Add docs for effort in Search Mode

[CShorten]

What's being changed:

Type of change:

• Documentation content updates (non-breaking change to fix/update documentation )
• Bug fix (non-breaking change to fixes an issue with the site)
• Feature or enhancements (non-breaking change to add functionality)

How has this been tested?

• Local build - the site works as expected when running yarn start

[orca-security-eu]

Orca Security Scan Summary

Status	Check	Issues by priority
Passed	Infrastructure as Code	0   0   0   0	View in Orca
Passed	SAST	0   0   0   0	View in Orca
Passed	Secrets	0   0   0   0	View in Orca
Passed	Vulnerabilities	0   0   0   0	View in Orca

[Copilot]

Pull request overview

Adds Search Mode effort documentation and examples, alongside clearer semantic-search behavior.

Changes:

• Documents effort levels and tradeoffs.
• Adds Python and TypeScript examples.
• Expands Search Mode’s conceptual introduction.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.

File	Description
docs/query-agent/guides/search_mode.md	Documents Search Mode and effort.
docs/query-agent/_includes/code/search_mode.py	Adds a Python effort example.
docs/query-agent/_includes/code/search_mode.mts	Adds a TypeScript effort example.

Suppressed comments (2)

docs/query-agent/_includes/code/search_mode.py:114

• The test suite executes this entire file using the repository's locked weaviate-agents 1.7.0, but that release's QueryAgent.search() signature does not accept effort. This call therefore raises TypeError: unexpected keyword argument 'effort'. Please wait for a compatible release and update pyproject.toml/uv.lock as part of this change.

    effort="ultrahigh",

docs/query-agent/_includes/code/search_mode.mts:108

• The repository currently locks weaviate-agents 1.6.0, whose QueryAgent.search() destructures only limit, collections, diversityWeight, and filtering; effort is not forwarded and is silently ignored at runtime. Upstream support is still in open PR #58, so publish a compatible release and update package.json/yarn.lock before adding this example.

    effort: "ultrahigh",

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.