Articles tagged ai.
Free Redis databases for AI agents, in one HTTP request
POST https://upstash.com/start-redis returns a free Upstash Redis database. No signup and no API key needed. Perfect for AI agents.
Running OpenClaw and Hermes on Upstash Box
AI infrastructure is moving fast. New gateways, new agent frameworks, new runtimes. The hard part is no longer finding the right tool. It's finding a stable place to run it. Today we're publishing…
Remote Development with Upstash Box
Remote development is having a moment. Here's why it matters and how Upstash Box makes it work for the way people actually build today.
Why Web Search Fails AI Agents (and What Context7 Fixes)
Large language models are fundamentally constrained by their training data. In practice, that means a fixed knowledge cutoff, where newer APIs, version changes, and evolving documentation are out of…
Context7 is Ready for Enterprise
Context7 now ships an on-premise edition with content scanning and moderation, addressing the data privacy and safety concerns that slowed enterprise adoption.
Building a really fast virtual filesystem for AI agents
How to build a virtual filesystem on top of Upstash Redis, with Redis Search powering grep for AI agents.
Running Symphony with Upstash Box in Minutes
It picks up tasks from your backlog, writes the code, and opens a pull request, without any sleep. Did you guess a developer? The correct answer is Symphony, and today we're showing you how to run it…
Ahi: A Framework to Run Independent Agents
Ahi is an open-source framework for running each agent in its own isolated container with tools, skills, durable data, and a schedule. No orchestration. No deployment. The Ahi name comes from the…
I Built 5 AI Agents to Review My PRs
We recently launched Upstash Box — a cloud computer for your agents with durable storage, serverless scaling, and usage-based pricing. Since day one of building the backend, the team has been pretty…
Upstash Box: Give your agents a computer
Upstash Box is a cloud computer for AI agents with durable storage, serverless scaling, and usage-based pricing. Run code, agents, and commands in isolated sandboxes.
Introducing Context7 Skill Wizard
The Context7 Skill Wizard auto-generates high-quality skills for AI from up-to-date documentation.
Quality and Safety in Context7
Library benchmarks, deduplication, version analysis, and content moderation in Context7.
Inside Context7's Quality Stack
How we keep Context7 documentation up to date.
Resumable AI SDK v5 Streams with Upstash Realtime
Build AI chat streams that survive page refreshes and network disconnects using Vercel AI SDK v5, Upstash Workflow, and Upstash Realtime.
Vercel Workflow vs Upstash Workflow
A detailed comparison of Vercel Workflow and Upstash Workflow.
Fast, Cost-Effective MCPs with Redis
How Upstash Redis powers production MCP servers
Adding AI Assistant to Docs in Minutes with AI SDK & Context7
Building AI assistants for documentation used to require complex RAG pipelines, vector databases, and constant maintenance. Not anymore. With AI SDK and Context7, you can add a production-ready AI…
Smooth Text Streaming in AI SDK v5
There's one pattern I've noticed over and over again in some of the most polished AI chat interfaces. This pattern is used by huge companies like Anthropic in production and make the AI chat…
Saving AI SDK v5 Chat Messages in Redis
I wrote an updated 2026 version of this article for Vercel AI SDK v6 over at xadd.dev! In 2023, Vercel introduced the first version of their AI SDK. In their words, it started as: "An interoperable,…
Quick Apply: Building a Serverless AI Interview Assistant
Job interviews are ripe for AI disruption. What if an AI could handle the initial screening conversation with candidates, freeing up human recruiters until it's time to engage the top prospects? I…
Making Next.js Navigation Fast af
Next.js has been my go-to framework for building full-stack apps for years. Built-in API routes, image optimization, and good integrations, there are a lot of reasons to use it. But there's one part…
F*ck Clean Code, You Need an Idea
There's a software development philosophy that aligns perfectly with my understanding of shipping ideas extremely fast. I've seen it work again and again over the past year. It helped me launch…
Build an AI Assistant with Dify and Upstash
In this blog, we'll build an AI assistant using Dify AI and Upstash. This assistant can: Store content and search knowledge from uploaded files using Upstash Vector and Dify's file uploading Make…
How to Build LLM Streams That Survive Reconnects, Refreshes, and Crashes
In this article, we're building extremely durable LLM streams that easily survive: Network outages Page refreshes Closing the website Closing the laptop lid Bonus: You can view the same stream on…
Context7 MCP: Up-to-Date Docs for Any Cursor Prompt
Last month, we introduced Context7 - a way to stop Cursor, Claude or any LLM from generating broken, outdated code. The idea: feed your LLM the latest documentation for the libraries you're using —…
Introducing Context7: Up-to-Date Docs for LLMs and AI Code Editors
I've spent the last year building with AI coding assistants. They're magical — when they work. But unless you're using a popular library that hasn't changed much since the model's training cutoff,…
Building an autonomous AI Twitter Agent
In this article, we'll build a completely autonomous AI agent that: finds the latest top story generates a summary and cover image tweets about the story using one of the most modern, convenient…
Building a RAG Chatbot for the Health Domain with Next.js
In this tutorial, we'll dive into how we built a modern Health Assistant application using Next.js, Upstash, Vercel AI SDK, LangChain, and OpenAI. The Health Assistant project exemplifies how…
Run Deepseek R1 on your local machine using Ollama
The great thing about open-source LLM models is that you can run them on your local machine, so you do not pay the providers while developing your application. In this mini tutorial, we will show you…
Building Email Analysis Agent with DeepSeek
Imagine having an AI assistant that could automatically analyze incoming emails, understand attached documents and suggest professional responses - all while maintaining the context of the…
Introducing Sparse and Hybrid Indexes
We are excited to announce a significant upgrade to our vector index. Upstash Vector now supports sparse and hybrid indexes! Up until now, Upstash Vector supported dense indexes for semantic…
Auto Translate your Website with OpenAI and Upstash Workflow
In this tutorial, you will learn how to automate i18n translation of a website using Upstash Workflow for task scheduling and OpenAI for translations. You will also learn to interact with the GitHub…
Optimize LLM Applications: Semantic Caching for Speed and Savings
Imagine you have an LLM-powered chatbot managing customer support inquiries. Whether you’re using OpenAI or a similar provider, as traffic grows, so do your costs, since most providers charge based…
Scheduling Audio Transcriptions with QStash
In this tutorial, you will learn how to build a scheduled audio transcription system using Upstash QStash for task scheduling and Fireworks AI for AI-powered transcriptions. You will also learn…
Adding Semantic Search to a Directus Application
In my previous blog, we reviewed how to add semantic search to a Strapi Application. In this blog post, we will explore how to add semantic search to a Directus application, another popular headless…
Build a RAG Chatbot with Upstash, OpenAI, Clerk, and Next.js
In this post, you will learn how to build your own career coach with Upstash Vector, Upstash Redis, OpenAI API, Clerk, Next.js App Router, and Vercel. Upstash RAG Chat SDK simplifies the per-user…
Adding Semantic Search into a Strapi Application
Semantic search is a searching technique that allows users/searchers to find relevant content that matches the query by its meaning. This technique uses vector representations of the content to find…
Building a PDF Chatbot with Upstash RAGChat
Recommendation from the Upstash Team: The RAG Chat SDK is designed to create prototypes more easily and quickly. For real projects, use Langchain, LlamaIndex, and the Vercel AI SDK. Chatbots are…
We Made RAG Chat Development Easier Than Ever
Recommendation from the Upstash Team: The RAG Chat SDK is designed to create prototypes more easily and quickly. For real projects, use Langchain, LlamaIndex, and the Vercel AI SDK. Are you tired of…
Indexing Millions of Wikipedia Articles With Upstash Vector
Upstash offers a vector database that enables scalable similarity searches across millions of vectors, complete with features such as namespaces, metadata filtering, and built-in embedding models. We…
Accurate AI Responses with Peaka's RAG Pipeline and Upstash Vector
The era of artificial intelligence (AI) is here, presenting vast opportunities for harnessing data for business purposes. However, these prospects are not without their hurdles, including…
Building AI Applications using Upstash and Vercel AI SDK
In this blog post, we will delve into the AI applications that can be created using Upstash Redis, Upstash Vector, and the Vercel AI SDK. We'll explore the unique features and capabilities of each…
Build an AI Powered Mobile Chatbot with Expo and Cloudflare AI
Imagine a smartphone e-commerce striving to ensure its customers enjoy seamless shopping. But how can they achieve this goal? Research suggests that tailored product suggestions play a vital role. In…
Trying Llama3 on Groq with Vercel AI
I have a list of things to try. Recently, after the ChatGPT and AI storm, this list is growing very fast. Groq and Vercel AI are on this list. Today, I will create a very basic app which will utilize…
Comparing Retrieval-Augmented Generation With Fine-Tuning
Large language models (LLMs) like GPT-4 or Claude Opus know the answer to many questions. Their creators trained them on the Internet, so they are jacks of all trades. However, this training takes a…
LangChain Explained?
Since large language models (LLMs) have risen in popularity, everyone wants to integrate AI into their product. While LLMs offer new ways to interact with data that can improve the UX of a product,…
DegreeGuru: Build a RAG Chatbot using Vercel AI SDK, Langchain, Upstash Vector and OpenAI
Welcome to this blog post, where we will talk about the inception and evolution of the DegreeGuru chatbot application utilizing Retrieval Augmented Generation (RAG) approach. Here, we delve into the…
Upstash Vector: Serverless Vector Database for AI and LLMs
Today, we're introducing Upstash Vector, a serverless vector database built for working with vector embeddings for AI models and LLMs. Upstash Vector will help you efficiently store and query…
Serverless LLM Scheduling with QStash and OpenRouter
Large language models (LLMs) are the hype right now; everyone wants to integrate them into their application and claim they’re using state-of-the-art “AI”. There are plenty of LLMs, each accessible…
How Upstash is Fueling PlanTripAI's Growth
In this article, I explore the pivotal role of Upstash in the development of PlanTripAI, an AI-driven trip planning startup.
Building an AI Chatbot trained on custom content with LangChain, Faiss and Next.js
In this post, I talk about how I built an open-source Custom Content AI Chatbot with Upstash, Next.js, LangChain and Fly.io. Upstash helped me to schedule model training, offered way of generous rate…
How to Create an AI Postcard Sender with Upstash QStash
In this article, we will look at how to make an AI Postcard sending app at a high level. We will focus mainly on scheduling tasks with Upstash QStash, a serverless message queue and task scheduler.…
Chat Model Response Caching With Upstash Redis in LangChain TS
LLMs can be a resource drain in production, consuming both time and money as user queries scale into the millions of tokens. Current chat models lack efficiency, often resulting in subpar user…
Caching LLM Output On-Demand with LangChain, Redis and QStash
In some applications, it may not be feasible to query an LLM when a user requests it. The process of sending a prompt to an API and waiting for its response can be particularly time-consuming. For…
How to create an AI app with Upstash, Next.js and Replicate
In this article, we will show you how to rate limit a Next.js app using Upstash Redis. We will be rebuilding lofianime.com, an app that generates AI images with a Stable Diffusion model on Replicate.…
Retaining Chat History Using LangChain and Upstash Redis
LangChain provides a simple interface to conduct conversations between a human and an AI. It can be easily configured to use , enabling you to store conversation history in memory. This may be…
Redis and Upstash Use cases with OpenAI Applications
Recently, we have observed many developers integrating Upstash with OpenAI and other AI APIs, such as Google Cloud AI, IBM Watson. Hugging Face. In this post, we will discuss the most common use…
AI Powered Text Generator using Next.js, Replicate and Redis®
With AI becoming more accessible, companies like Replicate have made it easier to integrate machine learning models into projects seamlessly. In this article, I'm going to discuss how I built…
