Hasanga Hendehewa’s Post

In this roundup of the latest AI case studies, we look at how developers are combining the incredible reasoning power of LLMs with their enterprise data using the RAG pattern and MongoDB. Read more on AI-powered apps: https://lnkd.in/egjjq3bw

What’s new with Firestore at Next ‘24 Firestore is popular among developers for its fast application and service building capabilities. The platform now boasts over 500,000 monthly active developers and powers 1.3 billion monthly active end users. Recent updates have enhanced productivity, enabled AI application development, and improved query expressiveness. New features include natural language query writing, AI-enabled solutions support, richer queries with range filters, Query Explain for troubleshooting, Customer Managed Encryption Keys (CMEK) support, and extended backup retention. Furthermore, Gemini Code Assist offers assistive capabilities for Firestore development. They have also expanded to generate solution architectures and provision Firestore resources. These updates aim to meet enterprise needs for privacy, serving latency, and data backup. For more information, reference the provided documentation and resources.

Sharing this again because this is key to making your apps (AI, GenAI, Custom) fast, flexible, and visual! Join Michael Hichwa and Andy Mendelsohn to learn how new GenAI-powered low-code innovations in Oracle APEX can help developers create better apps in less time. https://lnkd.in/gJw5Y5fc

Imagine an AI-powered app that uses real-time sounds to diagnose future problems. 🔊 This is what’s possible when you unify operational and vector data on one platform that puts developers first. Learn more here: https://lnkd.in/drnpqRWA MongoDB #LoveYourDevelopers

🧠 How can you assure that your AI Agents provide low latency responses to users? 🤖 In typical RAG-based application, one major issue is that the time required for the LLM to generate the response might results in high-latency experiences, especially with large scale applications.  One way to address this issue is saving common Q&A pairs into an in-memory cache and, since we are talking about AI Agents, we want to implement semantic caching. 🔎In this article, we are going to see how to leverage Azure Cosmos DB as both vectorDB for our knowledge base, and in-memory DB for our semantic cache. To learn more: 👉 CosmosDB Semantic Caching-->https://lnkd.in/dV89-e_t 👉LangChain connector for CosmosDB-->https://lnkd.in/dBpbBN4f 👉AI Agents with CosmosDB-->https://lnkd.in/dXTacMc3

Imagine an AI-powered app that uses real-time sounds to diagnose future problems. 🔊 This is what’s possible when you unify operational and vector data on one platform that puts developers first. Learn more here: https://lnkd.in/eBv6R7Dn MongoDB #LoveYourDevelopers

Imagine an AI-powered app that uses real-time sounds to diagnose future problems. 🔊 This is what’s possible when you unify operational and vector data on one platform that puts developers first. Learn more here: https://lnkd.in/geawwJAm MongoDB #LoveYourDevelopers

Imagine an AI-powered app that uses real-time sounds to diagnose future problems. 🔊 This is what’s possible when you unify operational and vector data on one platform that puts developers first. Learn more here: https://lnkd.in/dyKNqm64 MongoDB #LoveYourDevelopers

Imagine an AI-powered app that uses real-time sounds to diagnose future problems. 🔊 This is what’s possible when you unify operational and vector data on one platform that puts developers first. Learn more here: https://lnkd.in/gFRrwejs MongoDB #LoveYourDevelopers

Learn how Oracle Database 23ai brings AI to your data, making it simple to power app development and mission critical workloads with AI. Each week, we'll share a new feature of Oracle Database 23ai with examples so you can get up and running quickly. Save this page and check back each week to see new highlighted features. #Oracle23ai https://lnkd.in/eSJGRASM