Ticket Deduplicator

Finds duplicate tickets and emerging issue clusters.

Industry	Level	Difficulty	Recommended mode
Customer support	3 of 5	Advanced	flat

Coming soon

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

The problem

• Outages create hundreds of duplicate tickets.
• Duplicates hide the real volume.
• New issues are spotted late.

How SrvDB powers Ticket Deduplicator

1. New tickets are compared with open ones by cosine similarity.
2. Duplicates are linked to a parent.
3. Bursts near one vector reveal incidents.
4. search_batch for volume.

What changes

Today	With Ticket Deduplicator on SrvDB
Each duplicate handled	Handled once
Volume unclear	True issue counts
Incidents found late	Bursts detected early

How it works

1. Embed tickets.
2. Match against open tickets.
3. Link duplicates.
4. Alert on bursts.
5. Close in bulk.

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

• Outage detection
• Duplicate merging
• Knowledge-base gaps
• Bug triage
• Topic reports
• Churn-risk signals

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("./ticket-deduplicator-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 duplicates_of(ticket_text, k=5):
    hits = db.search(embed(ticket_text), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Tune thresholds per product.

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	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 (this page)	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)