Two ways in, soon three
REST API for your software and upload in the browser. In preparation: a Hot Folder per client for scanners and file servers.
Document recognition with local AI
docsniff reads invoices, delivery notes and receipts and returns validated, structured data. No cloud AI.
Totals and tax rate plausible
Every document runs through the same pipeline. Scroll along and see what happens to it.
Via REST API or browser upload, soon also via Hot Folder. docsniff spots duplicate documents by their SHA-256 hash.
If the PDF has a text layer, it is used. Scans and photos are read by Tesseract, word by word with a confidence score.
The local language model determines the document type: invoice from DE, NL, FR or GB, credit note, delivery note or receipt.
Each document type has a fixed JSON schema. The model must return valid fields, free-text answers are not possible.
Calculation rules, country-specific tax rates and tolerances check every result. Uncertain documents go to the review view.
Your software retrieves the structured data via REST API, webhooks are planned. You then archive the documents in your own archiving system.
REST API for your software and upload in the browser. In preparation: a Hot Folder per client for scanners and file servers.
Below the threshold, the document lands in the review view, with the original and the fields side by side.
Checks on or off, tolerances and tax rates per country.
Interface in German, Dutch, French and English.
Every file gets a SHA-256 fingerprint. If it arrives a second time, it is recognised instead of being booked again.
Text recognition, language model and database run on the same infrastructure. No document is sent to OpenAI, Google or any other AI provider.
Ollama with a Qwen model on a dedicated GPU. No request leaves the server.
Every record belongs to exactly one client. Without a client set, the database returns nothing at all.
You decide per client how long docsniff keeps documents. Audit-proof archiving remains with your archiving system.
IP ranges allowed per client, plus roles for users and administrators.
The same software in your own data centre, on your hardware. Not available yet. Interested? Just mention it in your enquiry.
PDF, JPG, PNG, TIFF and HEIC. It recognises invoices from Germany, the Netherlands, France, the United Kingdom and Ireland, as well as credit notes, delivery notes and receipts.
These German e-invoice formats already contain their data in machine-readable form and need no text recognition. docsniff is designed for all documents where that data is missing: paper, scans, photos and PDFs without XML.
Only to the docsniff infrastructure. Text recognition and the language model run there, with no calls to external AI services.
If the confidence is below your client threshold or a validation rule is triggered, the document goes to the review view. There you correct the fields with the original right beside them.
Your software retrieves the data as JSON via the REST API. Webhooks and a Hot Folder for scanners and file servers are planned. We will work out together which route suits your software.
The standard SLA provides for 95 % availability. A higher SLA can be agreed on request.
No. docsniff is not an archiving solution under GoBD, the German rules for compliant bookkeeping and archiving. For audit-proof retention of your documents you still need your own archiving or DMS system.
Not yet. A version for operation in your own data centre is planned. If you are interested, feel free to mention it in your enquiry.
Sales and consulting are handled by INOSYS GmbH in Würzburg. docsniff is operated by i can GmbH, also based in Würzburg.
Tell us which documents you deal with. Our sales partner INOSYS GmbH will get back to you with a date for the demo.