The Knowledge Graph Conference’s Post

If you're in NYC this week and want to learn about how to use graphs to build #generativeai applications that are more reliable and explainable, check out this hands-on session with the The Knowledge Graph Conference and Amazon Web Services (AWS) on building GraphRAG applications with #AmazonNeptune, Jupyter Notebooks, and LlamaIndex. Sign up link is below!

This is the time, where I have been using #partyrock from AWS Generative AI. Note: The image given below is generated by the #partyrock, when the prompt to generate a LinkedIn promotion post about #partyrock is given I'm thinking, but absolutely amazing series of image generation with the help of LLM (using Stability Diffusion XL LLM from Stability AI). The text generated is powered by LLM (Claude Instant from Anthropic). Use #partyrock to leverage your writing and drawing skill, and sure you will love it. Link for Party Rock from AWS : https://partyrock.aws/ #generativeai #awscloud #awslearning #bedrock #serverless #llm #stablediffusion

Choosing Your GenAI Path: A Simple Decision Tree Guide 🌲 Yesterday, we delved into the plethora of techniques available for Generative AI implementation—Prompting, RAG, Fine-tuning, and leveraging "Agents" for LLM action execution. With a clear understanding of each method's strengths and pitfalls, the burning question remains: where do I begin? While the conventional wisdom suggests starting with the model "as is" and progressing through prompt engineering, RAG, and fine-tuning, this path isn't one-size-fits-all. To guide your journey more effectively, I'm introducing a straightforward decision tree, designed to navigate the most common scenarios with ease. Dive deeper into this approach and explore the blog post here 👉 https://lnkd.in/d8g8PpRX A special shoutout to the Amazon Web Services (AWS) team for their insights: Jay Rao Babu Kariyaden Parambath Diagram available here 👉 https://lnkd.in/dh25TZb5 #genai #promptengineering #rag #finetuning

🆕 Claude 3.5 Sonnet is now available in Amazon Bedrock. Claude 3.5 Sonnet is multimodal, and outperforms Anthropic’s previous top-tier Claude 3 Opus model across a wide range of industry benchmarks, including graduate-level expert reasoning, code generation, and more. But that's not all – Claude 3.5 Sonnet delivers unparalleled performance at just one-fifth the cost of its predecessor, empowering customers to create cutting-edge, generative AI-powered solutions at a fraction of the cost. Embrace the future of generative AI and unlock new realms of possibility with Claude 3.5 Sonnet. #AWS #GenerativeAI #AmazonBedrock #AWSAIML #AWSGENAI

Great Labs and Workshop hosted by Amazon today showcasing the capabilities of their AI & ML AWS Services and allowing us to have a hands-on experience with many of their AI models. In particular using RAG (Retrieval-Augmented Generation) and its day-to-day application that many businesses can avail of. Being able to programmatically feed and alter specified data into a RAG Service that can leverage generative AI could be another big step in upping usability and reducing the need for FAQ's among many many other potentially game changing applications. Big thanks to the AWS Hosts & Automat-it for sponsoring the event! #aws #ai #machinelearning

Excited to share our latest blog post on the future of productivity agents with NinjaTech AI and AWS Trainium. Our guest post by Arash Sadrieh, Tahir Azim, and Tengfei Xue from NinjaTech AI offers insights into the cutting-edge productivity agent NinjaLLM, the backbone of MyNinja.ai, built using AWS Trainium chips. Learn how we leveraged multiple large language models optimized for specific tasks, and the cost-effective methods for training these models. Explore our approach to fine-tuning the models and our advancements in model evaluation, all aimed at making AI agents more productive. Don't miss the opportunity to discover our future plans for improving model performance and user experience. For an in-depth understanding, read the full post here: https://ift.tt/Op5BTFr

"🚀 AWS' latest re:Invent reveals a key insight into the current state of Generative AI—acceleration and anticipation are in the air, but with half of their new announcements still in preview mode, it seems they might be playing catch-up. Let's stay tuned to see how these rapid developments unfold and whether AWS can close the gap in the Generative AI race! 🧠💡 #GenerativeAI #AWS #Innovation #AI #MachineLearning #CloudComputing #reInvent #TechNews #AIrace"

Just completed an incredible course on Generative AI with Large Language Models (LLMs) offered by DeepLearning.AI and Amazon Web Services (AWS)! This course dives deep into how generative AI works and explores its real-world applications. Here are a few things I learned: - The fundamentals of LLMs, including data gathering, model selection, and deployment. - A deep dive into transformer architecture, training, and fine-tuning. - Optimization strategies using empirical scaling laws. - State-of-the-art training, tuning, and deployment methods. - Challenges and opportunities that generative AI brings to businesses. Feeling inspired and ready to apply my new skills! 💫 #GenerativeAI #LLMs #DeepLearning #AI #TechLearning #CelebrateSuccess

How many generative AI applications do you have running in production? Over the past year, we’ve seen tons of interesting, funny, and impressive applications of large language models (LLMs), but scaling these applications into production remains a challenge. Creating long-term successful generative AI application requires careful thought and consideration from the very beginning. It also requires cheese! To find out how we use cheese in LLMOps, join our session at AWS Innovate on February 22nd! Sign up here: https://go.aws/3SqE16N #awscloud #generatieveai #genai #bedrock #aws #llm #awsinnovate #llmops #fmops #mlops Sara 'Moose' van de Moosdijk, Pedro Paez Sanchez, Alex Thewsey, Alessandro Cerè, Tim WU, Hantzley Tauckoor, Prashant Advani, Suresh Pathak, Puneet Arora, Clevester Teo, Chomchana (Chom) Trevai, Ph.D., Catherine K.

Just finished attending week 2 of "Let's Ship It - with AWS! Generative AI | S1 E2 | Models and More Models." I am thrilled to discover the vast potential of generative AI, from generating entire proposals to creating images. Witnessing how far technology has come and how it can help business owners develop innovative products is amazing. I am excited to apply what I have learned and create something extraordinary myself! #AWS #GenerativeAI #Innovation #Technology #LetsShipIt Ps. just for fun, I used the "Rewrite with AI" feature on LI. I thought it was appropriate considering the topic 🤣