851
likes
67
comments
daily view 0
monthly view 0

Share

Live Analytics

Comments 0

You Don't Need Kubernetes to Deploy LLM Apps πŸš€ Here's an Easier Way Analytics Table

Income Estimates for You Don't Need Kubernetes to Deploy LLM Apps πŸš€ Here's an Easier Way

Based on this YouTube video's total view count of 58.5K views and industry-standard rates, the estimated total earning is $41 - $117 through ad revenue. Historical data is not yet available to calculate daily, weekly, or monthly averages.

About You Don't Need Kubernetes to Deploy LLM Apps πŸš€ Here's an Easier Way

Explore You Don't Need Kubernetes to Deploy LLM Apps πŸš€ Here's an Easier Way with 58,585 views, 851 likes, and 67 comments. Experience the impact of this video content that has captured audience attention.

Anyone can build an LLM Application... But the moment you want to publish it as a real service for real users - things get complicated VERY quickly! πŸ’€πŸ”₯ The hardest part is taking a local app that works perfectly on your computer and turning it into a public app that serves different users with different conversations - running 24/7 from any device. πŸ˜΅β€πŸ’« So today, we will take MariyaGPT β€” a real full-stack LLM application with an independent frontend, backend and database β€” clone it, and deploy it to production using the most beginner-friendly technique I could think of! πŸš€ Instead of becoming Kubernetes experts, we will click a few buttons, enter a bit of text, and get the same kind of production setup without all the headache. We will simply use Sevalla, a hosting platform that integrates all the powers of Kubernets directly into its UI. We’ll use Sevalla to publish all three parts of our app, PostgreSQL to store users and conversations, and OpenRouter to connect our backend to the LLM. We’ll also set up automatic scaling so our resources can grow and shrink as needed, and I’ll show you how to update the app even after it’s already live by pushing changes through GitHub. πŸ‘‰ Deploy your own LLM app with Sevalla: https://sevalla.com/?utm_source=pythonsimplified&utm_medium=Referral&utm_campaign=youtube πŸ“š What You'll Learn πŸ“š β€’ Why deploying an app to production is different from running it locally β€’ How a frontend, backend, PostgreSQL database and LLM work together β€’ Why the frontend, backend and database should run separately β€’ How to deploy a PostgreSQL database with Sevalla β€’ Why it’s important to hash user passwords before storing them in PostgreSQL β€’ How to organize independent frontend and backend components on GitHub β€’ How to update your production LLM app after it’s published using Sevalla Auto Deploy β€’ How to connect your production LLM app to OpenRouter β€’ How to configure environment variables and private networking β€’ How to configure automatic horizontal scaling β€’ How to deploy a full-stack LLM application to production πŸ› οΈ Tech Stack πŸ› οΈ Python FastAPI Flask PostgreSQL OpenRouter Sevalla GitHub HTML / CSS / JavaScript πŸ’‘ What we're building πŸ’‘ Our production application consists of four independent pieces: Frontend β†’ The interface users interact with Backend β†’ Application logic, authentication and security Database β†’ Users, conversations and messages OpenRouter β†’ Connects our backend to the LLM Instead of putting everything on one machine, each component can run independently. If one part gets busy, we can give just that part more resources instead of scaling everything else. πŸŽ₯ Previous PostgreSQL & Sevalla Tutorial: ⭐ Python PostgreSQL Flask GUI App - Build and Publish with Live Database: https://youtu.be/sFSFrxlLMq8 πŸ’» Commands Used in the Video πŸ’» 1. Create the PostgreSQL tables: psql \ -h HOST \ -U USER \ -p PORT \ -d DATABASE \ -f schema.sql 2. Generate a secure SESSION_SECRET: python -c "import secrets; print(secrets.token_urlsafe(64))" 3. Backend start command: uvicorn app:app --host 0.0.0.0 --port 8080 4. Frontend start command: gunicorn --bind 0.0.0.0:8080 app:app πŸ”— Resources πŸ”— ⭐ MariyaGPT Source Code: https://github.com/MariyaSha/MariyaGPT ⭐ Deploy your own MariyaGPT Fork with Sevalla: https://sevalla.com/?utm_source=pythonsimplified&utm_medium=Referral&utm_campaign=youtube ⭐ OpenRouter: https://openrouter.ai ⏰ Timestamps ⏰ 00:00 Intro 01:15 Local Apps vs Production Apps 02:40 The 4 Problems We Need to Solve 06:06 MariyaGPT Production Architecture 07:30 Clone the Project from GitHub 08:55 Deploying with Sevalla 09:30 Deploy the PostgreSQL Database 13:30 Deploy the Backend 14:40 Connect the Backend to PostgreSQL 16:13 Configure Environment Variables 17:22 Connect the LLM with OpenRouter 20:49 Deploy the Frontend 24:32 Set Up Automatic Horizontal Scaling 26:08 Deploy MariyaGPT to Production 27:30 Test the Live LLM App 28:40 Check Users & Conversations in PostgreSQL 30:10 Update the Live Application 31:15 Sevalla Auto Deploy from GitHub 32:12 Final Result πŸš€ If you build something really cool, don't forget to share it with me on social media! Tag me so I can see what you come up with! 😎 Find me on: LinkedIn: @mariyasha888 X: @MariyaSha888 Instagram: @mariyasha888 #Python #LLM #Sevalla #Kubernetes #PostgreSQL

About YouTube Real-Time View Count

With SocialCounts.org’s view counter, track your YouTube video’s live view count and YouTube likes count in real time with fast, reliable updates.

Watch every YouTube video live view count rise with our real-time YouTube views trackerβ€”built for accuracy and minimal delay.

Follow YouTube real time views as they happen, using our dedicated view counter for YouTube videos.

Get up-to-date live view count on YouTube and see real-time growth with SocialCounts.org’s smart tracking tools.

Embed Widget

Parameters:

  • fullscreen=true - Fullscreen counter
  • graph=true - Live graph chart
  • counter=0/1/2 - Select counter (0=likes, 1=views, 2=comments)
URL

Click to copy the embed URL to your clipboard