Query your documents with AI, privately
An AI knowledge base (RAG) powered by WeKnora, installed and maintained by DINAO. Ask questions to your own documents — which stay on our French servers, never sent to a third-party provider.
What is WeKnora?
WeKnora is an open source document understanding framework powered by LLMs, published by Tencent. It transforms raw documents into an queryable knowledge base, organized around three capabilities: fast Q&A via RAG for daily searches, an ReAct agent that autonomously orchestrates search, MCP tools, and web navigation for complex multi-step tasks, and a Wiki mode where agents distill documents into a self-maintaining markdown base, featuring an interactive knowledge graph.
The framework supports more than ten document formats (PDF, Word, images, Excel…), can automatically sync sources like Feishu, Notion, or Yuque, and serves answers directly via messaging channels (WeCom, Feishu, Slack, Telegram).
Its modular architecture — document parsing, vector processing, search engine, and inference — is freely configurable. WeKnora is compatible with many model providers, including OpenAI, DeepSeek, Qwen, Gemini, and Ollama for fully local usage.
Host WeKnora at DINAO
Resource tiers compatible with WeKnora prerequisites (minimum 4 vCPU / 8 Go / 20 Go). Hosted in France, fully managed.
- 4 dedicated vCPU
- 8 Go RAM
- 80 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 8 dedicated vCPU
- 16 Go RAM
- 160 GB NVMe
- Daily backups
- Managed & monitored by DINAO
2 hidden tier(s) (insufficient resources for this app) : Découverte, Standard
This application uses AI
The container hosts the application, not the AI engine (which requires dedicated GPUs) : inference is handled externally, with your own provider key. Prioritize a sovereign engine — Mistral AI, NumSpot, Scaleway, or OVHcloud AI Endpoints (France, GDPR) ; an international provider (OpenAI, Anthropic…) only if a specific capability requires it. Inference subscriptions are not included in hosting.
Technical details
You may also like…
Other applications managed by DINAO in the same category, hosted in France and GDPR compliant.
You might be wondering…
What is WeKnora?
WeKnora is an open source framework (published by Tencent) that transforms your raw documents into an AI-queryable knowledge base: Q&A via RAG with sourced answers, autonomous reasoning agent, and self-maintaining Wiki mode.
Are my documents used to train a model?
No. In local mode, your documents, their vector index, and your queries remain private on your instance. No data is shared or used for training.
What models can I use?
WeKnora is compatible with local open-weight models (via Ollama) for sovereign usage, or with external APIs (OpenAI, DeepSeek, Qwen, Gemini, Hunyuan…) if you prefer convenience.
What document formats are supported?
More than ten formats, including PDF, Word, images, and Excel, with integrated parsing, vectorization, and search engine.
Where are my data hosted?
On DINAO infrastructure in France. In local mode, your documents never leave the territory.
