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.

RAG for Codebases Without Cloud APIs: ChromaDB, Embedding Models, and Semantic Code Search

February 22, 2026

Agent-Tooling

Intermediate

Rag-Pipeline-Construction, Embedding-Model-Usage, Semantic-Code-Search

Rag, Embeddings, Chromadb, Local-Llm, Semantic-Search, Code-Search, Vector-Database

Ollama, Chromadb, Python, Nomic-Embed-Text

RAG for Codebases Without Cloud APIs#

When a codebase has hundreds of files, neither direct concatenation nor summarize-then-correlate is ideal for targeted questions like “where is authentication handled?” or “what calls the payment API?” RAG (Retrieval-Augmented Generation) indexes the codebase into a vector database and retrieves only the relevant chunks for each query.

The key advantage: query time is constant regardless of codebase size. Whether the codebase has 50 files or 5,000, a query takes the same time because only the top-K relevant chunks are retrieved and sent to the model.