Cloud
Start instantly, scale instantly
Use the full power of Lector as SaaS, always up to date.
For Developers and IT Teams.
Documentation, interfaces, integrations and operations – everything you need to connect Lector, in one place.
Documentation
Look It UpInstead of Asking.
API Documentation (opens in a new tab)
Interfaces for developers
Product Documentation (opens in a new tab)
The guide to working with Lector
Changelog (opens in a new tab)
What has changed in the product
Releases (opens in a new tab)
Release packages for DevOps
Status Page (opens in a new tab)
Availability of the Lector Cloud
Integrations
Lector FitsInto Your World
No system migration. No parallel operation. Lector integrates with your existing infrastructure.
Input
- REST API
- SFTP / file system
- Messaging / webhook
- Your own apps
Classify · Extract
Check · Route
Output
- Webhook
- REST API (pull)
- DMS / ECM / archive
- ERP
- Databases
- Cloud storage
- RPA (UiPath, Power Automate)
Standard input channels and webhook exports
Simple JSON structures for smooth integration into your systems
Well-documented interfaces (OpenAPI) and pull export via REST
Quick Start
Three Stepsto Your First Results.
Simple Configuration
Describe document classes and fields, choose an AI model, save.
Lector Does the Processing
Lector classifies, extracts and checks every incoming document.
Receive Structured Results
Check the results on your own documents and refine the description in short cycles.
Operations
Cloud, Hybridor in Your Own Data Centre.
For maximum control we offer hybrid and on-premise deployment alongside our cloud solution.
Hybrid
The best of both worlds
Use the power of state-of-the-art LLMs from the cloud within your own infrastructure.
On-Premise
Full control, full sovereignty
Run Lector in your own network with maximum data sovereignty.
On-Premise System Requirements
A system running Ubuntu with at least 16 CPU cores (32+ recommended), at least 32 GB RAM (64 GB recommended) and around 1 TB of storage. AI processing requires a GPU, e.g. Nvidia H100 (80 GB) or RTX 6000 Ada (48 GB).
Monitoring and Quality
Every processing step is traceable: Lector keeps an immutable history per document (audit trail), shows straight-through-processing rates per document class and provides usage statistics for system and AI components. Confidence values are provided for certain AI models. KPIs can be pulled into your own reporting via GraphQL, system metrics monitored via Prometheus. For quality itself there is the Evaluation Center: compare settings and models on real documents before they go live.
Consulting & Integration
We Build Your Document FactoryWith You.
Not a self-service project that ends up on your desk: our team sets up document classes, fields and the connection to your systems together with you.