The event focused on one of the latest advancements in Retrieval-Augmented Generation (RAG)βContextual Retrieval, developed by Anthropic. This approach enhances retrieval accuracy by first prepending chunk-specific context before embedding through the use of a "contextualizer prompt." Then the augmented chunks are indexed using both a vector database (as in classic RAG, better at semantic search) and a TF-IDF Index (better at exact match keyword search). The discussion covered key technical aspects, including chunking parameters, and comparing Contextual Retrieval to traditional RAG methods.
Join our Discord to start learning and building with other AI practitioners.
β
π¦ LlamaIndex RAG-A-THON
Anna, Lusk, The Wiz, Christos, Arjun, Seraacha, & Dr. Greg
It was an unforgettable weekend at the AGENTIC-RAG-A-THON! π β Many AI Makerspace (AIM) community members showed up in full force! From students to peer supporters, everyone generously shared their knowledge. It was great seeing so many people build ποΈ ship π’ and share π their RAG applications.
β
π‘ Transformation Spotlight
β
π¨ Mert Bozkir, a university student in Turkey, didn't let time zones stand in his way of learning new Gen AI. While he may only have 3 years of programming experience, he has some great words of wisdom for anyone considering a jump into the AI space. Read about his journey.
π£ S/o to AIM community member Anna Tucker (above), who not only volunteered all weekend at the hackathon with us just one week after moving to the Bay Area, but she has also recently transitioned from HR into AI Engineering! We celebrate you, Anna, and the incredible community vibes you've brought to AIM! π
ποΈ Build of the Week!β βMitul Tiwari, an AIM alumni, shared TapeAgents, a holistic framework for agent development and optimization. The tool which uses a unique "tape" approach to logging the thoughts, steps, and observations of an agent during a session, has now been released as an open-source project! Way to go, Mitul! Read more and chat about it here.
π Check out what the AIM community is building, shipping, and sharing!
The latest release at the LLM Edge when it comes to building, shipping, and sharing multi-agent applications comes from OpenAI, and itβs called Swarm. Check it out live with us!
The latest in alignment R&D at the LLM Edge comes from Meta and its called Mixture of Judges (MoJ). It's supposedly a step-change improvement over RLHF and DPO.
Weekly Concepts, Code, and Community! Every Saturday you'll receive a detailed overview of one the latest tools or techniques from the open-source LLM edge.
Hey, AIM community! Join Dr. Greg and The Wiz as they cover Large Reasoning Models next Wednesday, Jan 18. With the release of o1, o3, and the new Gemini, everyone is talking about Chain-of-Thought Reasoning and Test-Time Compute. What are these things, anyway? And what are the implications for building production LLM applications with models like this in 2025 and beyond? Join the discussion live on Wed. at 10 AM PT! Last week, we dove into the latest RAG Evaluation metrics and RAGAS...
π Hey, AIM community! As we near the end of 2024, our team is looking back at all we've accomplished as a community this year. Thanks to all of you for learning π, building π, shipping π’, and sharing π with us at the open-source LLM Edge! We'll be rooting for you to take your AI career to the next level in 2025, and when you do, we hope you'll lean on us to amplify your story and showcase your best work. In this way, you'll help the AI Makerspace community achieve its mission of becoming the...
π Hey, AIM community! Dr. Greg and the Wiz will go on-prem with LangGraph next week! Join us for our last YouTube Live event before the New Year π! Last Wednesday, Dr. Greg and The Wiz guest spoke with Malikeh from Arcee on the SLM Show about the year in summary at the LLM Edge, and what to expect in 2025! We also explored vLLM! We learned that Virtual LLM helps us relieve memory bottlenecks when serving LLMs through PagedAttention, just like Virtual Memory relieves memory bottlenecks in...