memoception
Data intelligence teams

3 TB of data, custom-stored with rules

Store, enrich, and recall very large data through the API.

3 TB
custom-stored
rules
metadata as it lands
SQL + graph
organize & query
20 req/s
API, with batching
How it fits together

   sources ──►  POST /custom/store  ──►  ┌──────────────┐
   (json, csv,     + rules (map, tag,    │  Memoception │
    sql, ts,        weight, redact)      │   records +  │
    jsonl…)                              │   content_id │
                                         └──────┬───────┘
                              /organize ─────────┤──► SQL schema · Neo4j graph
                              /query   ─────────►│    filter · project · traverse
                              recall   ─────────►│    fast fetch-and-rank @ 3 TB

The challenge

A data-intelligence team sits on multi-terabyte stores with thin metadata. They need structure, enrichment, and fast recall at scale — without hand-writing a pipeline per source or losing performance as the corpus grows.

How Memoception solves it

1
Custom-store via the API, with rules

Feed JSON/JSONL/CSV/SQL/TimescaleDB through /custom/store with a rules document — map titles, tag by field, weight by importance, redact PII — so every record gains metadata as it lands.

2
One standard, every format

The same rules vocabulary drives every format pipeline, so onboarding a new source is a config, not code. Each original keeps a content_id linking its representations.

3
Organize into SQL & graph, then query

/organize materializes the records as a relational schema or a Neo4j graph; /query filters, projects, and traverses them — SQL over the data, BFS over the relationships.

4
Performance at 3 TB

Recall stays a fast fetch-and-rank; exact lookups are indexed (id + tag), the API runs at 20 req/s per key with batching, and Pro storage holds 1.5 TB per project / 9 TB per account.

Built with
custom/store (rules)organize (SQL, Neo4j)query (sql + graph)batchindexed id/tag lookups