Skip to main content

​
Overview

Web Search Onyx can access the internet for questions that require up to date information or for niche information that the LLM may not be certain about. Users can toggle the Web Search Action on the fly to override the LLM’s decision. If Internal Search was used during the research process, Onyx will seamlessly combine web sources with internal documents in both the answer generation and for displaying in the UI.

​
Requirements

To provide Web Search functionality, Onyx requires both the ability to get search results and to be able to parse websites for more complete context. This is broken down into 1) the search provider and 2) the web scraper.

​
Search Providers

Onyx provides multiple search providers (pricing subject to change, please double check):
NameProviderPriceBenefit
ExaExa.ai$5/1000 queriesAI-optimized with better semantic capabilities.
SerperSerper.devFree tier + $0.30/1000 queriesFast and cost-effective.
BraveBrave Search APIUsage-basedIndependent search index with strong web coverage and simple API-based setup.
Google PSEGoogleFree tier + $5/1000 queriesOfficial Google search results, high-trust option for security-conscious teams.
SearXNGSearXNGSelf-hosted / infrastructure cost onlySelf-hostable metasearch option that can aggregate multiple engines and keep searches private.

​
Web Scrapers

As the Search Providers only give short snippets and metadata, a scraper is used to fetch the full site contents for more complete/reliable answers.
NameRequires ConfigBenefits
Onyx Web CrawlerNoBuilt-in crawler that works for most pages, keeps queries in your deployment, and is free to use.
FirecrawlYes, API key + base URLMore performant with better edge case handling.
ExaYes, API keyFetches and summarizes page content through Exa for teams already using Exa as their search provider.