Skip to main content

Advanced Search Failovers & PDF Document Parsers

Hiroshi OS supports multi-engine search fallbacks (SearXNG with DuckDuckGo fallback) and local/remote binary PDF text matrix extraction.

ReAct XML Interfaces

Execute queries across localized SearXNG instances or fallback DuckDuckGo HTML indices:
<search engine="searxng">rust async web server</search>

PDF Text Layout Extraction

Perform memory-mapped structural layout parses on workspace PDF documents:
<pdf_extract path="docs/references/api_manual.pdf"/>

Configurations

Configure the default timeout thresholds, SearXNG endpoint URLs, and safety size constraints inside your settings file:
advanced_search:
  searxng_url: "http://localhost:8080"
  fallback_to_ddg: true
  max_pdf_size_bytes: 15728640 # 15MB standard protection cap

Performance Metrics

Measurement Parameter AxisBoundary Limits
PDF Matrix Extraction SpeedParsing and restructuring a dense 5MB layout file executes in < 15ms
Search Deduplication IndexMerging and cleaning alternate cluster engines completes in < 8ms