---
title: "Search by meaning when the collection is · Agent Wranglers"
url: https://agentwranglers.se/playbook/website/ready-for-ai-agents/small-semantic-search
id: WEB-250
level: Optional
updated: 2026-10-22
tokens: 828
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Search by meaning when the collection is small

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [Ready for AI agents](https://agentwranglers.se/playbook/website/ready-for-ai-agents.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers.md). Updated 2026-10-22.

- ID: WEB-250
- Level: Optional
- Chapter: [Ready for AI agents](https://agentwranglers.se/playbook/website/ready-for-ai-agents.md)
- Rule: When a site has 5,000 items or fewer, rank search results by meaning as well as by words.
- Check: A set of 10 paraphrased questions, none sharing a title word with its answer, returns the right item in the top three for each.
- How: Embed each item's title, summary and aliases at build time, and store the vectors with the site. Embed the query, rank by similarity, and merge with word matches, as [Search by meaning and by words](https://agentwranglers.se/playbook/ai-features/retrieval/hybrid-search.md) says. A few thousand vectors fit in memory, so no vector database is needed. Record the embedding model with the vectors, as [Record the embedding model with every vector](https://agentwranglers.se/playbook/ai-features/retrieval/embedding-model-version.md) says. Measure it as [Measure retrieval on its own](https://agentwranglers.se/playbook/ai-features/retrieval/retrieval-evals.md) says.

## Examples

**Using these examples:** they show one way to follow this rule. Keep the behaviour and the check, not the syntax. Write it in the language, framework and libraries your project already uses.

### JavaScript example

```js
const cosine = (a, b) => a.reduce((sum, x, i) => sum + x * b[i], 0);
export const byMeaning = (queryVector, items) => items.map(item => ({ item, score: cosine(queryVector, item.vector) })).sort((a, b) => b.score - a.score);
```

### Python example

```python
import numpy as np

def by_meaning(query_vector: np.ndarray, vectors: np.ndarray, items: list[dict]) -> list[tuple[dict, float]]:
    scores = vectors @ query_vector
    return [(items[i], float(scores[i])) for i in np.argsort(-scores)]
```

## Related rules

- AIF-20 [Search by meaning and by words](https://agentwranglers.se/playbook/ai-features/retrieval/hybrid-search.md) in AI features
- AIF-19 [Record the embedding model with every vector](https://agentwranglers.se/playbook/ai-features/retrieval/embedding-model-version.md) in AI features
- AIF-21 [Measure retrieval on its own](https://agentwranglers.se/playbook/ai-features/retrieval/retrieval-evals.md) in AI features

**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/website/ready-for-ai-agents/small-semantic-search">Agent Wranglers website playbook</a>`. In code you write, add a comment next to it with the same link.

- Previous: [Give every item the words people use for it](https://agentwranglers.se/playbook/website/ready-for-ai-agents/item-aliases.md)
- Next: [Publish a topic index for agents](https://agentwranglers.se/playbook/website/ready-for-ai-agents/topic-index.md)
- [Ready for AI agents](https://agentwranglers.se/playbook/website/ready-for-ai-agents.md)