Features
Pre-built connectors (Google Drive, Notion, Slack, Confluence, etc.)
Automatic user-data syncing with incremental syncs and auth handling
Multimodal ingestion: text, PDFs, images, audio, video
Hybrid search: vector, keyword, and summary indexes
Entity extraction using plain-language definitions
Ragie Parse: structured data extraction from tables, forms, charts
Agentic OCR (beta) for low-quality scans and complex layouts
Tenant isolation via Partitions
Reranking and recency bias in retrieval
MCP Server and MCP Bridge for agentic knowledge base access
Whitelabel connectors (beta)
Glob-based sync filters to exclude documents by metadata
Webhooks for document status updates (including paused_insufficient_credits)
Base64-encoded image data in document element responses
Multi-language support including RTL
Automated neural architecture search (NAS)
INT8 and FP16 quantization
Hardware-aware optimization for NVIDIA GPUs
Model compression and pruning
NVIDIA TensorRT integration
Benchmarking and performance profiling
Deployment to cloud, edge, and mobile
Custom training with NAS-driven architectures
Computer vision model optimization
Deci AI Studio for model development
Automatic compilation pipeline for target hardware
