Unkey

Improving the UX in your own authentication is a small win with massive impact. I wrote about how Unkey spent time improving the experience for returning users. https://lnkd.in/eKuGpwC5

Happy Friday! Time for an Unkey update! 🚀We now allow permissions and roles to be created via the API 🔐 You can attach them to your API Keys via the API 🚅 If you are creating LLMs apps you can now sign up and get a semantic cache in 1 click. https://lnkd.in/exakxkhf

A simple way to improve performance when using #LLMs is to cache responses using the user query as the key. This has the disadvantage of only allowing for caching of exact matches. A more useful form of caching is semantic caching: caching based on the embedding of the query, and returning a response if the query passes a threshold of semantic similarity. This allows for a higher cache hit rate, meaning faster responses for your users and a reduced bill. With our new Unkey semantic cache gateway it takes 5 seconds. We support streaming for real time responses, for chat applications. 1. Visit https://lnkd.in/eaa4RD7C and enter a name for your cache gateway. 2. Set your baseURL to the gateway URL. 3. Make a request to your new gateway. You will see new logs arrive at the logs page https://lnkd.in/eagDKCub. After the first new request, subsequent requests will be cached. 4. Check your analytics and see your savings including time, money and how many tokens were served through the cache Check out how you can have faster, cheaper LLM responses. Want to see it in action? Check out our semantic caching chatbot demo.. Try something like... "Draft an email to my boss about the following: How great Unkey is" https://lnkd.in/eRXVUx4i

One more thing.. Audit logs are generally available on Unkey Automatically track every event in your Unkey workspace for - ✅ compliance - 🐞 easier debugging - 🕵️ detecting security breaches https://lnkd.in/ewKsxKwZ

Day 5 of Unkey accelerate 🚀 Now you can recover keys again after creation! 🔐👀 When building your UI, you can now show the plaintext keys, not just when creating new keys. You don't have to worry about encryption or storage, simply retrieve keys in plaintext via our API Check out the full details: https://lnkd.in/ebEFcD_D

It's day 4 of Unkey accelerate: We launched our API Toolbox an opinionated CLI for building better APIs using: - Cloudflare workers - Hono.js - Turso Database - Your choice of Drizzle or Prisma - Documentation using Fumadocs - Unkey features built in You can get started with npx @unkey/create-api or read about the release below: https://lnkd.in/ezc3m7Bf

Launchweek day 3 for Unkey: Semantic Caching Faster, cheaper LLM API calls Try it out here: https://lnkd.in/eRXVUx4i Read the details here: https://lnkd.in/eQbcfxb4

Launchweek Day 2 for Unkey Releasing our serverless cache package for typescript, backed by any storage - tiered caching - stale-while-revalidate - fully typesafe Checkout out the blog post for more details! https://lnkd.in/gX5meUSf