> For the complete documentation index, see [llms.txt](https://trust.memori.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://trust.memori.ai/en/legal-documents/gpai-general-purpose-ai-models/gpai-document-dps.md). # GPAI Document: DPs Document for Downstream Providers The DPs (Downstream Providers) document is intended for all providers of AI systems that integrate MemoriNLP into their own products and services. It is the only one of the three documents distributed **proactively** by Memori s.r.l., without the need for a formal request. It contains the technical and operational information needed for proper integration and to fulfill the regulatory obligations of the resulting AI system. ### What the DPs document contains * **Model identification:** name, release dates, dependencies * **Architecture (summary):** hybrid multi-level NLP system, input/output modalities, size * **Distribution channels and license:** SaaS, PaaS, Private Cloud, On-Premise — terms of use, prohibitions, NDA * **Additional services:** AIsuru Academy (paid training on generative AI and agent creation) * **Acceptable Use Policy and intended uses** * **Technical means of integration (DPs only):** RESTful API, JavaScript SDK, step-by-step documentation, code examples (Python, JS, Node.js) * **Required hardware and software:** N/A on the customer side (cloud-based service); minimum browser requirements for web access * **Training data (summary):** type, origin, data curation methodologies ### How to receive the DPs document The DPs document is made available automatically and proactively by Memori s.r.l. to all parties that integrate MemoriNLP. To receive the document, write to **** stating: * **Company name and VAT number** of the organization * **Delivery model used** (SaaS, PaaS, Private Cloud, On-Premise) * **Technical contact** responsible for the integration * **Intended use case** for the resulting AI system {% hint style="warning" %} By integrating MemoriNLP, the customer assumes the role of "AI provider" of the resulting system under the AI Act and must carry out its own risk assessment specific to the implemented use case. The DPs document does not replace this obligation. {% endhint %}

Request DPs