README.md · GIZ/Asistente

metadata

title: EUDR Assistant
emoji: 🧐
colorFrom: yellow
colorTo: gray
sdk: gradio
sdk_version: 4.44.1
app_file: app.py
fullWidth: true
pinned: false
startup_duration_timeout: 1h
license: apache-2.0
models:
  - BAAI/bge-m3
  - BAAI/bge-reranker-v2-m3
  - meta-llama/Llama-3.1-8B-Instruct

short_description: AI-powered conversational assistant for EU Deforestation Regulation compliance

Technical Documentation of the system in accordance with EU AI Act

System Name: EUDR Chatbot

Provider / Supplier: GIZ Data Service Center

As of: September 2025

1. General Description of the System

EUDR Bot is an AI-powered conversational assistant designed to help you understand compliance with and analyze the EU Deforestation Regulation. This tool leverages advanced language models to help you get clear and structured answers about EUDR requirements, compliance procedures, and regulatory guidance.

It combines a generative language assistant with a knowledge base implemented via Retrieval-Augmented Generation (RAG). In addition to the RAG, the tool also provide quick analysis on the geojson of plot by leveraging the Whisp. The scope and functionality of the tool is focused on EU Deforestation Regulation compliance and related documentation in context of 'Ecuador' and 'Guatemala' only.

2. Models Used

Generative LLM

Model Name: meta-llama/Llama-3.1-8B-Instruct
Model Source API: Nebius AI

Retriever/Embedding

Model Name: BAAI/bge-m3
Model Source: Local Instance

Re-ranker

Model Name: BAAI/bge-reranker-v2-m3
Model Source: Local Instance

External API's

Whisp Info: https://openforis.org/solutions/whisp/
API Endpoint https://whisp.openforis.org/documentation/api-guide

3. Model Training Data

All the models mentioned above are being consumed without any fine-tuning or training being performed by the developer team of EUDR Bot. And hence there is no training data which had been used by the development team of EUDR Bot.

4. Knowledge Base (Retrieval Component)

Data Sources: Public EUDR documentation, regulatory guidance, and compliance materials
Embedding Model: BAAI/bge-m3
Embedding Dimension: 1024
Vector Database: Qdrant (via API)
Framework: Langchain (custom RAG pipeline)
Top-k: 10 relevant text segments per query

5. System Limitations and Non-Purposes

The system does not make autonomous decisions.
No processing of personal data except for the usage statistics as mentioned in Disclaimer.
Results are intended for orientation only – not for legal or regulatory compliance advice.
Users should consult official EU documentation and legal experts for definitive compliance guidance.

6. Transparency Towards Users

The user interface clearly indicates the use of a generative AI model.
An explanation of the RAG method is included.
We collect usage statistics as detailed in Disclaimer tab of the app along with the explicit display in the user interface of the tool.
Feedback mechanism available (via https://huggingface.co/spaces/GIZ/Asistente_EUDR/discussions/new).

7. Monitoring, Feedback, and Incident Reporting

User can provide feedback via UI by giving (Thumbs-up or down to AI-Generated answer). Alternatively for more detailed feedback please use https://huggingface.co/spaces/GIZ/Asistente_EUDR/discussions/new to report any issue.
Technical development is carried out by the GIZ Data Service Center.
No automated bias detection – but low risk due to content restrictions.

8. Contact

For any questions, please contact via https://huggingface.co/spaces/GIZ/Asistente_EUDR/discussions/new or send us email to [email protected]