Softlandia
Blog
Posts tagged with
#RAG
AI Engine explained – The path to smarter automation
An AI engine acts as a versatile toolkit, enabling businesses to automate tasks previously requiring human intellect. It transforms messy data into structured, actionable insights, streamlining business processes and enhancing decision-making speed.
Deploying Qdrant with gRPC & Auth on Azure: A FastAPI Singleton Client Guide
Deploy Qdrant to Azure with HTTP/2 and gRPC and access it asynchronously via a singleton instance of the Qdrant client via FastAPI dependency injection.
Finnish talk show host Arto Nyberg interviewed AI developed by Softlandia
An example of applied AI was witnessed by over half a million Finns during a live special broadcast of the Arto Nyberg talk show: we had the opportunity to implement a real-time talking and moving AI avatar for the program.
Bytewax & Softlandia Workshop Recap: Stateful Streaming Slack GenAI RAG Bot
On February 16th, Softlandia and Bytewax ran an engaging online workshop designed to introduce the basics of incorporating AI into Slackbots.
Serverless LLMs (demo!) and other GenAI trends for 2024
Small language models are one of the biggest trends in GenAI in 2024. They can be already run for free on serverless platforms!
YOKOT.AI – lessons learned from our customers after 4 months in production
In this blog post we are discussing the importance of finding and defining just the right use case for your AI solution, why it is more efficient to use a complete RAG architecture instead of figuring out your own solution and how to ensure your corporate data remains private.
Microsoft Copilot, Grok, ChatGPT and YOKOT.AI – a Look into RAGs
What is common with Microsoft Copilot, Grok, ChatGPT and YOKOT.AI? They are all RAGs!
Simplifying Documentation With The Help of Generative AI – Introducing YOKOT.AI Document Generation Workflow
How do you go from an effective internal knowledge management to actually utilizing that knowledge to support your documentation processes?