# Agentic Document Analyser

> VLM-powered document-to-structured-JSON pipeline for compliance evidence processing.

Source: https://aiexponent.com/docs/agentic-document-analyser · Content verified 2026-10-04

Converts unstructured compliance documents (risk assessments, model cards, contracts, audit logs) into structured JSON using Vision-Language Models. Acts as the evidence processing layer for the AiExponent compliance toolchain. Feeds Article 11 technical documentation and Article 19 automatically-generated-log preservation workflows.

- EU AI Act: Articles 11 + 19 (Evidence Processing)
- Source: https://github.com/aiexponent/agentic-document-analyser
- Licence: Apache License 2.0

## Quick start

```bash
docker compose up
```

## Features

- Vision-Language Model (Qwen2-VL) for unified layout analysis and OCR in a single pass
- Detects and classifies document elements: text blocks, headings, tables, figures, form fields, signatures
- Returns precise bounding boxes for every detected element
- Parallel page processing for multi-page PDFs
- Structured JSON output consumable by downstream compliance tools
- Docker Compose deployment: four microservices, one command

## Known limitations

- Requires Docker Compose; no standalone pip package available.
- Depends on Fireworks AI API key; no offline/local inference by default.
- No persistent storage; results are not retained between container restarts.
- No authentication on the /analyze endpoint, so it is not suitable for public deployment without a reverse proxy.
- Alpha quality: no production hardening, rate limiting, or database backend yet.

## Contributing

Issues: https://github.com/aiexponent/agentic-document-analyser/issues · Contributing guide: https://github.com/aiexponent/agentic-document-analyser/blob/main/CONTRIBUTING.md

---

Not legal advice. Not a notified body. The tools produce evidence, not conformity assessment.
All docs as Markdown: https://aiexponent.com/llms.txt · Guide for coding agents: https://aiexponent.com/agents.md