Overview

BLU DELTA Document API

The BLU DELTA Document API is a secure HTTPS-based REST service that leverages advanced AI models to extract structured data from semi-structured business documents.
It supports multiple file formats, including PDF, TIF, and PNG. Documents are uploaded via POST requests, and the API responds with structured JSON for seamless system integration.

Latest Major Version: V2
Endpoint: https://document.bludelta.ai/
API Documentation

Key Features

1. Document Grouping

Automatically groups pages belonging to the same document in multi-page scans.
Example: A single uploaded PDF containing multiple invoices and delivery notes will be analyzed, and the API will return a JSON mapping each page to its respective document.
See API documentation for implementation details.

2. Document Classification

Classifies business documents by type using AI-powered prediction models.
Supported categories include:

Invoice
Order
Delivery Note
And more...
See API documentation for a full list.

3. Data Recognition & Extraction

Extracts key structured fields from semi-structured business documents.
Typical use cases include extracting:

Invoice number, date and total amounts
Order and delivery references
VAT, and currency
Bank details (IBAN, BIC)
Contact information

The recognition model is trained on diverse document layouts, ensuring high accuracy even with varying formats.

If a document type is not recognized or requires customization, please contact: office@blumatix.com

EU AI Act Compliance

BLU DELTA is classified as a "limited-risk AI system" under the EU Artificial Intelligence Act. This classification applies to systems that assist in information extraction without autonomous decision-making. Accordingly, the following principles apply:

Transparency: BLU DELTA uses machine learning models to extract data from documents. This should be clearly communicated to end users.
Function Documentation: The system can extract standard document (Invoice, Delivery Note, etc.) fields (e.g., vendor, amount, date) and also supports customer-specific fields. Depending on the configuration, these fields may be defined manually, rule-based, or with the aid of AI components. Extraction accuracy and limitations should be understood before integration.
Traceability: All model and API versions are documented. Results are traceable and—where applicable—reproducible, depending on the underlying model architecture. Deterministic models provide consistent outputs, whereas models with stochastic elements (e.g., certain LLMs) may yield variable results.
No Autonomous Decisions: BLU DELTA provides structured suggestions, not final decisions. It does not perform accounting, validation, or legal checks.
Responsible Use: Integrators are responsible for ensuring appropriate quality control. Fully automated workflows ("dark processing") must include safeguards like verification steps and logging.

We recommend that partners retain JSON responses for audit purposes and clearly disclose to users when AI-extracted data is used.

Disclaimer – Limitation of Liability

While BLU DELTA aims to provide accurate data extraction, errors may occur due to the probabilistic nature of AI models. The extracted information must be reviewed and validated before use in critical processes. Blumatix shall not be held liable for any damages arising from the reliance on AI-generated results without appropriate human verification. Responsibility for end-to-end correctness lies with the implementing party.