Building RAG-based LLM Applications
- Date
- 2023-12-07
- Location
- San Francisco, CA, USA
- Host
- Personal
About this event
Retrieval-augmented generation has quickly moved from a promising idea to one of the most practical ways to build useful LLM products. If you care about making language models more accurate, more grounded, and more valuable in real applications, this meetup is a chance to learn how people are actually approaching RAG in the real world while meeting others working through the same questions. This is not a vague AI networking night. It is a focused in-person meetup in San Francisco for people who want to talk seriously about building RAG-based LLM applications: what works, what breaks, and what decisions matter when you move from demos to products. About the Event Building with LLMs is easy to start and hard to do well. RAG sits right in the middle of that challenge: it promises fresher knowledge, better factual grounding, and more control, but it also introduces new tradeoffs around retrieval quality, latency, evaluation, orchestration, and user experience. This meetup is designed to bring together practitioners, builders, and curious technical people around those tradeoffs. The focus is on practical understanding rather than hype. Whether you are experimenting with your first pipeline or refining an existing system, the goal is to create a space where people can compare approaches, share lessons, and sharpen their thinking. Because it is in person, the format also matters. Conversations tend to get more specific when people can ask follow-up questions face to face, sketch architectures, and swap implementation notes without forcing everything into a formal presentation slot. Expect a community-centered evening that blends learning and networking. The event is tagged across AI, LLM, community, networking, and meetup for a reason: the value is not only in the content, but also in the people in the room. What to Expect You can expect a structured but approachable meetup format centered on RAG-based application development. The evening will likely move through a mix of content and conversation so attendees can both learn and connect. Topics that often matter in this kind of discussion include: how to decide when RAG is the right approach for an application chunking, indexing, and retrieval design choices prompt patterns that work well with retrieved context reducing hallucinations and improving answer reliability evaluating whether a RAG system is actually helping users tradeoffs between speed, quality, complexity, and cost the difference between a prototype that looks good and a system that holds up in production You should also expect plenty of peer-to-peer exchange. In a strong meetup like this, some of the most useful moments come from hearing how someone else handled document ingestion, search relevance, observability, fallback behavior, or feedback loops in their stack. There will also be space for networking with others in the local AI and LLM community. If you are looking for collaborators, feedback on an idea, perspective on your architecture, or simply a better sense of what other teams are building, this setting is well suited to that. Why Attend If you are building anything with LLMs, RAG is one of the most important patterns to understand well. It is often the bridge between a general-purpose model and an application that can answer with useful, domain-specific context. Attending gives you a more grounded view of how people are applying that pattern in practice. This meetup is especially valuable because it focuses on applied thinking. You will not just hear that RAG matters; you will spend time around people who are actively exploring the design and operational questions behind it. That means better questions, more concrete conversations, and more insight you can carry back into your own work. You may leave with: a clearer mental model for how RAG systems are put together better instincts for the common failure modes practical ideas for improving retrieval quality and response usefulness a sharper sense of how to evaluate user-facing performance new connections in the San Francisco AI builder community For many attendees, the biggest payoff will be momentum. A focused evening with the right people can help you move faster, avoid avoidable mistakes, and get unstuck on decisions that are hard to reason through alone. Practical Details This event takes place in person in San Francisco, USA on Wednesday, December 6 at 6:00 PM PST. The in-person format makes it a good fit for local builders or anyone who values real conversation over passive attendance. Plan for an evening meetup atmosphere: accessible, social, and centered on discussion. If you are attending, it is worth coming ready to talk about what you are building, what questions you are wrestling with, and what kinds of systems or use cases interest you most. A few ways to get more out of the night: come with one specific RAG challenge or question you want to explore be ready to describe your project or interest area in a few clear sentences bring an open mind about different architectures, tools, and workflows leave time to stay after the formal portion for conversations If you want a smarter, more practical understanding of RAG-based LLM applications and you want to meet other people doing serious work in the space, this meetup is exactly the right room to be in.
Who should attend
This is for people who want practical, grounded conversations about building with LLMs, not just broad interest in AI. - You are building or planning an **LLM-powered product** and want to understand how RAG can improve accuracy, context, and usefulness. - You work as an **engineer, developer, technical founder, or product-minded builder** and want clearer thinking on retrieval pipelines, prompting, evaluation, or system design. - You have already experimented with LLMs and are now asking harder questions about **reliability, hallucinations, relevance, latency, or production tradeoffs**. - You are curious about how other people in the **San Francisco AI community** are approaching real application development and want to compare notes in person. - You learn best by talking with peers, asking direct questions, and hearing what has actually worked for others rather than reading generic summaries online. - You are looking to meet **serious practitioners, collaborators, or thoughtful peers** around AI, LLMs, and applied product development. If that sounds like you, you will likely find both the content and the room genuinely useful.