MongoDB’s Post

A lot of you have been asking about my skincare routine. Yeah... that's a lie. But many of you have been wondering what Agentic RAG is. Here's your answer, served fresh and hot! 🔥 I just dropped a video showcasing the following: 1️⃣ How to build an Agentic RAG system using Anthropic's Claude 3.5 Sonnet, LlamaIndex, and MongoDB. 2️⃣ The magic of combining traditional RAG with AI agent superpowers 3️⃣ An Airbnb listing recommender that's smarter than your average chatbot The best part of Agentic RAG? It enables the AI Agent to decide when to use a knowledge source or its brain. 📺 Video: https://lnkd.in/eZN9AAwX 🗒️ Check out the full tutorial and code: https://lnkd.in/ehgrUycR #agenticrag #aiagents #genai #mongodb #llamaindex #ai

For the second time in a row, MongoDB Atlas Vector Search has been named “The Most Loved Vector Search Database” in Retool’s 2024 “State of AI” report, published last week. 🏆 🏆 This report validates that customers don't want a stand-alone vector database but an integrated solution that unifies vector (embedding), metadata, and operational data to make a developer's life far easier to generate more accurate answers with up-to-date and relevant context that large language models (LLMs) aren't trained on. Check out our blog post for more on the Retool report and the benefits of Atlas Vector Search: https://lnkd.in/dSChWN8m

Discover how scalar quantization can be used to reduce the memory footprint of vector embeddings in Elasticsearch: https://gag.gl/tVVrxQ #ElasticSearchLabs #ML #Elasticsearch

Discover how scalar quantization can be used to reduce the memory footprint of vector embeddings in Elasticsearch: https://gag.gl/tVVrxQ #ElasticSearchLabs #ML #Elasticsearch

Discover how scalar quantization can be used to reduce the memory footprint of vector embeddings in Elasticsearch: https://gag.gl/tVVrxQ #ElasticSearchLabs #ML #Elasticsearch

Discover how scalar quantization can be used to reduce the memory footprint of vector embeddings in Elasticsearch: https://gag.gl/tVVrxQ #ElasticSearchLabs #ML #Elasticsearch

Discover how scalar quantization can be used to reduce the memory footprint of vector embeddings in Elasticsearch: https://gag.gl/tVVrxQ #ElasticSearchLabs #ML #Elasticsearch

Discover how scalar quantization can be used to reduce the memory footprint of vector embeddings in Elasticsearch: https://gag.gl/tVVrxQ #ElasticSearchLabs #ML #Elasticsearch

Yes, you've heard about Google's latest model Gemma. It's what everyone in AI is talking about. Let me take you a bit further than just surface-level information. My latest article(linked below) shows how to build a RAG system using open-source models from Hugging Face, Gemma and MongoDB. In a few steps, you will utilise the latest state-of-the-art model for text completion. 🔥Here are the key takeaways: 1️⃣ Quick overview of a RAG system 2️⃣ Information on Google’s latest open model, Gemma 3️⃣ Utilising Gemma in a RAG system as the base model 4️⃣ Building an end-to-end RAG system with an open-source base and embedding models from Hugging Face 👇🏽👇🏽👇🏽 Article: https://lnkd.in/ex7bNstU #artificialintelligence #generatieveai #aistack #opensource #huggingface

Excited to share some amazing news! I've completed Code Vipassana Season 6 - Data to AI with Gemini & Gemma. This hands-on series of sessions focused on building 'Data to AI applications' using the Gemini and Gemma models for various use cases on Google Cloud. Here's a glimpse of what we learned: • Developed a Patent Search App • Worked with Gemini in Java • Created a web app to turn a picture into a website using Gemini models • Utilized BigQuery & Gemini for structured & unstructured data analytics • Built deterministic generative AI with Gemini function calling in Java • Learned how to fine-tune large language models • Mastered data management simplified with generative AI • Attended an informative session on 'Tuning and Serving GEMMA on RAY on VERTEX AI' • Created a Q&A App with Multi-Modal RAG using Gemini Pro from scratch A huge thanks to all the speakers for their patience and teaching: Guillaume Laforge, Thu Ya K., Romin Irani, Ivan Nardini and Bhushan Garware, Ph.D. Special thanks to Abirami Sukumaran and the leads for their support throughout the sessions. Looking forward to more such sessions!! #CodeVipassana #AI #Gemini #Gemma #GoogleCloud #BigQuery #GenerativeAI #MachineLearning #DataAnalytics #VertexAI #LearningEveryDay