Image created with gemini-2.5-flash-image with claude-sonnet-4-5. Image prompt: Photorealistic 35mm cinema photograph of a child in a warm-lit bedroom sitting among an arc of glowing TV screens, surrounded by scattered open reference books, index cards, and newspapers with visible highlighting and sticky notes creating a visual web between physical and digital sources, one screen showing a document interface with citation highlights, warm pastels contrasted with cool screen glow, shallow depth of field, cozy yet information-dense atmosphere, large bold text ‘RAG’ at top.
Building “RAG 2.0” is just making Claude Code running over your filesystem 🤖🗂️ To make this work well, you need to solve three things 1️⃣ Virtualize your filesystem to prevent the agent from messing stuff up. AgentFS by @tursodatabase is a nice example of how you can give the https://x.com/jerryjliu0/status/2000677592559706396
NEW Research from Apple. When you think about it, RAG systems are fundamentally broken. Retrieval and generation are optimized separately, retrieval selects documents based on surface-level similarity while generators produce answers without feedback about what information is https://x.com/omarsar0/status/2000570838920434037
Ever opened a repo and thought: “What does this codebase actually do?” “Where did I put that file?” 🤔 You’re not alone. With the release of Gemini 3 Flash ⚡ from @GoogleDeepMind, we decided to build something fun (and useful): a file-system explorer agent that answers those https://x.com/llama_index/status/2001324278617424017
Adaptive retrieval is the way to go! And this RouteRAG paper shows why. Let’s talk about it: RAG systems have a retrieval problem. The default approach to multi-hop reasoning today relies on fixed retrieval pipelines. It typically involves fetching text + maybe graph data, and https://x.com/dair_ai/status/2000400449355325806
𝐅𝐢𝐧𝐞-𝐠𝐫𝐚𝐢𝐧𝐞𝐝 𝐬𝐞𝐦𝐚𝐧𝐭𝐢𝐜 𝐬𝐞𝐚𝐫𝐜𝐡 𝐢𝐬 𝐦𝐨𝐯𝐢𝐧𝐠 𝐟𝐫𝐨𝐦 𝐫𝐞𝐬𝐞𝐚𝐫𝐜𝐡 𝐭𝐨 𝐩𝐫𝐨𝐝𝐮𝐜𝐭𝐢𝐨𝐧 In our latest article, we dive into how ColBERT and ColPali enable token-level and patch-level retrieval, unlocking much more precise semantic search https://x.com/qdrant_engine/status/2001245992906002545
Leave a Reply