Code Search

Find code by what it does.

Industry	Level	Difficulty	Recommended mode
Software engineering	1 of 5	Beginner	flat

Coming soon

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

The problem

• Naming conventions hide functionality.
• Large repos are hard to navigate.
• Proprietary code can’t leave.

How SrvDB powers Code Search

1. Functions and doc sections are embedded with a code model.
2. Questions find matching code.
3. Runs locally or in CI.
4. Changes indexed with upsert and delete.

What changes

Today	With Code Search on SrvDB
grep for names	Search by behaviour
Tribal knowledge	Searchable codebase
Cloud indexing	Local index

How it works

1. Parse repo.
2. Embed chunks.
3. Search.
4. Update on commit.
5. Share the index.

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.
• delete and compact(): remove items immediately from search, then reclaim disk space.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.

Use cases

• “Where do we validate tokens?”
• Find examples of an API
• Locate error handling
• Find config loaders
• Onboarding
• Refactoring scope

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("./code-search-db", dimension=768)

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 where_is(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

• Embedding model choice matters for code.

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 Software engineering projects

Level	Project	What it does
1 · Beginner	Code Search (this page)	Find code by what it does.
2 · Intermediate	Codebase Q&A	Ask how the system works and get answers citing files.
3 · Advanced	Bug Dedup Engine	Links duplicate bug reports and similar stack traces.
4 · Expert	Coding Agent Memory	Long-term, crash-safe memory for autonomous coding agents.
5 · Frontier	Air-gapped Dev Copilot	A self-hosted developer assistant for isolated environments.

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