FTS5 vs Cloudflare Vectorize: A/B Results on When Keyword Beats Semantic Search

May 20, 2026

Search-Engine-Selection, Embedding-Pipeline-Design, Ab-Testing-Search-Relevance

Fts5, Vectorize, Cloudflare, Semantic-Search, Full-Text-Search, Bm25, Embeddings, Bge-Base-En, Search-Relevance

Fts5, Sqlite, Vectorize, Workers-Ai, Cloudflare-Workers, D1

FTS5 vs Cloudflare Vectorize#

The “FTS5 vs vectors” debate is usually hand-wavy. Both sides cite plausible reasons, neither runs the same queries through both engines on the same corpus, and the conclusion is whichever one the author shipped. With identical data and identical queries you can measure exactly where each wins.

The result: FTS5 and Vectorize have non-overlapping strengths. The right answer for most knowledge-base workloads is “ship both” behind an opt-in flag — not pick one. This page is the measurements, the cost math, and the dual-engine pattern.

Agent Memory and Retrieval: Patterns for Persistent, Searchable Agent Knowledge

February 22, 2026

Agent-Tooling

Intermediate

Memory-System-Design, Rag-Implementation, Context-Optimization

Memory, Retrieval, Rag, Vector-Databases, Context-Window, Embeddings

Chromadb, Pgvector, Sqlite, Redis, Python

Agent Memory and Retrieval#

An agent without memory repeats mistakes, forgets context, and relearns the same facts every session. An agent with too much memory wastes context window tokens on irrelevant history and retrieves noise instead of signal. Effective memory sits between these extremes – storing what matters, retrieving what is relevant, and forgetting what is stale.

This reference covers the concrete patterns for building agent memory systems, from simple file-based approaches to production-grade retrieval pipelines.