Skip to main content

​
What is FlexOrch?

FlexOrch is a document intelligence pipeline that converts unstructured files — PDFs, Word documents, spreadsheets, emails, XML invoices — into clean, structured datasets ready for LLM fine-tuning, RAG, or analytics. The core flow:
Each step is automated. You get a structured dataset with a quality grade, PII summary, and your choice of export format.

​
Key capabilities

Document types

PDF, DOCX, PPTX, TXT, XLSX, HTML, XML, EML/MSG, JPG/PNG/TIFF — 13 formats processed automatically, with automatic OCR and deskew for scanned pages.

Structured extraction

Invoice, expense report, purchase order, payroll, bank statement, sales proposal, budget, delivery note, tax declaration — 9 schema types.

PII detection & masking

46 PII types across TR, EU, and US jurisdictions. KVKK & GDPR-aligned privacy controls with full audit trail.

Quality scoring

Every document gets a quality score (0–100) and grade (A–D) based on extraction completeness, noise ratio, and OCR confidence.

Export formats

JSONL (fine-tuning), CSV, Parquet, Markdown (RAG), XML, XLSX, HuggingFace Arrow — 9 formats.

Open source audit

flexorch-audit — zero-dependency PII detection and quality scoring library for Python and JavaScript.

​
Plans

​
Where to start

Quickstart

Process your first document in 5 minutes.

API Reference

Full endpoint reference, auto-generated from the OpenAPI spec.

Open Source

Use flexorch-audit independently for PII detection and quality scoring.

Python SDK

Install flexorch-sdk and start processing in a few lines.

MCP Server

Connect Claude and other AI agents to FlexOrch through the Model Context Protocol.