Research Group Brain

A shared, searchable memory for a lab: notes, data descriptions, figures.

Industry	Level	Difficulty	Recommended mode
Education & research	4 of 5	Expert	flat

Coming soon

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

The problem

• Knowledge leaves with graduating students.
• Lab notebooks are unsearchable.
• Figures are hard to find.

How SrvDB powers Research Group Brain

1. Notes, protocols and figure captions (and images with multimodal embeddings) go into SrvDB.
2. Everyone searches one memory.
3. An agent drafts summaries.
4. Crash-safe storage on a lab server.

What changes

Today	With Research Group Brain on SrvDB
Knowledge leaves with people	Knowledge stays
Unsearchable notebooks	Searchable memory
Lost figures	Found by description

How it works

1. Collect notes and figures.
2. Embed.
3. Search and summarise.
4. Add continuously.
5. Back up the folder.

SrvDB features it uses

• Several databases: each database is a directory, so different data types or tenants stay separate.
• 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.
• Thread-safe handles: one database object can be shared between threads; searches run in parallel.

Use cases

• Onboarding students
• Protocol reuse
• Figure retrieval
• Grant reports
• Reproducibility
• Collaboration

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("./research-group-brain-db", dimension=512)

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 lab_recall(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

• Curate what goes in.

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	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 (this page)	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)