Listing Guardian

Detects duplicate and counterfeit-looking listings.

Industry	Level	Difficulty	Recommended mode
Retail & e-commerce	3 of 5	Advanced	flat

Coming soon

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

The problem

• Marketplaces fill with duplicate listings.
• Counterfeits copy real listings.
• Manual moderation does not scale.

How SrvDB powers Listing Guardian

1. Listing text and images are embedded.
2. New listings are compared with existing and known-counterfeit ones.
3. High-similarity listings go to moderators.
4. Decisions fed back with upsert.

What changes

Today	With Listing Guardian on SrvDB
Manual moderation	Prioritised review
Duplicate clutter	Merged listings
Counterfeits slip through	Similarity flags

How it works

1. Embed listings.
2. Score new listings.
3. Queue suspects.
4. Moderate.
5. Feed back decisions.

SrvDB features it uses

• True cosine scores: scores in [-1, 1] mean the same in every mode, so thresholds are stable.
• search_batch: runs many queries at once, in parallel inside Rust.
• 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

• Duplicate listings
• Counterfeit signals
• Fake-review clusters
• Prohibited items
• Brand protection
• Catalogue hygiene

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("./listing-guardian-db", dimension=512)

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

Limits and honest notes

• Moderators decide.

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 Retail & e-commerce projects

Level	Project	What it does
1 · Beginner	Semantic Product Search	Shoppers describe what they want and find it.
2 · Intermediate	Shopping Assistant	Answers product questions from your catalogue and reviews.
3 · Advanced	Listing Guardian (this page)	Detects duplicate and counterfeit-looking listings.
4 · Expert	Multimodal Kiosk	In-store kiosk that searches by text or photo.
5 · Frontier	Edge Recommender	“More like this” recommendations running on store or app hardware.

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