Platform
Platform Features
A complete document intelligence platform. From ingestion to retrieval to streaming AI answers — every component built for production.
Search & Retrieval
Hybrid Search (RRF)
CoreVector + BM25 ranked lists merged with Reciprocal Rank Fusion. Neither approach alone — both working together.
Cross-Encoder Re-ranking
PrecisionTop-N candidates jointly scored against the raw query by a cross-encoder model. The most accurate, most expensive step applied last.
LanceDB Vector Store
StorageS3-native columnar vector store with sub-100ms ANN retrieval. Tiered abstraction separates the embedding provider from the store.
Full-Text BM25 Index
IndexLanceDB built-in FTS keeps keyword and vector search in the same store. Zero extra infrastructure.
Document Ingestion
PDF Type Detection
IntelligenceStructural heuristics detect Native, Scanned, and Sandwich PDFs automatically — choosing the optimal extraction path per document.
WASM OCR (Tesseract)
OCRIn-process OCR via tesseract.js. Page-level rasterization pipeline with progressive status reporting. Force OCR override available.
Office Document Extraction
FormatsDOCX, PPTX, XLSX, ODT and legacy formats (.doc, .xls). Embedded images extracted and OCR-processed separately.
Async Worker Threads
PerformanceIngestion runs in Node.js Worker Threads (or BullMQ in Enterprise). Zero UI blocking. Auto-classification included in the async pass.
AI & Chat
Streaming SSE Chat
UXAnswers stream token-by-token to the browser via Server-Sent Events. No waiting for the full response before reading begins.
Deep-Linked Source Citations
TransparencyEvery answer links back to the exact document, page, and passage used. Click to jump directly to the source.
Multi-Model Support
FlexibilityConnect Local (WASM), Ollama, or Cloud LLMs. Embedding provider is independently configurable from the chat LLM.
Auto-Classification Engine
ComplianceHigh-Water Mark: documents are locked to the highest severity between user-declared and AI-assessed classification. Irreversible downgrade protection.
Security & Access Control
Private-by-Default ACL
Iron-CladEvery vector query is anchored on owner_id. Creators always have access even if no explicit sharing exists. Hard-filter at the engine level.
Defense-in-Depth
Zero-TrustVector ACL filter at retrieval + relational permission cross-check before delivery. Two independent layers, both must pass.
Pre-Signed S3 Downloads
DownloadsDocument downloads use authenticated pre-signed S3 URLs with a strict 60-second TTL. No long-lived access tokens.
AES-GCM Secret Storage
SecretsAll secrets encrypted at rest in S3 using AES-GCM, derived from the operator's master passphrase. Decrypted in-memory on boot only.
Administration
Fleet Health Dashboard
OpsAll nodes report heartbeats every 60 seconds to the shared registry. Ops team sees CPU, memory, uptime, primary/replica status at a glance.
Audit Log
ComplianceEvery share, revoke, classification change, and admin action captured as a high-priority audit event. Immutable append-only log.
System Settings Registry
StatelessAll system-wide configuration lives in the relational DB (system_settings table). Nodes cache with a short TTL — no config files on disk.
Multi-Tenant Groups
TenancyUsers belong to one or more groups with group-scoped roles. Cross-group users are supported. Privacy scoping enforced at every layer.
See it for yourself.
Deploy locally in under 5 minutes. No cloud account required.