repairs
Long diagnostics	Faster fixes

How it works

1. Embed repair records.
2. Query by symptom.
3. Rank fixes.
4. Repair.
5. Record 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.
• True cosine scores: scores in [-1, 1] mean the same in every mode, so thresholds are stable.

Use cases

• Engine faults
• Electrical issues
• EV battery faults
• Robot actuator errors
• Fleet trucks
• Warranty analysis

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("./diagnostic-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_repairs(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

• Technicians verify every fix.

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	Answers drivers’ questions from the owner’s manual, offline.
2 · Intermediate	Diagnostic Assistant (this page)	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)