IMPETUS Expert Agent

Description

This repository contains the code for the Retrieval Augmented Generation (RAG) System, an artificial intelligence tool developed as part of the European project IMPETUS. The RAG system is designed to facilitate access to and synthesis of project-specific information by integrating advanced retrieval and generation models. It allows users to query key project results in natural language, providing contextually accurate responses and references to source documents.

The RAG is part of the functionalities of the IMPETUSPlatform, aimed at enhancing navigation and interaction with the knowledge generated during the project.

Project Context

The IMPETUS project seeks to strengthen regional climate resilience through innovative approaches, including federated knowledge strategies. This system supports the strategy of sharing knowledge in a decentralized and scalable manner, enabling collaboration across multiple demonstration sites and platforms.

Key Features of the RAG System:

1. Document Processing: Works with deliverables, technical reports, and other project-generated data.
2. Semantic Search: Implements an embedding-based system to capture the semantic meaning of texts for effective retrieval.
3. Response Generation: Synthesizes clear and relevant responses by combining retrieved documents.
4. Transparency and Traceability: Each response includes references to the original documents.

System Architecture

The system is based on a modular architecture that includes the following core components:

• Interface Module: Handles communication between the system backend and the user.
• Retrieval Engine: Manages data indexing and retrieves relevant information.
• Language Model: Generates responses based on the queries and context provided by the retrieval engine.
• Logger: Records relevant information for analysis and continuous improvement.

License

This project is licensed under the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International (CC BY-NC-ND 4.0) license.

You are free to:

• Share: Copy and redistribute the material in any medium or format.

Under the following terms:

• Attribution: You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
• NonCommercial: You may not use the material for commercial purposes.
• NoDerivatives: If you remix, transform, or build upon the material, you may not distribute the modified material.

For more information, see the full license text.