A data substrate and a vector database, side by side
Similarity search finds lookalikes. It does not explain a decision. How to keep the rule version next to the model’s answer.
Stuzhuk Lab — Chemistry of Code
Chemistry of Code
← All posts
Tag
Databases
All blog posts with this tag.
ACL and multi-tenancy in RAG: filter permissions before retrieval, not after
Production RAG cannot leave authorization to the model. How to isolate tenants, apply access lists before retrieval, close hidden leak channels, and measure recall under tight filters.
How one connection kills a database
An open transaction after an unhandled exception blocks a migration and every queued query—the GitHub and Postgres pattern.
Vector databases for AI agents in 2026: beyond raw ANN speed
Qdrant, Pinecone, Weaviate, pgvector, and Milvus compared for agent memory: filtering, hybrid search, tenancy, and quantization.
Vector databases in production: the index and storage layer for semantic search
How to run a vector database as an index layer: ANN algorithms, filters, tenancy, operations, and when pgvector beats a dedicated store.
Production RAG Engineering in 2026: Chunking, Hybrid Search, Reranking, and Evals
A practical guide to production RAG architecture: ingestion, chunking, hybrid retrieval, reranking, evaluation, observability, security, and staged delivery for engineering teams.
Why an AI Agent Can Cost Less Than RAG
More LLM calls do not necessarily cost more: support teams should measure the cost of resolving a question, not generating one answer.
Production RAG: Lessons from Processing 10,000 Listings a Day
A production RAG pipeline depends on document chunking, embeddings, pgvector, cost controls, and observability—not just an LLM.
Database Optimization: Six Strategies That Cut Query Time by 60%
Profiling, indexes, ORM refactors, materialized views, connection pooling, and cache — a practical PostgreSQL and MySQL guide.
A PostgreSQL-backed job queue in Go: the Swig example
Jobs table, row locks, JSONB payloads, LISTEN/NOTIFY, and goroutine workers — no Redis if Postgres is already in your stack.
SQLite Is All You Need for Durable Workflows
DBOS and Obelisk: local SQLite plus Litestream to S3 for workflow state; Postgres when you need HA and shared scale.
Semantic layer between storage and BI: why AI analytics needs it
Metrics Layer / Headless BI as an executable contract for metrics—not a data catalog—and why LLMs should not invent SQL on their own.
Python vector databases: what breaks after the notebook
Chroma, Pinecone, Qdrant, Weaviate—not QPS charts, but packaging, API stability, and the path from dev to production.
Shrinking a 3 GB SQLite dictionary to ~10 MB with an FST
The tsk case: finite state transducers in Rust, shared Finnish suffixes, and why SQLite FTS was only a stepping stone.