Part Finder

Find existing parts by describing what they do.

Industry	Level	Difficulty	Recommended mode
Mechanical engineering	1 of 5	Beginner	flat

Coming soon

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

The problem

• Engineers redesign parts that already exist.
• Part numbers say nothing about function.
• PLM search is keyword-based.

How SrvDB powers Part Finder

1. Part descriptions and drawing notes are embedded in SrvDB.
2. A functional description finds candidate parts.
3. Scores rank how close each is.
4. New parts added with upsert.

What changes

Today	With Part Finder on SrvDB
New part numbers for old parts	Reuse existing parts
Keyword PLM search	Search by function
Part proliferation	Fewer duplicates

How it works

1. Export part metadata.
2. Embed descriptions.
3. Search by requirement.
4. Review candidates.
5. Add new parts.

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

• Bracket and fastener reuse
• Standard-part selection
• Supplier part lookup
• Cost reduction
• Design reviews
• Obsolescence replacement

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("./part-finder-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 existing_parts_like(requirement, k=5):
    hits = db.search(embed(requirement), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Engineers verify fit, form and function.

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 (this page)	Find existing parts by describing what they do.
2 · Intermediate	FMEA Assistant	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)