Connect local AI to Nextcloud, SharePoint, or a DMS
Timo Wevelsiep•Updated: 15.08.2026Editorial note: Versions, commands and prices may change. Please verify critical steps independently before production use. This guide does not replace individual consulting.
Start with local AI and add data sources deliberately? The AI Cube Pro provides Open WebUI, a local model, and knowledge spaces. We connect Nextcloud, SharePoint, DMS, and business systems separately after assessing interfaces and permissions. Explore the AI Cube Pro
An AI chat over company knowledge sounds simple: read files, split them, create embeddings, and search. This approach is known as retrieval-augmented generation (RAG). In production, the lifecycle matters more than the first import. New versions, deleted files, changed sharing, and disabled users must reliably propagate to the index.
Two distinct starting points
Manual knowledge spaces
Open WebUI manages files and collections as knowledge. Users or authorised teams upload selected documents and use them in chat. This fits constrained collections, pilots, and content intentionally maintained in Open WebUI.
Automated data sources
If Nextcloud, SharePoint, or a DMS remains the system of record, the AI needs a synchronisation pipeline. It reads approved areas, handles changes incrementally, and carries source, version, permissions, and deletion state as metadata.
This is not a hardware switch. It is a separate software and permission task.
Data path of a RAG pipeline
- retrieve files and metadata through a documented interface;
- distinguish new, changed, moved, and deleted objects;
- extract supported formats with controlled parsers;
- split content into useful retrieval units;
- map users, groups, or tenants from the source and enforce access before vector search;
- update embeddings and versioned metadata;
- filter by permission before retrieval;
- connect answers to source passages and versions.
Nextcloud
Nextcloud exposes files through authenticated WebDAV and provides properties including file IDs, modification time, and permission information. A dedicated technical account with minimal scope is used for integration. Public share links are generally unsuitable for a controlled enterprise index.
Identity mapping remains essential. A service account may read content for indexing, but search must apply the signed-in user's rights. Importing everything with a privileged account does not solve that requirement.
The detailed guide to connecting Open WebUI and Nextcloud covers delta synchronisation, ACL metadata, and deletion for this particular combination.
SharePoint and Microsoft Graph
Microsoft Graph exposes sites, document libraries, DriveItems, and permissions. The application registration receives only necessary rights. Large estates need change tracking, stable object IDs, and a traceable mapping to Entra ID groups.
Sharing links and inherited permissions are more complex than a folder list. Define included sites and verify whether item-level rights can be reproduced before implementation.
DMS and professional software
A DMS connection depends on its API, export facilities, metadata quality, and permission output. Periodic full exports are simple but slow and poor at deletion. Webhooks or change feeds are better when provided reliably.
If a source cannot expose permissions in machine-readable form, constrain scope to generally approved collections, maintain an explicit access mapping, or do not implement the integration. The model must never decide what a user may see.
Product foundation and project scope
The AI Cube Pro provides the local platform with Open WebUI, a model, and manual knowledge spaces. For automated sources, WZ-IT scopes the connector, synchronisation, parser, vector store, access filter, monitoring, and deletion process separately. This keeps the base product quick to deploy while fitting the integration to the real system estate.
Acceptance criteria
- new documents become searchable within the agreed interval;
- a new version replaces old content traceably;
- deleted or withdrawn content disappears from retrieval and answer context;
- users with different rights receive different results;
- answers expose source and document version;
- parser, synchronisation, and stale-index failures are monitored.
Sources
Rather have it operated?
You'd rather not run Local AI for Business yourself? WZ-IT handles setup, operations and maintenance - privacy-focused from Germany.
Enquiry
Assess local AI for your use case
Start with the AI Cube Pro or have us assess a custom AI platform, knowledge connection, or integration.
Frequently Asked Questions
Answers to the most important questions
Documents can be uploaded manually into knowledge spaces. A continuously synchronised Nextcloud, SharePoint, or DMS connection needs a separate pipeline for retrieval, changes, permissions, and deletion.
No. Permissions must be read from the source, mapped to identities in the AI system, and enforced before every retrieval. The source must be assessed to determine whether it exposes sufficient information.
A production pipeline detects deletion or permission withdrawal and removes related chunks, metadata, and embeddings from the search index. A one-time import cannot provide this lifecycle.
Open WebUI and its manual knowledge spaces are included. Automated data sources, custom RAG pipelines, and interfaces are scoped separately by system, data volume, and permission model.
More on Local AI for Business
- The open-source LLM stack
- What is LiteLLM?
- What is Langfuse?
- What is vLLM?
- vLLM vs. Ollama
- What is RAG?
- Connect Open WebUI to Nextcloud (RAG with ACLs)
- What is local AI?
- Cloud AI vs. self-hosted
- AI sovereignty for companies
- Which LLM to self-host?
- Sizing GPU & VRAM
- Inference vs. Training
- Qdrant vs. pgvector
- The EU AI Act for companies
- Local AI for confidentiality professions
- Processing documents with AI
- AI agents & automation
- RAG with permissions
- Chatbot or knowledge navigator?
- AI agents: permissions and approvals
- AI assistants and the works council
- GDPR-compliant AI: assessment criteria
- What does a local AI server cost?
- Size a local AI server by users
- LLM models on 128 GB unified memory
- RAG with Nextcloud, SharePoint, and DMS
- Provide secure remote access to local AI
- Connect AI Cubes with ConnectX-7
- Run Open WebUI as a production appliance
- Configure ASUS Ascent GX10 for business
- Configure NVIDIA DGX Spark for business
- Configure Acer Veriton GN100 for business
- Configure Dell Pro Max with GB10 for business
- Configure Gigabyte AI TOP ATOM for business
- Configure HP ZGX Nano G1n for business
- Configure Lenovo ThinkStation PGX for business
- Configure MSI EdgeXpert for business





