Alex Rattray’s Post

Hey OpenAI, Can you please include a retrieveAndPoll function in the Assistants API SDK, similar to createAndPoll? Because I still have to write a loop to get the message content from any run that requires an action. 🙏 Also, the method to cancel a run doesn’t work properly, as it keeps the run in a "Cancelling" status until it expires. Thanks! #buildinpublic #code

The products which are productionized are the only ones which generate value. If you are building applications on top of an LLM and want to productionize it then this guide book is of great help. We at KI Reply help iur customers in achieving the same with perfection! Contact Daniel Hummel or Ramakant Agrawal or at [email protected] #productionizellm #value #genai #llamaimdex

Social Media Marketing News & Trends!! #GoogleDocs voice typing coming to #Safari, Edge #Google to run Microfuchsia in a Virtual Machine on Android to make certain tasks more secure Google files Patent for Multi Car Group Navigation feature in #Maps App Google Chrome enhances Listen to this Page with background playback option #GitHub Expands Copilot Enterprise Search in #VisualStudio and #VSCode JFrog and GitHub team up to closely integrate their source code and binary platforms #Devolopers can now Sign up for Private Preview of GitHub #Copilot for #Azure First official #OpenAI Library for .NET goes Beta Java Devs in VS Code can now ask Copilot for #Syntax Rewrites #socialmediamarketingtrends #digitalmarketingtools #digitalmarketingtrends #businessgrowthstrategy #businessanalytics #smallbusinessmarketing #socialmediamarketingtechniques #socialmediamarketingtools

For a #kubernetes refresher, I created and deployed a simple app to Google Kubernetes Engine #gke . I built a #docker image of the application and pushed it to Artifact Registry. Then I proceeded to create a cluster and deploy the application on it. Detailed instructions on how to achieve this are in the Readme file. here's a link to the repo https://lnkd.in/dDVmikSY

SemanticKernel – 📎Chat Service demo running Llama2 LLM locally in Ubuntu. Hi! Today’s post is a demo on how to interact with a local LLM using Semantic Kernel. In my previous post, I wrote about how to use LM Studio to host a local server. Today we will use ollama in Ubuntu to host the LLM. Ollama Ollama is an open-source language model platform designed for local interaction with large language models (LLMs). It provides developers with a convenient way to run LLMs on their own machines, allowing experimentation, fine-tuning, and customization. With Ollama, you can create and execute scripts directly, without relying on external... #techcommunity #azure #microsoft https://lnkd.in/gWKXGz8i

Kotlin's feature for creating internal DSLs is impressive. It makes building complex features easier and cleaner by reducing syntactic smells. I'm working on a project that generates JSON using DSLs similar to Jetpack Compose. It's amazing how I accomplished this in just a few lines of code. The best part is that it's very fast when running on AWS Lambda, taking only 8ms to generate JSON and using only 24MB of memory on GraalVM. I hope everyone finds this interesting. #Kotlin #AWSLambda #DSLs #KotlinMultiplatform #GraalVm #jetpackCompose #Kotlin #kotlinDevs #kotlin #google #GDE #googleDevelopers

Meet 🐦 Glide, an open blazing-fast model gateway to speed up your GenAI app development and make your LLM apps production ready 🚀 Glide strives to help you to solve common problems that occur during development and running GenAI apps by moving them out of your specific applications on the level of your infrastructure. All you need to do to start leveraging that is to talk to your models via Glide ✨ As a part of this initial scope, we had to set up a bunch of common things to make it roll. As for the core functionality, we have brought up: - The routing functionality with four types of routing strategies (including a tricky one like the least latency routing) - The first-class adaptive resiliency & fallbacking across all routing strategies - Unified Chat API that supports popular model providers like OpenAI, Azure OpenAI (on-prem models), Cohere, OctoML, Anthropic - The ability to have model-specific prompts - Installation via Docker & Homebrew The most exciting things are ahead of us, so looking forward to get more cool stuff in scope of Public Preview 🚀 🚀 🚀 If you like the idea, feel free to give us a star, join our Discord and watch for our upcoming releases. Let's equip GenAI revolution with a resilient open infrastructure together 🙌 📦 Release: https://lnkd.in/ezD4jtNj 📚 Docs: https://glide.einstack.ai/ 📺 Demo: https://lnkd.in/eaySzQQz 💬 Discord: https://lnkd.in/e6_zFSWf 🗺️ Roadmap: https://lnkd.in/eicCXdQc #genai #llmops #llm #llmsecurity #mlops #datascience #machinelearning #cncf

Kubernetes has been one of the backbones for scaling and deploying apps. Explore the crucial role of rate limiters in our latest collaborative deep dive with Pratik B. 🚀 https://lnkd.in/g-FZZSYw

This topic has been in my queue for quite sometime now - finally able to get around to it and check-off the next item from my long 𝗧𝗢-𝗗𝗢 list ... 𝐎𝐥𝐥𝐚𝐦𝐚 is a very powerful LLM hosting platform, which can be used to download and run the popular pre-trained LLM models locally ... Here comes the primer on how to setup and run 𝐎𝐥𝐥𝐚𝐦𝐚 using docker ... https://bit.ly/4cLdcBE ... #deeplearning #llm #ollama