Borescope Image Search

Find similar borescope images and the findings they led to.

Industry	Level	Difficulty	Recommended mode
Aerospace	4 of 5	Expert	hnsw

Coming soon

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

The problem

• Borescope inspections produce many images.
• Comparing to past damage is manual.
• Expertise is scarce.

How SrvDB powers Borescope Image Search

1. Images and inspection notes embedded together.
2. New images retrieve similar past ones.
3. hnsw for large libraries.
4. Offline at the engine shop.

What changes

Today	With Borescope Image Search on SrvDB
Manual comparison	Similar images found
Scarce experts	Shared visual memory
Unused archives	Searchable images

How it works

1. Embed images.
2. Store with findings.
3. Query new images.
4. Inspector reviews.
5. Add outcomes.

SrvDB features it uses

• HNSW graph (hnsw): approximate search that visits a small part of large collections; tune with set_ef_search().
• Fully offline: SrvDB runs in-process and never opens a network connection.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.
• upsert: inserts new items and replaces changed ones, so the knowledge base stays current.

Use cases

• Blade damage
• Coating loss
• Cracks
• Burn marks
• Foreign object damage
• Training

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("./borescope-image-search-db", dimension=512, mode="hnsw")

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

Limits and honest notes

• Needs a validated image embedding model; inspectors decide.

Caution

SrvDB is not certified software. Use it for decision support and knowledge retrieval, never in flight-critical or certified systems.

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 Aerospace projects

Level	Project	What it does
1 · Beginner	Maintenance Knowledge Assistant	Cited answers from manuals and service bulletins for technicians.
2 · Intermediate	Safety Report Analyzer	Clusters safety reports and links similar events.
3 · Advanced	Fleet Finding Matcher	Matches new maintenance findings to similar findings across the fleet.
4 · Expert	Borescope Image Search (this page)	Find similar borescope images and the findings they led to.
5 · Frontier	Mission Knowledge System	Offline mission and ground-segment knowledge for space operations.

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