“2mn context window LLMs are already facts of today. 100mn context window are in very advanced stage of work in progress. There are some popular papers from big labs that have found ways to do 1-Bn context window.. So RAG’s long-term (5Years+) future is uncertain.
“AI can do much more than code completions. Our AI Engineer builds custom AI agents with RAG from simple English prompts.
“The Top ML Papers of the Week (Oct 28 – Nov 3): – MrT5 – SimpleQA – Multimodal RAG – o1 Replication Journey – Geometry of Concepts in LLMs – Relaxed Recursive Transformers Read on for more:” / X
“Build advanced RAG systems with @MLflow and LlamaIndex Workflows! Go beyond the basics: 🔍 Combine vector search, keyword-based search (BM25), and web search in parallel 🧠 LlamaIndex Workflows for flexible, event-driven orchestration 📊 MLflow for experiment tracking,
“Say hello to Grounding with Google Search, available in the Gemini API + Google AI Studio! You can now access real time, fresh, up to date information from Google Search when building with Gemini by enabling the Grounding tool.
“Google is dancing! 💃 Today, @GoogleAI launched “Grounding” with Google Search in the Gemini API & AI Studio 🔍 I had a chance to preview it, and I integrated Gemini into an app in <2 hours, start to finish 👏👏 @shresbm & @OfficialLoganK join to discuss
“This AI agent has left me wondering whether traditional RAG applications have a future besides simple use cases. PromptQL is a natural language API that executes Python and SQL-like queries on top of structured, unstructured, and any data behind an API. The most fascinating
“💚Building RAG Agents with LLMs Agents powered by LLMs have shown great retrieval capability for using tools, looking at documents, and plan their approaches. This course by Nvidia will show you how to deploy an agent system in practice
“New Cookbook: An open source implementation of Contextual RAG from Anthropic! In short, it involves: 1. Using Llama 3.2 3B to efficiently generate context for each chunk 2. Building two data indices: vector and BM25 3. Performing hybrid search using reciprocal rank fusion 4.
Leave a Reply