DigitalOcean - Videos
Back to Channel
Cloud Chats Episode 74: DigitalOcean MCP Server, MS Build, Google I/O and Codex
In this episode, we will explore our newly launched DigitalOcean MCP Server. We dive into some of the major announcements made in MS Build and Google I/O, most importantly what it means for us. Als...
Accelerate Growth with Smart Cloud Solutions for Indian Businesses
Managing cloud infrastructure doesn’t have to be complex and costly. Join us for an exclusive webinar to learn how DigitalOcean and Tata Tele Business Services can simplify cloud solutions for gro...
From Prompt to App in Minutes - Introducing the DigitalOcean MCP Server
The *DigitalOcean MCP Server* for App Platform is now available. https://github.com/digitalocean-labs/mcp-digitalocean/ In this video, Amit Jotwani, Developer Advocate at DigitalOcean, walks thro...
Deploy LLMs in DigitalOcean Managed Kubernetes Cluster
In this video, Yash Sharma, Developer Advocate at DigitalOcean, shows how you can deploy and serve large language model (LLM) using multiple GPUs in managed DigitalOcean Kubernetes cluster which en...
Enhance Your GenAI Solutions through Agent Insights
The demo highlights how users can leverage Agent insights for cost forecasting, monitoring performance metrics and even effective troubleshooting. This in turn brings in transparency and enables us...
Cloud Chats Episode 73: Gemini 2.0, LLM Evaluation Framework and AI Powered Travel Companion
We’ll be exploring models such as Gemini 2.0 and its image generation capabilities, as well as AM-Thinking-v1, which focuses on reasoning. We’ll also cover Opik, an LLM evaluation framework, and Gl...
Sail to Success: What's New on the GenAI Platform
Join us for our monthly “What’s New in GenAI” webinar, where our product experts will walk you through the latest updates and improvements to the GenAI platform. Stay in the loop and get your quest...
Cloud Chats Episode 72: Should You Really Be Using AI for That?
This week, we’re questioning the default instinct to throw AI at everything. Writing, coding, problem solving....even thinking. One professor says he’d rather see a student’s prompt than their AI-g...
Blum on Scaling Products, Not Complexity
Blum is a fast-growing cryptocurrency trading platform that blends gaming, crypto onboarding, and finance. With nearly 100 million users and 10 million daily active users across 90+ countries, Blum...
New GPU Droplets accelerated by NVIDIA
Learn about DigitalOcean’s latest GPU Droplets to accelerate your AI workloads, including the newly-available NVIDIA RTX 4000 Ada Generation, NVIDIA RTX 6000 Ada Generation, and NVIDIA L40S.” Join...
New GPU Droplets accelerated by NVIDIA
Join us for an in-depth look at the latest updates to DigitalOcean's GPU Droplets offering. Learn about new, powerful solutions from NVIDIA that can accelerate your workloads, enhance performance, ...
Marketcircle on Moving to the Cloud
Marketcircle’s application Daylite is dedicated to helping small businesses manage everything from customer management to project management and sales engagement. Before moving to the cloud, Market...
Shark Tales: Jason Dobry
Join the Discord conversation: https://discord.com/invite/digitalocean Follow us on X: https://x.com/digitalocean Like us on Facebook: https://www.facebook.com/DigitalOceanCloudHosting Follow us on...
API rate limiting using DigitalOcean’s Managed Caching for Valkey
In this video, Haimantika Mitra showcases how you can build an API rate limiter using DigitalOcean’s Managed Caching for Valkey. Valkey’s in-memory data structure and atomic operations, makes it an...
Cloud Migrations Done Right: Kubernetes, Databases, and Dev Velocity
Modern cloud migrations aren't just about lifting and shifting workloads—they're about rethinking your architecture to improve velocity, scalability, and maintainability. In this webinar, we’ll wal...
Review Your Cloud Architecture to Support Business Growth
As your cloud environment grows, inefficiencies in architecture can lead to rising costs, resource waste, and scalability bottlenecks. Without regular reviews and refinements, businesses risk payin...
Managed Caching for Valkey: A Sneak Peek into Our Upcoming Database Engine
We're hosting a live webinar to introduce you to our upcoming database engine, Managed Caching for Valkey: our fully managed, high-performance caching solution. This session will guide you through ...
AI-Powered Technical Support: Automating Issue Analysis from Screenshots
In this video, Narasimha Badrinath showcases an AI-powered technical support assistant that analyzes user-shared screenshots to identify and resolve issues efficiently. 00:00 - Introduction to the...
Build a Real-Time Kubernetes AI Agent with GenAI | Step-by-Step Tutorial
In this tutorial, we'll show you how to create a real-time AI-powered Kubernetes assistant using DigitalOcean's GenAI platform and Functions. Learn to set up your GenAI agent, connect it to Digital...
Chat with Your Images: Llama Vision Instruct Model on a 1-Click GPU Droplet
In this video, Narasimha Badrinath demonstrates an app powered by the Llama Vision Instruct Model, deployed on a 1-Click GPU Droplet, designed to answer questions about any image. 00:00 - Intro 00...
Visual Question Answering with Llama 3.2 HuggingFace
In this tutorial you will learn how to implement a scalable, cost-efficient, and streamlined approach for implementing AI-driven image processing. By using GPU Droplets for compute power and Digita...
Using GPU Droplets to build RAG Agent using a Graph DB
Ever wonder how to go beyond token-level insights? Check out our new RAG demo using Named Entity Recognition to link documents in a knowledge graph—unlock deeper context and more precise queries th...
Automating Kubernetes Deployments on DigitalOcean with GitOps Principles
In this video, Yash Sharma, Developer Advocate at DigitalOcean, highlights how you can automate DigitalOcean’s managed K8s deployments with tools like ArgoCD. He has also discussed how you can leve...
GenAI: Using Function Calling to retrieve real-time data
One of the biggest challenges with AI models is their inability to access real-time data from external sources. But what if you could build an AI-powered agent that connects to APIs and provides up...
Sail to Success: Introducing the GenAI Platform
In this recorded webinar, DigitalOcean experts explore the GenAI Platform, showcasing how developers can easily build, deploy, and scale production-ready AI applications. Learn how our platform s...
Easily Manage Access to Your DigitalOcean Spaces Buckets
Struggling with data access management? With DigitalOcean Spaces, setting up permissions is simple and hassle-free. Whether you're running a photography business or any other data-driven operation,...
Your Daily Dose Of AI - An Agentic Way to Stay Updated
In this video, Narasimha Badrinath, Senior Developer Advocate at DigitalOcean, demonstrates a simple app built with an agentic approach to help users stay updated on the latest developments in AI. ...
Simplify Cross-Region Routing with VPC Peering
In this video, Yash Sharma, Developer Advocate at DigitalOcean, highlights the importance of VPC peering for secure cross region traffic routing. He also discusses how DigitalOcean can help to set ...
Scale cloud native workloads securely with Internal Load Balancer
In this video, Yash Sharma, Developer Advocate at DigitalOcean, highlights the importance of internal load balancer to scale private cloud native workloads with security. He also discusses how Digi...
Build Scalable Cloud Native Application With Global Load Balancer
In this video, Yash Sharma, Developer Advocate at DigitalOcean, highlights the importance of global load balancer to scale your cloud native applications while making sure applications are resilien...
CrewAI + DeepSeek + GenAI Platform = Modern Agentic Stack
In this video, Narasimha Badrinath, Senior Developer Advocate at DigitalOcean, demonstrates how to build a Market Research Assistant using amazing technologies like GenAI Platform, DeepSeek R1, and...
Multi-Agent Chat Solution on GenAI Platform
In this demo, Narasimha Badrinath, Senior Developer Advocate at DigitalOcean, showcases how a multi-agent chatbot solution can be built on the GenAI Platform using function routing. 00:00 - Intro...
Create a Droplet Autoscale Group Using POSTMAN for API Calls
Learn how to create a Droplet Autoscale group that enables seamless horizontal scaling by automatically adding or removing droplets in response to workload demand (using POSTMAN for the API calls)....