AI tutorials
Discover how to build, deploy and run AI applications in production on Koyeb. The fastest way to deploy applications globally.
Use FLUX, PyTorch, and Streamlit to Build an AI Image Generation App
Learn how to use the FLUX model to generate images based on prompts in real-time.
Use Stable Diffusion and PyTorch to Build an Image Inpainting Service
Learn how to create an image inpainting service using Stable Diffusion and Gradio and deploy it on Koyeb.
Fine-Tune MistralAI and Evaluate the Fine-Tuned Model on Koyeb Serverless GPUs
A step-by-step guide to learn how to fine-tune MistralAI on domain-specific knowledge and evaluate the fine-tuned model's performance.
Fine-Tune Llama 3.1 8B using QLORA on Koyeb Serverless GPUs
Learn how to fine-tune an Llama 3.1 8B using QLORA on your favourite project's documentation. This will enable the model to answer questions with (hopefully) correct, and up-to-date information.
Deploy Portkey Gateway to Koyeb to Streamline Requests to 200+ LLMs
Learn how to deploy Portkey Gateway, a request and prompt router for LLMs with a unified API, and build an application that can query more than one LLM easily.
Deploy Fooocus and Generate AI Images on Koyeb GPUs
Learn how to deploy and configure Fooocus, an AI-based image generation tool, on Koyeb.
Build a Video Processing Pipeline with AssemblyAI on Koyeb
Learn how to build a powerful video processing pipeline with AssemblyAI and deploy it to Koyeb
Using LlamaIndex and MongoDB to Build a Job Search Assistant
Learn how to build a job search assistant with LlamaIndex using Retrieval-Augmented Generation (RAG) and MongoDB.
How to Deploy Flowise to Koyeb to Create Custom AI Workflows
Learn how to set up Flowise, a platform for creating customized LLM orchestration workflows and AI agents, on Koyeb.
Using Autonomous AI Agents with SerpApi and AutoGPT to Build a Trip Planner
Learn how to create a trip planning application using autonomous AI agents in order to plan trips by analyzing user requirements and preferences.
Using Groq to Build a Real-Time Language Translation App
Learn how to use Groq, speech-to-text (STT), and text-to-speech (TTS) to build an app to automatically translate between languages in real-time.
Use LlamaIndex to Build a Retrieval-Augmented Generation (RAG) Application
Learn how to build a retrieval-augmented generation application to query general AI models with specific contextual information.
Build a Multimodal Chat App using LLava, Chainlit, and Replicate
This tutorial walks through how to build a multimodal vision chat app powered by LLaVa, Chainlit, and Replicate.
Build a Retrieval-Augmented Generation Chatbot using pgvector
In this tutorial, we show how to deploy an RAG chatbot built with the OpenAI embedding API, Replicate, pgvector, and the Koyeb Managed PostgreSQL service.
Use LlamaIndex, Streamlit, and OpenAI to Query Unstructured Data
Learn how to use LlamaIndex, a data framework specializing in context augmentation, to quickly query general LLMs with custom data.
Use MistralAI, FastAPI, and FastUI to Build a Conversational AI Chatbot
This tutorial walks through how to build a chatbot powered by MistralAI, with FastAPI as the backend and FastUI as the front end.
Use AutoGen, Chainlit, and OpenAI to Generate Dynamic AI Personas
Learn step-by-step how to set up and utilize AutoGen within Chainlit. You'll discover how to create and interact with AI personas that are tailored to your specific needs, be it scriptwriting for YouTube content or ideating SaaS products.
Use pgvector and Hugging Face to Build an Optimized FAQ Search with Sentence Similarity
In this tutorial, we showcase how to deploy a FAQ search service built with Hugging Face's Inference API, pgvector, Koyeb's Managed Postgres. The optimized FAQ Search leverages sentence similarity searching to provide the most relevant results to a user's search terms.
Use LangChain, Deepgram, and Mistral 7B to Build a Youtube Video Summarization App
This guide explains how to build a YouTube video summarization using Langchain, Deepgram, and Mistral 7B. Deploy your AI workload on Koyeb to enjoy high-performance microVMs, seamless scaling, and fast global deployments.