> For the complete documentation index, see [llms.txt](https://pmse.gitbook.io/pmse-dhdk/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://pmse.gitbook.io/pmse-dhdk/1.-project-charter/1.1-project-description-and-scope.md).
# 1.1 Project Description and Scope
Project Name
GNA AI-Powered Chatbot Application - PROTOTYPE
Project ID
GNACHAT-PT-2025-001
Grantor or Customer
Istituto Centrale per l'Archeologia (ICA) - Ministero della cultura
License
MIT License
{% hint style="info" %}
Project ID:
* **GNA: Geoportale Nazionale per l'Archeologia**
* **CHAT:** Stands for "Chatbot", representing the core focus of the project.
* **PT**: Prototype.
* **2025:** The year the project is initiated.
* **001:** Sequence number to distinguish it from future projects.
{% endhint %}
| Document Version | Date | Contributor | State |
| ---------------- | ---------- | ----------------- | ----- |
| 1.0 | 03/02/2025 | Lucrezia, QA Team | Final |
The GNA Chatbot Application is an advanced AI-powered software solution developed to streamline customer service operations through the use of machine learning and natural language processing (NLP) technologies. This application will empower the grantor to automate and optimize user interaction processes, leading to faster response times, reduced operational costs, and more personalized user experiences. It will query and generate knowledge-driven responses using data from the user manual of **Geoportale Nazionale per l'Archeologia**, ensuring relevant and accurate information is provided to users.
## Scope and Objectives
The primary goal of the AI-powered chatbot application is to improve access to structured information regarding the procedures for cataloging Italian archaeological sites and cultural heritage artifacts, as adopted by the Istituto Centrale per l'Archeologia (ICA). By extracting, organizing, and processing information from the user documentation of the Geoportale Nazionale per l'Archeologia, the AI Assistant lays the groundwork for a knowledge-intensive application. The machine learning system, supported by the textual database, integrates both retrieval mechanisms and generative AI to provide precise, contextually relevant, and well-informed responses to user queries, in Italian language.
Initially, a **demo version** will be developed to showcase potential functionalities to the grantor and stakeholders, using a modular and iterative approach to understand user needs and refine technical methodologies. This demo will serve as the **Minimum Viable Product (MVP)**, focusing on core capabilities to validate key assumptions and gather early feedback. Based on insights from this phase, the chatbot will be enhanced and iteratively improved. Ultimately, the full application will be deployed and seamlessly integrated into the GNA's web platform.
### Prototype
The prototype involves the development of a machine learning-based system designed to support user interactions. It includes the operation of a vector database to compare queries and retrieve relevant information from the knowledge base. Additionally, Mistral LLM integration is incorporated. The user interface is designed to ensure seamless customer interaction and support. Reference documentation will also be provided to assist with further extension and development.
**Expected Outcomes**:
* **Demonstration of core functionality**: Showcase the primary features and capabilities of the system to stakeholders and potential users.
* **Proof of concept**: Provide a working version of the application that serves as a foundation for further development and deployment.
* **Identification of improvement areas**: Highlight potential issues and gather suggestions for enhancements to be addressed in future versions.
* **User feedback collection**: Gather insights from initial users to refine the application and identify areas for improvement.
### Full Application
The ultimate scope is to design, develop, and deploy a chatbot application that leverages AI and knowledge retrieval systems to provide users with intelligent and contextually accurate responses from a structured dataset. The goal of the project is to develop a fully deployed application hosted on the GNA web-based platform with user documentation.
**Expected Outcomes**:
* Fully functional AI application capable of processing and responding to customer inquiries.
* A backend infrastructure for data storage and model management.
* Integration with existing customer relationship management (CRM) system.
* Documentation and training materials for end-users and technical teams.
***
See also *Definitions, Acronyms, and Abbreviations*:
{% content-ref url="/pages/ZLxSqWOWH0wzdcPDDdvR" %}
[2.1 SRS Introduction](/pmse-dhdk/2.-software-requirement-specification/2.1-srs-introduction.md)
{% endcontent-ref %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://pmse.gitbook.io/pmse-dhdk/1.-project-charter/1.1-project-description-and-scope.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.