Blog · Category

Engineering

8 posts in this category.

  1. MAY 2026

    Engineering · · 11 min

    Chunking inside the engine: when the DB owns segmentation

    Most RAG stacks chunk in Python glue between Postgres and a vector store. The result is a second pipeline that drifts. This post walks through what it looks like when chunking is a declarative rule attached to a column, reranking is a query operator, and the engine — not the application — owns segmentation.

  2. Engineering · · 8 min

    Hybrid search done right: lexical, vector, and filter in one plan

    A walk through the RedDB query planner fusing BM25, vector similarity, and a structured filter into a single execution plan — with EXPLAIN output, the cost model behind it, and what happens on the edge cases that trip up naive two-stage rerankers.

  3. Engineering · · 14 min

    One WAL, four data models: how cross-modality transactions actually work

    A deep dive into the shared write-ahead log that lets a document update, a vector insert, a KV write, and a blob commit land in the same transaction. Record layout, the fsync contention tradeoff, and the four mitigations we shipped before the tail latency became someone else's incident.

  4. Engineering · · 1 min

    Hello from inside the engine

    A first note on what we're building and why a multi-model engine matters in 2026.

  5. Engineering · · 10 min

    Stop stitching Postgres, pgvector, S3, and Redis

    Every modern app you ship is four databases in a trenchcoat. Here is the bill — in failure surfaces, ops playbooks, and consistency models — that nobody costs out before signing.

  6. Engineering · · 7 min

    The tradeoffs we made to fit four engines in one

    Document, vector, KV and blob in the same transaction is not free. Here's the per-modality tuning surface we cut, the plugin story we sacrificed, and the cold-blob latency tail we accepted.

  7. APR 2026

    Engineering · · 9 min

    Why 'best of breed' loses at small scale

    The ops cost of running four engines instead of one, measured in person-hours at team sizes of 2, 5, and 15 engineers. Multi-model isn't only a scale concern — it's a small-team unlock.

  8. Engineering · · 9 min

    When you don't need RedDB

    An honest list of workloads where Postgres + pgvector, SQLite, or a single-purpose store will serve you better than RedDB. If your shape is on this list, save yourself the migration.

© 2026 RedDB.io. AGPL-3.0 self-host · Managed Cloud.