Study Assistant

Answers questions only from the student’s own course material.

Industry	Level	Difficulty	Recommended mode
Education & research	2 of 5	Intermediate	flat

Coming soon

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

The problem

• Generic chatbots stray from the syllabus.
• Students need sources.
• Not all schools allow cloud AI.

How SrvDB powers Study Assistant

1. Notes and readings are embedded locally.
2. Answers cite course passages.
3. Runs offline.
4. Per-course databases.

What changes

Today	With Study Assistant on SrvDB
Off-syllabus answers	Grounded answers
No sources	Every answer cited
Cloud concerns	Local

How it works

1. Ingest course material.
2. Ask.
3. Review cited passages.
4. Add new lectures.
5. Revise.

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.
• 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

• Exam revision
• Homework help
• Concept explanations
• Lab preparation
• Language learning
• Accessibility support

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("./study-assistant-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 study_answer(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

• Encourage learning, not copying.

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 Education & research projects

Level	Project	What it does
1 · Beginner	Paper Search	Search a personal or lab library of papers by meaning.
2 · Intermediate	Study Assistant (this page)	Answers questions only from the student’s own course material.
3 · Advanced	Reviewer Matcher	Matches papers or proposals to suitable reviewers.
4 · Expert	Research Group Brain	A shared, searchable memory for a lab: notes, data descriptions, figures.
5 · Frontier	Scientific Similarity Lab	Similarity search over spectra, molecules and other scientific data.

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