FMEA Assistant

Drafts and reviews FMEAs grounded in past FMEAs and failures.

Industry	Level	Difficulty	Recommended mode
Mechanical engineering	2 of 5	Intermediate	flat

Coming soon

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

The problem

• FMEAs start from blank sheets.
• Past failure modes are forgotten.
• Quality varies by team.

How SrvDB powers FMEA Assistant

1. Past FMEA rows and failure reports are embedded.
2. A new function retrieves relevant failure modes.
3. A local LLM drafts rows with citations.
4. Accepted rows fed back.

What changes

Today	With FMEA Assistant on SrvDB
Blank-sheet FMEAs	Drafts from history
Forgotten failures	Recalled automatically
Inconsistent quality	Shared knowledge

How it works

1. Embed past FMEAs.
2. Query per function.
3. Draft rows.
4. Engineer review.
5. Upsert accepted rows.

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.
• Several databases: each database is a directory, so different data types or tenants stay separate.

Use cases

• Design FMEA
• Process FMEA
• Supplier FMEA
• Change reviews
• Audit preparation
• Training

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("./fmea-assistant-db", dimension=768)

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

Limits and honest notes

• FMEA ownership stays with engineers.

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 Mechanical engineering projects

Level	Project	What it does
1 · Beginner	Part Finder	Find existing parts by describing what they do.
2 · Intermediate	FMEA Assistant (this page)	Drafts and reviews FMEAs grounded in past FMEAs and failures.
3 · Advanced	Vibration Signature Matcher	Matches vibration signatures to known fault patterns.
4 · Expert	Geometric Design Search	Search CAD models by shape using 3D shape embeddings.
5 · Frontier	Simulation Lookup	Find the nearest previously simulated cases before running a new simulation.

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