Crawler Control
Active documentation scraper
Configure target structures, trigger real-time crawl jobs, and audit document drift and semantic vector outputs.
port 11235health / ready / metrics / playgroundweekly buildsamd64 + arm64
Configuration Preset
Define target scraping parameters
One URL per line, or comma-separated. 1 URL queued.
articlemain.content.docs-content.markdown-body
Terminal Output
Real-time execution log from Python subprocess
Subprocess logs will stream here when execution starts.
RAG Exporter Status
Export pipeline metrics and schema details
Total Chunks
0
Format
JSON
Section chunks are parsed and hashes are generated dynamically on completion. Each chunk corresponds to a distinct logical header with associated raw text and code blocks.
Semantic Chunks Preview
First few generated chunks in output/latest/rag_chunks.json
No semantic chunks exported yet.
LLM Drift Log
Changelog derived from Version A (bak) and Version B (new)
Run the crawler twice to perform dynamic drift checks.