Hey everyone! I am SUPER excited to publish our newest Weaviate podcast with Kyle Davis, the creator of RAGKit!<p>At a high-level, the podcast covers our understanding of RAG systems through 4 key areas: (1) Ingest / ETL, (2) Search, (3) Generate / Agents, and (4) Evaluation.<p>Discussing these lead to all sorts of topics from Knowledge Graph RAG, to Function Calling and Tool Selection, Re-ranking, Quantization, and many more!<p>This discussion forced me to re-think many of my previously held beliefs about the current RAG stack, particularly the definition of “Agents”. I came in believing that the best way of viewing “Agents” is an abstraction on top of multiple pipelines, such as an “Email Agent”, but Kyle presented the idea of looking at “Agents” as scoping the tools each LLM call is connected to, such as `read_email` or `calculator`. Would love to know what people think about this one, as I think getting a consensus definition of “Agents” can clarify a lot of the current confusion for people building with LLMs / Generative AI.<p>I hope you find the podcast useful, this was such a fun one! Thank you so much for joining Kyle!<p>https://youtu.be/oEsJqMLYAfc
We think that RAG is fundamentally limited:<p><a href="https://www.aryn.ai/post/rag-is-a-band-aid-we-need-llm-powered-unstructured-analytics-luna" rel="nofollow">https://www.aryn.ai/post/rag-is-a-band-aid-we-need-llm-power...</a><p>We call our approach - Luna — LLM-powered unstructured analytics. We do see a world where LLMs are used to answer questions, but it’s a more complex compound AI system that references a corpus (knowledge source), and uses LLMs to process that data.<p>The discussion around context sizes is a red herring. They can’t grow as fast the demand for data.<p>The discussion around agents needs a lot more thinking through. They’re likely to specialize — ours will be coming with strategies for answering questions — ie query planning.