> For the complete documentation index, see [llms.txt](https://experience-digital-transform.gitbook.io/experience-digital-transformation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://experience-digital-transform.gitbook.io/experience-digital-transformation/generative-ai/generative-ai.md). # Generative AI Sovereign, open-source generative AI for public-sector knowledge and services, enabling grounded, multilingual AI assistants built on trusted institutional content. ### Sovereign generative AI for the public sector {% hint style="info" %} **GENIE.AI** is an ITU open-source initiative and the practical example behind this Knowledge Product — a sovereign, Digital Public Good (DPG)-compliant Retrieval-Augmented Generation (RAG) platform for the public sector, with multilingual support. {% endhint %} ## What it is Retrieval-Augmented Generation (RAG) means an AI system doesn't just answer from what a model was trained on — it first retrieves relevant passages from an organization's own trusted documents, then answers grounded in that retrieved material. GENIE.AI is built around this idea for the public sector: responses stay grounded in an institution's own knowledge, and the system is designed to abstain rather than fabricate when the knowledge base doesn't contain the answer. It is **sovereign** by design: embedding, reranking, generation, and translation models run on infrastructure the operator controls, rather than depending on third-party model APIs. ## Why it matters * Governments and public institutions can build AI services around their **own trusted information**, not a generic model's best guess. * Because models and data run on infrastructure the operator controls, **sovereignty and data ownership** stay with the institution. * Being **open source** and DPG-compliant reduces dependency on a single proprietary platform. * **Multilingual access** broadens who can use the system: English is GENIE.AI's retrieval source language, while the interface and generated answers are translatable. ## Key Capabilities

:crosshairs:

Grounded answers

Responses are retrieved from real institutional content; the system abstains rather than fabricates when it doesn't know.

:shield-halved:

Sovereign deployment

Embedding, reranking, generation, and translation models run on infrastructure the operator controls.

:code-branch:

Open source

A Digital Public Good, avoiding lock-in to a single proprietary vendor.

:language:

Multilingual access

English is the retrieval source of truth; the interface and answers are translatable.

:cubes:

DPI-friendly design

Deployable via Docker Compose or Swarm, fitting alongside other public-sector infrastructure.

:landmark-dome:

Public-sector focus

Built around chat, search, and document/knowledge Q&A needs — not general-purpose consumer use.

## Explore GENIE.AI {% hint style="success" %} **Explore the full GENIE.AI documentation →** [genie-ai-7e342b.opensource.unicc.org/docs/core/project-overview](https://genie-ai-7e342b.opensource.unicc.org/docs/core/project-overview/) {% endhint %} --- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://experience-digital-transform.gitbook.io/experience-digital-transformation/generative-ai/generative-ai.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.