Adjusting default search assistant

[Weves]

Description

^

How Has This Been Tested?

Tested search assistant locally.

Backporting (check the box to trigger backport action)

Note: You have to check that the action passes, otherwise resolve the conflicts manually and tag the patches.

• This PR should be backported (make sure to check that the backport attempt succeeds)
• [Optional] Override Linear Check

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
internal-search	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Apr 2, 2025 11:35pm

[greptile-apps]

PR Summary

This PR updates the default search assistant persona in backend/onyx/seeding/personas.yaml by increasing the number of document chunks to 25 and disabling the LLM relevance filter for safer query processing.

• Updated default "Search" persona by increasing num_chunks from 10 to 25.
• Disabled llm_relevance_filter to prevent rate limit issues with some LLM providers.
• Verify that increased context does not trigger token overflows or degrade response quality.

_{1 file(s) reviewed, no comment(s)
Edit PR Review Bot Settings | Greptile}