Auto-Retrain
Automatically re-crawl URL-based knowledge sources to keep your chatbot up to date
Auto-Retrain
Keep your chatbot's knowledge current by automatically re-crawling URL sources on a schedule.
Enabling
In the Knowledge tab, toggle the auto-retrain switch on any URL-type source. Sources show an "Auto-retrain" badge when enabled.
How It Works
- A scheduled task runs every hour
- Finds URL sources with auto-retrain enabled
- Checks if enough time has passed since the last retrain (default: 24 hours)
- Re-crawls the URL
- Compares word count — if content changed by more than 10 words, re-indexes
- If unchanged, skips re-indexing (saves processing)
Status Indicators
| Badge | Meaning |
|---|---|
| Auto-retrain | Enabled, running normally |
| Retrain failed | Last crawl attempt failed |
Configuration
- Interval: 24 hours (configurable per source via
retrainInterval) - Content change detection: Compares word counts before and after crawl
- Skips unchanged content: Only re-indexes when content actually changed
Last updated on