Shopping Assistant

Answers product questions from your catalogue and reviews.

Industry	Level	Difficulty	Recommended mode
Retail & e-commerce	2 of 5	Intermediate	flat

Coming soon

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

The problem

• Customers ask questions product pages don’t answer.
• Support costs rise.
• Generic bots invent facts.

How SrvDB powers Shopping Assistant

1. Specifications, FAQs and reviews are embedded.
2. Answers cite products and reviews.
3. Local LLM keeps data in-house.
4. Updated nightly.

What changes

Today	With Shopping Assistant on SrvDB
Unanswered questions	Grounded answers
Invented facts	Cited sources
Support load	Self-service

How it works

1. Embed content.
2. Answer with citations.
3. Escalate gaps.
4. Refresh.
5. Measure.

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.
• Thread-safe handles: one database object can be shared between threads; searches run in parallel.

Use cases

• Compatibility questions
• Size and fit
• Comparisons
• Care instructions
• Delivery questions
• Store staff help

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("./shopping-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 product_answer(question, k=5):
    hits = db.search(embed(question), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Answers must cite catalogue data.

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 (this page)	Answers product questions from your catalogue and reviews.
3 · Advanced	Listing Guardian	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)