Chunking Strategies That Actually Improve RAG
Fixed, recursive, and semantic chunking compared on the same corpus — with the recall numbers that show why splitting documents well matters more than your embedding model.
Practical notes on backend architecture, frontend SEO, and deployment work from real product builds.
5
Categories
22
Articles
188 min
Read time
Fixed, recursive, and semantic chunking compared on the same corpus — with the recall numbers that show why splitting documents well matters more than your embedding model.
Combine PostgreSQL full-text search and pgvector in a single query with Reciprocal Rank Fusion — keyword precision plus semantic recall, with a real benchmark.
Add pgvector to an existing Postgres, store embeddings alongside your relational data, and run fast similarity queries — schema, index, and SQL included.
Build a working Retrieval-Augmented Generation pipeline in Node.js — ingest, embed, retrieve, prompt — no framework, just the moving parts explained with real code.
A decision guide comparing pgvector with Pinecone/Qdrant/Weaviate on cost, recall, ops and scale — with real query benchmarks and a default to start from.
A practical guide to AI for backend engineers: embeddings, vector search, RAG, and LLM APIs — what they are, where they fit, and the cost and latency numbers to track.
A practical guide to partitioning large PostgreSQL tables (100M+ rows): choosing RANGE/LIST/HASH, creating declarative partitions, using partition pruning to speed up queries, indexing per partition, and near-free data retention with DETACH/DROP PARTITION.
A practical, end-to-end guide to integrating Vietnam's VNPay payment gateway into a NestJS API: build the payment URL, sign vnp_SecureHash with HMAC-SHA512, handle Return URL vs IPN, verify signatures, and keep the order flow idempotent.
How GoGoDuk meters API usage at scale with ClickHouse — Redis Streams ingestion, a ReplacingMergeTree schema, and AggregatingMergeTree materialized views for real-time per-customer dashboards and usage-based billing.
A developer how-to for the GoGoDuk Directions API: call /v1/directions, read real ETA and distance, decode the polyline onto your map, render turn-by-turn, and handle the ESTIMATED fallback.
Compare Google Maps Platform pricing and Vietnam limitations, then migrate geocoding, reverse geocoding, and address autocomplete to GoGoDuk with real code.
A deep technical breakdown of the newly released Redis 8.8 (June 2, 2026). Explore the new O(1) sparse-friendly Array structure by antirez, the native INCREX rate-limiting command, and Hash field-level subkey notifications.
Explore practical PostGIS database optimization techniques from the Gogoduk Map API project. Learn how migrating from Geometry to Geography, designing Partial GIST indexes, and simplifying polygons can achieve 10ms query times.
Learn how Gogoduk builds API Rate Limiting and Quota Alerting systems with Redis and Go. Discover how to use Lua scripts for atomicity, prevent memory leaks, and leverage SETNX to deduplicate notifications.
A comprehensive guide to building a fast, accent-insensitive, and typo-tolerant Vietnamese address autocomplete system in PostgreSQL using unaccent, FTS, and Trigram indexing.
A practical system-design guide to tracking user online/offline status using Redis Bitmaps. Calculate RAM requirements, learn core commands, and solve real-world production pitfalls.
Learn how to reduce checkout abandonment rates and eliminate data entry errors by implementing a single-field Vietnam address autocomplete API in your forms.
Explore the backend challenges of mapping Vietnamese administrative divisions (Provinces, Districts, Wards) for logistics routing, pricing, and spatial data modeling.
A developer-focused look at GoGoDuk, a Vietnam map API platform for geocoding, address search, POI search, and admin boundaries with a free tier.
A practical guide to NestJS modular architecture for production APIs, covering modules, service boundaries, DTO validation, dependency injection, and maintainability.
A practical Next.js App Router SEO checklist covering metadata, canonical URLs, OpenGraph, structured data, sitemap, RSS, and performance.
A production-focused guide to Dockerizing a NestJS app with multi-stage builds, environment configuration, health checks, CI/CD, and deployment readiness.