Browse categories
English
$
USD
Connect to your AI
I will set up your private self hosted ai server with open webui and ollama
Carlray Edwards
About this gig
I set up Open WebUI, Ollama, and AI model API access on Windows, Mac, Linux, or VPS.
For simple tasks, you can run models locally and when you want to use AI models like Claude, ChatGPT, Gemini, or Grok, you can connect to them via a cloud API.
EVERY SETUP INCLUDES
- Docker with HTTPS, automatic updates and backups
- User accounts with individual logins for each person
- Local models matched to your hardware
- Your API key connected
- Written admin guide (Standard and Premium)
- 30 minutes of one-on-one consulting
Message me before ordering. Orders placed before messaging will be canceled.
ADD-ONS
- I connect your documents to the AI so you can ask questions about your own files $40
- Tailscale remote access $30
- Second machine or server setup $25
- One-hour live walkthrough $30
For your privacy and security, you will create the access to your computer that I'll be using through the terminal. Once the project is complete, you will revoke that access and I will no longer be able to get into your computer.
Looking forward to helping you take your AI setup to the next level.
Get to know Carlray Edwards
Carlray Edwards
Creative and Professional
- FromUnited States
- Member sinceApr 2022
- Avg. response time9 hours
- Last delivery1 year
Languages
English
Hi, my name is Carlray and I am located in Ann Arbor Michigan. I build private, self-hosted technology systems: AI servers that run on your own hardware, media servers, home servers, and the network setup that keeps them safe. The focus is privacy and security where your data stays within your control and you walk away with the know how to manage your new systems. I also do photography, videography and audio and video editing.
FAQ
1 - Do I need a powerful computer or GPU?
No. Before anything is installed, I match models to your RAM and CPU. A GPU only adds speed, it doesn't change what can run. If your machine can't run what you want, I'll let you know before the project starts.
2 - Is this actually private?
Local models run on your machine and nothing leaves it. If you connect a cloud API, those requests go to that provider under your account.
3 - What do you need from me?
You create the access to your computer that I'll use through the terminal, an SSH key or a temporary login, and you revoke it once the project is complete. The requirements form takes about ten minutes.
4 - What are the ongoing costs?
Ollama and Open WebUI are free and open source. Local models run on your hardware. The real recurring cost is a cloud API, paid per use to the provider, and we'll figure out what that costs you during onboarding.
5 - Will it be as good as ChatGPT?
No. Local models are slower and they don't match ChatGPT's level of detail, reasoning, or communication. For simple tasks, they'll do the job. For tool calling, file edits, and scheduled work, you'll want an API model. This is something we can figure out together during the project.
6 - What happens after delivery?
You get a written admin guide covering updates, backups, and user management. Premium includes 14 days of support. After that, follow-up work is available when you need it.
