Applications → Ollama + Qdrant
Ollama runs open-source large language models locally on your ReefOffice server. Qdrant stores vector embeddings that make your documents searchable. Together they power private AI — no data ever leaves your server to be processed by an external AI provider.
Ollama handles the compute — it downloads, loads and runs open-source AI models (LLaMA, Mistral, Qwen, Phi, Gemma and hundreds more) directly on your server. Qdrant provides the memory — it stores vector embeddings (mathematical representations of text meaning) that enable semantic search across your documents. Every ReefOffice plan uses Qdrant to index document contents for search; Private AI plans add Ollama-powered generation for answering questions about your documents.
Ollama runs hundreds of open-source models on your server's CPU or GPU — LLaMA, Mistral, Qwen, Gemma, Phi, DeepSeek and more. Models are downloaded, cached and executed locally. No API calls to external providers, no data leaving your infrastructure.
Qdrant stores vector embeddings of your files, invoices, contracts and notes. Semantic search finds documents by meaning, not just keywords. Built-in on every ReefOffice plan — your documents are indexed automatically.
On Private AI plans, Ollama generates answers from your document corpus. Ask "which invoices are unpaid?" or "summarise the latest contract" — the answer is generated on your server from your indexed documents, with source references.
Choose the model that fits your use case. Run a small, fast model for everyday chat, a multilingual model for document Q&A, or a larger model for complex reasoning. Switch between models with a single command.
Private AI plans include dedicated GPU capacity on ReefOffice infrastructure in Germany. For local-only setups, Ollama uses CPU with optimised inference — slower but entirely private. Optional external model keys can supplement local capacity.
Every ReefOffice plan automatically indexes your documents using bge-m3 embeddings via Qdrant. New files in Nextcloud, Paperless and Dolibarr are processed without manual setup — your document corpus stays searchable from day one.
Technical detail
Ollama wraps llama.cpp for efficient local inference with support for GPU acceleration, quantised models (GGUF format) and prompt caching. On ReefOffice it runs as a NixOS native service. Qdrant is a high-performance vector database written in Rust, running as a Docker container with persisted storage and API-key authentication. Documents are embedded using bge-m3 (a multilingual, MIT-licensed model) and stored in Qdrant — all on your ReefOffice server.
Ollama powers Open WebUI for private ChatGPT-style chat and Hermes Agent for autonomous AI tasks. Qdrant provides the vector search layer used by the ReefOffice document search feature, by Activepieces automation triggers ("when a document matches"), and by Hermes for context-aware agent actions. Both services are internal and API-protected — they are never exposed directly to the internet.
For document search and indexing, yes — embedding generation with bge-m3 runs efficiently on CPU and completes within seconds for typical document volumes. For chat and AI answers, performance depends on model size and hardware. Small models (3-8B parameters) give responsive answers on modern CPU. For larger models or faster generation, Private AI plans include GPU capacity on ReefOffice infrastructure.
Models vary from 1.5 GB (small quantised) to 40+ GB (full-precision 70B models). ReefOffice pre-installs the recommended models for your plan (typically bge-m3 for embeddings and Qwen 2.5 7B for generation). Additional models are downloaded on demand and cached. Storage for vector embeddings depends on document volume — roughly 1 GB per 100,000 pages.
Yes. On plans without local GPU, you can connect an external AI provider key (OpenAI, Anthropic, Mistral AI, or any OpenAI-compatible API). Open WebUI and Hermes will use the external API for generation while keeping your document search and retrieval local through Qdrant. This gives you private search with AI answers generated by a provider of your choice.
Book a demo and see how Ollama and Qdrant on ReefOffice give you private AI capabilities — document search, semantic answers and local model execution — all on your own server.