• This does not have ChatGPT-like quality of responses, far from it, since this is hosted on a low spec. server (4$ a month) for cost reasons. Production LLMs would need a higher spec., most specifically VRAM.

• For now, this is just a high-level explanation of what tools I used and what they’re for. Currently, I’m focused on working on a centralized data ingestion platform. I’ll update this soon with a complete tutorial. The platform I’m building pulls in context for AI use from multiple sources such as Google Drive, Notion, Jira, and more, and lets you plug chatbots into your app that can use that context.

• Also, open source language models have come a long way, they are getting cheaper to host (requires less resources) and more effective!

Stay tuned for updates!

LLM Provider Data Privacy Concerns

Data privacy has become a real concern since tools like ChatGPT, Claude, and others became popular. For regular users, it might not seem like a big deal. But for companies, there's a risk that sensitive info such as internal documents, code, or client data could be stored or even used by the AI provider if they’re not careful.

There have already been a few incidents. In 2023, Samsung banned ChatGPT after an employee accidentally shared confidential source code. Apple, JPMorgan, and others also restricted its use. Even though providers like OpenAI say they don’t train on API data, many companies still feel uneasy. A KPMG survey found that 78% of business leaders in the U.S. listed data privacy as one of their biggest concerns when using AI.

Because of this, more businesses are starting to host their own LLMs, keeping both the model and the data within their own systems. This gives them more control, helps with compliance like GDPR or HIPAA, and lowers the risk of sensitive data being exposed to external platforms.

My Approach to Self-Hosting LLMs

So what’s the solution? I wanted to explore how these models could be hosted independently without relying on third-party services. The open-source community is amazing because for almost every paid platform or tool, there’s often a self-hostable alternative you can run on your own server or even locally.

Here’s what I deployed:

• Open WebUI
  This is the chat interface. It can save conversations, switch between local models (powered by Ollama), enable web search, and more.

• Ollama
  This handles the models, including downloading, deleting, and running them in the background. It also exposes an inference API, which is really useful.

Ideally, I’d love to run all of this on my own physical server. But I don’t have a home lab setup yet. Running large language models requires a good amount of VRAM, which most budget VPS plans don’t offer.

Quick Note on Cloud Hosting

The whole point of this setup is to give you more control over your data without sacrificing usability. Hosting on a cloud VPS doesn’t give full control, since your data still lives on someone else’s physical servers. Once it's there, you’re bound by the provider’s terms of service. In some cases, they could take down your server and you could lose everything if you're not prepared.

Still, this shows that it’s possible to self-host these tools even on a tight budget. If you want to use LLMs for production, you’ll need a machine with enough VRAM to get something close to ChatGPT-quality responses.

For this setup, I used the cheapest Hetzner VPS (CX22), which costs me €3.99 per month plus €0.60 for IPv4. It’s relatively cheap compared to DigitalOcean.

Try It Yourself

You can test it out here:

Link: openwebui.chrismargate.dev
Email: guest@chrismargate.dev
Password: rVh3qNBUpiqWW1cNEdkoe3v1iQuuTik9+zmg6q74jos=

Hope you enjoyed this short blog! I’ll be updating it soon with more details.

Finding the right YouTube content creators for your game can be a daunting task. Gamer Hunt makes it simple by letting you subscribe to games (your own titles as well as others that are similar) to uncover channels and videos featuring those games.

• Discover Similar Game Creators: Add games similar to yours, and instantly see which influencers are already playing or covering them.

• Find Your Own Game Influencers: Subscribe to your game’s YouTube gaming channel to surface creators who have created content so you can connect directly with relevant voices.

Challenges in Finding Gaming Influencers

1. Fragmented Data Sources
   Game studios often have to manually monitor multiple YouTube gaming channels to see which influencers are driving the most engagement.

2. Time Consuming Research
   Influencer scouting takes hours, or possibly even days, of scanning videos for potential influencers just to find the first 100.

3. Limited Competitive Intelligence
   Without automated scraping, it is hard to benchmark against competitors or discover rising channels before they go mainstream.

Key Features of Gamer Hunt

1. Automated Gaming Channel/Topic Scraping
   Simply add any YouTube gaming channel or topic channel URL, and Gamer Hunt will pull a combination of both the latest videos and most watched/engaged videos, with their data such as the number of views, comments, likes, and much more.

2. Metadata Aggregation and Analytics
   All scraped data is organized in an easy to navigate dashboard. Filter and sort by view count, comment count, likes count, etc.

3. Scalable and Extensible
   Gamer Hunt architecture is designed for growth. Future integrations will add influencer data from Twitch, Twitter, Kick, and more, which will make it the all in one solution for gaming audience insights.

Getting Started with Gamer Hunt

1. Sign Up and Log In
   Create your free account at app.gamerhunt.xyz. No personal data or passwords required! Just your email for verification.

2. Add a Game Subscription (YouTube Gaming Channel)
   At the top of the left sidebar, you will find a dropdown. Open the dropdown and click "Add game". Follow instructions for adding a game and continue until checkout (free!).

3. Voila!
   Wait for your feed to magically get populated by content regarding the game you added. Sometimes, this may take a few minutes, if nothing appears after 2 minutes, refresh the page and you should see all your items!

Special thanks

• Adrian Esguerra (https://www.linkedin.com/in/adrian-esguerra-66139b282/)

  Frontend development and core ideas that helped bring it to life!