Policy Search

Find the right policy passage from a plain question.

Industry	Level	Difficulty	Recommended mode
Governance, risk & compliance	1 of 5	Beginner	flat

Coming soon

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

The problem

• Policies are spread over many documents.
• Staff can’t find the rule.
• Versions drift.

How SrvDB powers Policy Search

1. Policies embedded by section.
2. Questions retrieve passages.
3. Updates via upsert.
4. Local deployment.

What changes

Today	With Policy Search on SrvDB
Searching folders	Instant passages
Outdated versions	Current only
Ad-hoc answers	Sourced answers

How it works

1. Collect policies.
2. Embed.
3. Search.
4. Track questions.
5. Update.

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.
• Fully offline: SrvDB runs in-process and never opens a network connection.

Use cases

• Acceptable use
• Data classification
• Access control
• Retention
• Incident reporting
• Third-party rules

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("./policy-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 policy_passages(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

• Policy owners keep documents current.

Caution

SrvDB supports compliance work; it does not certify compliance with any framework.

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 Governance, risk & compliance projects

Level	Project	What it does
1 · Beginner	Policy Search (this page)	Find the right policy passage from a plain question.
2 · Intermediate	Questionnaire Autopilot	Answers security and vendor questionnaires from past approved answers.
3 · Advanced	Control Mapper	Suggests mappings between controls across frameworks.
4 · Expert	Regulatory Change Agent	Assesses which policies and controls a new regulation affects.
5 · Frontier	Continuous Compliance Platform	On-prem AI retrieval for evidence, controls and audits with an audit trail.

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