Overview
KnowledgeBase goes beyond basic RAG with powerful features for production use: intelligent auto-detection, per-source processing, dynamic document management, and fine-grained search tuning.Auto-Detection
Automatic loader and splitter selection based on file type and content
Indexed Processing
Different loaders and splitters for each source file
Direct Content
Ingest raw text strings without files — mix with file sources
Vector Search Tuning
Fine-tune top_k, similarity threshold, hybrid alpha, and filters per Task
Document Management
Add, remove, refresh, and update documents after initial setup
Storage Persistence
Persist document metadata to a storage backend for tracking and auditing
Isolated Search
Scope queries to a single KnowledgeBase when sharing a collection