Second-source Finder

Suggests substitute components by specification similarity.

Industry	Level	Difficulty	Recommended mode
Electrical & electronics	2 of 5	Intermediate	flat

Coming soon

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

The problem

• Shortages stop production.
• Substitute search is manual.
• Specs are described inconsistently.

How SrvDB powers Second-source Finder

1. Component specifications are embedded.
2. A shortage part queries similar candidates.
3. Scores rank closeness.
4. Engineers verify.

What changes

Today	With Second-source Finder on SrvDB
Manual distributor search	Ranked candidates
Production stops	Faster substitutes
Inconsistent specs	Meaning-based matching

How it works

1. Embed spec descriptions.
2. Query with the short part.
3. Rank.
4. Verify parameters.
5. Record approvals.

SrvDB features it uses

• Exact search (flat): every query compares against every stored vector, so results are exact and explainable.
• True cosine scores: scores in [-1, 1] mean the same in every mode, so thresholds are stable.
• 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.

Use cases

• Regulators
• MOSFETs
• Connectors
• Passives
• MCUs
• Sensors

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

Limits and honest notes

• Electrical and footprint compatibility must be verified.

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 Electrical & electronics projects

Level	Project	What it does
1 · Beginner	Datasheet Q&A	Ask questions of your component datasheets and get page citations.
2 · Intermediate	Second-source Finder (this page)	Suggests substitute components by specification similarity.
3 · Advanced	Test Log Analyzer	Finds similar past test failures and anomalous logs.
4 · Expert	Hardware Lab Agent	An agent that remembers bench sessions, scope captures and decisions.
5 · Frontier	RF Fingerprint Lab	Similarity search over RF spectrum fingerprints (research).

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