Simon Bisson’s Post

How do you extend a LLMs knowledge to things it wasn't trained on, such as proprietary information? RAG. How do you achieve even better question and answer performance over complex data sets? Here comes "GraphRAG". It's amazing to continually see the advancements that are coming in the pipeline to improve GenAI applications. #GenAI #Microsoft #Azure #OpenAI #RAG

Make time to see Lino Tadros' session at the next GenAI Conference today. Lino will dive deep into Embeddings and Vectorization fundamentals. Attendees will gain crucial insights into the importance and applications of these technologies. The session will explore multiple embedding models and vectorization databases, including ChromaDB, FAISS, Pinecone, Azure AI Search, and Azure PostgreSQL. Tadros will demonstrate practical applications using Semantic Kernel and Langchain. Attendees will walk out with essential knowledge for leveraging embeddings and vectorization in their projects. https://buff.ly/4egmg22

Generate Synthetic QnAs from Real-world Data on Azure

Generate Synthetic QnAs from Real-world Data on Azure

#Neo4j, recently announced support for the enterprise version of its cloud-hosted service, #Aura, on #Azure. Available in the #AzureMarketplace, it’s a SaaS version of the familiar on-premises tool, allowing you to get started with data without having to spend time configuring your install. A tool like Neo4j that can sit on top of a large-scale data lake like Microsoft’s #Fabric gives you another useful way to build out the information sources for a #RAG application. Here, you can use the graph visualization tool that comes as part of Neo4j to explore the complexities of your lake houses, generating the underlying links between your data and giving you a more flexible and understandable view of your data. https://lnkd.in/deRFyT3w #infoworld #knowledgegraphs

In a landscape dominated by Snowflake and AWS, it's easy to overlook Google Cloud Platform (GCP) and specifically, BigQuery. But here's why you shouldn't. I just released a new YouTube video where I demonstrate Gemini, Google's latest Large Language Model (LLM), inside Google BigQuery. My theory? GCP is shifting BigQuery to the forefront of its platform, integrating deeply with other key tools like notebooks, AI Studio, dashboards, and NoSQL databases like Firestore. Integrating Gemini inside of BQ can really help democratize access to cloud tools by lowering to barriers to entry. Key Highlights from the Video: → Why BigQuery is a Powerhouse: BigQuery is a serverless, highly scalable, and cost-effective multi-cloud data warehouse designed for large-scale data analytics. → Integration Mastery: From notebooks to AI Studio, GCP is blending BigQuery seamlessly with other essential tools for a more cohesive user experience. → Practical Demonstration: Watch how Gemini enhances BigQuery's functionalities, making complex data interactions simpler and more intuitive. https://lnkd.in/gVmSAXCk

🔹 Climbing the AI Ladder with Purpose! 🔹 Using IBM’s AI Ladder framework and MongoDB to push data capabilities further. From organizing to deploying insights, each step strengthens our foundation for AI-driven impact. Looking forward to reaching new heights in data and AI innovation! #DataExcellence #IBM #MongoDB #AIInnovation #MachineLearning #DataScience

I'm honored to be speaking at Build this year! We'll have a 45-minute breakout session and an expert demo session highlighting just how easy it is to build an AI-powered application with Azure Database for PostgreSQL. I hope to see you at both! #AI #Azure #MSFTBuild2024 #Postgresql #AzureData

Want to learn how MongoDB and Together AI are partnering to empower #GenAI innovation? 🤔 Don't miss the latest episode of the MongoDB Podcast with TogetherAI's Heejin Jeong and Hassan El Mghari who shared valuable insights on the cutting-edge RAG system, the benefits of integrating AI with MongoDB, and a sneak peek into the future of AI-driven user experiences. Watch today! ⬇️ #MongoDB #AI #Innovation #AWS #Microsoft #Azure #SQL #Google #GoogleCloud #Oracle

🚀 Exciting Innovation in Search AI! 🚀 Search AI Lake and Elastic Cloud Serverless are here! A cloud-native architecture for real-time, low-latency search. 🌐 - Organizations will benefit from: Seamless Search: Search AI Lake can dive into vast amounts of unstructured data without needing metadata or tables, making it ideal for AI training, security, and observability workloads. - Scalability: By decoupling storage from compute, Elastic promises enormous scalability, making this tool perfect for training large language models (LLMs). - Advanced Search Capabilities: Supports traditional, vector, hybrid, and faceted search, enhancing applications like GenAI training and Retrieval Augmented Generation (RAG). - Interoperability: Uses the Elastic Common Schema (ECS) format and the Elasticsearch Query Language, enabling federated searches across diverse data sources. - Real-Time Processing: Built on the robust foundation of ElasticSearch, known for its real-time data processing and open-source roots. 👉 Learn more in @techzine article here: https://gag.gl/CogELL Join the conversation and share your thoughts on how this innovation could impact your data strategies! 💬 #DataInnovation #SearchTechnology #AITraining #BigData #ElasticSearch #GenAI #TechNews