https://docs.ai.gwdg.de/en/categories/chat-ai/index.htmlHugoenhttps://docs.ai.gwdg.de/en/user/ai-services/coco-ai/code_completion/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/coco-ai/code_completion/index.htmlMany code editors feature LLM integration these days. Code completion tools provide inline suggestions as you type, helping you write code faster by predicting the next line. They help by completing function signatures and suggesting entire code blocks based on context. They also offer a chat interface for explaining, generating, and editing code directly in your editor. Info To use the internal models hosted on our platform with the below mentioned tools, you need a SAIA API key. If you don’t have one yet, refer to SAIA API keys to request one. The external models are not available via the API.https://docs.ai.gwdg.de/en/user/ai-services/coco-ai/agentic_coding/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/coco-ai/agentic_coding/index.htmlAgentic coding goes beyond chat and inline suggestions. These tools leverage the model’s ability to autonomously complete multi-step tasks. It’s able to read your codebase, edit files, and run terminal commands. Info Comparison with commercial models: The Commercial Models - Agentic coding page covers agentic coding workflows using external providers such as Codex and Claude Code. OpenCode and Claude Code support both commercial-provider API keys and a SAIA API key; the sections below describe the SAIA setup for both. The tools described below provide comparable agentic coding capabilities using your SAIA API key and models hosted on GWDG’s HPC infrastructure. This allows users to benefit from modern coding assistants while keeping data processing within the institute’s infrastructure, helping to meet data protection, compliance, and confidentiality requirements. For many research and administrative use cases, this provides a practical alternative to external AI services without sacrificing core agentic coding functionality.https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/models/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/models/index.htmlChat AI provides a large assortment of state-of-the-art open-weight Large Language Models (LLMs) which are hosted on our platform with the highest standards of data protection. The data sent to these models, including the prompts and message contents, are never stored at any location on our systems. Additionally, Chat AI offers models hosted externally such as Anthropic Claude and OpenAI GPT-5. Available models are regularly upgraded as newer, more capable ones are released. We select models to include in our services based on user demand, cost, and performance across various benchmarks, such as HumanEval, MATH, HellaSwag, MMLU, etc. Certain models are more capable at specific tasks and with specific settings, which are described below to the best of our knowledge.https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/faq/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/faq/index.htmlData Privacy Are my conversations or usage data used for AI training or similar purposes? No, whether you use internal or external models, your conversations and data are not used to train any AI models. When using internal models, are my messages and conversations stored on your servers at any stage? No, user messages and AI responses are not stored at any stage on our servers. Once your message is sent and you receive the response, the conversation is only available in your browser.https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/features/personas/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/features/personas/index.htmlChat AI supports loading preset personas from configurations in the form of JSON files. Each JSON file includes the system prompt, settings, and conversations, allowing you to easily load a persona into Chat AI. While these files can be imported using the import function, Chat AI also supports directly importing public JSON files from the web, by specifying it in the URL. Example personas If all you need is a quick link to load a specific persona, this is your chapter. These are some of the interesting and useful personas the AI community came up with:https://docs.ai.gwdg.de/en/user/ai-services/arcana/rag-service/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/arcana/rag-service/index.htmlWarning This service is currently in beta phase and is updated regularly. The same applies to the documentation. RAG (Retrieval-Augmented Generation) is an advanced AI technique designed to improve the accuracy, reliability, and contextual relevance of AI-generated responses. Traditional AI models, such as large language models (LLMs), rely solely on pre-trained data to generate answers. While these models can provide insightful responses, they are limited by the information they were trained on, which may become outdated or may not cover specific topics in detail.https://docs.ai.gwdg.de/en/user/ai-services/arcana/getting-started/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/arcana/getting-started/index.htmlWarning This service is currently in beta phase and is updated regularly. The same applies to the documentation. Table of contents: First Login Creating an Arcana Uploading Files Viewing your Access Link Updating files in an Arcana The process screenshots contain blank blocks. These are in the positions that will be replaced with the username. First Login Go to the main Arcana page and click on register. You will need to log in with your Academic Cloud account first.https://docs.ai.gwdg.de/en/user/ai-services/arcana/how-to-use/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/arcana/how-to-use/index.htmlWarning This service is currently in beta phase and is updated regularly. This also applies to the documentation. Warning Previously, RAG/Arcanas only worked with specific models. This is no longer the case, and Arcanas now work with every model. The previous method of using Arcanas with models that have ‘RAG’ in their name (or the little book icon) will not be supported in future. Please use the GWDG Tools as described below!https://docs.ai.gwdg.de/en/procurement/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/procurement/index.htmlAvailable AI Products Within the Academic Cloud The Academic Cloud is a modular service portal available nationwide for universities, colleges, and research institutions. As a shared platform, it enables the provision, development, and use of digital services across institutional boundaries and supports cross-institutional collaboration.https://docs.ai.gwdg.de/en/user/ai-services/arcana/api-usage/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/arcana/api-usage/index.htmlWarning This service is currently in beta phase and is updated regularly. The same applies to the documentation. The Arcana Manager exposes and api endpoint for you to use. With the api endpoint you can perform all the actions that the frontend Arcana Manager is capable of. To use the API, you’ll first need an API key, which you can request on our website. This key works across all our services. If you’re already using the LLMs via the api, you can use the same key. Otherwise you can request your key following this documentation.https://docs.ai.gwdg.de/en/user/ai-services/arcana/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/arcana/index.htmlArcana is a Retrieval-Augmented Generation (RAG) service that enables you to interact with Documents - such as research papers, manuals, or study materials - using natural language. The Arcana service works together with our Chat AI Service. LLMs benefit from RAG (Retrieval-Augmented Generation) by using the relevant information provided in a Document Collection (Arcana) for generating more accurate, reliable, and contextually grounded responses. In order to use it, you need to activate your account for the Arcana page and set up an Arcana following the Getting Started Guide. Once this is done, you can share it with colleagues or the public. Details about this process can be found in the usage examples.https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/index.htmlChat AI is a web service that provides access to a wide range of large language models (LLMs) through a feature-rich, user-friendly interface. It offers a curated selection of popular open-weights models running in our own data center, alongside anonymized access to external models from commercial providers. The web interface is hosted on GWDG’s cloud infrastructure and securely forwards your requests through our scalable SAIA backend to the selected model, routing either to local HPC hardware or, for models marked as external, to the commercial vendor’s service endpoint. Our AI team updates the list of supported models regularly and is continuously developing new features.https://docs.ai.gwdg.de/en/user/ai-services/coco-ai/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/coco-ai/index.htmlCoCo AI is our AI-assisted coding service, utilizing Chat AI and is accessible via your SAIA API key. It brings large language models directly into your development environment for code suggestions, chat-based assistance, and autonomous multi-step coding tasks. Getting Started Before configuring any tool, you need: A SAIA API key. If you don’t have one yet, request one here. A supported editor or terminal. See the sections below. A model to use. Browse the available models. We recommend starting with qwen3-coder-30b-a3b-instruct or devstral-2-123b-instruct-2512 for coding tasks. Info Only models hosted on GWDG’s HPC infrastructure (internal models) are available via the API. External models (e.g., GPT-4, Claude) are accessible through the Chat AI web interface only and cannot be used with CoCo AI.https://docs.ai.gwdg.de/en/user/ai-services/arcana/docling-process/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/arcana/docling-process/index.htmlWarning This service is currently in beta phase and is updated regularly. The same applies to the documentation. The RAG Service provides users with an efficient way to upload and process PDF documents using Docling. The system converts uploaded PDFs into Markdown format while also automatically annotating them. This enhanced Markdown output, referred to as Markdown Plus, includes metadata and structural annotations for improved document parsing and customization.https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/features/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/features/index.htmlThis section collects all functionality that extends and customizes Chat AI beyond basic text generation. Features let you shape the assistant’s personality, integrate external knowledge, and configure model behavior for different use cases. The Version history is also tracked here, showing which features were added or updated in each release. Available Features Memory Memories are pieces of information that the chatbot can learn from conversation to behave in a more personalized way. Personas Define roles and tones for the assistant (e.g., interviewer, tutor, casual style). Personas make it easy to quickly switch the model’s behavior. Arcana / Retrieval-Augmented Generation (RAG) Connect your own data sources (documents, notes, datasets) to ground responses in factual context. Tools Chat AI models are given access to a variety of tools to accomplish non text-based tasks or improve responses. Web search Image Generation Image Modification Text to speech (tts) MCP Support You can add custom public Model Context Protocol (MCP) servers to Chat AI.https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/features/mcp/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/features/mcp/index.htmlChat AI supports adding public Model Context Protocol (MCP) servers as tool providers to your Chat AI experience. This tool requires a model context protocol server URL, which should be a simple HTTPS address. In general this allows Chat AI to interact with additional tools, data sources, or further processing capabilities beyond what is built into Chat AI. Any data from your Chat AI context may be sent to the server you entered.https://docs.ai.gwdg.de/en/user/ai-services/arcana/public-arcanas/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/arcana/public-arcanas/index.htmlWarning This service is currently in beta phase and is updated regularly. The same applies to the documentation. Here is a list of public links for Arcanas. These are sorted in categories and contain public material. Please refer to the How to use section of you need help working with these. GWDG Services Contains knowledge about the GWDG Services and Documentation. Example question: Welche Dienste könnte ich als Forscher bei der GWDG nutzen? Institute for Computer Science Contain knowledge about the computer science study track. Example question: Wie funktioniert der Studiengang angewandte Informatik? In case you find a broken link, please let us know via our support contacts.https://docs.ai.gwdg.de/en/user/ai-services/arcana/support/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/arcana/support/index.htmlWarning This service is currently in beta phase and is updated regularly. The same applies to the documentation. If you run into problem using this service please contact our KISSKI support We also need your help providing publicly available Arcana links. If you have one that you think is relevant to a larger group of users, please also reach out to us so we can publish it.https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/features/tools/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/features/tools/index.htmlOverview This document describes a custom multimodal tool server hosted on GWDG infrastructure. It provides core AI capabilities: image generation, image editing, text-to-speech (TTS), and web search, accessible directly through the Chat AI UI. These tools are designed to enrich user interaction by enabling dynamic media creation and transformation within conversational workflows. Prerequisites To use the tool server, the following conditions must be met:https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/features/versions/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/ai-services/chat-ai/features/versions/index.htmlThis page lists all Chat AI releases, starting with the newest. Each entry describes new features, improvements, and fixes, with short explanations for how to use them. v0.9.0 — September 2025 New Features Redesigned UI A fresh interface with collapsible left and right sidebars for maximum chatting space. Optimized for handling arbitrarily large conversations and attachments smoothly.