Document intelligence · Back office · Finance · Gov

Paperwork in Clean data out

We build end-to-end document intelligence pipelines for scanned invoices, forms, and PDFs in Vietnamese and Japanese—combining layout analysis, OCR, VLM extraction, deterministic schema rules, and a targeted human review queue.

Problem
Scanned invoices and forms in Vietnamese and Japanese, still typed in by hand.
Proven
VI/JA OCR in production: accuracy 94% → 98%, latency ~40% lower.
docs.untern.ai / inbox / HD-0004127.pdf
page 1 / 1VI · JAUploaded

HÓA ĐƠN GIÁ TRỊ GIA TĂNG

請求書 · VAT invoice

Số: 0004127

Đơn vị bán: Công ty TNHH Minh An

Mã số thuế: 0312 457 889

Ngày 18 tháng 11 năm 2026

Hàng hóaSLThành tiền
Thùng carton 5 lớp1,20021,600,000
Băng keo OPP 100y4006,400,000
Pallet nhựa 12006013,200,000
Phí vận chuyển13,818,519

Thuế GTGT 8%: 3,601,481

Tổng cộng: 48,620,000 ₫

(Ký, ghi rõ họ tên) — 署名

Extracted

schema: vat_invoice.v3

Invoice no.
Seller
Tax code
Issue date
VAT 8%
Total
6 fields·1 sent to a reviewerApprove

Architecture

Built for production Not a slide deck

What you get

Concrete outputs Measured on your data

01

Schema-valid JSON

PaddleOCR layout + OCR and VLM extraction validated against your target schema with deterministic rules (totals, tax, dates) and an LLM judge.

02

Human review only where unsure

Pages that pass schema checks flow straight through; uncertain fields route to a Label Studio queue and Next.js review app instead of slowing down the whole batch.

03

RAG-ready index

Extracted documents are chunked and indexed into Qdrant for cited search and Q&A, backed by Triton + TensorRT GPU inference, Redis, and PostgreSQL.

How we deliver

Small team Short loops

  1. 01

    Start from your real data

    A week with your documents, cameras or logs. We agree on one number that means “working” and freeze a test set before we train anything.

  2. 02

    Prototype behind a gate

    Baselines first, then models and agents. Every change runs against the frozen set, so progress is a chart, not an opinion.

  3. 03

    Harden for production

    Quantize, serve, trace and cost it. Retraining, rollback and monitoring are built in, not bolted on.

  4. 04

    Hand over, stay close

    Your team gets the code, the decision records and a walkthrough. We stay on call while it settles.

FAQ

Common questions Direct answers

What languages and document formats does the Document AI pipeline handle?
The pipeline processes scanned invoices, forms, and PDFs ingested from S3, MinIO, or a FastAPI upload API, with production OCR tuned for Vietnamese and Japanese layouts as well as English documents.
How do you prevent noisy scans or OCR errors from reaching downstream systems?
Every extracted record runs through deterministic validation rules—checking fields like totals, tax, and dates—alongside an LLM judge. Only records that fail validation or fall below confidence thresholds are sent to a Label Studio human review queue.
How is Document AI deployed and served in production?
Layout, OCR, and extraction models run on Triton Inference Server with TensorRT on GPU infrastructure, orchestrated with Redis and PostgreSQL, with optional Qdrant indexing and a Next.js review interface.
How do we start a Document AI engagement with Untern?
We start with a week on your real documents, agree on one metric that defines working, and freeze a test set before training or tuning anything. You can begin with a Proof Sprint for a runnable prototype and clear go/no-go numbers before committing to full production.

Have a problem AI should solve?

Tell us what the data looks like and what “working” would mean for you. One of the founders will reply.