> 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/2.-software-requirement-specification/2.4-system-architecture/2.4.1-general-application-diagram.md).

# 2.4.1 General application diagram

The diagram below presents the overall architecture of the full version of the **GNA AI Assistant Application**, showing its key components and their interactions. It follows a structured AI pipeline from data sources to user consumption.

<figure><img src="/files/yP8Z3jN6LtWQUhAmPkY4" alt=""><figcaption><p>General application diagram.</p></figcaption></figure>

#### **Key Functionalities:**

1. **Data Sources**

   The AI assistant gathers data from multiple sources:

   * **HTML** (web pages)
   * **MediaWiki** (structured knowledge from wikis)
   * **CSV** (tabular data)
   * **Chat logs** (conversational data)
2. #### **Backend Development**

   This module handles software requirements, unit testing, and modular software components (e.g., Python-based functions) to ensure reliability.
3. **AI Pipeline Development**

   This is the core AI system responsible for:

   * **Coding** the AI logic
   * **Training and configuring** the model
   * **Validating** the model's performance
   * **Evaluating** results to improve accuracy
4. **Data Management**

   Ensures high-quality data through:

   * **Extraction** from sources
   * **Validation** of integrity
   * **Cleaning** of inconsistencies
   * **Standardization** for consistency
   * **Curation** for optimal AI development
5. **Model Deployment**

   The trained AI model is:

   * **Packaged** for distribution
   * **Containerized** for scalability
   * **Deployed** to a hosting service
6. #### **Serve (Hosting Service)**

   The AI model is hosted on a server to provide responses to user queries.
7. #### **Consume (Chatbot Application)**

   Users interact with the AI assistant via the chatbot interface.
8. #### **Monitoring**

   Performance and user interactions are monitored to ensure continuous improvements.

#### <mark style="color:blue;">**Flow of Information**</mark>

1. Data is collected and processed through **Data Management**.
2. The AI model is developed, validated, and evaluated in **AI Pipeline Development**.
3. The model is deployed and hosted in **Serve**.
4. The chatbot application allows users to interact with the assistant.
5. Performance is continuously monitored for refinements.

This architecture ensures a well-structured and efficient AI-powered chatbot assistant for the **Geoportale Nazionale dell’Archeologia (GNA)**.


---

# 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/2.-software-requirement-specification/2.4-system-architecture/2.4.1-general-application-diagram.md?ask=<question>&goal=<endgoal>
```

`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.