I will deploy a private self hosted ai llm chatbot on your own server

T
tomvinsonneau
T
tomvinsonneau
Tom Vinsonneau
Sommige informatie wordt in het Engels weergegeven.

Over deze dienst

Your company data should not leave your infrastructure. I deploy a fully private AI assistant on YOUR server. No OpenAI, no data sent to third parties.


WHAT YOU GET

  • Ollama or vLLM installed and tuned on your Linux server (CPU or GPU)
  • - Open-source model of your choice: Llama, Mistral, DeepSeek, Qwen
  • - Clean web chat interface (Open WebUI) with user accounts
  • - HTTPS, firewall and server hardening
  • - OpenAI-compatible API so your apps can plug in
  • - Optional RAG: the AI answers from YOUR documents
  • - Written documentation and a handover call

WHY ME

I am a French infrastructure engineer running production Linux servers and my own network (AS215142) every day. Your deployment is stable, secure and documented.


WHAT I NEED

SSH access to a VPS or dedicated server. I can advise on the right specs.


FRANCAIS

Je deploie une IA 100% privee sur VOTRE serveur : aucune donnee ne sort de votre infrastructure. Modeles open-source, interface web, HTTPS, API compatible OpenAI, RAG sur vos documents. Contactez-moi en francais !

Maak kennis met Tom Vinsonneau

Tom Vinsonneau

AI DevOps and Network Infrastructure Engineer

  • Afkomstig uitFrankrijk
  • Lid sindsjun 2026
  • Talen

    Frans, Engels, Spaans
Hi, I'm Tom, a French engineer running production infrastructure daily. I'm infrastructure director of a hosting company operating its own network (AS215142). What I do: - Self-hosted AI & LLM: Ollama, vLLM, private ChatGPT, RAG chatbots - DevOps: VPS setup & hardening, Docker, CI/CD, monitoring, anti-DDoS - Systems & Networks: Microsoft 365, Entra ID, Intune, AD, VPN - Dev: Next.js, Node.js, Python, PHP, Flutter Clear communication, documented delivery, real support after handover. Je parle francais : contactez-moi en francais !