Contract Q&A

Ask questions about a contract set and get answers with clause citations.

Industry	Level	Difficulty	Recommended mode
Legal	2 of 5	Intermediate	flat

Coming soon

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

The problem

• Reviewing large contract sets takes days.
• Answers need exact citations.
• Clients’ documents are privileged.

How SrvDB powers Contract Q&A

1. Each deal’s documents get their own SrvDB database.
2. Questions retrieve clauses; a local LLM answers citing them.
3. Deleting a deal’s database removes it completely.
4. persist() after ingestion.

What changes

Today	With Contract Q&A on SrvDB
Manual reading	Answers with citations in seconds
Notes scattered	Every answer links to its clause
Privilege concerns	Local only

How it works

1. Ingest the deal documents.
2. Embed clauses.
3. Ask questions.
4. Verify citations.
5. Archive or delete per policy.

SrvDB features it uses

• Several databases: each database is a directory, so different data types or tenants stay separate.
• Exact search (flat): every query compares against every stored vector, so results are exact and explainable.
• 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

• Change-of-control questions
• Assignment restrictions
• Renewal dates
• Exclusivity
• Most-favoured-nation clauses
• Notice requirements

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("./contract-qa-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 ask_contracts(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

• Verify every answer against the cited clause.

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 Legal projects

Level	Project	What it does
1 · Beginner	Clause Finder	Finds the closest clauses your firm has already used, across every contract.
2 · Intermediate	Contract Q&A (this page)	Ask questions about a contract set and get answers with clause citations.
3 · Advanced	Playbook Deviation Detector	Flags clauses that drift from your negotiation playbook.
4 · Expert	E-discovery Assistant	Deduplicates, clusters and prioritises review sets by meaning.
5 · Frontier	Air-gapped Investigation Suite	Offline analysis of highly sensitive investigation documents.

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