Knowledge Base Search

Customers and agents find the right article from their own words.

Industry	Level	Difficulty	Recommended mode
Customer support	1 of 5	Beginner	flat

Coming soon

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

The problem

• Customers describe problems differently from article titles.
• Agents search several tools.
• Good articles go unused.

How SrvDB powers Knowledge Base Search

1. Every article section is embedded in SrvDB.
2. Any question finds the closest sections.
3. Article updates use upsert.
4. Runs inside your help centre backend.

What changes

Today	With Knowledge Base Search on SrvDB
Keyword search fails on real questions	Search by meaning
Agents switch tools	One search box
Articles unused	Surfaced when relevant

How it works

1. Export articles.
2. Embed sections.
3. Serve search.
4. Track unanswered queries.
5. Update articles.

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

• Customer self-service
• Agent lookup
• In-app help
• Release-note search
• Community answers
• Internal IT 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("./kb-search-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 find_articles(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

• Article quality limits answer quality.

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 Customer support projects

Level	Project	What it does
1 · Beginner	Knowledge Base Search (this page)	Customers and agents find the right article from their own words.
2 · Intermediate	Helpdesk Answer Bot	Drafts replies from similar solved tickets and articles.
3 · Advanced	Ticket Deduplicator	Finds duplicate tickets and emerging issue clusters.
4 · Expert	Customer Memory Agent	Remembers each customer’s history across conversations.
5 · Frontier	Offline Support Kiosk	A self-service assistant that works without internet.

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