Skip to main content

Prerequisites

  • A FlexOrch account (sign up free)
  • An API key — generate one under Settings → API Keys

Option 1 — Python SDK

1

Install the SDK

2

Upload a document

3

Wait for processing

4

Build a dataset and export

Building a dataset is a separate, explicit step — a completed job doesn’t have one until you build it.

Option 2 — TypeScript SDK

1

Install the SDK

2

Upload and wait

3

Build a dataset and export

Building a dataset is a separate, explicit step — a completed job doesn’t have one until you build it.

Option 3 — REST API (cURL)

1

Upload a document

Response (202 Accepted — the same multi-file-capable shape used for batch uploads, with one entry in jobs for a single file):
2

Poll for completion

Completed response includes processing_summary.quality (grade, score), processing_summary.privacy (PII findings), processing_summary.execution_id (needed for the next step), and execution_summary.degraded.
3

Build and export a dataset


What’s next?

Supported file types

PDF, DOCX, PPTX, XLSX, HTML, XML e-invoices, EML, images — full list.

PII detection

46 types across TR, EU, and US — TCKN, IBAN, email, phone, passport, and more.

Export formats

JSONL, CSV, Parquet, Markdown, XML, XLSX, HuggingFace Arrow.

Automate with connectors

Connect an S3 bucket and process documents automatically.