NetraOCR
NetraOCR is Shivicx's enterprise document intelligence platform. It turns PDFs and images into clean text and structured data — the fields your business actually cares about — ready to review, export, or use in your own workflows.
Unlike a raw text scanner, NetraOCR is built around extraction templates: you describe the fields you want (invoice number, line items, totals, tax IDs, anything), and the NetraOCRx engine returns typed, predictable JSON keyed exactly to your schema.
In one sentence
Upload a document → NetraOCR reads it with the NetraOCRx engine → you get back structured JSON you can act on.
What you can do
- Extract structured data from invoices, receipts, purchase orders, IDs, forms, and more — across PDF and common image formats.
- Define custom templates describing the exact fields and sub-fields to pull, or generate a template automatically with AI.
- Verify document integrity — run forensic and AI-powered tampering checks to flag forged or manipulated documents.
- Bulk process entire folders of documents asynchronously.
- Integrate via API — everything in the console is available over a clean REST API secured with API key + secret credentials.
Two ways to use NetraOCR
How it works
- Upload a document (single, base64, or bulk).
- The NetraOCRx engine reads it with the selected template and extracts the exact fields you defined.
- Optionally, an integrity check runs in the background to detect tampering.
- You retrieve results synchronously (single uploads) or by polling job status (bulk), then review, export, or fetch them over the API.
Where to go next
- New to NetraOCR? Start with Getting Started.
- Want the vocabulary first? Read Core Concepts.
- Integrating programmatically? Jump to the API Overview.
Supported formats & limits
PDF, PNG, JPG/JPEG, TIFF, BMP, and WebP are supported. Single files can be up to 50 MB; bulk uploads up to 600 MB total. See Uploading Documents for details.