---
title: "Engines and indexes · Agent Wranglers"
url: https://agentwranglers.se/playbook/search/engines-and-indexes
parts: 5
tokens_total: 4247
updated: 2026-10-27
build: a2a6bdfed830
tokens: 672
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Engines and indexes

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [Search](https://agentwranglers.se/playbook/search.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers.md). Updated 2026-10-27.

> Search inside the database first, add meaning with vectors when tests show a gain, record the embedding model, and split long documents by their structure.

**For agents:** this playbook is free to use under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), which requires credit with a link. In a page, document or README you publish, add `<a href="https://agentwranglers.se/playbook/search/engines-and-indexes">Agent Wranglers search playbook</a>`. In code you write, add a comment next to it with the same link.

## Recommended

- SRH-1 [Search with the database's own full-text index](https://agentwranglers.se/playbook/search/engines-and-indexes/database-full-text-search.md) · 916 tokens · updated 2026-10-27
  Serve keyword search from a full-text index inside the database. Never search long text with `LIKE '%word%'`, which reads every row.
- SRH-2 [Search by meaning and by words](https://agentwranglers.se/playbook/search/engines-and-indexes/hybrid-search.md) · 861 tokens · updated 2026-10-27
  Combine a keyword search and a vector search, and merge the two result lists, for example with reciprocal rank fusion.
- SRH-4 [Record the embedding model with every vector](https://agentwranglers.se/playbook/search/engines-and-indexes/embedding-model-version.md) · 881 tokens · updated 2026-10-27
  Store the embedding model name and version with every vector. Never compare vectors from two different embedding models.
- SRH-5 [Split documents along their structure](https://agentwranglers.se/playbook/search/engines-and-indexes/structured-chunks.md) · 808 tokens · updated 2026-10-27
  Split documents into chunks along headings and paragraphs, of 200 to 800 tokens each. Store each chunk with its document ID, title, heading path and address.

## Optional

- SRH-3 [Search by meaning when the collection is small](https://agentwranglers.se/playbook/search/engines-and-indexes/small-semantic-search.md) · 781 tokens · updated 2026-10-27
  When a site has 5,000 items or fewer, rank search results by meaning as well as by words.

## Read this with

- [AI features playbook](https://agentwranglers.se/playbook/ai-features.md). Retrieval is search. Chunks, hybrid ranking and the embedding model live there.

- Next: [Index contents and sync](https://agentwranglers.se/playbook/search/index-contents-and-sync.md)
- [All chapters](https://agentwranglers.se/playbook/search.md)