We’re glad you’re here. This community is all about exploring the human side of AI — through bite-sized insights, quips, quirks, and practical stories you can use right away. 📝 We Encourage You to Post Often - Share wins, ask questions, and share interesting AI news. - Keep posts short, practical and easy to digest (think 60–second reads). - Use our Post Protocol: catchy title, strong hook, main insight, and a takeaway or prompt. - If you like, add your Author Footer (name, one-line tagline, and a url to LinkedIn). 🎓 Start Learning In the Classroom New here? A great place to begin is our Classroom Training. It’s designed to help you build AI literacy and fluency in small, practical bites you can use in conversations, projects, and learning. 🚀 Your First Step Introduce yourself below! Share a bit about who you are, how you’re using AI, or where you’re curious to start. 📌 Before You Post Please take a moment to review our Community Rules. Keeping things respectful, helpful, and light-hearted ensures everyone gets the most out of being here. We’re building this community one small piece at a time — and we’re glad you’re part of it.

New to AI? The best way to sound AI–smart fast is to start in our Classroom. Our unique style of training builds literacy and fluency in small, practical bites you can use right away. https://www.skool.com/ai-bits-and-pieces/classroom/8090164b

A few weeks ago, I wrote a post saying I had zero idea what “chunking” even was. Now, a few weeks later I definitely understand more, but not enough.That’s why today is fully dedicated to Pillar 1: Chunking. Back then I got great examples: 🍞 “Slice a loaf of bread into pieces.” 🍕 “Cut a pizza into slices.”Perfect analogies — and still true. But now I understand why chunking is so important: 🔹 What Chunking Really Is Chunking is the most critical preprocessing step in any RAG system. IT means breaking large documents into smaller, meaningful segments (“chunks”), which are then embedded, indexed, and retrieved later. Chunks are the atomic information units your RAG system uses. If the chunks are bad, retrieval is bad — and the LLM can’t fix it. 🔹 The Core Dilemma Chunking is always a balance between: 1️⃣ Precision – smaller chunks give cleaner embeddings 2️⃣ Context – bigger chunks give more meaning to the LLM Too big → diluted meaningToo small → missing context→ And THAT is the hardest challenge in chunking. 🔹 Best Practices for Chunking Here are the key strategies I’m learning: 📌 Recursive Character ChunkingRespects natural text boundaries (paragraphs, sentences).Often the recommended default. 📌 Overlap (10–20%) Ensures context isn’t lost at the edges.Example: 500-token chunk → 50–100-token overlap. 📌 Optimal Sizes A strong starting point is 512–1024 tokens per chunk. 📌 Advanced Methods– Semantic Chunking: uses embeddings to detect topic changes– Agentic Chunking: LLM splits text into atomic, meaningful statements These methods help avoid context loss and improve retrieval quality. 🔹 Why This Matters Chunking literally determines what your RAG system can find.And if retrieval fails, the LLM fails — it can’t magically invent the missing context. All resources, diagrams, and notes as always:👉 Notebook: https://notebooklm.google.com/notebook/ea1c87b2-0eda-43f8-a389-ba1f57e758ce