Image created with GPT Image 1. Image prompt: Wearing a trenchcoat cut from encyclopedia pages and holographic scrapbook scans, a Black detective-model strides through a collage alley lit by paper lanterns and info-orbs, holding a magnifying glass ring that glows with citations — retrieval-augmented glamour, shot like noir Afrofuturism.
GraphRAG: The Marriage of Knowledge Graphs and RAG: Emil Eifrem – YouTube https://www.youtube.com/watch?v=knDDGYHnnSI&t=1s
🚀 Amazon Nova Premier, our most capable teacher model for creating custom distilled models, is now available on Amazon Bedrock! Built for complex tasks like Retrieval-Augmented Generation (RAG), function calling, and agentic coding, its one-million-token context window enables https://x.com/AmazonScience/status/1917738059346633132
2/ @Saboo_Shubham_ built a Customer Support Voice RAG Agent using Firecrawl and OpenAI Agents SDK. 📞 It can bring any documentation or knowledge base to life in just a few minutes. https://x.com/AtomSilverman/status/1919066828862530007
5/ Google just published a 2nd 76-page whitepaper on AI Agents that covers more advanced topics: @Hesamation > agentic RAG > single agent evaluation > evaluating multiple agents > real-world agentic architectures https://x.com/AtomSilverman/status/1918424777632694595
RAG is the number 1 use-case of LLMs in Enterprises, but so far primarily limited to text-only. How can we bridge the modality gap, and make it understand and use complex visual information like graphs & charts? In this talk @Nils_Reimers will outline how to build an” / X https://x.com/jxnlco/status/1919830678524289263
Amazon’s Nova Premier is now available on Bedrock It’s the company’s most capable teacher model for creating custom distilled models for tasks like RAG, function calling, and agentic coding Also includes a 1M-token context window https://x.com/rowancheung/status/1917844395329470973
Run your entire AI workflow locally for free with n8n + Docker + MCP (Model Context Protocol): – Run LLMs and AI agents locally – Create RAG workflows with vector databases – Automate with visual workflow builder – Connect agents to real APIs/tools – Full privacy with https://x.com/victor_explore/status/1914887663725035805
Github 👨🔧: Get your documents ready for gen AI → Parses multiple document formats like PDF, DOCX, XLSX, HTML, and images. → Features advanced PDF understanding: page layout, reading order, table structure, code, formulas, image classification. → Uses a unified https://x.com/rohanpaul_ai/status/1919320664781332876
Google just published a 2nd 76-page whitepaper on AI Agents that covers more advanced topics: > agentic RAG > single agent evaluation > evaluating multiple agents > real-world agentic architectures If you already know the basics don’t miss out on this one. https://x.com/Hesamation/status/1917958907051311562
19/ @Sumanth_077 shared a step-by-step tutorial on how to build a PDF RAG Agent 🚀 https://x.com/AtomSilverman/status/1918424808578269323
6/ @AlexReibman and @n_sri_laasya form @AgentOpsAI are hosting sessions on how to build, evaluate, and scale multi-agent systems next week — Evals 101 (measuring what actually matters) after — Chatbots 101 (beyond basic RAG) sign up below https://x.com/AtomSilverman/status/1918424779843162324
Let’s build a PDF RAG Agent, step-by-step:” / X https://x.com/Sumanth_077/status/1917949092355080246
Github 👨🔧: Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques. → Build an agentic RAG system interacting with a personal knowledge base (Notion example provided). → Learn production-ready LLM system architecture https://x.com/rohanpaul_ai/status/1919309052657451227
I built a Customer Support Voice RAG Agent using Firecrawl and OpenAI Agents SDK. It can bring any documentation or knowledge base to life in just a few minutes. 100% Opensource Code with step-by-step tutorial. https://x.com/Saboo_Shubham_/status/1908708028993728941
Static retrieval in RAG models limits adaptation to evolving semantic needs, hindering generation quality. This paper introduces a dynamic RAG using context-guided retrieval and joint optimization. This improves knowledge utilization, achieving up to 55.1 ROUGE-L with GPT-4o. https://x.com/rohanpaul_ai/status/1920368066338136288
Command A, our state-of-the-art generative model, is now the highest-scoring generalist LLM on the Bird Bench leaderboard for SQL! It outperforms other systems that rely on extensive scaffolding to tackle these SQL benchmarks, and instead delivers these results out-of-the-box, https://x.com/cohere/status/1918386633772286278
An interesting approach from @AdobeResearch to summarizing multiple documents👇 MiDAS-PRo divides this process in 3 steps: – Planning to organize the process – Reasoning to figure out the key aspects from the docs – Summarizing: Using the plan to generate an accurate summary https://x.com/TheTuringPost/status/1917990621501112799
