Nanonets OCR
for LuumenAI
Read OCR models and past extractions, then run a new document through one
Connect Nanonets OCR and Luumen can see which models your account has, whether each one is ready, and what fields and tables it extracts. It reads back results from documents already processed, page by page. When you need a new document read, it runs the extraction against the model you name and shows you the plan first. Authentication is by API key.
The Nanonets OCR toolbox
6 tools: 5 read, 1 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet OCR ModelGet readiness, accuracy, extraction fields, and table configuration for one Nanonets OCR model.
- ReadGet OCR Prediction FileGet normalized extraction results for every page of one previously processed Nanonets OCR file.
- ReadGet OCR Prediction PageGet normalized extracted fields and tables for one OCR prediction page.
- ReadList OCR ModelsList the OCR models available to the connected Nanonets account, including each model's ID, readiness state, and extraction categories.
- ReadList OCR PredictionsList compact OCR prediction-page summaries for a model within an inclusive UTC date range.
- WriteExtract From Public URLSynchronously extract model-defined fields and tables from one publicly reachable document URL. Approval by default
One prompt, start to finish
What a governed Nanonets OCR run looks like inside Luumen.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — extract from public url — is shown as a plan and requires approval by default. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Nanonets OCR — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut Nanonets OCR to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.